diff --git a/.github/workflows/cwlcheck.yml b/.github/workflows/cwlcheck.yml deleted file mode 100644 index 9d9385ce6a2..00000000000 --- a/.github/workflows/cwlcheck.yml +++ /dev/null @@ -1,29 +0,0 @@ -name: cwlcheck -on: - pull_request: - branches: - - develop - push: - branches: - - develop - -jobs: - build: - name: cwlcheck - runs-on: ubuntu-latest - steps: - - uses: actions/checkout@v4 - with: - path: repo - - - name: install schema_salad and cwltool - run: | - # Requires the most updated version of cwl to work around fields with the name 'id' - pip install 'cwltool @ git+https://github.com/common-workflow-language/cwltool.git@3.1.20231016170136' - - - name: check cwl files - run: | - cd repo/workflow/cwl - for i in *.cwl; do - cwltool --validate ${i} - done diff --git a/cmake/cwl_generation.cmake b/cmake/cwl_generation.cmake index 2543d038703..43b3e79331b 100644 --- a/cmake/cwl_generation.cmake +++ b/cmake/cwl_generation.cmake @@ -29,16 +29,4 @@ foreach(TOOL ${executables}) TARGET generate_cwl_files POST_BUILD COMMAND ${OPENMS_BINARY_DIR}/${TOOL} -write_cwl ${CMAKE_CURRENT_SOURCE_DIR}/workflow/cwl ) - - # Add test for cwl - add_test(generate_cwl_files_${TOOL} ${OPENMS_BINARY_DIR}/${TOOL} -write_cwl .) - add_test(generate_cwl_files_${TOOL}_out ${CMAKE_COMMAND} -E compare_files --ignore-eol ${CMAKE_CURRENT_SOURCE_DIR}/workflow/cwl/${TOOL}.cwl ${TOOL}.cwl) - set_tests_properties(generate_cwl_files_${TOOL}_out PROPERTIES DEPENDS generate_cwl_files_${TOOL}) endforeach() - - -# Create install paths for cwl files -if(NOT WIN32) - file(GLOB cwl_files ${CMAKE_CURRENT_SOURCE_DIR}/workflow/cwl/*.cwl) - install(FILES ${cwl_files} DESTINATION ${CMAKE_INSTALL_DATADIR}/commonwl) -endif() diff --git a/workflow/cwl/AccurateMassSearch.cwl b/workflow/cwl/AccurateMassSearch.cwl deleted file mode 100644 index 259312c9e95..00000000000 --- a/workflow/cwl/AccurateMassSearch.cwl +++ /dev/null @@ -1,90 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: AccurateMassSearch -doc: Match MS signals to molecules from a database by mass. -inputs: - in: - doc: featureXML or consensusXML file - type: File - out: - doc: mzTab file - type: string - out_annotation: - doc: A copy of the input file, annotated with matching hits from the database. - type: string? - positive_adducts: - doc: This file contains the list of potential positive adducts that will be looked for in the database. Edit the list if you wish to exclude/include adducts. By default CHEMISTRY/PositiveAdducts.tsv in OpenMS/share is used. - type: File - negative_adducts: - doc: This file contains the list of potential negative adducts that will be looked for in the database. Edit the list if you wish to exclude/include adducts. By default CHEMISTRY/NegativeAdducts.tsv in OpenMS/share is used. - type: File - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - db__mapping: - doc: Database input file(s), containing three tab-separated columns of mass, formula, identifier. If 'mass' is 0, it is re-computed from the molecular sum formula. By default CHEMISTRY/HMDBMappingFile.tsv in OpenMS/share is used! If empty, the default will be used. - type: File[] - db__struct: - doc: Database input file(s), containing four tab-separated columns of identifier, name, SMILES, INCHI.The identifier should match with mapping file. SMILES and INCHI are reported in the output, but not used otherwise. By default CHEMISTRY/HMDB2StructMapping.tsv in OpenMS/share is used! If empty, the default will be used. - type: File[] - algorithm__mass_error_value: - doc: Tolerance allowed for accurate mass search. - type: double? - algorithm__mass_error_unit: - doc: Unit of mass error (ppm or Da) - type: string? - algorithm__ionization_mode: - doc: Positive or negative ionization mode? If 'auto' is used, the first feature of the input map must contain the meta-value 'scan_polarity'. If its missing, the tool will exit with error. - type: string? - algorithm__isotopic_similarity: - doc: Computes a similarity score for each hit (only if the feature exhibits at least two isotopic mass traces). - type: string? - algorithm__use_feature_adducts: - doc: Whether to filter AMS candidates mismatching available feature adduct annotation. - type: string? - algorithm__keep_unidentified_masses: - doc: Keep features that did not yield any DB hit. - type: string? - algorithm__id_format: - doc: Use legacy (ProteinID/PeptideID based storage of metabolomics data) with mzTab-v1.0.0 as output format or novel Identification Data (ID) with mzTab-v2.0.0-M as output format (ID and its MzTab-M output is currently only support for featureXML files). - type: string? - algorithm__mzTab__exportIsotopeIntensities: - doc: "[featureXML input only] Export column with available isotope trace intensities (opt_global_MTint)" - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - out_annotation: - type: File? - outputBinding: - glob: $(inputs.out_annotation) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - AccurateMassSearch -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/AssayGeneratorMetabo.cwl b/workflow/cwl/AssayGeneratorMetabo.cwl deleted file mode 100644 index 3f4375ffece..00000000000 --- a/workflow/cwl/AssayGeneratorMetabo.cwl +++ /dev/null @@ -1,242 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: AssayGeneratorMetabo -doc: Assay library generation from DDA data (Metabolomics) -inputs: - sirius_executable: - doc: The Sirius executable. Provide a full or relative path, or make sure it can be found in your PATH environment. - type: File? - in: - doc: MzML input file(s) used for assay library generation - type: File[] - in_id: - doc: FeatureXML input file(s) containing identification information (e.g. AccurateMassSearch) - type: File[] - out: - doc: Assay library output file - type: string - fragment_annotation: - doc: Fragment annotation method - type: string? - ambiguity_resolution_mz_tolerance: - doc: Mz tolerance for the resolution of identification ambiguity over multiple files - type: double? - ambiguity_resolution_mz_tolerance_unit: - doc: Unit of the ambiguity_resolution_mz_tolerance - type: string? - ambiguity_resolution_rt_tolerance: - doc: RT tolerance in seconds for the resolution of identification ambiguity over multiple files - type: double? - total_occurrence_filter: - doc: Filter compound based on total occurrence in analysed samples - type: double? - fragment_annotation_score_threshold: - doc: Filters annotations based on the explained intensity of the peaks in a spectrum - type: double? - decoy_generation: - doc: Decoys will be generated using the fragmentation tree re-rooting approach. This option does only work in combination with the fragment annotation via Sirius. - type: boolean? - decoy_generation_method: - doc: Uses different methods for decoy generation. Basis for the method is the fragmentation-tree re-rooting approach ('original'). This approach can be extended by using 'resolve_overlap', which will resolve overlapping fragments of the highest intensity fragments chosen, by adding -CH2 mass to the overlapping fragments. 'Add_shift' will add a -CH2 mass shift to the target fragments and use them as additional decoys if fragmentation-tree re-rooting failed. 'Both' combines the extended methods (resolve_overlap, add_shift). - type: string? - method: - doc: Spectrum with the highest precursor intensity or a consensus spectrum is used for assay library construction (if no fragment annotation is used). - type: string? - use_exact_mass: - doc: Use exact mass for precursor and fragment annotations - type: boolean? - exclude_ms2_precursor: - doc: Excludes precursor in ms2 from transition list - type: boolean? - precursor_mz_distance: - doc: Max m/z distance of the precursor entries of two spectra to be merged in [Da]. - type: double? - precursor_recalibration_window: - doc: Tolerance window for precursor selection (Annotation of precursor mz and intensity) - type: double? - precursor_recalibration_window_unit: - doc: Unit of the precursor_mz_tolerance_annotation - type: string? - consensus_spectrum_precursor_rt_tolerance: - doc: Tolerance window (left and right) for precursor selection [seconds], for consensus spectrum generation (only available without fragment annotation) - type: double? - use_known_unknowns: - doc: Use features without identification information - type: boolean? - min_transitions: - doc: Minimal number of transitions - type: long? - max_transitions: - doc: Maximal number of transitions - type: long? - cosine_similarity_threshold: - doc: Threshold for cosine similarity of MS2 spectra from the same precursor used in consensus spectrum creation - type: double? - transition_threshold: - doc: Further transitions need at least x% of the maximum intensity (default 5%) - type: double? - min_fragment_mz: - doc: Minimal m/z of a fragment ion choosen as a transition - type: double? - max_fragment_mz: - doc: Maximal m/z of a fragment ion choosen as a transition - type: double? - read_sirius_stdout: - doc: Read and print the standard output and error of the Sirius executable, even if it succeeds. - type: boolean? - out_workspace_directory: - doc: Output directory for SIRIUS workspace - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - deisotoping__use_deisotoper: - doc: Use Deisotoper (if no fragment annotation is used) - type: boolean? - deisotoping__fragment_tolerance: - doc: Tolerance used to match isotopic peaks - type: double? - deisotoping__fragment_unit: - doc: Unit of the fragment tolerance - type: string? - deisotoping__min_charge: - doc: The minimum charge considered - type: long? - deisotoping__max_charge: - doc: The maximum charge considered - type: long? - deisotoping__min_isopeaks: - doc: The minimum number of isotopic peaks (at least 2) required for an isotopic cluster - type: long? - deisotoping__max_isopeaks: - doc: The maximum number of isotopic peaks (at least 2) considered for an isotopic cluster - type: long? - deisotoping__keep_only_deisotoped: - doc: Only monoisotopic peaks of fragments with isotopic pattern are retained - type: boolean? - deisotoping__annotate_charge: - doc: Annotate the charge to the peaks - type: boolean? - preprocessing__filter_by_num_masstraces: - doc: Number of mass traces each feature has to have to be included. To use this parameter, setting the feature_only flag is necessary - type: long? - preprocessing__precursor_mz_tolerance: - doc: Tolerance window for precursor selection (Feature selection in regard to the precursor) - type: double? - preprocessing__precursor_mz_tolerance_unit: - doc: Unit of the precursor_mz_tolerance - type: string? - preprocessing__precursor_rt_tolerance: - doc: Tolerance window (left and right) for precursor selection [seconds] - type: double? - preprocessing__isotope_pattern_iterations: - doc: Number of iterations that should be performed to extract the C13 isotope pattern. If no peak is found (C13 distance) the function will abort. Be careful with noisy data - since this can lead to wrong isotope patterns - type: long? - preprocessing__feature_only: - doc: Uses the feature information from in_featureinfo to reduce the search space to MS2 associated with a feature - type: boolean? - preprocessing__no_masstrace_info_isotope_pattern: - doc: Use this flag if the masstrace information from a feature should be discarded and the isotope_pattern_iterations should be used instead - type: boolean? - project__maxmz: - doc: "Just consider compounds with a precursor mz lower or equal\nthis maximum mz. All other compounds in the input file\nare ignored." - type: long? - project__processors: - doc: Number of cpu cores to use. If not specified SIRIUS uses all available cores. - type: long? - project__loglevel: - doc: "Set logging level of the Jobs SIRIUS will execute.\nValid values: SEVERE, WARNING, INFO, FINER, ALL\nDefault: WARNING" - type: string? - project__ignore_formula: - doc: Ignore given molecular formula in internal .ms format, while processing. - type: boolean? - project__q: - doc: Suppress shell output - type: boolean? - sirius__ppm_max: - doc: Maximum allowed mass deviation in ppm for decomposing masses [ppm]. - type: double? - sirius__ppm_max_ms2: - doc: "Maximum allowed mass deviation in ppm for decomposing masses in MS2 [ppm].If not specified, the same value as for the MS1 is used. " - type: double? - sirius__tree_timeout: - doc: Time out in seconds per fragmentation tree computations. 0 for an infinite amount of time - type: long? - sirius__compound_timeout: - doc: Maximal computation time in seconds for a single compound. 0 for an infinite amount of time. - type: long? - sirius__no_recalibration: - doc: Disable recalibration of input spectra - type: boolean? - sirius__profile: - doc: Name of the configuration profile - type: string? - sirius__formulas: - doc: Specify the neutral molecular formula of the measured compound to compute its tree or a list of candidate formulas the method should discriminate. Omit this option if you want to consider all possible molecular formulas - type: string? - sirius__ions_enforced: - doc: "The iontype/adduct of the MS/MS data. Example: [M+H]+, \n[M-H]-, [M+Cl]-, [M+Na]+, [M]+. You can also provide a \ncomma separated list of adducts." - type: string? - sirius__candidates: - doc: The number of formula candidates in the SIRIUS output - type: long? - sirius__candidates_per_ion: - doc: Minimum number of candidates in the output for each ionization. Set to force output of results for each possible ionization, even if not part of highest ranked results. - type: long? - sirius__elements_considered: - doc: Set the allowed elements for rare element detection. Write SBrClBSe to allow the elements S,Br,Cl,B and Se. - type: string? - sirius__elements_enforced: - doc: "Enforce elements for molecular formula determination. Write CHNOPSCl to allow the elements C, H, N, O, P, S and Cl. Add numbers in brackets to restrict the minimal and maximal allowed occurrence of these elements: CHNOP[5]S[8]Cl[1-2]. When one number is given then it is interpreted as upper bound." - type: string? - sirius__no_isotope_score: - doc: Disable isotope pattern score. - type: boolean? - sirius__no_isotope_filter: - doc: Disable molecular formula filter. When filtering is enabled, molecular formulas are excluded if their theoretical isotope pattern does not match the theoretical one, even if their MS/MS pattern has high score. - type: boolean? - sirius__ions_considered: - doc: "the iontype/adduct of the MS/MS data. Example: [M+H]+, [M-H]-, [M+Cl]-, [M+Na]+, [M]+. You can also provide a comma separated list of adducts." - type: string? - sirius__db: - doc: "Search formulas in the Union of the given databases db-name1,db-name2,db-name3. If no database is given all possible molecular formulas will be respected (no database is used). Example: possible DBs: ALL,BIO,PUBCHEM,MESH,HMDB,KNAPSACK,CHEBI,PUBMED,KEGG,HSDB,MACONDA,METACYC,GNPS,ZINCBIO,UNDP,YMDB,PLANTCYC,NORMAN,ADDITIONAL,PUBCHEMANNOTATIONBIO,PUBCHEMANNOTATIONDRUG,PUBCHEMANNOTATIONSAFETYANDTOXIC,PUBCHEMANNOTATIONFOOD,KEGGMINE,ECOCYCMINE,YMDBMINE" - type: string? - sirius__solver: - doc: "For GUROBI and CPLEX environment variables need to be configured. \n(see SIRIUS manual: https://boecker-lab.github.io/docs.sirius.github.io/install/)." - type: string? - fingerid__db: - doc: "Search structures in the Union of the given databases db-name1,db-name2,db-name3. If no database is given all possible molecular formulas will be respected (no database is used). Example: possible DBs: ALL,BIO,PUBCHEM,MESH,HMDB,KNAPSACK,CHEBI,PUBMED,KEGG,HSDB,MACONDA,METACYC,GNPS,ZINCBIO,UNDP,YMDB,PLANTCYC,NORMAN,ADDITIONAL,PUBCHEMANNOTATIONBIO,PUBCHEMANNOTATIONDRUG,PUBCHEMANNOTATIONSAFETYANDTOXIC,PUBCHEMANNOTATIONFOOD,KEGGMINE,ECOCYCMINE,YMDBMINE" - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - AssayGeneratorMetabo -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/BaselineFilter.cwl b/workflow/cwl/BaselineFilter.cwl deleted file mode 100644 index 98c7866535b..00000000000 --- a/workflow/cwl/BaselineFilter.cwl +++ /dev/null @@ -1,56 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: BaselineFilter -doc: Removes the baseline from profile spectra using a top-hat filter. -inputs: - in: - doc: "input raw data file " - type: File - out: - doc: "output raw data file " - type: string - struc_elem_length: - doc: Length of the structuring element (should be wider than maximal peak width - see documentation). - type: double? - struc_elem_unit: - doc: Unit of 'struc_elem_length' parameter. - type: string? - method: - doc: The name of the morphological filter to be applied. If you are unsure, use the default. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - BaselineFilter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/CVInspector.cwl b/workflow/cwl/CVInspector.cwl deleted file mode 100644 index 1dedb4ae41d..00000000000 --- a/workflow/cwl/CVInspector.cwl +++ /dev/null @@ -1,56 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: CVInspector -doc: Visualize and validate PSI mapping and CV files. -inputs: - cv_files: - doc: List of ontology files in OBO format. - type: File[] - cv_names: - doc: List of identifiers (one for each ontology file). - type: string[] - mapping_file: - doc: Mapping file in CVMapping (XML) format. - type: File - ignore_cv: - doc: A list of CV identifiers which should be ignored. - type: string[]? - html: - doc: Writes an HTML version of the mapping file with annotated CV terms - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - html: - type: File? - outputBinding: - glob: $(inputs.html) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - CVInspector -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/ClusterMassTraces.cwl b/workflow/cwl/ClusterMassTraces.cwl deleted file mode 100644 index 1a28d65b824..00000000000 --- a/workflow/cwl/ClusterMassTraces.cwl +++ /dev/null @@ -1,65 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: ClusterMassTraces -doc: Creates pseudo spectra. -inputs: - in: - doc: Mass traces - type: File - out: - doc: output file - type: string - min_pearson_correlation: - doc: Minimal pearson correlation score - type: double? - min_peak_nr: - doc: Minimal peak nr to output pseudo spectra - type: long? - max_lag: - doc: Maximal lag - type: long? - max_rt_apex_difference: - doc: Maximal difference of the apex in retention time - type: double? - max_intensity_cutoff: - doc: Maximal intensity to be added to a spectrum - type: double? - add_precursor: - doc: Add a precursor mass - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - ClusterMassTraces -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/ClusterMassTracesByPrecursor.cwl b/workflow/cwl/ClusterMassTracesByPrecursor.cwl deleted file mode 100644 index 66eb6350b10..00000000000 --- a/workflow/cwl/ClusterMassTracesByPrecursor.cwl +++ /dev/null @@ -1,71 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: ClusterMassTracesByPrecursor -doc: Correlate precursor masstraces with fragment ion masstraces in SWATH maps based on their elution profile. -inputs: - in_ms1: - doc: MS1 mass traces - type: File - in_swath: - doc: MS2 / SWATH mass traces - type: File - out: - doc: output file - type: string - assign_unassigned_to_all: - doc: Assign unassigned MS2 fragments to all precursors (only for ms1_centrif) - type: boolean? - min_pearson_correlation: - doc: Minimal pearson correlation score to match elution profiles to each other. - type: double? - max_lag: - doc: Maximal lag (e.g. by how many spectra the peak may be shifted at most). This parameter will depend on your chromatographic setup but a number between 1 and 3 is usually sensible. - type: long? - min_nr_ions: - doc: Minimal number of ions to report a spectrum. - type: long? - max_rt_apex_difference: - doc: Maximal difference of the apex in retention time (in seconds). This is a hard parameter, all profiles further away will not be considered at all. - type: double? - swath_lower: - doc: Swath lower isolation window - type: double? - swath_upper: - doc: Swath upper isolation window - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - ClusterMassTracesByPrecursor -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/CometAdapter.cwl b/workflow/cwl/CometAdapter.cwl deleted file mode 100644 index 81c33ca4dee..00000000000 --- a/workflow/cwl/CometAdapter.cwl +++ /dev/null @@ -1,228 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: CometAdapter -doc: Annotates MS/MS spectra using Comet. -inputs: - in: - doc: Input file - type: File - out: - doc: Output file - type: string - database: - doc: FASTA file - type: File - comet_executable: - doc: The Comet executable. Provide a full or relative path, or make sure it can be found in your PATH environment. - type: File - pin_out: - doc: Output file - for Percolator input - type: string? - default_params_file: - doc: Default Comet params file. All parameters of this take precedence. A template file can be generated using 'comet.exe -p' - type: File? - precursor_mass_tolerance: - doc: "Precursor monoisotopic mass tolerance (Comet parameter: peptide_mass_tolerance). See also precursor_error_units to set the unit." - type: double? - precursor_error_units: - doc: "Unit of precursor monoisotopic mass tolerance for parameter precursor_mass_tolerance (Comet parameter: peptide_mass_units)" - type: string? - isotope_error: - doc: This parameter controls whether the peptide_mass_tolerance takes into account possible isotope errors in the precursor mass measurement. Use -8/-4/0/4/8 only for SILAC. - type: string? - fragment_mass_tolerance: - doc: "This is half the bin size, which is used to segment the MS/MS spectrum. Thus, the value should be a bit higher than for other search engines, since the bin might not be centered around the peak apex (see 'fragment_bin_offset').CAUTION: Low tolerances have heavy impact on RAM usage (since Comet uses a lot of bins in this case). Consider using use_sparse_matrix and/or spectrum_batch_size." - type: double? - fragment_error_units: - doc: Fragment monoisotopic mass error units - type: string? - fragment_bin_offset: - doc: "Offset of fragment bins. Recommended by Comet: low-res: 0.4, high-res: 0.0" - type: double? - instrument: - doc: "Comets theoretical_fragment_ions parameter: theoretical fragment ion peak representation, high-res: sum of intensities plus flanking bins, ion trap (low-res) ms/ms: sum of intensities of central M bin only" - type: string? - use_A_ions: - doc: use A ions for PSM - type: boolean? - use_B_ions: - doc: use B ions for PSM - type: string? - use_C_ions: - doc: use C ions for PSM - type: boolean? - use_X_ions: - doc: use X ions for PSM - type: boolean? - use_Y_ions: - doc: use Y ions for PSM - type: string? - use_Z_ions: - doc: use Z ions for PSM - type: boolean? - use_NL_ions: - doc: use neutral loss (NH3, H2O) ions from b/y for PSM - type: boolean? - enzyme: - doc: The enzyme used for peptide digestion. - type: string? - second_enzyme: - doc: Additional enzyme used for peptide digestion. - type: string? - num_enzyme_termini: - doc: Specify the termini where the cleavage rule has to match - type: string? - missed_cleavages: - doc: Number of possible cleavage sites missed by the enzyme. It has no effect if enzyme is unspecific cleavage. - type: long? - min_peptide_length: - doc: Minimum peptide length to consider. - type: long? - max_peptide_length: - doc: Maximum peptide length to consider. - type: long? - num_hits: - doc: Number of peptide hits (PSMs) per spectrum in output file - type: long? - precursor_charge: - doc: "Precursor charge range to search (if spectrum is not annotated with a charge or if override_charge!=keep any known): 0:[num] == search all charges, 2:6 == from +2 to +6, 3:3 == +3" - type: string? - override_charge: - doc: "_keep any known_: keep any precursor charge state (from input), _ignore known_: ignore known precursor charge state and use precursor_charge parameter, _ignore outside range_: ignore precursor charges outside precursor_charge range, _keep known search unknown_: keep any known precursor charge state. For unknown charge states, search as singly charged if there is no signal above the precursor m/z or use the precursor_charge range" - type: string? - ms_level: - doc: MS level to analyze, valid are levels 2 (default) or 3 - type: long? - activation_method: - doc: If not ALL, only searches spectra of the given method - type: string? - digest_mass_range: - doc: MH+ peptide mass range to analyze - type: string? - max_fragment_charge: - doc: Set maximum fragment charge state to analyze as long as still lower than precursor charge - 1. (Allowed max 5) - type: long? - max_precursor_charge: - doc: set maximum precursor charge state to analyze (allowed max 9) - type: long? - clip_nterm_methionine: - doc: If set to true, also considers the peptide sequence w/o N-term methionine separately and applies appropriate N-term mods to it - type: boolean? - spectrum_batch_size: - doc: max. number of spectra to search at a time; use 0 to search the entire scan range in one batch - type: long? - mass_offsets: - doc: One or more mass offsets to search (values subtracted from deconvoluted precursor mass). Has to include 0.0 if you want the default mass to be searched. - type: double[]? - minimum_peaks: - doc: Required minimum number of peaks in spectrum to search (default 10) - type: long? - minimum_intensity: - doc: Minimum intensity value to read in - type: double? - remove_precursor_peak: - doc: no = no removal, yes = remove all peaks around precursor m/z, charge_reduced = remove all charge reduced precursor peaks (for ETD/ECD). phosphate_loss = remove the HPO3 (-80) and H3PO4 (-98) precursor phosphate neutral loss peaks. See also remove_precursor_tolerance - type: string? - remove_precursor_tolerance: - doc: one-sided tolerance for precursor removal in Thompson - type: double? - clear_mz_range: - doc: for iTRAQ/TMT type data; will clear out all peaks in the specified m/z range, if not 0:0 - type: string? - fixed_modifications: - doc: Fixed modifications, specified using Unimod (www.unimod.org) terms, e.g. 'Carbamidomethyl (C)' or 'Oxidation (M)' - type: string[]? - variable_modifications: - doc: Variable modifications, specified using Unimod (www.unimod.org) terms, e.g. 'Carbamidomethyl (C)' or 'Oxidation (M)' - type: string[]? - binary_modifications: - doc: "List of modification group indices. Indices correspond to the binary modification index used by comet to group individually searched lists of variable modifications.\nNote: if set, both variable_modifications and binary_modifications need to have the same number of entries as the N-th entry corresponds to the N-th variable_modification.\n if left empty (default), all entries are internally set to 0 generating all permutations of modified and unmodified residues.\n For a detailed explanation please see the parameter description in the Comet help." - type: long[]? - max_variable_mods_in_peptide: - doc: Set a maximum number of variable modifications per peptide - type: long? - require_variable_mod: - doc: If true, requires at least one variable modification per peptide - type: boolean? - reindex: - doc: Recalculate peptide to protein association using OpenMS. Annotates target-decoy information. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - PeptideIndexing__decoy_string: - doc: String that was appended (or prefixed - see 'decoy_string_position' flag below) to the accessions in the protein database to indicate decoy proteins. If empty (default), it's determined automatically (checking for common terms, both as prefix and suffix). - type: string? - PeptideIndexing__decoy_string_position: - doc: Is the 'decoy_string' prepended (prefix) or appended (suffix) to the protein accession? (ignored if decoy_string is empty) - type: string? - PeptideIndexing__missing_decoy_action: - doc: "Action to take if NO peptide was assigned to a decoy protein (which indicates wrong database or decoy string): 'error' (exit with error, no output), 'warn' (exit with success, warning message), 'silent' (no action is taken, not even a warning)" - type: string? - PeptideIndexing__write_protein_sequence: - doc: If set, the protein sequences are stored as well. - type: boolean? - PeptideIndexing__write_protein_description: - doc: If set, the protein description is stored as well. - type: boolean? - PeptideIndexing__keep_unreferenced_proteins: - doc: If set, protein hits which are not referenced by any peptide are kept. - type: boolean? - PeptideIndexing__unmatched_action: - doc: "If peptide sequences cannot be matched to any protein: 1) raise an error; 2) warn (unmatched PepHits will miss target/decoy annotation with downstream problems); 3) remove the hit." - type: string? - PeptideIndexing__aaa_max: - doc: Maximal number of ambiguous amino acids (AAAs) allowed when matching to a protein database with AAAs. AAAs are 'B', 'J', 'Z' and 'X'. - type: long? - PeptideIndexing__mismatches_max: - doc: Maximal number of mismatched (mm) amino acids allowed when matching to a protein database. The required runtime is exponential in the number of mm's; apply with care. MM's are allowed in addition to AAA's. - type: long? - PeptideIndexing__IL_equivalent: - doc: Treat the isobaric amino acids isoleucine ('I') and leucine ('L') as equivalent (indistinguishable). Also occurrences of 'J' will be treated as 'I' thus avoiding ambiguous matching. - type: boolean? - PeptideIndexing__allow_nterm_protein_cleavage: - doc: Allow the protein N-terminus amino acid to clip. - type: string? - PeptideIndexing__enzyme__name: - doc: "Enzyme which determines valid cleavage sites - e.g. trypsin cleaves after lysine (K) or arginine (R), but not before proline (P). Default: deduce from input" - type: string? - PeptideIndexing__enzyme__specificity: - doc: "Specificity of the enzyme. Default: deduce from input.\n 'full': both internal cleavage sites must match.\n 'semi': one of two internal cleavage sites must match.\n 'none': allow all peptide hits no matter their context (enzyme is irrelevant)." - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - pin_out: - type: File? - outputBinding: - glob: $(inputs.pin_out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - CometAdapter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/ConsensusID.cwl b/workflow/cwl/ConsensusID.cwl deleted file mode 100644 index 7550a70fd25..00000000000 --- a/workflow/cwl/ConsensusID.cwl +++ /dev/null @@ -1,83 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: ConsensusID -doc: Computes a consensus of peptide identifications of several identification engines. -inputs: - in: - doc: input file - type: File[] - out: - doc: output file - type: string - rt_delta: - doc: "[idXML input only] Maximum allowed retention time deviation between identifications belonging to the same spectrum." - type: double? - mz_delta: - doc: "[idXML input only] Maximum allowed precursor m/z deviation between identifications belonging to the same spectrum." - type: double? - per_spectrum: - doc: (only idXML) if set, mapping will be done based on exact matching of originating mzml file and spectrum_ref - type: boolean? - algorithm: - doc: "Algorithm used for consensus scoring.\n* PEPMatrix: Scoring based on posterior error probabilities (PEPs) and peptide sequence similarities (scored by a substitution matrix). Requires PEPs as scores.\n* PEPIons: Scoring based on posterior error probabilities (PEPs) and fragment ion similarities ('shared peak count'). Requires PEPs as scores.\n* best: For each peptide ID, use the best score of any search engine as the consensus score. Requires the same score type in all ID runs.\n* worst: For each peptide ID, use the worst score of any search engine as the consensus score. Requires the same score type in all ID runs.\n* average: For each peptide ID, use the average score of all search engines as the consensus. Requires the same score type in all ID runs.\n* ranks: Calculates a consensus score based on the ranks of peptide IDs in the results of different search engines. The final score is in the range (0, 1], with 1 being the best score. No requirements about score types." - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - filter__considered_hits: - doc: The number of top hits in each ID run that are considered for consensus scoring ('0' for all hits). - type: long? - filter__min_support: - doc: For each peptide hit from an ID run, the fraction of other ID runs that must support that hit (otherwise it is removed). - type: double? - filter__count_empty: - doc: Count empty ID runs (i.e. those containing no peptide hit for the current spectrum) when calculating 'min_support'? - type: boolean? - filter__keep_old_scores: - doc: if set, keeps the original scores as user params - type: boolean? - PEPIons__mass_tolerance: - doc: Maximum difference between fragment masses (in Da) for fragments to be considered 'shared' between peptides . - type: double? - PEPIons__min_shared: - doc: The minimal number of 'shared' fragments (between two suggested peptides) that is necessary to evaluate the similarity based on shared peak count (SPC). - type: long? - PEPMatrix__matrix: - doc: Substitution matrix to use for alignment-based similarity scoring - type: string? - PEPMatrix__penalty: - doc: Alignment gap penalty (the same value is used for gap opening and extension) - type: long? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - ConsensusID -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/ConsensusMapNormalizer.cwl b/workflow/cwl/ConsensusMapNormalizer.cwl deleted file mode 100644 index d8fe83e29ce..00000000000 --- a/workflow/cwl/ConsensusMapNormalizer.cwl +++ /dev/null @@ -1,59 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: ConsensusMapNormalizer -doc: Normalizes maps of one consensusXML file -inputs: - in: - doc: input file - type: File - out: - doc: output file - type: string - algorithm_type: - doc: "The normalization algorithm that is applied. 'robust_regression' scales each map by a fator computed from the ratios of non-differential background features (as determined by the ratio_threshold parameter), 'quantile' performs quantile normalization, 'median' scales all maps to the same median intensity, 'median_shift' shifts the median instead of scaling (WARNING: if you have regular, log-normal MS data, 'median_shift' is probably the wrong choice. Use only if you know what you're doing!)" - type: string? - ratio_threshold: - doc: "Only for 'robust_regression': the parameter is used to distinguish between non-outliers (ratio_threshold < intensity ratio < 1/ratio_threshold) and outliers." - type: double? - accession_filter: - doc: Use only features with accessions (partially) matching this regular expression for computing the normalization factors. Useful, e.g., if you have known house keeping proteins in your samples. When this parameter is empty or the regular expression matches the empty string, all features are used (even those without an ID). No effect if quantile normalization is used. - type: string? - description_filter: - doc: Use only features with description (partially) matching this regular expression for computing the normalization factors. Useful, e.g., if you have known house keeping proteins in your samples. When this parameter is empty or the regular expression matches the empty string, all features are used (even those without an ID). No effect if quantile normalization is used. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - ConsensusMapNormalizer -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/DTAExtractor.cwl b/workflow/cwl/DTAExtractor.cwl deleted file mode 100644 index 9fc0efead21..00000000000 --- a/workflow/cwl/DTAExtractor.cwl +++ /dev/null @@ -1,53 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: DTAExtractor -doc: Extracts spectra of an MS run file to several files in DTA format. -inputs: - in: - doc: "input file " - type: File - out: - doc: base name of DTA output files (RT, m/z and extension are appended) - type: string - mz: - doc: "m/z range of precursor peaks to extract.\nThis option is ignored for MS level 1" - type: string? - rt: - doc: retention time range of spectra to extract - type: string? - level: - doc: MS levels to extract - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - [] -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - DTAExtractor -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/DatabaseFilter.cwl b/workflow/cwl/DatabaseFilter.cwl deleted file mode 100644 index 1b2e59e4887..00000000000 --- a/workflow/cwl/DatabaseFilter.cwl +++ /dev/null @@ -1,53 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: DatabaseFilter -doc: Filters a protein database (FASTA format) based on identified proteins -inputs: - in: - doc: Input FASTA file, containing a database. - type: File - id: - doc: Input file containing identified peptides and proteins. - type: File - method: - doc: Switch between white-/blacklisting - type: string? - out: - doc: Output FASTA file where the reduced database will be written to. - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - DatabaseFilter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/DatabaseSuitability.cwl b/workflow/cwl/DatabaseSuitability.cwl deleted file mode 100644 index 966e6406c8f..00000000000 --- a/workflow/cwl/DatabaseSuitability.cwl +++ /dev/null @@ -1,83 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: DatabaseSuitability -doc: Computes a suitability score for a database which was used for a peptide identification search. Also reports the quality of LC-MS spectra. -inputs: - in_id: - doc: Input idXML file from a peptide identification search with a combined database. PeptideIndexer is needed, FDR is forbidden. - type: File - in_spec: - doc: Input MzML file used for the peptide identification - type: File - in_novo: - doc: Input idXML file containing de novo peptides (unfiltered) - type: File - database: - doc: Input FASTA file of the database in question - type: File - novo_database: - doc: Input deNovo sequences derived from MzML given in 'in_spec' concatenated to one FASTA entry - type: File - out: - doc: Optional tsv output containing database suitability information as well as spectral quality. - type: string? - novo_threshold: - doc: Minimum score a de novo sequence has to have to be defined as 'correct'. The default of 60 is proven to be a good estimate for sequences generated by Novor. - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__no_rerank: - doc: Use this flag if you want to disable re-ranking. Cases, where a de novo peptide scores just higher than the database peptide, are overlooked and counted as a de novo hit. This might underestimate the database quality. - type: boolean? - algorithm__reranking_cutoff_percentile: - doc: Swap a top-scoring deNovo hit with a lower scoring DB hit if their xcorr score difference is in the given percentile of all score differences between the first two decoy hits of a PSM. The lower the value the lower the decoy cut-off will be. Therefore it will be harder for a lower scoring DB hit to be re-ranked to the top. - type: double? - algorithm__FDR: - doc: Filter peptide hits based on this q-value. (e.g., 0.05 = 5 % FDR) - type: double? - algorithm__number_of_subsampled_runs: - doc: "Controls how many runs should be done for calculating corrected suitability. (0 : number of runs will be estimated automaticly) ATTENTION: For each run a seperate ID-search is performed. This can result in some serious run time." - type: long? - algorithm__keep_search_files: - doc: Set this flag if you wish to keep the files used by and produced by the internal ID search. - type: boolean? - algorithm__disable_correction: - doc: Set this flag to disable the calculation of the corrected suitability. - type: boolean? - algorithm__force: - doc: Set this flag to enforce re-ranking when no cross correlation score is present. For re-ranking the default score found at each peptide hit is used. Use with care! - type: boolean? -outputs: - out: - type: File? - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - DatabaseSuitability -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/DeMeanderize.cwl b/workflow/cwl/DeMeanderize.cwl deleted file mode 100644 index 16241f13c68..00000000000 --- a/workflow/cwl/DeMeanderize.cwl +++ /dev/null @@ -1,53 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: DeMeanderize -doc: Orders the spectra of MALDI spotting plates correctly. -inputs: - in: - doc: Input experiment file, containing the wrongly sorted spectra. - type: File - out: - doc: Output experiment file with correctly sorted spectra. - type: string - num_spots_per_row: - doc: Number of spots in one column, until next row is spotted. - type: long? - RT_distance: - doc: RT distance between two spots which is used to calculated pseudo RT. - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - DeMeanderize -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/Decharger.cwl b/workflow/cwl/Decharger.cwl deleted file mode 100644 index a213ebb58ae..00000000000 --- a/workflow/cwl/Decharger.cwl +++ /dev/null @@ -1,106 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: Decharger -doc: Decharges and merges different feature charge variants of the same peptide. -inputs: - in: - doc: "input file " - type: File - out_cm: - doc: output consensus map - type: string - out_fm: - doc: output feature map - type: string? - outpairs: - doc: output file - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__FeatureDeconvolution__charge_min: - doc: Minimal possible charge - type: long? - algorithm__FeatureDeconvolution__charge_max: - doc: Maximal possible charge - type: long? - algorithm__FeatureDeconvolution__charge_span_max: - doc: Maximal range of charges for a single analyte, i.e. observing q1=[5,6,7] implies span=3. Setting this to 1 will only find adduct variants of the same charge - type: long? - algorithm__FeatureDeconvolution__q_try: - doc: Try different values of charge for each feature according to the above settings ('heuristic' [does not test all charges, just the likely ones] or 'all' ), or leave feature charge untouched ('feature'). - type: string? - algorithm__FeatureDeconvolution__retention_max_diff: - doc: Maximum allowed RT difference between any two features if their relation shall be determined - type: double? - algorithm__FeatureDeconvolution__retention_max_diff_local: - doc: Maximum allowed RT difference between between two co-features, after adduct shifts have been accounted for (if you do not have any adduct shifts, this value should be equal to 'retention_max_diff', otherwise it should be smaller!) - type: double? - algorithm__FeatureDeconvolution__mass_max_diff: - doc: Maximum allowed mass difference [in Th] for a single feature. - type: double? - algorithm__FeatureDeconvolution__potential_adducts: - doc: "Adducts used to explain mass differences in format: 'Element:Charge(+/-):Probability[:RTShift[:Label]]', i.e. the number of '+' or '-' indicate the charge, e.g. 'Ca:++:0.5' indicates +2. Probabilites have to be in (0,1]. RTShift param is optional and indicates the expected RT shift caused by this adduct, e.g. '(2)H4H-4:0:1:-3' indicates a 4 deuterium label, which causes early elution by 3 seconds. As a fifth parameter you can add a label which is tagged on every feature which has this adduct. This also determines the map number in the consensus file." - type: string[]? - algorithm__FeatureDeconvolution__max_neutrals: - doc: Maximal number of neutral adducts(q=0) allowed. Add them in the 'potential_adducts' section! - type: long? - algorithm__FeatureDeconvolution__max_minority_bound: - doc: Maximum count of the least probable adduct (according to 'potential_adducts' param) within a charge variant. E.g. setting this to 2 will not allow an adduct composition of '1(H+),3(Na+)' if Na+ is the least probable adduct - type: long? - algorithm__FeatureDeconvolution__min_rt_overlap: - doc: Minimum overlap of the convex hull' RT intersection measured against the union from two features (if CHs are given) - type: double? - algorithm__FeatureDeconvolution__intensity_filter: - doc: Enable the intensity filter, which will only allow edges between two equally charged features if the intensity of the feature with less likely adducts is smaller than that of the other feature. It is not used for features of different charge. - type: boolean? - algorithm__FeatureDeconvolution__negative_mode: - doc: Enable negative ionization mode. - type: string? - algorithm__FeatureDeconvolution__default_map_label: - doc: Label of map in output consensus file where all features are put by default - type: string? - algorithm__FeatureDeconvolution__verbose_level: - doc: Amount of debug information given during processing. - type: long? -outputs: - out_cm: - type: File - outputBinding: - glob: $(inputs.out_cm) - out_fm: - type: File? - outputBinding: - glob: $(inputs.out_fm) - outpairs: - type: File? - outputBinding: - glob: $(inputs.outpairs) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - Decharger -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/DecoyDatabase.cwl b/workflow/cwl/DecoyDatabase.cwl deleted file mode 100644 index f13cd6c566e..00000000000 --- a/workflow/cwl/DecoyDatabase.cwl +++ /dev/null @@ -1,83 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: DecoyDatabase -doc: Create decoy sequence database from forward sequence database. -inputs: - in: - doc: Input FASTA file(s), each containing a database. It is recommended to include a contaminant database as well. - type: File[] - out: - doc: Output FASTA file where the decoy database will be written to. - type: string - decoy_string: - doc: String that is combined with the accession of the protein identifier to indicate a decoy protein. - type: string? - decoy_string_position: - doc: Should the 'decoy_string' be prepended (prefix) or appended (suffix) to the protein accession? - type: string? - only_decoy: - doc: Write only decoy proteins to the output database instead of a combined database. - type: boolean? - type: - doc: Type of sequence. RNA sequences may contain modification codes, which will be handled correctly if this is set to 'RNA'. - type: string? - method: - doc: Method by which decoy sequences are generated from target sequences. Note that all sequences are shuffled using the same random seed, ensuring that identical sequences produce the same shuffled decoy sequences. Shuffled sequences that produce highly similar output sequences are shuffled again (see shuffle_sequence_identity_threshold). - type: string? - shuffle_max_attempts: - doc: "shuffle: maximum attempts to lower the amino acid sequence identity between target and decoy for the shuffle algorithm" - type: long? - shuffle_sequence_identity_threshold: - doc: "shuffle: target-decoy amino acid sequence identity threshold for the shuffle algorithm. If the sequence identity is above this threshold, shuffling is repeated. In case of repeated failure, individual amino acids are 'mutated' to produce a different amino acid sequence." - type: double? - seed: - doc: Random number seed (use 'time' for system time) - type: string? - enzyme: - doc: Enzyme used for the digestion of the sample. Only applicable if parameter 'type' is 'protein'. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - Decoy__non_shuffle_pattern: - doc: Residues to not shuffle (keep at a constant position when shuffling). Separate by comma, e.g. use 'K,P,R' here. - type: string? - Decoy__keepPeptideNTerm: - doc: Whether to keep peptide N terminus constant when shuffling / reversing. - type: string? - Decoy__keepPeptideCTerm: - doc: Whether to keep peptide C terminus constant when shuffling / reversing. - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - DecoyDatabase -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/Digestor.cwl b/workflow/cwl/Digestor.cwl deleted file mode 100644 index fe9539f8ea3..00000000000 --- a/workflow/cwl/Digestor.cwl +++ /dev/null @@ -1,68 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: Digestor -doc: Digests a protein database in-silico. -inputs: - in: - doc: input file - type: File - out: - doc: Output file (peptides) - type: string - out_type: - doc: Set this if you cannot control the filename of 'out', e.g., in TOPPAS. - type: string? - missed_cleavages: - doc: The number of allowed missed cleavages - type: long? - min_length: - doc: Minimum length of peptide - type: long? - max_length: - doc: Maximum length of peptide - type: long? - enzyme: - doc: The type of digestion enzyme - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - FASTA__ID: - doc: "Identifier to use for each peptide: copy from parent protein (parent); a consecutive number (number); parent ID + consecutive number (both)" - type: string? - FASTA__description: - doc: Keep or remove the (possibly lengthy) FASTA header description. Keeping it can increase resulting FASTA file significantly. - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - Digestor -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/DigestorMotif.cwl b/workflow/cwl/DigestorMotif.cwl deleted file mode 100644 index d51c96fc20b..00000000000 --- a/workflow/cwl/DigestorMotif.cwl +++ /dev/null @@ -1,65 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: DigestorMotif -doc: Digests a protein database in-silico -inputs: - in: - doc: FASTA input file - type: File - out: - doc: "output file (peptides)\n" - type: string - missed_cleavages: - doc: the number of allowed missed cleavages - type: long? - mass_accuracy: - doc: give your mass accuracy in ppb - type: long? - min_length: - doc: minimum length of peptide - type: long? - out_option: - doc: indicate 1 (peptide table only), 2 (statistics only) or (both peptide table + statistics) - type: long? - enzyme: - doc: The enzyme used for peptide digestion. - type: string? - motif: - doc: the motif for the restricted peptidome - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - DigestorMotif -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/EICExtractor.cwl b/workflow/cwl/EICExtractor.cwl deleted file mode 100644 index bb314d2f17e..00000000000 --- a/workflow/cwl/EICExtractor.cwl +++ /dev/null @@ -1,81 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: EICExtractor -doc: Extracts intensities from dedicates positions in a LC/MS map -inputs: - in: - doc: Input raw data file - type: File[] - in_header: - doc: "[for Waters data only] Read additional information from _HEADER.TXT. Provide one for each raw input file." - type: File[]? - pos: - doc: Input config file stating where to find signal - type: File - rt_tol: - doc: RT tolerance in [s] for finding max peak (whole RT range around RT middle) - type: double? - mz_tol: - doc: m/z tolerance in [ppm] for finding a peak - type: double? - rt_collect: - doc: "# of scans up & down in RT from highest point for ppm estimation in result" - type: long? - out_separator: - doc: Separator character for output CSV file. - type: string? - out: - doc: Output quantitation file (multiple columns for each input compound) - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - auto_rt__enabled: - doc: Automatically detect injection peaks from TIC and quantify all m/z x RT combinations. - type: boolean? - auto_rt__FHWM: - doc: Expected full width at half-maximum of each raw RT peak in [s]. Gaussian smoothing filter with this width is applied to TIC. - type: double? - auto_rt__SNThreshold: - doc: S/N threshold for a smoothed raw peak to pass peak picking. Higher thesholds will result in less peaks. - type: double? - auto_rt__out_debug_TIC: - doc: Optional output file (for first input) containing the smoothed TIC, S/N levels and picked RT positions - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - auto_rt__out_debug_TIC: - type: File? - outputBinding: - glob: $(inputs.auto_rt__out_debug_TIC) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - EICExtractor -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/ERPairFinder.cwl b/workflow/cwl/ERPairFinder.cwl deleted file mode 100644 index dc99bd29dbd..00000000000 --- a/workflow/cwl/ERPairFinder.cwl +++ /dev/null @@ -1,75 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: ERPairFinder -doc: Util which can be used to evaluate pair ratios on enhanced resolution (zoom) scans. -inputs: - in: - doc: Input mzML file containing the ER spectra. - type: File - pair_in: - doc: "Pair-file in the format: m/z-light m/z-heavy charge rt" - type: File - out: - doc: Output consensusXML file were the pairs of the feature are written into. - type: string - feature_out: - doc: Output featureXML file, only written if given, skipped otherwise. - type: string? - precursor_mass_tolerance: - doc: Precursor mass tolerance which is used for the pair finding and the matching of the given pair m/z values to the features. - type: double? - RT_tolerance: - doc: Maximal deviation in RT dimension in seconds a feature can have when comparing to the RT values given in the pair file - type: double? - max_charge: - doc: Maximal charge state features should be search for. - type: long? - intensity_threshold: - doc: Intensity threshold, for the meaning see the documentation of the IsotopeWaveletFeatureFinder documentation. - type: double? - max_isotope: - doc: Max isotope of the isotope distribution to be considered - type: long? - expansion_range: - doc: The range that is used to extend the isotope distribution with null intensity peaks in Th. - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - feature_out: - type: File? - outputBinding: - glob: $(inputs.feature_out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - ERPairFinder -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/Epifany.cwl b/workflow/cwl/Epifany.cwl deleted file mode 100644 index 6ee3d8e6103..00000000000 --- a/workflow/cwl/Epifany.cwl +++ /dev/null @@ -1,140 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: Epifany -doc: Runs a Bayesian protein inference. -inputs: - in: - doc: "Input: identification results" - type: File[] - exp_design: - doc: "(Currently unused) Input: experimental design" - type: File? - out: - doc: "Output: identification results with scored/grouped proteins" - type: string - out_type: - doc: "Output type: auto detected by file extension but can be overwritten here." - type: string? - protein_fdr: - doc: Additionally calculate the target-decoy FDR on protein-level based on the posteriors - type: boolean? - conservative_fdr: - doc: Use (D+1)/(T) instead of (D+1)/(T+D) for reporting protein FDRs. - type: string? - picked_fdr: - doc: Use picked protein FDRs. - type: string? - picked_decoy_string: - doc: If using picked protein FDRs, which decoy string was used? Leave blank for auto-detection. - type: string? - picked_decoy_prefix: - doc: If using picked protein FDRs, was the decoy string a prefix or suffix? Ignored during auto-detection. - type: string? - greedy_group_resolution: - doc: Post-process inference output with greedy resolution of shared peptides based on the parent protein probabilities. Also adds the resolved ambiguity groups to output. - type: string? - min_psms_extreme_probability: - doc: Set PSMs with probability lower than this to this minimum probability. - type: double? - max_psms_extreme_probability: - doc: Set PSMs with probability higher than this to this maximum probability. - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__psm_probability_cutoff: - doc: Remove PSMs with probabilities less than this cutoff - type: double? - algorithm__top_PSMs: - doc: Consider only top X PSMs per spectrum. 0 considers all. - type: long? - algorithm__keep_best_PSM_only: - doc: Epifany uses the best PSM per peptide for inference. Discard the rest (true) or keepe.g. for quantification/reporting? - type: string? - algorithm__update_PSM_probabilities: - doc: (Experimental:) Update PSM probabilities with their posteriors under consideration of the protein probabilities. - type: string? - algorithm__user_defined_priors: - doc: (Experimental:) Uses the current protein scores as user-defined priors. - type: boolean? - algorithm__annotate_group_probabilities: - doc: Annotates group probabilities for indistinguishable protein groups (indistinguishable by experimentally observed PSMs). - type: string? - algorithm__use_ids_outside_features: - doc: (Only consensusXML) Also use IDs without associated features for inference? - type: boolean? - algorithm__model_parameters__prot_prior: - doc: Protein prior probability ('gamma' parameter). Negative values enable grid search for this param. - type: double? - algorithm__model_parameters__pep_emission: - doc: Peptide emission probability ('alpha' parameter). Negative values enable grid search for this param. - type: double? - algorithm__model_parameters__pep_spurious_emission: - doc: Spurious peptide identification probability ('beta' parameter). Usually much smaller than emission from proteins. Negative values enable grid search for this param. - type: double? - algorithm__model_parameters__pep_prior: - doc: Peptide prior probability (experimental, should be covered by combinations of the other params). - type: double? - algorithm__model_parameters__regularize: - doc: Regularize the number of proteins that produce a peptide together (experimental, should be activated when using higher p-norms). - type: boolean? - algorithm__model_parameters__extended_model: - doc: Uses information from different peptidoforms also across runs (automatically activated if an experimental design is given!) - type: boolean? - algorithm__loopy_belief_propagation__scheduling_type: - doc: "(Not used yet) How to pick the next message: priority = based on difference to last message (higher = more important). fifo = first in first out. subtree = message passing follows a random spanning tree in each iteration" - type: string? - algorithm__loopy_belief_propagation__convergence_threshold: - doc: Initial threshold under which MSE difference a message is considered to be converged. - type: double? - algorithm__loopy_belief_propagation__dampening_lambda: - doc: Initial value for how strongly should messages be updated in each step. 0 = new message overwrites old completely (no dampening; only recommended for trees),0.5 = equal contribution of old and new message (stay below that),In-between it will be a convex combination of both. Prevents oscillations but hinders convergence. - type: double? - algorithm__loopy_belief_propagation__max_nr_iterations: - doc: (Usually auto-determined by estimated but you can set a hard limit here). If not all messages converge, how many iterations should be done at max per connected component? - type: long? - algorithm__loopy_belief_propagation__p_norm_inference: - doc: P-norm used for marginalization of multidimensional factors. 1 == sum-product inference (all configurations vote equally) (default),<= 0 == infinity = max-product inference (only best configurations propagate)The higher the value the more important high probability configurations get. - type: double? - algorithm__param_optimize__aucweight: - doc: How important is target decoy AUC vs calibration of the posteriors? 0 = maximize calibration only, 1 = maximize AUC only, between = convex combination. - type: double? - algorithm__param_optimize__conservative_fdr: - doc: Use (D+1)/(T) instead of (D+1)/(T+D) for parameter estimation. - type: string? - algorithm__param_optimize__regularized_fdr: - doc: Use a regularized FDR for proteins without unique peptides. - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - Epifany -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/ExecutePipeline.cwl b/workflow/cwl/ExecutePipeline.cwl deleted file mode 100644 index 9119280fd37..00000000000 --- a/workflow/cwl/ExecutePipeline.cwl +++ /dev/null @@ -1,50 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: ExecutePipeline -doc: Executes workflows created by TOPPAS. -inputs: - in: - doc: The workflow to be executed. - type: File - out_dir: - doc: "Directory for output files (default: user's home directory)" - type: string? - resource_file: - doc: A TOPPAS resource file (*.trf) specifying the files this workflow is to be applied to - type: string? - num_jobs: - doc: Maximum number of jobs running in parallel - type: long? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - [] -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - ExecutePipeline -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/ExternalCalibration.cwl b/workflow/cwl/ExternalCalibration.cwl deleted file mode 100644 index 5ce5d4d7948..00000000000 --- a/workflow/cwl/ExternalCalibration.cwl +++ /dev/null @@ -1,59 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: ExternalCalibration -doc: Applies an external mass recalibration. -inputs: - in: - doc: Input peak file - type: File - out: - doc: "Output file " - type: string - offset: - doc: Mass offset in ppm - type: double? - slope: - doc: Slope (dependent on m/z) - type: double? - power: - doc: Power (dependent on m/z) - type: double? - ms_level: - doc: Target MS levels to apply the transformation onto. Scans with other levels remain unchanged. - type: long[]? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - ExternalCalibration -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FLASHDeconv.cwl b/workflow/cwl/FLASHDeconv.cwl deleted file mode 100644 index dfd12eb0858..00000000000 --- a/workflow/cwl/FLASHDeconv.cwl +++ /dev/null @@ -1,161 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FLASHDeconv -doc: Ultra-fast high-quality deconvolution enables online processing of top-down MS data -inputs: - in: - doc: Input file (mzML) - type: File - in_log: - doc: log file generated by FLASHIda (IDA*.log). Only needed for coupling with FLASHIda acquisition - type: string? - out: - doc: Default output tsv file containing deconvolved features - type: string - out_mzml: - doc: Output mzml file containing deconvolved spectra (of all MS levels) - type: string? - out_annotated_mzml: - doc: Output mzml file containing annotated spectra. For each annotated peak, monoisotopic mass, charge, and isotope index are stored as meta data. Unannotated peaks are also copied as well without meta data. - type: string? - out_promex: - doc: Output ms1ft (promex compatible) file containing deconvolved spectra. Only for MS1 level - type: string? - min_precursor_snr: - doc: Minimum precursor SNR (SNR within the precursor envelope range) for identification. Similar to precursor interference level, but far more stringent as it also considers the isotope distribution shape of signal.When FLASHIda log file is used, this parameter is ignored. Applied only for topFD msalign outputs. - type: double? - target_precursor_charge: - doc: Charge state of the target precursor. All precursor charge is fixed to this value. This parameter is useful for targeted studies where MS2 spectra are generated from a fixed precursor (e.g., Native-MS). This option also gives the maximum charge and masses (together with precursor m/z) of fragment ions, which overrides -Algorithm:max_charge and -Algorithm:max_mass. - type: long? - target_precursor_mz: - doc: Target precursor m/z value. This option must be used with -target_precursor_charge option. Otherwise it will be ignored. If -target_precursor_charge option is used but this option is not used, the precursor m/z value written in MS2 spectra will be used by default. Together with -target_precursor_charge, this option overrides -Algorithm:max_mass. - type: double? - mzml_mass_charge: - doc: Charge state of deconvolved masses in mzml output (specified by out_mzml) - type: long? - preceding_MS1_count: - doc: Specifies the number of preceding MS1 spectra for MS2 precursor determination. In TDP, the precursor peak of a MS2 spectrum may not belong to any deconvolved masses in the MS1 spectrum immediately preceding the MS2 spectrum. Increasing this parameter to N allows for the search for the deconvolved masses in the N preceding MS1 spectra from the MS2 spectrum, increasing the chance that its precursor is deconvolved. - type: long? - write_detail: - doc: To write peak information per deconvolved mass in detail or not in tsv files for deconvolved spectra. If set to 1, all peak information (m/z, intensity, charge and isotope index) per mass is reported. - type: long? - max_MS_level: - doc: Maximum MS level (inclusive) for deconvolution. - type: long? - forced_MS_level: - doc: If set to an integer N, MS level of all spectra will be set to N regardless of original MS level. Useful when deconvolving datasets containing only MS2 spectra. - type: long? - merging_method: - doc: "Method for spectra merging before deconvolution. 0: No merging 1: Average gaussian method to perform moving gaussian averaging of spectra per MS level. Effective to increase proteoform ID sensitivity (in particular for Q-TOF datasets). 2: Block method to perform merging of all spectra into a single one per MS level (e.g., for NativeMS datasets)" - type: long? - report_FDR: - doc: Report qvalues (roughly, point-wise FDR) for deconvolved masses in the tsv files for deconvolved spectra. Dummy masses to calculate qvalues and FDR are also reported. Beta version. - type: long? - use_RNA_averagine: - doc: If set to 1, RNA averagine model is used - type: long? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - Algorithm__tol: - doc: "ppm tolerance for MS1, MS2, ... " - type: double[]? - Algorithm__min_mass: - doc: Minimum mass (Da) - type: double? - Algorithm__max_mass: - doc: Maximum mass (Da) - type: double? - Algorithm__min_charge: - doc: Minimum charge state for MS1 spectra (can be negative for negative mode) - type: long? - Algorithm__max_charge: - doc: Maximum charge state for MS1 spectra (can be negative for negative mode) - type: long? - Algorithm__min_mz: - doc: If set to positive value, minimum m/z to deconvolve. - type: double? - Algorithm__max_mz: - doc: If set to positive value, maximum m/z to deconvolve. - type: double? - Algorithm__min_rt: - doc: If set to positive value, minimum RT to deconvolve. - type: double? - Algorithm__max_rt: - doc: If set to positive value, maximum RT to deconvolve. - type: double? - Algorithm__isolation_window: - doc: Default isolation window with. If the input mzML file does not contain isolation window width information, this width will be used. - type: double? - Algorithm__min_isotope_cosine: - doc: Cosine similarity thresholds between avg. and observed isotope patterns for MS1, 2, ... (e.g., -min_isotope_cosine 0.8 0.6 to specify 0.8 and 0.6 for MS1 and MS2, respectively) - type: double[]? - Algorithm__allowed_isotope_error: - doc: Allowed isotope index error for decoy and qvalue report. If it is set to 1, for example, +-1 isotope errors are not counted as false. Beta version. - type: long? - Algorithm__min_intensity: - doc: Intensity threshold - type: double? - FeatureTracing__mass_error_ppm: - doc: Feature tracing mass ppm tolerance. When negative, MS1 tolerance for mass deconvolution will be used (e.g., 16 ppm is used when -Algorithm:tol 16). - type: double? - FeatureTracing__quant_method: - doc: Method of quantification for mass traces. For LC data 'area' is recommended, 'median' for direct injection data. 'max_height' simply uses the most intense peak in the trace. - type: string? - FeatureTracing__min_sample_rate: - doc: Minimum fraction of scans along the feature trace that must contain a peak. To raise feature detection sensitivity, lower this value close to 0. - type: double? - FeatureTracing__min_trace_length: - doc: Minimum expected length of a mass trace (in seconds). - type: double? - FeatureTracing__max_trace_length: - doc: Maximum expected length of a mass trace (in seconds). Set to a negative value to disable maximal length check during mass trace detection. - type: double? - FeatureTracing__min_isotope_cosine: - doc: Cosine similarity threshold between avg. and observed isotope pattern for mass features. if not set, controlled by -Algorithm:min_isotope_cosine_ option - type: double? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - out_mzml: - type: File? - outputBinding: - glob: $(inputs.out_mzml) - out_annotated_mzml: - type: File? - outputBinding: - glob: $(inputs.out_annotated_mzml) - out_promex: - type: File? - outputBinding: - glob: $(inputs.out_promex) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FLASHDeconv -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FalseDiscoveryRate.cwl b/workflow/cwl/FalseDiscoveryRate.cwl deleted file mode 100644 index 75c24567be9..00000000000 --- a/workflow/cwl/FalseDiscoveryRate.cwl +++ /dev/null @@ -1,92 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FalseDiscoveryRate -doc: Estimates the false discovery rate on peptide and protein level using decoy searches. -inputs: - in: - doc: Identifications from searching a target-decoy database. - type: File - out: - doc: Identifications with annotated FDR - type: string - PSM: - doc: Perform FDR calculation on PSM level - type: string? - peptide: - doc: "Perform FDR calculation on peptide level and annotates it as meta value\n(Note: if set, also calculates FDR/q-value on PSM level.)" - type: boolean? - protein: - doc: Perform FDR calculation on protein level - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - FDR__PSM: - doc: Filter PSMs based on q-value (e.g., 0.05 = 5% FDR, disabled for 1) - type: double? - FDR__protein: - doc: Filter proteins based on q-value (e.g., 0.05 = 5% FDR, disabled for 1) - type: double? - FDR__cleanup__remove_proteins_without_psms: - doc: Remove proteins without PSMs (due to being decoy or below PSM FDR threshold). - type: string? - FDR__cleanup__remove_psms_without_proteins: - doc: Remove PSMs without proteins (due to being decoy or below protein FDR threshold). - type: string? - FDR__cleanup__remove_spectra_without_psms: - doc: "Remove spectra without PSMs (due to being decoy or below protein FDR threshold). Caution: if remove_psms_without_proteins is false, protein level filtering does not propagate." - type: string? - algorithm__no_qvalues: - doc: If 'true' strict FDRs will be calculated instead of q-values (the default) - type: boolean? - algorithm__use_all_hits: - doc: If 'true' not only the first hit, but all are used (peptides only) - type: boolean? - algorithm__split_charge_variants: - doc: If 'true' charge variants are treated separately (for peptides of combined target/decoy searches only). - type: boolean? - algorithm__treat_runs_separately: - doc: If 'true' different search runs are treated separately (for peptides of combined target/decoy searches only). - type: boolean? - algorithm__add_decoy_peptides: - doc: If 'true' decoy peptides will be written to output file, too. The q-value is set to the closest target score. - type: boolean? - algorithm__add_decoy_proteins: - doc: If 'true' decoy proteins will be written to output file, too. The q-value is set to the closest target score. - type: boolean? - algorithm__conservative: - doc: If 'true' (D+1)/T instead of (D+1)/(T+D) is used as a formula. - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FalseDiscoveryRate -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FeatureFinderCentroided.cwl b/workflow/cwl/FeatureFinderCentroided.cwl deleted file mode 100644 index 44262f58b2f..00000000000 --- a/workflow/cwl/FeatureFinderCentroided.cwl +++ /dev/null @@ -1,144 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FeatureFinderCentroided -doc: Detects two-dimensional features in LC-MS data. -inputs: - in: - doc: input file - type: File - out: - doc: output file - type: string - seeds: - doc: User specified seed list - type: File? - out_mzq: - doc: Optional output file of MzQuantML. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__debug: - doc: When debug mode is activated, several files with intermediate results are written to the folder 'debug' (do not use in parallel mode). - type: boolean? - algorithm__intensity__bins: - doc: "Number of bins per dimension (RT and m/z). The higher this value, the more local the intensity significance score is.\nThis parameter should be decreased, if the algorithm is used on small regions of a map." - type: long? - algorithm__mass_trace__mz_tolerance: - doc: "Tolerated m/z deviation of peaks belonging to the same mass trace.\nIt should be larger than the m/z resolution of the instrument.\nThis value must be smaller than that 1/charge_high!" - type: double? - algorithm__mass_trace__min_spectra: - doc: Number of spectra that have to show a similar peak mass in a mass trace. - type: long? - algorithm__mass_trace__max_missing: - doc: "Number of consecutive spectra where a high mass deviation or missing peak is acceptable.\nThis parameter should be well below 'min_spectra'!" - type: long? - algorithm__mass_trace__slope_bound: - doc: "The maximum slope of mass trace intensities when extending from the highest peak.\nThis parameter is important to separate overlapping elution peaks.\nIt should be increased if feature elution profiles fluctuate a lot." - type: double? - algorithm__isotopic_pattern__charge_low: - doc: Lowest charge to search for. - type: long? - algorithm__isotopic_pattern__charge_high: - doc: Highest charge to search for. - type: long? - algorithm__isotopic_pattern__mz_tolerance: - doc: "Tolerated m/z deviation from the theoretical isotopic pattern.\nIt should be larger than the m/z resolution of the instrument.\nThis value must be smaller than that 1/charge_high!" - type: double? - algorithm__isotopic_pattern__intensity_percentage: - doc: Isotopic peaks that contribute more than this percentage to the overall isotope pattern intensity must be present. - type: double? - algorithm__isotopic_pattern__intensity_percentage_optional: - doc: Isotopic peaks that contribute more than this percentage to the overall isotope pattern intensity can be missing. - type: double? - algorithm__isotopic_pattern__optional_fit_improvement: - doc: Minimal percental improvement of isotope fit to allow leaving out an optional peak. - type: double? - algorithm__isotopic_pattern__mass_window_width: - doc: Window width in Dalton for precalculation of estimated isotope distributions. - type: double? - algorithm__isotopic_pattern__abundance_12C: - doc: Rel. abundance of the light carbon. Modify if labeled. - type: double? - algorithm__isotopic_pattern__abundance_14N: - doc: Rel. abundance of the light nitrogen. Modify if labeled. - type: double? - algorithm__seed__min_score: - doc: "Minimum seed score a peak has to reach to be used as seed.\nThe seed score is the geometric mean of intensity score, mass trace score and isotope pattern score.\nIf your features show a large deviation from the averagene isotope distribution or from an gaussian elution profile, lower this score." - type: double? - algorithm__fit__max_iterations: - doc: Maximum number of iterations of the fit. - type: long? - algorithm__feature__min_score: - doc: "Feature score threshold for a feature to be reported.\nThe feature score is the geometric mean of the average relative deviation and the correlation between the model and the observed peaks." - type: double? - algorithm__feature__min_isotope_fit: - doc: Minimum isotope fit of the feature before model fitting. - type: double? - algorithm__feature__min_trace_score: - doc: "Trace score threshold.\nTraces below this threshold are removed after the model fitting.\nThis parameter is important for features that overlap in m/z dimension." - type: double? - algorithm__feature__min_rt_span: - doc: Minimum RT span in relation to extended area that has to remain after model fitting. - type: double? - algorithm__feature__max_rt_span: - doc: Maximum RT span in relation to extended area that the model is allowed to have. - type: double? - algorithm__feature__rt_shape: - doc: Choose model used for RT profile fitting. If set to symmetric a gauss shape is used, in case of asymmetric an EGH shape is used. - type: string? - algorithm__feature__max_intersection: - doc: Maximum allowed intersection of features. - type: double? - algorithm__feature__reported_mz: - doc: "The mass type that is reported for features.\n'maximum' returns the m/z value of the highest mass trace.\n'average' returns the intensity-weighted average m/z value of all contained peaks.\n'monoisotopic' returns the monoisotopic m/z value derived from the fitted isotope model." - type: string? - algorithm__user-seed__rt_tolerance: - doc: Allowed RT deviation of seeds from the user-specified seed position. - type: double? - algorithm__user-seed__mz_tolerance: - doc: Allowed m/z deviation of seeds from the user-specified seed position. - type: double? - algorithm__user-seed__min_score: - doc: Overwrites 'seed:min_score' for user-specified seeds. The cutoff is typically a bit lower in this case. - type: double? - algorithm__advanced__pseudo_rt_shift: - doc: Pseudo RT shift used when . - type: double? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - out_mzq: - type: File? - outputBinding: - glob: $(inputs.out_mzq) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FeatureFinderCentroided -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FeatureFinderIdentification.cwl b/workflow/cwl/FeatureFinderIdentification.cwl deleted file mode 100644 index 8b8301c8818..00000000000 --- a/workflow/cwl/FeatureFinderIdentification.cwl +++ /dev/null @@ -1,192 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FeatureFinderIdentification -doc: Detects features in MS1 data based on peptide identifications. -inputs: - in: - doc: "Input file: LC-MS raw data" - type: File - id: - doc: "Input file: Peptide identifications derived directly from 'in'" - type: File - id_ext: - doc: "Input file: 'External' peptide identifications (e.g. from aligned runs)" - type: File? - out: - doc: "Output file: Features" - type: string - lib_out: - doc: "Output file: Assay library" - type: string? - chrom_out: - doc: "Output file: Chromatograms" - type: string? - candidates_out: - doc: "Output file: Feature candidates (before filtering and model fitting)" - type: string? - candidates_in: - doc: "Input file: Feature candidates from a previous run. If set, only feature classification and elution model fitting are carried out, if enabled. Many parameters are ignored." - type: File? - debug: - doc: Sets the debug level - type: long? - quantify_decoys: - doc: Whether decoy peptides should be quantified (true) or skipped (false). - type: boolean? - min_psm_cutoff: - doc: Minimum score for the best PSM of a spectrum to be used as seed. Use 'none' for no cutoff. - type: string? - add_mass_offset_peptides: - doc: If for every peptide (or seed) also an offset peptide is extracted (true). Can be used to downstream to determine MBR false transfer rates. (0.0 = disabled) - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - extract__batch_size: - doc: Nr of peptides used in each batch of chromatogram extraction. Smaller values decrease memory usage but increase runtime. - type: long? - extract__mz_window: - doc: "m/z window size for chromatogram extraction (unit: ppm if 1 or greater, else Da/Th)" - type: double? - extract__n_isotopes: - doc: Number of isotopes to include in each peptide assay. - type: long? - extract__isotope_pmin: - doc: Minimum probability for an isotope to be included in the assay for a peptide. If set, this parameter takes precedence over 'extract:n_isotopes'. - type: double? - extract__rt_quantile: - doc: Quantile of the RT deviations between aligned internal and external IDs to use for scaling the RT extraction window - type: double? - extract__rt_window: - doc: RT window size (in sec.) for chromatogram extraction. If set, this parameter takes precedence over 'extract:rt_quantile'. - type: double? - detect__peak_width: - doc: Expected elution peak width in seconds, for smoothing (Gauss filter). Also determines the RT extration window, unless set explicitly via 'extract:rt_window'. - type: double? - detect__min_peak_width: - doc: Minimum elution peak width. Absolute value in seconds if 1 or greater, else relative to 'peak_width'. - type: double? - detect__signal_to_noise: - doc: Signal-to-noise threshold for OpenSWATH feature detection - type: double? - detect__mapping_tolerance: - doc: RT tolerance (plus/minus) for mapping peptide IDs to features. Absolute value in seconds if 1 or greater, else relative to the RT span of the feature. - type: double? - svm__samples: - doc: Number of observations to use for training ('0' for all) - type: long? - svm__no_selection: - doc: By default, roughly the same number of positive and negative observations, with the same intensity distribution, are selected for training. This aims to reduce biases, but also reduces the amount of training data. Set this flag to skip this procedure and consider all available observations (subject to 'svm:samples'). - type: boolean? - svm__xval_out: - doc: "Output file: SVM cross-validation (parameter optimization) results" - type: string? - svm__kernel: - doc: SVM kernel - type: string? - svm__xval: - doc: Number of partitions for cross-validation (parameter optimization) - type: long? - svm__log2_C: - doc: Values to try for the SVM parameter 'C' during parameter optimization. A value 'x' is used as 'C = 2^x'. - type: double[]? - svm__log2_gamma: - doc: Values to try for the SVM parameter 'gamma' during parameter optimization (RBF kernel only). A value 'x' is used as 'gamma = 2^x'. - type: double[]? - svm__log2_p: - doc: Values to try for the SVM parameter 'epsilon' during parameter optimization (epsilon-SVR only). A value 'x' is used as 'epsilon = 2^x'. - type: double[]? - svm__epsilon: - doc: Stopping criterion - type: double? - svm__cache_size: - doc: Size of the kernel cache (in MB) - type: double? - svm__no_shrinking: - doc: Disable the shrinking heuristics - type: boolean? - svm__predictors: - doc: Names of OpenSWATH scores to use as predictors for the SVM (comma-separated list) - type: string? - svm__min_prob: - doc: Minimum probability of correctness, as predicted by the SVM, required to retain a feature candidate - type: double? - model__type: - doc: Type of elution model to fit to features - type: string? - model__add_zeros: - doc: Add zero-intensity points outside the feature range to constrain the model fit. This parameter sets the weight given to these points during model fitting; '0' to disable. - type: double? - model__unweighted_fit: - doc: Suppress weighting of mass traces according to theoretical intensities when fitting elution models - type: boolean? - model__no_imputation: - doc: If fitting the elution model fails for a feature, set its intensity to zero instead of imputing a value from the initial intensity estimate - type: boolean? - model__each_trace: - doc: Fit elution model to each individual mass trace - type: boolean? - model__check__min_area: - doc: Lower bound for the area under the curve of a valid elution model - type: double? - model__check__boundaries: - doc: Time points corresponding to this fraction of the elution model height have to be within the data region used for model fitting - type: double? - model__check__width: - doc: Upper limit for acceptable widths of elution models (Gaussian or EGH), expressed in terms of modified (median-based) z-scores. '0' to disable. Not applied to individual mass traces (parameter 'each_trace'). - type: double? - model__check__asymmetry: - doc: Upper limit for acceptable asymmetry of elution models (EGH only), expressed in terms of modified (median-based) z-scores. '0' to disable. Not applied to individual mass traces (parameter 'each_trace'). - type: double? - EMGScoring__max_iteration: - doc: Maximum number of iterations for EMG fitting. - type: long? - EMGScoring__init_mom: - doc: Alternative initial parameters for fitting through method of moments. - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - lib_out: - type: File? - outputBinding: - glob: $(inputs.lib_out) - chrom_out: - type: File? - outputBinding: - glob: $(inputs.chrom_out) - candidates_out: - type: File? - outputBinding: - glob: $(inputs.candidates_out) - svm__xval_out: - type: File? - outputBinding: - glob: $(inputs.svm__xval_out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FeatureFinderIdentification -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FeatureFinderIsotopeWavelet.cwl b/workflow/cwl/FeatureFinderIsotopeWavelet.cwl deleted file mode 100644 index da0bfb83528..00000000000 --- a/workflow/cwl/FeatureFinderIsotopeWavelet.cwl +++ /dev/null @@ -1,68 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FeatureFinderIsotopeWavelet -doc: Detects two-dimensional features in LC-MS data. -inputs: - in: - doc: input file - type: File - out: - doc: output file - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__max_charge: - doc: The maximal charge state to be considered. - type: long? - algorithm__intensity_threshold: - doc: "The final threshold t' is build upon the formula: t' = av+t*sd, where t is the intensity_threshold, av the average intensity within the wavelet transformed signal and sd the standard deviation of the transform. If you set intensity_threshold=-1, t' will be zero.\nAs the 'optimal' value for this parameter is highly data dependent, we would recommend to start with -1, which will also extract features with very low signal-to-noise ratio. Subsequently, one might increase the threshold to find an optimized trade-off between false positives and true positives. Depending on the dynamic range of your spectra, suitable value ranges include: -1, [0:10], and if your data features even very high intensity values, t can also adopt values up to around 30. Please note that this parameter is not of an integer type, s.t. you can also use t:=0.1, e.g." - type: double? - algorithm__intensity_type: - doc: Determines the intensity type returned for the identified features. 'ref' (default) returns the sum of the intensities of each isotopic peak within an isotope pattern. 'trans' refers to the intensity of the monoisotopic peak within the wavelet transform. 'corrected' refers also to the transformed intensity with an attempt to remove the effects of the convolution. While the latter ones might be preferable for qualitative analyses, 'ref' might be the best option to obtain quantitative results. Please note that intensity values might be spoiled (in particular for the option 'ref'), as soon as patterns overlap (see also the explanations given in the class documentation of FeatureFinderAlgorihtmIsotopeWavelet). - type: string? - algorithm__check_ppm: - doc: Enables/disables a ppm test vs. the averagine model, i.e. potential peptide masses are checked for plausibility. In addition, a heuristic correcting potential mass shifts induced by the wavelet is applied. - type: boolean? - algorithm__hr_data: - doc: Must be true in case of high-resolution data, i.e. for spectra featuring large m/z-gaps (present in FTICR and Orbitrap data, e.g.). Please check a single MS scan out of your recording, if you are unsure. - type: boolean? - algorithm__sweep_line__rt_votes_cutoff: - doc: Defines the minimum number of subsequent scans where a pattern must occur to be considered as a feature. - type: long? - algorithm__sweep_line__rt_interleave: - doc: Defines the maximum number of scans (w.r.t. rt_votes_cutoff) where an expected pattern is missing. There is usually no reason to change the default value. - type: long? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FeatureFinderIsotopeWavelet -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FeatureFinderMRM.cwl b/workflow/cwl/FeatureFinderMRM.cwl deleted file mode 100644 index 7bddb66a88d..00000000000 --- a/workflow/cwl/FeatureFinderMRM.cwl +++ /dev/null @@ -1,65 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FeatureFinderMRM -doc: Detects two-dimensional features in LC-MS data. -inputs: - in: - doc: input file - type: File - out: - doc: output file - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__min_rt_distance: - doc: Minimal distance of MRM features in seconds. - type: double? - algorithm__min_num_peaks_per_feature: - doc: Minimal number of peaks which are needed for a single feature - type: long? - algorithm__min_signal_to_noise_ratio: - doc: Minimal S/N ratio a peak must have to be taken into account. Set to zero if the MRM-traces contains mostly signals, and no noise. - type: double? - algorithm__write_debug_files: - doc: If set to true, for each feature a plot will be created, in the subdirectory 'debug' - type: boolean? - algorithm__resample_traces: - doc: If set to true, each trace, which is in this case a part of the MRM monitoring trace with signal is resampled, using the minimal distance of two data points in RT dimension - type: boolean? - algorithm__write_debuginfo: - doc: If set to true, debug messages are written, the output can be somewhat lengthy. - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FeatureFinderMRM -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FeatureFinderMetabo.cwl b/workflow/cwl/FeatureFinderMetabo.cwl deleted file mode 100644 index e505b306b56..00000000000 --- a/workflow/cwl/FeatureFinderMetabo.cwl +++ /dev/null @@ -1,141 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FeatureFinderMetabo -doc: Assembles metabolite features from centroided (LC-)MS data using the mass trace approach. -inputs: - in: - doc: Centroided mzML file - type: File - out: - doc: FeatureXML file with metabolite features - type: string - out_chrom: - doc: Optional mzML file with chromatograms - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__common__noise_threshold_int: - doc: Intensity threshold below which peaks are regarded as noise. - type: double? - algorithm__common__chrom_peak_snr: - doc: Minimum signal-to-noise a mass trace should have. - type: double? - algorithm__common__chrom_fwhm: - doc: Expected chromatographic peak width (in seconds). - type: double? - algorithm__mtd__mass_error_ppm: - doc: Allowed mass deviation (in ppm). - type: double? - algorithm__mtd__reestimate_mt_sd: - doc: Enables dynamic re-estimation of m/z variance during mass trace collection stage. - type: string? - algorithm__mtd__quant_method: - doc: Method of quantification for mass traces. For LC data 'area' is recommended, 'median' for direct injection data. 'max_height' simply uses the most intense peak in the trace. - type: string? - algorithm__mtd__trace_termination_criterion: - doc: Termination criterion for the extension of mass traces. In 'outlier' mode, trace extension cancels if a predefined number of consecutive outliers are found (see trace_termination_outliers parameter). In 'sample_rate' mode, trace extension in both directions stops if ratio of found peaks versus visited spectra falls below the 'min_sample_rate' threshold. - type: string? - algorithm__mtd__trace_termination_outliers: - doc: Mass trace extension in one direction cancels if this number of consecutive spectra with no detectable peaks is reached. - type: long? - algorithm__mtd__min_sample_rate: - doc: Minimum fraction of scans along the mass trace that must contain a peak. - type: double? - algorithm__mtd__min_trace_length: - doc: Minimum expected length of a mass trace (in seconds). - type: double? - algorithm__mtd__max_trace_length: - doc: Maximum expected length of a mass trace (in seconds). Set to a negative value to disable maximal length check during mass trace detection. - type: double? - algorithm__epd__enabled: - doc: Enable splitting of isobaric mass traces by chromatographic peak detection. Disable for direct injection. - type: string? - algorithm__epd__width_filtering: - doc: Enable filtering of unlikely peak widths. The fixed setting filters out mass traces outside the [min_fwhm, max_fwhm] interval (set parameters accordingly!). The auto setting filters with the 5 and 95% quantiles of the peak width distribution. - type: string? - algorithm__epd__min_fwhm: - doc: Minimum full-width-at-half-maximum of chromatographic peaks (in seconds). Ignored if parameter width_filtering is off or auto. - type: double? - algorithm__epd__max_fwhm: - doc: Maximum full-width-at-half-maximum of chromatographic peaks (in seconds). Ignored if parameter width_filtering is off or auto. - type: double? - algorithm__epd__masstrace_snr_filtering: - doc: Apply post-filtering by signal-to-noise ratio after smoothing. - type: boolean? - algorithm__ffm__local_rt_range: - doc: RT range where to look for coeluting mass traces - type: double? - algorithm__ffm__local_mz_range: - doc: MZ range where to look for isotopic mass traces - type: double? - algorithm__ffm__charge_lower_bound: - doc: Lowest charge state to consider - type: long? - algorithm__ffm__charge_upper_bound: - doc: Highest charge state to consider - type: long? - algorithm__ffm__report_summed_ints: - doc: Set to true for a feature intensity summed up over all traces rather than using monoisotopic trace intensity alone. - type: string? - algorithm__ffm__enable_RT_filtering: - doc: Require sufficient overlap in RT while assembling mass traces. Disable for direct injection data.. - type: string? - algorithm__ffm__isotope_filtering_model: - doc: Remove/score candidate assemblies based on isotope intensities. SVM isotope models for metabolites were trained with either 2% or 5% RMS error. For peptides, an averagine cosine scoring is used. Select the appropriate noise model according to the quality of measurement or MS device. - type: string? - algorithm__ffm__mz_scoring_13C: - doc: Use the 13C isotope peak position (~1.003355 Da) as the expected shift in m/z for isotope mass traces (highly recommended for lipidomics!). Disable for general metabolites (as described in Kenar et al. 2014, MCP.). - type: string? - algorithm__ffm__use_smoothed_intensities: - doc: Use LOWESS intensities instead of raw intensities. - type: string? - algorithm__ffm__report_convex_hulls: - doc: Augment each reported feature with the convex hull of the underlying mass traces (increases featureXML file size considerably). - type: string? - algorithm__ffm__remove_single_traces: - doc: Remove unassembled traces (single traces). - type: string? - algorithm__ffm__mz_scoring_by_elements: - doc: Use the m/z range of the assumed elements to detect isotope peaks. A expected m/z range is computed from the isotopes of the assumed elements. If enabled, this ignores 'mz_scoring_13C' - type: string? - algorithm__ffm__elements: - doc: Elements assumes to be present in the sample (this influences isotope detection). - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - out_chrom: - type: File? - outputBinding: - glob: $(inputs.out_chrom) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FeatureFinderMetabo -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FeatureFinderMetaboIdent.cwl b/workflow/cwl/FeatureFinderMetaboIdent.cwl deleted file mode 100644 index 8b445bfc284..00000000000 --- a/workflow/cwl/FeatureFinderMetaboIdent.cwl +++ /dev/null @@ -1,132 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FeatureFinderMetaboIdent -doc: Detects features in MS1 data based on metabolite identifications. -inputs: - in: - doc: "Input file: LC-MS raw data" - type: File - id: - doc: "Input file: Metabolite identifications" - type: File - out: - doc: "Output file: Features" - type: string - lib_out: - doc: "Output file: Assay library" - type: string? - chrom_out: - doc: "Output file: Chromatograms" - type: string? - trafo_out: - doc: "Output file: Retention times (expected vs. observed)" - type: string? - force: - doc: Overrides tool-specific checks - type: boolean? - candidates_out: - doc: "Optional output file: Feature candidates (before filtering and model fitting)." - type: string? - debug: - doc: Sets the debug level - type: long? - log: - doc: Name of log file (created only when specified) - type: string? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - extract__mz_window: - doc: "m/z window size for chromatogram extraction (unit: ppm if 1 or greater, else Da/Th)" - type: double? - extract__rt_window: - doc: RT window size (in sec.) for chromatogram extraction. If set, this parameter takes precedence over 'extract:rt_quantile'. - type: double? - extract__n_isotopes: - doc: Number of isotopes to include in each peptide assay. - type: long? - extract__isotope_pmin: - doc: Minimum probability for an isotope to be included in the assay for a peptide. If set, this parameter takes precedence over 'extract:n_isotopes'. - type: double? - detect__peak_width: - doc: Expected elution peak width in seconds, for smoothing (Gauss filter). Also determines the RT extration window, unless set explicitly via 'extract:rt_window'. - type: double? - detect__min_peak_width: - doc: Minimum elution peak width. Absolute value in seconds if 1 or greater, else relative to 'peak_width'. - type: double? - detect__signal_to_noise: - doc: Signal-to-noise threshold for OpenSWATH feature detection - type: double? - model__type: - doc: Type of elution model to fit to features - type: string? - model__add_zeros: - doc: Add zero-intensity points outside the feature range to constrain the model fit. This parameter sets the weight given to these points during model fitting; '0' to disable. - type: double? - model__unweighted_fit: - doc: Suppress weighting of mass traces according to theoretical intensities when fitting elution models - type: boolean? - model__no_imputation: - doc: If fitting the elution model fails for a feature, set its intensity to zero instead of imputing a value from the initial intensity estimate - type: boolean? - model__each_trace: - doc: Fit elution model to each individual mass trace - type: boolean? - model__check__min_area: - doc: Lower bound for the area under the curve of a valid elution model - type: double? - model__check__boundaries: - doc: Time points corresponding to this fraction of the elution model height have to be within the data region used for model fitting - type: double? - model__check__width: - doc: Upper limit for acceptable widths of elution models (Gaussian or EGH), expressed in terms of modified (median-based) z-scores. '0' to disable. Not applied to individual mass traces (parameter 'each_trace'). - type: double? - model__check__asymmetry: - doc: Upper limit for acceptable asymmetry of elution models (EGH only), expressed in terms of modified (median-based) z-scores. '0' to disable. Not applied to individual mass traces (parameter 'each_trace'). - type: double? - EMGScoring__max_iteration: - doc: Maximum number of iterations for EMG fitting. - type: long? - EMGScoring__init_mom: - doc: Alternative initial parameters for fitting through method of moments. - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - lib_out: - type: File? - outputBinding: - glob: $(inputs.lib_out) - chrom_out: - type: File? - outputBinding: - glob: $(inputs.chrom_out) - trafo_out: - type: File? - outputBinding: - glob: $(inputs.trafo_out) - candidates_out: - type: File? - outputBinding: - glob: $(inputs.candidates_out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FeatureFinderMetaboIdent -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FeatureFinderMultiplex.cwl b/workflow/cwl/FeatureFinderMultiplex.cwl deleted file mode 100644 index d93fa4a3e73..00000000000 --- a/workflow/cwl/FeatureFinderMultiplex.cwl +++ /dev/null @@ -1,151 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FeatureFinderMultiplex -doc: Determination of peak ratios in LC-MS data -inputs: - in: - doc: LC-MS dataset in either centroid or profile mode - type: File - out: - doc: Output file containing the individual peptide features. - type: string? - out_multiplets: - doc: Optional output file containing all detected peptide groups (i.e. peptide pairs or triplets or singlets or ..). The m/z-RT positions correspond to the lightest peptide in each group. - type: string? - out_blacklist: - doc: Optional output file containing all peaks which have been associated with a peptide feature (and subsequently blacklisted). - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__labels: - doc: "Labels used for labelling the samples. If the sample is unlabelled (i.e. you want to detect only single peptide features) please leave this parameter empty. [...] specifies the labels for a single sample. For example\n\n[][Lys8,Arg10] ... SILAC\n[][Lys4,Arg6][Lys8,Arg10] ... triple-SILAC\n[Dimethyl0][Dimethyl6] ... Dimethyl\n[Dimethyl0][Dimethyl4][Dimethyl8] ... triple Dimethyl\n[ICPL0][ICPL4][ICPL6][ICPL10] ... ICPL" - type: string? - algorithm__charge: - doc: "Range of charge states in the sample, i.e. min charge : max charge." - type: string? - algorithm__isotopes_per_peptide: - doc: "Range of isotopes per peptide in the sample. For example 3:6, if isotopic peptide patterns in the sample consist of either three, four, five or six isotopic peaks. " - type: string? - algorithm__rt_typical: - doc: Typical retention time [s] over which a characteristic peptide elutes. (This is not an upper bound. Peptides that elute for longer will be reported.) - type: double? - algorithm__rt_band: - doc: The algorithm searches for characteristic isotopic peak patterns, spectrum by spectrum. For some low-intensity peptides, an important peak might be missing in one spectrum but be present in one of the neighbouring ones. The algorithm takes a bundle of neighbouring spectra with width rt_band into account. For example with rt_band = 0, all characteristic isotopic peaks have to be present in one and the same spectrum. As rt_band increases, the sensitivity of the algorithm but also the likelihood of false detections increases. - type: double? - algorithm__rt_min: - doc: Lower bound for the retention time [s]. (Any peptides seen for a shorter time period are not reported.) - type: double? - algorithm__mz_tolerance: - doc: m/z tolerance for search of peak patterns. - type: double? - algorithm__mz_unit: - doc: Unit of the 'mz_tolerance' parameter. - type: string? - algorithm__intensity_cutoff: - doc: Lower bound for the intensity of isotopic peaks. - type: double? - algorithm__peptide_similarity: - doc: Two peptides in a multiplet are expected to have the same isotopic pattern. This parameter is a lower bound on their similarity. - type: double? - algorithm__averagine_similarity: - doc: The isotopic pattern of a peptide should resemble the averagine model at this m/z position. This parameter is a lower bound on similarity between measured isotopic pattern and the averagine model. - type: double? - algorithm__averagine_similarity_scaling: - doc: Let x denote this scaling factor, and p the averagine similarity parameter. For the detection of single peptides, the averagine parameter p is replaced by p' = p + x(1-p), i.e. x = 0 -> p' = p and x = 1 -> p' = 1. (For knock_out = true, peptide doublets and singlets are detected simultaneously. For singlets, the peptide similarity filter is irreleavant. In order to compensate for this 'missing filter', the averagine parameter p is replaced by the more restrictive p' when searching for singlets.) - type: double? - algorithm__missed_cleavages: - doc: Maximum number of missed cleavages due to incomplete digestion. (Only relevant if enzymatic cutting site coincides with labelling site. For example, Arg/Lys in the case of trypsin digestion and SILAC labelling.) - type: long? - algorithm__spectrum_type: - doc: Type of MS1 spectra in input mzML file. 'automatic' determines the spectrum type directly from the input mzML file. - type: string? - algorithm__averagine_type: - doc: The type of averagine to use, currently RNA, DNA or peptide - type: string? - algorithm__knock_out: - doc: Is it likely that knock-outs are present? (Supported for doublex, triplex and quadruplex experiments only.) - type: boolean? - labels__Arg6: - doc: "Label:13C(6) | C(-6) 13C(6) | unimod #188" - type: double? - labels__Arg10: - doc: "Label:13C(6)15N(4) | C(-6) 13C(6) N(-4) 15N(4) | unimod #267" - type: double? - labels__Lys4: - doc: "Label:2H(4) | H(-4) 2H(4) | unimod #481" - type: double? - labels__Lys6: - doc: "Label:13C(6) | C(-6) 13C(6) | unimod #188" - type: double? - labels__Lys8: - doc: "Label:13C(6)15N(2) | C(-6) 13C(6) N(-2) 15N(2) | unimod #259" - type: double? - labels__Leu3: - doc: "Label:2H(3) | H(-3) 2H(3) | unimod #262" - type: double? - labels__Dimethyl0: - doc: "Dimethyl | H(4) C(2) | unimod #36" - type: double? - labels__Dimethyl4: - doc: "Dimethyl:2H(4) | 2H(4) C(2) | unimod #199" - type: double? - labels__Dimethyl6: - doc: "Dimethyl:2H(4)13C(2) | 2H(4) 13C(2) | unimod #510" - type: double? - labels__Dimethyl8: - doc: "Dimethyl:2H(6)13C(2) | H(-2) 2H(6) 13C(2) | unimod #330" - type: double? - labels__ICPL0: - doc: "ICPL | H(3) C(6) N O | unimod #365" - type: double? - labels__ICPL4: - doc: "ICPL:2H(4) | H(-1) 2H(4) C(6) N O | unimod #687" - type: double? - labels__ICPL6: - doc: "ICPL:13C(6) | H(3) 13C(6) N O | unimod #364" - type: double? - labels__ICPL10: - doc: "ICPL:13C(6)2H(4) | H(-1) 2H(4) 13C(6) N O | unimod #866" - type: double? -outputs: - out: - type: File? - outputBinding: - glob: $(inputs.out) - out_multiplets: - type: File? - outputBinding: - glob: $(inputs.out_multiplets) - out_blacklist: - type: File? - outputBinding: - glob: $(inputs.out_blacklist) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FeatureFinderMultiplex -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FeatureLinkerLabeled.cwl b/workflow/cwl/FeatureLinkerLabeled.cwl deleted file mode 100644 index aade3fde7c1..00000000000 --- a/workflow/cwl/FeatureLinkerLabeled.cwl +++ /dev/null @@ -1,68 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FeatureLinkerLabeled -doc: Groups corresponding isotope-labeled features in a feature map. -inputs: - in: - doc: Input file - type: File - out: - doc: Output file - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__rt_estimate: - doc: If 'true' the optimal RT pair distance and deviation are estimated by fitting a gaussian distribution to the histogram of pair distance. Note that this works only datasets with a significant amount of pairs! If 'false' the parameters 'rt_pair_dist', 'rt_dev_low' and 'rt_dev_high' define the optimal distance. - type: string? - algorithm__rt_pair_dist: - doc: optimal pair distance in RT [sec] from light to heavy feature - type: double? - algorithm__rt_dev_low: - doc: maximum allowed deviation below optimal retention time distance - type: double? - algorithm__rt_dev_high: - doc: maximum allowed deviation above optimal retention time distance - type: double? - algorithm__mz_pair_dists: - doc: optimal pair distances in m/z [Th] for features with charge +1 (adapted to +2, +3, .. by division through charge) - type: double[]? - algorithm__mz_dev: - doc: "maximum allowed deviation from optimal m/z distance\n" - type: double? - algorithm__mrm: - doc: this option should be used if the features correspond mrm chromatograms (additionally the precursor is taken into account) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FeatureLinkerLabeled -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FeatureLinkerUnlabeled.cwl b/workflow/cwl/FeatureLinkerUnlabeled.cwl deleted file mode 100644 index d49b38e7257..00000000000 --- a/workflow/cwl/FeatureLinkerUnlabeled.cwl +++ /dev/null @@ -1,95 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FeatureLinkerUnlabeled -doc: Groups corresponding features from multiple maps. -inputs: - in: - doc: input files separated by blanks - type: File[] - out: - doc: Output file - type: string - design: - doc: input file containing the experimental design - type: File? - keep_subelements: - doc: "For consensusXML input only: If set, the sub-features of the inputs are transferred to the output." - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__second_nearest_gap: - doc: Only link features whose distance to the second nearest neighbors (for both sides) is larger by 'second_nearest_gap' than the distance between the matched pair itself. - type: double? - algorithm__use_identifications: - doc: Never link features that are annotated with different peptides (features without ID's always match; only the best hit per peptide identification is considered). - type: boolean? - algorithm__ignore_charge: - doc: "false [default]: pairing requires equal charge state (or at least one unknown charge '0'); true: Pairing irrespective of charge state" - type: boolean? - algorithm__ignore_adduct: - doc: "true [default]: pairing requires equal adducts (or at least one without adduct annotation); true: Pairing irrespective of adducts" - type: string? - algorithm__distance_RT__max_difference: - doc: Never pair features with a larger RT distance (in seconds). - type: double? - algorithm__distance_RT__exponent: - doc: Normalized RT differences ([0-1], relative to 'max_difference') are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow) - type: double? - algorithm__distance_RT__weight: - doc: Final RT distances are weighted by this factor - type: double? - algorithm__distance_MZ__max_difference: - doc: Never pair features with larger m/z distance (unit defined by 'unit') - type: double? - algorithm__distance_MZ__unit: - doc: Unit of the 'max_difference' parameter - type: string? - algorithm__distance_MZ__exponent: - doc: Normalized ([0-1], relative to 'max_difference') m/z differences are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow) - type: double? - algorithm__distance_MZ__weight: - doc: Final m/z distances are weighted by this factor - type: double? - algorithm__distance_intensity__exponent: - doc: Differences in relative intensity ([0-1]) are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow) - type: double? - algorithm__distance_intensity__weight: - doc: Final intensity distances are weighted by this factor - type: double? - algorithm__distance_intensity__log_transform: - doc: Log-transform intensities? If disabled, d = |int_f2 - int_f1| / int_max. If enabled, d = |log(int_f2 + 1) - log(int_f1 + 1)| / log(int_max + 1)) - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FeatureLinkerUnlabeled -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FeatureLinkerUnlabeledKD.cwl b/workflow/cwl/FeatureLinkerUnlabeledKD.cwl deleted file mode 100644 index 857b150b6df..00000000000 --- a/workflow/cwl/FeatureLinkerUnlabeledKD.cwl +++ /dev/null @@ -1,125 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FeatureLinkerUnlabeledKD -doc: Groups corresponding features from multiple maps. -inputs: - in: - doc: input files separated by blanks - type: File[] - out: - doc: Output file - type: string - design: - doc: input file containing the experimental design - type: File? - keep_subelements: - doc: "For consensusXML input only: If set, the sub-features of the inputs are transferred to the output." - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__mz_unit: - doc: Unit of m/z tolerance - type: string? - algorithm__nr_partitions: - doc: Number of partitions in m/z space - type: long? - algorithm__warp__enabled: - doc: Whether or not to internally warp feature RTs using LOWESS transformation before linking (reported RTs in results will always be the original RTs) - type: string? - algorithm__warp__rt_tol: - doc: Width of RT tolerance window (sec) - type: double? - algorithm__warp__mz_tol: - doc: m/z tolerance (in ppm or Da) - type: double? - algorithm__warp__max_pairwise_log_fc: - doc: "Maximum absolute log10 fold change between two compatible signals during compatibility graph construction. Two signals from different maps will not be connected by an edge in the compatibility graph if absolute log fold change exceeds this limit (they might still end up in the same connected component, however). Note: this does not limit fold changes in the linking stage, only during RT alignment, where we try to find high-quality alignment anchor points. Setting this to a value < 0 disables the FC check." - type: double? - algorithm__warp__min_rel_cc_size: - doc: Only connected components containing compatible features from at least max(2, (warp_min_occur * number_of_input_maps)) input maps are considered for computing the warping function - type: double? - algorithm__warp__max_nr_conflicts: - doc: Allow up to this many conflicts (features from the same map) per connected component to be used for alignment (-1 means allow any number of conflicts) - type: long? - algorithm__link__rt_tol: - doc: Width of RT tolerance window (sec) - type: double? - algorithm__link__mz_tol: - doc: m/z tolerance (in ppm or Da) - type: double? - algorithm__link__charge_merging: - doc: whether to disallow charge mismatches (Identical), allow to link charge zero (i.e., unknown charge state) with every charge state, or disregard charges (Any). - type: string? - algorithm__link__adduct_merging: - doc: whether to only allow the same adduct for linking (Identical), also allow linking features with adduct-free ones, or disregard adducts (Any). - type: string? - algorithm__distance_RT__exponent: - doc: Normalized RT differences ([0-1], relative to 'max_difference') are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow) - type: double? - algorithm__distance_RT__weight: - doc: Final RT distances are weighted by this factor - type: double? - algorithm__distance_MZ__exponent: - doc: Normalized ([0-1], relative to 'max_difference') m/z differences are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow) - type: double? - algorithm__distance_MZ__weight: - doc: Final m/z distances are weighted by this factor - type: double? - algorithm__distance_intensity__exponent: - doc: Differences in relative intensity ([0-1]) are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow) - type: double? - algorithm__distance_intensity__weight: - doc: Final intensity distances are weighted by this factor - type: double? - algorithm__distance_intensity__log_transform: - doc: Log-transform intensities? If disabled, d = |int_f2 - int_f1| / int_max. If enabled, d = |log(int_f2 + 1) - log(int_f1 + 1)| / log(int_max + 1)) - type: string? - algorithm__LOWESS__span: - doc: Fraction of datapoints (f) to use for each local regression (determines the amount of smoothing). Choosing this parameter in the range .2 to .8 usually results in a good fit. - type: double? - algorithm__LOWESS__num_iterations: - doc: Number of robustifying iterations for lowess fitting. - type: long? - algorithm__LOWESS__delta: - doc: Nonnegative parameter which may be used to save computations (recommended value is 0.01 of the range of the input, e.g. for data ranging from 1000 seconds to 2000 seconds, it could be set to 10). Setting a negative value will automatically do this. - type: double? - algorithm__LOWESS__interpolation_type: - doc: "Method to use for interpolation between datapoints computed by lowess. 'linear': Linear interpolation. 'cspline': Use the cubic spline for interpolation. 'akima': Use an akima spline for interpolation" - type: string? - algorithm__LOWESS__extrapolation_type: - doc: "Method to use for extrapolation outside the data range. 'two-point-linear': Uses a line through the first and last point to extrapolate. 'four-point-linear': Uses a line through the first and second point to extrapolate in front and and a line through the last and second-to-last point in the end. 'global-linear': Uses a linear regression to fit a line through all data points and use it for interpolation." - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FeatureLinkerUnlabeledKD -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FeatureLinkerUnlabeledQT.cwl b/workflow/cwl/FeatureLinkerUnlabeledQT.cwl deleted file mode 100644 index dba94b8d456..00000000000 --- a/workflow/cwl/FeatureLinkerUnlabeledQT.cwl +++ /dev/null @@ -1,104 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FeatureLinkerUnlabeledQT -doc: Groups corresponding features from multiple maps. -inputs: - in: - doc: input files separated by blanks - type: File[] - out: - doc: Output file - type: string - design: - doc: input file containing the experimental design - type: File? - keep_subelements: - doc: "For consensusXML input only: If set, the sub-features of the inputs are transferred to the output." - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__use_identifications: - doc: Never link features that are annotated with different peptides (only the best hit per peptide identification is taken into account). - type: boolean? - algorithm__nr_partitions: - doc: How many partitions in m/z space should be used for the algorithm (more partitions means faster runtime and more memory efficient execution). - type: long? - algorithm__min_nr_diffs_per_bin: - doc: "If IDs are used: How many differences from matching IDs should be used to calculate a linking tolerance for unIDed features in an RT region. RT regions will be extended until that number is reached." - type: long? - algorithm__min_IDscore_forTolCalc: - doc: "If IDs are used: What is the minimum score of an ID to assume a reliable match for tolerance calculation. Check your current score type!" - type: double? - algorithm__noID_penalty: - doc: "If IDs are used: For the normalized distances, how high should the penalty for missing IDs be? 0 = no bias, 1 = IDs inside the max tolerances always preferred (even if much further away)." - type: double? - algorithm__ignore_charge: - doc: "false [default]: pairing requires equal charge state (or at least one unknown charge '0'); true: Pairing irrespective of charge state" - type: boolean? - algorithm__ignore_adduct: - doc: "true [default]: pairing requires equal adducts (or at least one without adduct annotation); true: Pairing irrespective of adducts" - type: string? - algorithm__distance_RT__max_difference: - doc: Never pair features with a larger RT distance (in seconds). - type: double? - algorithm__distance_RT__exponent: - doc: Normalized RT differences ([0-1], relative to 'max_difference') are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow) - type: double? - algorithm__distance_RT__weight: - doc: Final RT distances are weighted by this factor - type: double? - algorithm__distance_MZ__max_difference: - doc: Never pair features with larger m/z distance (unit defined by 'unit') - type: double? - algorithm__distance_MZ__unit: - doc: Unit of the 'max_difference' parameter - type: string? - algorithm__distance_MZ__exponent: - doc: Normalized ([0-1], relative to 'max_difference') m/z differences are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow) - type: double? - algorithm__distance_MZ__weight: - doc: Final m/z distances are weighted by this factor - type: double? - algorithm__distance_intensity__exponent: - doc: Differences in relative intensity ([0-1]) are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow) - type: double? - algorithm__distance_intensity__weight: - doc: Final intensity distances are weighted by this factor - type: double? - algorithm__distance_intensity__log_transform: - doc: Log-transform intensities? If disabled, d = |int_f2 - int_f1| / int_max. If enabled, d = |log(int_f2 + 1) - log(int_f1 + 1)| / log(int_max + 1)) - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FeatureLinkerUnlabeledQT -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FileConverter.cwl b/workflow/cwl/FileConverter.cwl deleted file mode 100644 index 20c26eb254e..00000000000 --- a/workflow/cwl/FileConverter.cwl +++ /dev/null @@ -1,101 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FileConverter -doc: Converts between different MS file formats. -inputs: - in: - doc: Input file to convert. - type: File - in_type: - doc: "Input file type -- default: determined from file extension or content\n" - type: string? - UID_postprocessing: - doc: "unique ID post-processing for output data.\n'none' keeps current IDs even if invalid.\n'ensure' keeps current IDs but reassigns invalid ones.\n'reassign' assigns new unique IDs." - type: string? - out: - doc: Output file - type: string - out_type: - doc: "Output file type -- default: determined from file extension or content\nNote: that not all conversion paths work or make sense." - type: string? - TIC_DTA2D: - doc: Export the TIC instead of the entire experiment in mzML/mzData/mzXML -> DTA2D conversions. - type: boolean? - MGF_compact: - doc: Use a more compact format when writing MGF (no zero-intensity peaks, limited number of decimal places) - type: boolean? - force_MaxQuant_compatibility: - doc: "[mzXML output only] Make sure that MaxQuant can read the mzXML and set the msManufacturer to 'Thermo Scientific'." - type: boolean? - force_TPP_compatibility: - doc: "[mzML output only] Make sure that TPP parsers can read the mzML and the precursor ion m/z in the file (otherwise it will be set to zero by the TPP)." - type: boolean? - convert_to_chromatograms: - doc: "[mzML output only] Assumes that the provided spectra represent data in SRM mode or targeted MS1 mode and converts them to chromatogram data." - type: boolean? - change_im_format: - doc: "[mzML output only] How to store ion mobility scans (none: no change in format; multiple_spectra: store each IM frame as multiple scans (one per drift time value); concatenated: store whole frame as single scan with IM values in a FloatDataArray" - type: string? - write_scan_index: - doc: Append an index when writing mzML or mzXML files. Some external tools might rely on it. - type: string? - lossy_compression: - doc: "Use numpress compression to achieve optimally small file size using linear compression for m/z domain and slof for intensity and float data arrays (attention: may cause small loss of precision; only for mzML data)." - type: boolean? - lossy_mass_accuracy: - doc: Desired (absolute) m/z accuracy for lossy compression (e.g. use 0.0001 for a mass accuracy of 0.2 ppm at 500 m/z, default uses -1.0 for maximal accuracy). - type: double? - process_lowmemory: - doc: "Whether to process the file on the fly without loading the whole file into memory first (only for conversions of mzXML/mzML to mzML).\nNote: this flag will prevent conversion from spectra to chromatograms." - type: boolean? - NET_executable: - doc: The .NET framework executable. Only required on linux and mac. - type: File? - ThermoRaw_executable: - doc: The ThermoRawFileParser executable. - type: File? - no_peak_picking: - doc: Disables vendor peak picking for raw files. - type: boolean? - no_zlib_compression: - doc: Disables zlib compression for raw file conversion. Enables compatibility with some tools that do not support compressed input files, e.g. X!Tandem. - type: boolean? - include_noise: - doc: Include noise data in mzML output. - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FileConverter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FileFilter.cwl b/workflow/cwl/FileFilter.cwl deleted file mode 100644 index 3e466b83cf7..00000000000 --- a/workflow/cwl/FileFilter.cwl +++ /dev/null @@ -1,272 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FileFilter -doc: Extracts or manipulates portions of data from peak, feature or consensus-feature files. -inputs: - in: - doc: Input file - type: File - in_type: - doc: "Input file type -- default: determined from file extension or content" - type: string? - out: - doc: Output file - type: string - out_type: - doc: "Output file type -- default: determined from file extension or content" - type: string? - rt: - doc: Retention time range to extract - type: string? - mz: - doc: m/z range to extract (applies to ALL ms levels!) - type: string? - int: - doc: Intensity range to extract - type: string? - sort: - doc: Sorts the output according to RT and m/z. - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - peak_options__sn: - doc: Write peaks with S/N > 'sn' values only - type: double? - peak_options__rm_pc_charge: - doc: Remove MS(2) spectra with these precursor charges. All spectra without precursor are kept! - type: long[]? - peak_options__pc_mz_range: - doc: MSn (n>=2) precursor filtering according to their m/z value. Do not use this flag in conjunction with 'mz', unless you want to actually remove peaks in spectra (see 'mz'). RT filtering is covered by 'rt' and compatible with this flag. - type: string? - peak_options__pc_mz_list: - doc: List of m/z values. If a precursor window covers ANY of these values, the corresponding MS/MS spectrum will be kept. - type: double[]? - peak_options__level: - doc: MS levels to extract - type: long[]? - peak_options__sort_peaks: - doc: Sorts the peaks according to m/z - type: boolean? - peak_options__no_chromatograms: - doc: No conversion to space-saving real chromatograms, e.g. from SRM scans - type: boolean? - peak_options__remove_chromatograms: - doc: Removes chromatograms stored in a file - type: boolean? - peak_options__remove_empty: - doc: Removes spectra and chromatograms without peaks. - type: boolean? - peak_options__mz_precision: - doc: Store base64 encoded m/z data using 32 or 64 bit precision - type: string? - peak_options__int_precision: - doc: Store base64 encoded intensity data using 32 or 64 bit precision - type: string? - peak_options__indexed_file: - doc: Whether to add an index to the file when writing - type: string? - peak_options__zlib_compression: - doc: Whether to store data with zlib compression (lossless compression) - type: boolean? - peak_options__numpress__masstime: - doc: "Apply MS Numpress compression algorithms in m/z or rt dimension (recommended: linear)" - type: string? - peak_options__numpress__lossy_mass_accuracy: - doc: Desired (absolute) m/z accuracy for lossy compression (e.g. use 0.0001 for a mass accuracy of 0.2 ppm at 500 m/z, default uses -1.0 for maximal accuracy). - type: double? - peak_options__numpress__intensity: - doc: "Apply MS Numpress compression algorithms in intensity dimension (recommended: slof or pic)" - type: string? - peak_options__numpress__float_da: - doc: "Apply MS Numpress compression algorithms for the float data arrays (recommended: slof or pic)" - type: string? - spectra__remove_zoom: - doc: Remove zoom (enhanced resolution) scans - type: boolean? - spectra__remove_mode: - doc: Remove scans by scan mode - type: string? - spectra__remove_activation: - doc: Remove MSn scans where any of its precursors features a certain activation method - type: string? - spectra__remove_collision_energy: - doc: Remove MSn scans with a collision energy in the given interval - type: string? - spectra__remove_isolation_window_width: - doc: Remove MSn scans whose isolation window width is in the given interval - type: string? - spectra__select_zoom: - doc: Select zoom (enhanced resolution) scans - type: boolean? - spectra__select_mode: - doc: "Selects scans by scan mode\n" - type: string? - spectra__select_activation: - doc: Retain MSn scans where any of its precursors features a certain activation method - type: string? - spectra__select_collision_energy: - doc: Select MSn scans with a collision energy in the given interval - type: string? - spectra__select_isolation_window_width: - doc: Select MSn scans whose isolation window width is in the given interval - type: string? - spectra__select_polarity: - doc: Retain MSn scans with a certain scan polarity - type: string? - spectra__replace_pc_charge: - doc: Replaces in_charge with out_charge in all precursors. - type: string? - spectra__blackorwhitelist__file: - doc: "Input file containing MS2 spectra that should be retained or removed from the mzML file!\nMatching tolerances are taken from 'spectra:blackorwhitelist:similarity_threshold|rt|mz' options.\n" - type: File? - spectra__blackorwhitelist__similarity_threshold: - doc: Similarity threshold when matching MS2 spectra. (-1 = disabled). - type: double? - spectra__blackorwhitelist__rt: - doc: Retention tolerance [s] when matching precursor positions. (-1 = disabled) - type: double? - spectra__blackorwhitelist__mz: - doc: m/z tolerance [Th] when matching precursor positions. (-1 = disabled) - type: double? - spectra__blackorwhitelist__use_ppm_tolerance: - doc: If ppm tolerance should be used. Otherwise Da are used. - type: string? - spectra__blackorwhitelist__blacklist: - doc: "True: remove matched MS2. False: retain matched MS2 spectra. Other levels are kept" - type: string? - feature__q: - doc: Overall quality range to extract [0:1] - type: string? - consensus__map: - doc: Non-empty list of maps to be extracted from a consensus (indices are 0-based). - type: long[]? - consensus__map_and: - doc: Consensus features are kept only if they contain exactly one feature from each map (as given above in 'map') - type: boolean? - consensus__blackorwhitelist__blacklist: - doc: "True: remove matched MS2. False: retain matched MS2 spectra. Other levels are kept" - type: string? - consensus__blackorwhitelist__file: - doc: "Input file containing consensus features whose corresponding MS2 spectra should be removed from the mzML file!\nMatching tolerances are taken from 'consensus:blackorwhitelist:rt' and 'consensus:blackorwhitelist:mz' options.\nIf consensus:blackorwhitelist:maps is specified, only these will be used.\n" - type: File? - consensus__blackorwhitelist__maps: - doc: Maps used for black/white list filtering - type: long[]? - consensus__blackorwhitelist__rt: - doc: Retention tolerance [s] for precursor to consensus feature position - type: double? - consensus__blackorwhitelist__mz: - doc: m/z tolerance [Th] for precursor to consensus feature position - type: double? - consensus__blackorwhitelist__use_ppm_tolerance: - doc: If ppm tolerance should be used. Otherwise Da are used. - type: string? - f_and_c__charge: - doc: Charge range to extract - type: string? - f_and_c__size: - doc: Size range to extract - type: string? - f_and_c__remove_meta: - doc: Expects a 3-tuple (=3 entries in the list), i.e. 'lt|eq|gt' ; the first is the name of meta value, followed by the comparison operator (equal, less or greater) and the value to compare to. All comparisons are done after converting the given value to the corresponding data value type of the meta value (for lists, this simply compares length, not content!)! - type: string[]? - f_and_c__remove_hull: - doc: Remove hull from features. - type: boolean? - id__remove_clashes: - doc: Remove features with id clashes (different sequences mapped to one feature) - type: boolean? - id__keep_best_score_id: - doc: in case of multiple peptide identifications, keep only the id with best score - type: boolean? - id__sequences_whitelist: - doc: Keep only features containing whitelisted substrings, e.g. features containing LYSNLVER or the modification (Oxidation). To control comparison method used for whitelisting, see 'id:sequence_comparison_method'. - type: string[]? - id__sequence_comparison_method: - doc: Comparison method used to determine if a feature is whitelisted. - type: string? - id__accessions_whitelist: - doc: keep only features with white listed accessions, e.g. sp|P02662|CASA1_BOVIN - type: string[]? - id__remove_annotated_features: - doc: Remove features with annotations - type: boolean? - id__remove_unannotated_features: - doc: Remove features without annotations - type: boolean? - id__remove_unassigned_ids: - doc: Remove unassigned peptide identifications - type: boolean? - id__blacklist: - doc: "Input file containing MS2 identifications whose corresponding MS2 spectra should be removed from the mzML file!\nMatching tolerances are taken from 'id:rt' and 'id:mz' options.\nThis tool will require all IDs to be matched to an MS2 spectrum, and quit with error otherwise. Use 'id:blacklist_imperfect' to allow for mismatches." - type: File? - id__rt: - doc: Retention tolerance [s] for precursor to id position - type: double? - id__mz: - doc: m/z tolerance [Th] for precursor to id position - type: double? - id__blacklist_imperfect: - doc: Allow for mismatching precursor positions (see 'id:blacklist') - type: boolean? - algorithm__SignalToNoise__max_intensity: - doc: maximal intensity considered for histogram construction. By default, it will be calculated automatically (see auto_mode). Only provide this parameter if you know what you are doing (and change 'auto_mode' to '-1')! All intensities EQUAL/ABOVE 'max_intensity' will be added to the LAST histogram bin. If you choose 'max_intensity' too small, the noise estimate might be too small as well. If chosen too big, the bins become quite large (which you could counter by increasing 'bin_count', which increases runtime). In general, the Median-S/N estimator is more robust to a manual max_intensity than the MeanIterative-S/N. - type: long? - algorithm__SignalToNoise__auto_max_stdev_factor: - doc: "parameter for 'max_intensity' estimation (if 'auto_mode' == 0): mean + 'auto_max_stdev_factor' * stdev" - type: double? - algorithm__SignalToNoise__auto_max_percentile: - doc: "parameter for 'max_intensity' estimation (if 'auto_mode' == 1): auto_max_percentile th percentile" - type: long? - algorithm__SignalToNoise__auto_mode: - doc: "method to use to determine maximal intensity: -1 --> use 'max_intensity'; 0 --> 'auto_max_stdev_factor' method (default); 1 --> 'auto_max_percentile' method" - type: long? - algorithm__SignalToNoise__win_len: - doc: window length in Thomson - type: double? - algorithm__SignalToNoise__bin_count: - doc: number of bins for intensity values - type: long? - algorithm__SignalToNoise__min_required_elements: - doc: minimum number of elements required in a window (otherwise it is considered sparse) - type: long? - algorithm__SignalToNoise__noise_for_empty_window: - doc: noise value used for sparse windows - type: double? - algorithm__SignalToNoise__write_log_messages: - doc: Write out log messages in case of sparse windows or median in rightmost histogram bin - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FileFilter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FileInfo.cwl b/workflow/cwl/FileInfo.cwl deleted file mode 100644 index b0f1b9094fe..00000000000 --- a/workflow/cwl/FileInfo.cwl +++ /dev/null @@ -1,78 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FileInfo -doc: Shows basic information about the file, such as data ranges and file type. -inputs: - in: - doc: input file - type: File - in_type: - doc: "input file type -- default: determined from file extension or content" - type: string? - out: - doc: Optional output file. If left out, the output is written to the command line. - type: string? - out_tsv: - doc: Second optional output file. Tab separated flat text file. - type: string? - m: - doc: Show meta information about the whole experiment - type: boolean? - p: - doc: Shows data processing information - type: boolean? - s: - doc: Computes a five-number statistics of intensities, qualities, and widths - type: boolean? - d: - doc: Show detailed listing of all spectra and chromatograms (peak files only) - type: boolean? - c: - doc: Check for corrupt data in the file (peak files only) - type: boolean? - v: - doc: Validate the file only (for mzML, mzData, mzXML, featureXML, idXML, consensusXML, pepXML) - type: boolean? - i: - doc: Check whether a given mzML file contains valid indices (conforming to the indexedmzML standard) - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File? - outputBinding: - glob: $(inputs.out) - out_tsv: - type: File? - outputBinding: - glob: $(inputs.out_tsv) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FileInfo -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FileMerger.cwl b/workflow/cwl/FileMerger.cwl deleted file mode 100644 index 074ae9bf971..00000000000 --- a/workflow/cwl/FileMerger.cwl +++ /dev/null @@ -1,71 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FileMerger -doc: Merges several MS files into one file. -inputs: - in: - doc: Input files separated by blank - type: File[] - in_type: - doc: "Input file type (default: determined from file extension or content)" - type: string? - out: - doc: Output file - type: string - annotate_file_origin: - doc: Store the original filename in each feature using meta value "file_origin" (for featureXML and consensusXML only). - type: boolean? - append_method: - doc: "(ConsensusXML-only) Append quantitative information about features row-wise or column-wise.\n- 'append_rows' is usually used when the inputs come from the same MS run (e.g. caused by manual splitting or multiple algorithms on the same file)\n- 'append_cols' when you want to combine consensusXMLs from e.g. different fractions to be summarized in ProteinQuantifier or jointly exported with MzTabExporter." - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - rt_concat__gap: - doc: The amount of gap (in seconds) to insert between the RT ranges of different input files. RT concatenation is enabled if a value > 0 is set. - type: double? - raw__rt_auto: - doc: Assign retention times automatically (integers starting at 1) - type: boolean? - raw__rt_custom: - doc: List of custom retention times that are assigned to the files. The number of given retention times must be equal to the number of input files. - type: double[]? - raw__rt_filename: - doc: Try to guess the retention time of a file based on the filename. This option is useful for merging DTA files, where filenames should contain the string 'rt' directly followed by a floating point number, e.g. 'my_spectrum_rt2795.15.dta' - type: boolean? - raw__ms_level: - doc: If 1 or higher, this number is assigned to spectra as the MS level. This option is useful for DTA files which do not contain MS level information. - type: long? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FileMerger -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/FuzzyDiff.cwl b/workflow/cwl/FuzzyDiff.cwl deleted file mode 100644 index 1047a259778..00000000000 --- a/workflow/cwl/FuzzyDiff.cwl +++ /dev/null @@ -1,65 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: FuzzyDiff -doc: Compares two files, tolerating numeric differences. -inputs: - in1: - doc: first input file - type: File - in2: - doc: second input file - type: File - ratio: - doc: acceptable relative error. Only one of 'ratio' or 'absdiff' has to be satisfied. Use "absdiff" to deal with cases like "zero vs. epsilon". - type: double? - absdiff: - doc: "acceptable absolute difference. Only one of 'ratio' or 'absdiff' has to be satisfied. " - type: double? - whitelist: - doc: Lines containing one of these strings are skipped - type: string[]? - matched_whitelist: - doc: Lines where one file contains one string and the other file another string are skipped. Input is given as list of colon separated tuples, e.g. String1:String2 String3:String4 - type: string[]? - verbose: - doc: "set verbose level:\n0 = very quiet mode (absolutely no output)\n1 = quiet mode (no output unless differences detected)\n2 = default (include summary at end)\n3 = continue after errors\n" - type: long? - tab_width: - doc: tabulator width, used for calculation of column numbers - type: long? - first_column: - doc: number of first column, used for calculation of column numbers - type: long? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - [] -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - FuzzyDiff -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/GNPSExport.cwl b/workflow/cwl/GNPSExport.cwl deleted file mode 100644 index 540b0cbeaf7..00000000000 --- a/workflow/cwl/GNPSExport.cwl +++ /dev/null @@ -1,83 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: GNPSExport -doc: "Export representative consensus MS/MS scan per consensusElement into a .MGF file format.\nSee the documentation on https://ccms-ucsd.github.io/GNPSDocumentation/featurebasedmolecularnetworking-with-openms" -inputs: - in_cm: - doc: Input consensusXML file containing only consensusElements with "peptide" annotations. - type: File - in_mzml: - doc: "Original mzml files containing the ms2 spectra (aka peptide annotation). \nMust be in order that the consensusXML file maps the original mzML files." - type: File[] - out: - doc: Output MGF file. - type: string - out_quantification: - doc: Output feature quantification table. - type: string - out_pairs: - doc: Output supplementary pairs table for IIMN. - type: string? - out_meta_values: - doc: Output meta value file. - type: string? - output_type: - doc: specificity of mgf output information - type: string? - peptide_cutoff: - doc: Number of most intense peptides to consider per consensus element; '-1' to consider all identifications. - type: long? - ms2_bin_size: - doc: Bin size (Da) for fragment ions when merging ms2 scans. - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - merged_spectra__cos_similarity: - doc: Cosine similarity threshold for merged_spectra output. - type: double? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - out_quantification: - type: File - outputBinding: - glob: $(inputs.out_quantification) - out_pairs: - type: File? - outputBinding: - glob: $(inputs.out_pairs) - out_meta_values: - type: File? - outputBinding: - glob: $(inputs.out_meta_values) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - GNPSExport -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/HighResPrecursorMassCorrector.cwl b/workflow/cwl/HighResPrecursorMassCorrector.cwl deleted file mode 100644 index fc3d3794bb3..00000000000 --- a/workflow/cwl/HighResPrecursorMassCorrector.cwl +++ /dev/null @@ -1,90 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: HighResPrecursorMassCorrector -doc: Corrects the precursor mass and charge determined by the instrument software. -inputs: - in: - doc: Input file (centroided data) - type: File - out: - doc: Output file - type: string - out_csv: - doc: "Optional CSV output file for results on 'nearest_peak' or 'highest_intensity_peak' algorithm (see corresponding subsection) containing columns: RT, uncorrectedMZ, correctedMZ, deltaMZ." - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - feature__in: - doc: Features used to correct precursor masses. - type: File? - feature__mz_tolerance: - doc: The precursor mass tolerance. Used to determine matching to feature mass traces. - type: double? - feature__mz_tolerance_unit: - doc: Unit of precursor mass tolerance - type: string? - feature__rt_tolerance: - doc: Additional retention time tolerance added to feature boundaries. - type: double? - feature__max_trace: - doc: Maximum isotopic trace considered in matching a precursor to a feature. - type: long? - feature__believe_charge: - doc: Assume precursor charge to be correct. - type: boolean? - feature__keep_original: - doc: Make a copy of the precursor and MS2 (true) or discard the original (false). - type: boolean? - feature__assign_all_matching: - doc: Correct a precursor using all matching features (true) or only the nearest (false). Only evaluated if copies are created (feature:keep_original). - type: boolean? - nearest_peak__mz_tolerance: - doc: The precursor mass tolerance to find the closest MS1 peak. (Disable method by setting value to 0.0) - type: double? - nearest_peak__mz_tolerance_unit: - doc: Unit of precursor mass tolerance - type: string? - highest_intensity_peak__mz_tolerance: - doc: The precursor mass tolerance to find the highest intensity MS1 peak. Suggested value 1/max. expected charge. (Disable method by setting value to 0.0) - type: double? - highest_intensity_peak__mz_tolerance_unit: - doc: Unit of precursor mass tolerance - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - out_csv: - type: File? - outputBinding: - glob: $(inputs.out_csv) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - HighResPrecursorMassCorrector -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/IDConflictResolver.cwl b/workflow/cwl/IDConflictResolver.cwl deleted file mode 100644 index 35d4305a0e5..00000000000 --- a/workflow/cwl/IDConflictResolver.cwl +++ /dev/null @@ -1,50 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: IDConflictResolver -doc: Resolves ambiguous annotations of features with peptide identifications -inputs: - in: - doc: Input file (data annotated with identifications) - type: File - out: - doc: Output file (data with one peptide identification per feature) - type: string - resolve_between_features: - doc: A map may contain multiple features with both identical (possibly modified i.e. not stripped) sequence and charge state. The feature with the 'highest intensity' is very likely the most reliable one. When switched on, the filter removes the sequence annotation from the lower intensity features, thereby resolving the multiplicity. Only the most reliable features for each (possibly modified i.e. not stripped) sequence maintain annotated with this peptide sequence. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - IDConflictResolver -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/IDDecoyProbability.cwl b/workflow/cwl/IDDecoyProbability.cwl deleted file mode 100644 index 69ddfaf8233..00000000000 --- a/workflow/cwl/IDDecoyProbability.cwl +++ /dev/null @@ -1,59 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: IDDecoyProbability -doc: "Estimates peptide probabilities using a decoy search strategy.\nWARNING: This util is deprecated." -inputs: - in: - doc: Identification input of combined forward decoy search (reindex with PeptideIndexer first) - type: File? - fwd_in: - doc: Identification input of forward run - type: File? - rev_in: - doc: Identification input of decoy run - type: File? - out: - doc: Identification output with forward scores converted to probabilities - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - decoy_algorithm__number_of_bins: - doc: Number of bins used for the fitting, if sparse datasets are used, this number should be smaller - type: long? - decoy_algorithm__lower_score_better_default_value_if_zero: - doc: This value is used if e.g. a E-value score is 0 and cannot be transformed in a real number (log of E-value) - type: double? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - IDDecoyProbability -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/IDExtractor.cwl b/workflow/cwl/IDExtractor.cwl deleted file mode 100644 index a8a120b4cef..00000000000 --- a/workflow/cwl/IDExtractor.cwl +++ /dev/null @@ -1,56 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: IDExtractor -doc: Extracts 'n' peptides randomly or best 'n' from idXML files. -inputs: - in: - doc: input file - type: File - out: - doc: output file - type: string - number_of_peptides: - doc: Number of randomly chosen peptides - type: long? - number_of_rand_invokations: - doc: Number of rand invocations before random draw (basically a seed) - type: long? - best_hits: - doc: If this flag is set the best n peptides are chosen. - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - IDExtractor -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/IDFileConverter.cwl b/workflow/cwl/IDFileConverter.cwl deleted file mode 100644 index ae416057f1f..00000000000 --- a/workflow/cwl/IDFileConverter.cwl +++ /dev/null @@ -1,182 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: IDFileConverter -doc: Converts identification engine file formats. -inputs: - in: - doc: "Input file or directory containing the data to convert. This may be:\n- a single file in OpenMS database format (.oms),\n- a single file in a multi-purpose XML format (.idXML, .mzid, .pepXML, .protXML),\n- a single file in a search engine-specific format (Mascot: .mascotXML, OMSSA: .omssaXML, X! Tandem: .xml, Percolator: .psms, xQuest: .xquest.xml),\n- a single file in fasta format (can only be used to generate a theoretical mzML),\n- a single text file (tab separated) with one line for all peptide sequences matching a spectrum (top N hits),\n- for Sequest results, a directory containing .out files.\n" - type: File - out: - doc: Output file - type: string - out_type: - doc: "Output file type (default: determined from file extension)" - type: string? - mz_file: - doc: "[pepXML, Sequest, Mascot, X! Tandem, mzid, Percolator only] Retention times and native spectrum ids (spectrum_references) will be looked up in this file" - type: File? - mz_name: - doc: "[pepXML only] Experiment filename/path (extension will be removed) to match in the pepXML file ('base_name' attribute). Only necessary if different from 'mz_file'." - type: string? - peptideprophet_analyzed: - doc: "[pepXML output only] Write output in the format of a PeptideProphet analysis result. By default a 'raw' pepXML is produced that contains only search engine results." - type: boolean? - score_type: - doc: "[Percolator only] Which of the Percolator scores to report as 'the' score for a peptide hit" - type: string? - ignore_proteins_per_peptide: - doc: "[Sequest only] Workaround to deal with .out files that contain e.g. \"+1\" in references column,\nbut do not list extra references in subsequent lines (try -debug 3 or 4)" - type: boolean? - scan_regex: - doc: "[Mascot, pepXML, Percolator only] Regular expression used to extract the scan number or retention time. See documentation for details." - type: string? - no_spectra_data_override: - doc: "[+mz_file only] Avoid overriding 'spectra_data' in protein identifications if 'mz_file' is given and 'spectrum_reference's are added/updated. Use only if you are sure it is absolutely the same 'mz_file' as used for identification." - type: boolean? - no_spectra_references_override: - doc: "[+mz_file only] Avoid overriding 'spectrum_reference' in peptide identifications if 'mz_file' is given and a 'spectrum_reference' is already present." - type: boolean? - add_ionmatch_annotation: - doc: "[+mz_file only] Annotate the identifications with ion matches from spectra in 'mz_file' using the given tolerance (in Da). This will take quite some time." - type: double? - concatenate_peptides: - doc: "[FASTA output only] Will concatenate the top peptide hits to one peptide sequence, rather than write a new peptide for each hit." - type: boolean? - number_of_hits: - doc: "[FASTA output only] Controls how many peptide hits will be exported. A value of 0 or less exports all hits." - type: long? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - fasta_to_mzml__isotope_model: - doc: Model to use for isotopic peaks ('none' means no isotopic peaks are added, 'coarse' adds isotopic peaks in unit mass distance, 'fine' uses the hyperfine isotopic generator to add accurate isotopic peaks. Note that adding isotopic peaks is very slow. - type: string? - fasta_to_mzml__max_isotope: - doc: Defines the maximal isotopic peak which is added if 'isotope_model' is 'coarse' - type: long? - fasta_to_mzml__max_isotope_probability: - doc: Defines the maximal isotopic probability to cover if 'isotope_model' is 'fine' - type: double? - fasta_to_mzml__add_metainfo: - doc: Adds the type of peaks as metainfo to the peaks, like y8+, [M-H2O+2H]++ - type: boolean? - fasta_to_mzml__add_losses: - doc: Adds common losses to those ion expect to have them, only water and ammonia loss is considered - type: boolean? - fasta_to_mzml__sort_by_position: - doc: Sort output by position - type: string? - fasta_to_mzml__add_precursor_peaks: - doc: Adds peaks of the unfragmented precursor ion to the spectrum - type: boolean? - fasta_to_mzml__add_all_precursor_charges: - doc: Adds precursor peaks with all charges in the given range - type: boolean? - fasta_to_mzml__add_abundant_immonium_ions: - doc: Add most abundant immonium ions (for Proline, Cystein, Iso/Leucine, Histidin, Phenylalanin, Tyrosine, Tryptophan) - type: boolean? - fasta_to_mzml__add_first_prefix_ion: - doc: If set to true e.g. b1 ions are added - type: boolean? - fasta_to_mzml__add_y_ions: - doc: Add peaks of y-ions to the spectrum - type: string? - fasta_to_mzml__add_b_ions: - doc: Add peaks of b-ions to the spectrum - type: string? - fasta_to_mzml__add_a_ions: - doc: Add peaks of a-ions to the spectrum - type: boolean? - fasta_to_mzml__add_c_ions: - doc: Add peaks of c-ions to the spectrum - type: boolean? - fasta_to_mzml__add_x_ions: - doc: Add peaks of x-ions to the spectrum - type: boolean? - fasta_to_mzml__add_z_ions: - doc: Add peaks of z-ions to the spectrum (sometimes observed in CID and for some AAs in ExD due to H abstraction) - type: boolean? - fasta_to_mzml__add_zp1_ions: - doc: Add peaks of z+1-radical cations (also [z+H]*^{+} or simply z*) to the spectrum (often observed in ExD) - type: boolean? - fasta_to_mzml__add_zp2_ions: - doc: Add peaks of z+2-radical cations (also [z+2H]*^{2+} or simply z') to the spectrum (often observed in ExD esp. with higher precursor charges >3 and smaller z-ions.) - type: boolean? - fasta_to_mzml__y_intensity: - doc: Intensity of the y-ions - type: double? - fasta_to_mzml__b_intensity: - doc: Intensity of the b-ions - type: double? - fasta_to_mzml__a_intensity: - doc: Intensity of the a-ions - type: double? - fasta_to_mzml__c_intensity: - doc: Intensity of the c-ions - type: double? - fasta_to_mzml__x_intensity: - doc: Intensity of the x-ions - type: double? - fasta_to_mzml__z_intensity: - doc: Intensity of the z-ions - type: double? - fasta_to_mzml__relative_loss_intensity: - doc: Intensity of loss ions, in relation to the intact ion intensity - type: double? - fasta_to_mzml__precursor_intensity: - doc: Intensity of the precursor peak - type: double? - fasta_to_mzml__precursor_H2O_intensity: - doc: Intensity of the H2O loss peak of the precursor - type: double? - fasta_to_mzml__precursor_NH3_intensity: - doc: Intensity of the NH3 loss peak of the precursor - type: double? - fasta_to_mzml__enzyme: - doc: Enzym used to digest the fasta proteins - type: string? - fasta_to_mzml__missed_cleavages: - doc: Number of allowed missed cleavages while digesting the fasta proteins - type: long? - fasta_to_mzml__min_charge: - doc: Minimum charge - type: long? - fasta_to_mzml__max_charge: - doc: Maximum charge - type: long? - fasta_to_mzml__precursor_charge: - doc: "Manually set precursor charge. (default: 0, meaning max_charge + 1 will be used as precursor charge)" - type: long? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - IDFileConverter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/IDFilter.cwl b/workflow/cwl/IDFilter.cwl deleted file mode 100644 index a9cb8e5aa5e..00000000000 --- a/workflow/cwl/IDFilter.cwl +++ /dev/null @@ -1,173 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: IDFilter -doc: Filters results from protein or peptide identification engines based on different criteria. -inputs: - in: - doc: "input file " - type: File - out: - doc: "output file " - type: string - var_mods: - doc: Keep only peptide hits with variable modifications (as defined in the 'SearchParameters' section of the input file). - type: boolean? - remove_duplicate_psm: - doc: Removes duplicated PSMs per spectrum and retains the one with the higher score. - type: boolean? - remove_shared_peptides: - doc: Only peptides matching exactly one protein are kept. Remember that isoforms count as different proteins! - type: boolean? - keep_unreferenced_protein_hits: - doc: Proteins not referenced by a peptide are retained in the IDs. - type: boolean? - remove_decoys: - doc: Remove proteins according to the information in the user parameters. Usually used in combination with 'delete_unreferenced_peptide_hits'. - type: boolean? - delete_unreferenced_peptide_hits: - doc: Peptides not referenced by any protein are deleted in the IDs. Usually used in combination with 'score:prot' or 'thresh:prot'. - type: boolean? - remove_peptide_hits_by_metavalue: - doc: Expects a 3-tuple (=3 entries in the list), i.e. 'lt|eq|gt|ne' ; the first is the name of meta value, followed by the comparison operator (equal, less, greater, not equal) and the value to compare to. All comparisons are done after converting the given value to the corresponding data value type of the meta value (for lists, this simply compares length, not content!)! - type: string[]? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - precursor__rt: - doc: Retention time range to extract. - type: string? - precursor__mz: - doc: Mass-to-charge range to extract. - type: string? - precursor__length: - doc: Keep only peptide hits with a sequence length in this range. - type: string? - precursor__charge: - doc: Keep only peptide hits with charge states in this range. - type: string? - score__pep: - doc: The score which should be reached by a peptide hit to be kept. - type: double? - score__prot: - doc: The score which should be reached by a protein hit to be kept. All proteins are filtered based on their singleton scores irrespective of grouping. Use in combination with 'delete_unreferenced_peptide_hits' to remove affected peptides. - type: double? - score__protgroup: - doc: The score which should be reached by a protein group to be kept. Performs group level score filtering (including groups of single proteins). Use in combination with 'delete_unreferenced_peptide_hits' to remove affected peptides. - type: double? - whitelist__proteins: - doc: "Filename of a FASTA file containing protein sequences.\nAll peptides that are not referencing a protein in this file are removed.\nAll proteins whose accessions are not present in this file are removed." - type: File? - whitelist__protein_accessions: - doc: "All peptides that do not reference at least one of the provided protein accession are removed.\nOnly proteins of the provided list are retained." - type: string[]? - whitelist__peptides: - doc: "Only peptides with the same sequence and modification assignment as any peptide in this file are kept. Use with 'whitelist:ignore_modifications' to only compare by sequence.\n" - type: File? - whitelist__ignore_modifications: - doc: Compare whitelisted peptides by sequence only. - type: boolean? - whitelist__modifications: - doc: Keep only peptides with sequences that contain (any of) the selected modification(s) - type: string[]? - blacklist__proteins: - doc: "Filename of a FASTA file containing protein sequences.\nAll peptides that are referencing a protein in this file are removed.\nAll proteins whose accessions are present in this file are removed." - type: File? - blacklist__protein_accessions: - doc: "All peptides that reference at least one of the provided protein accession are removed.\nOnly proteins not in the provided list are retained." - type: string[]? - blacklist__peptides: - doc: "Peptides with the same sequence and modification assignment as any peptide in this file are filtered out. Use with 'blacklist:ignore_modifications' to only compare by sequence.\n" - type: File? - blacklist__ignore_modifications: - doc: Compare blacklisted peptides by sequence only. - type: boolean? - blacklist__modifications: - doc: Remove all peptides with sequences that contain (any of) the selected modification(s) - type: string[]? - blacklist__RegEx: - doc: Remove all peptides with (unmodified) sequences matched by the RegEx e.g. [BJXZ] removes ambiguous peptides. - type: string? - in_silico_digestion__fasta: - doc: fasta protein sequence database. - type: File? - in_silico_digestion__enzyme: - doc: enzyme used for the digestion of the sample - type: string? - in_silico_digestion__specificity: - doc: Specificity of the filter - type: string? - in_silico_digestion__missed_cleavages: - doc: "range of allowed missed cleavages in the peptide sequences\nBy default missed cleavages are ignored" - type: long? - in_silico_digestion__methionine_cleavage: - doc: Allow methionine cleavage at the N-terminus of the protein. - type: boolean? - missed_cleavages__number_of_missed_cleavages: - doc: "range of allowed missed cleavages in the peptide sequences.\nFor example: 0:1 -> peptides with two or more missed cleavages will be removed,\n0:0 -> peptides with any missed cleavages will be removed" - type: string? - missed_cleavages__enzyme: - doc: enzyme used for the digestion of the sample - type: string? - rt__p_value: - doc: Retention time filtering by the p-value predicted by RTPredict. - type: double? - rt__p_value_1st_dim: - doc: Retention time filtering by the p-value predicted by RTPredict for first dimension. - type: double? - mz__error: - doc: Filtering by deviation to theoretical mass (disabled for negative values). - type: double? - mz__unit: - doc: Absolute or relative error. - type: string? - best__n_spectra: - doc: Keep only the 'n' best spectra (i.e., PeptideIdentifications) (for n > 0). A spectrum is considered better if it has a higher scoring peptide hit than the other spectrum. - type: long? - best__n_peptide_hits: - doc: Keep only the 'n' highest scoring peptide hits per spectrum (for n > 0). - type: long? - best__spectrum_per_peptide: - doc: "Keep one spectrum per peptide. Value determines if same sequence but different charges or modifications are treated as separate peptides or the same peptide. (default: false = filter disabled)." - type: string? - best__n_protein_hits: - doc: Keep only the 'n' highest scoring protein hits (for n > 0). - type: long? - best__strict: - doc: "Keep only the highest scoring peptide hit.\nSimilar to n_peptide_hits=1, but if there are ties between two or more highest scoring hits, none are kept." - type: boolean? - best__n_to_m_peptide_hits: - doc: Peptide hit rank range to extracts - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - IDFilter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/IDMapper.cwl b/workflow/cwl/IDMapper.cwl deleted file mode 100644 index a429848ce8d..00000000000 --- a/workflow/cwl/IDMapper.cwl +++ /dev/null @@ -1,80 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: IDMapper -doc: Assigns protein/peptide identifications to features or consensus features. -inputs: - id: - doc: Protein/peptide identifications file - type: File - in: - doc: Feature map/consensus map file - type: File - out: - doc: Output file (the format depends on the input file format). - type: string - rt_tolerance: - doc: "RT tolerance (in seconds) for the matching of peptide identifications and (consensus) features.\nTolerance is understood as 'plus or minus x', so the matching range increases by twice the given value." - type: double? - mz_tolerance: - doc: "m/z tolerance (in ppm or Da) for the matching of peptide identifications and (consensus) features.\nTolerance is understood as 'plus or minus x', so the matching range increases by twice the given value." - type: double? - mz_measure: - doc: Unit of 'mz_tolerance'. - type: string? - mz_reference: - doc: "Source of m/z values for peptide identifications. If 'precursor', the precursor-m/z from the idXML is used. If 'peptide',\nmasses are computed from the sequences of peptide hits; in this case, an identification matches if any of its hits matches.\n('peptide' should be used together with 'feature:use_centroid_mz' to avoid false-positive matches.)" - type: string? - ignore_charge: - doc: "For feature/consensus maps: Assign an ID independently of whether its charge state matches that of the (consensus) feature." - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - feature__use_centroid_rt: - doc: Use the RT coordinates of the feature centroids for matching, instead of the RT ranges of the features/mass traces. - type: boolean? - feature__use_centroid_mz: - doc: "Use the m/z coordinates of the feature centroids for matching, instead of the m/z ranges of the features/mass traces.\n(If you choose 'peptide' as 'mz_reference', you should usually set this flag to avoid false-positive matches.)" - type: string? - consensus__use_subelements: - doc: Match using RT and m/z of sub-features instead of consensus RT and m/z. A consensus feature matches if any of its sub-features matches. - type: boolean? - consensus__annotate_ids_with_subelements: - doc: Store the map index of the sub-feature in the peptide ID. - type: boolean? - spectra__in: - doc: MS run used to annotated unidentified spectra to features or consensus features. - type: File? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - IDMapper -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/IDMassAccuracy.cwl b/workflow/cwl/IDMassAccuracy.cwl deleted file mode 100644 index 3ebeec9f72e..00000000000 --- a/workflow/cwl/IDMassAccuracy.cwl +++ /dev/null @@ -1,83 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: IDMassAccuracy -doc: Calculates a distribution of the mass error from given mass spectra and IDs. -inputs: - in: - doc: Input mzML file list, containing the spectra. - type: File[] - id_in: - doc: Input idXML file list, containing the identifications. - type: File[] - out_precursor: - doc: Output file which contains the deviations from the precursors - type: string? - precursor_error_ppm: - doc: If this flag is used, the precursor mass tolerances are estimated in ppm instead of Da. - type: boolean? - out_fragment: - doc: Output file which contains the fragment ion m/z deviations - type: string? - fragment_error_ppm: - doc: If this flag is used, the fragment mass tolerances are estimated in ppm instead of Da. - type: boolean? - fragment_mass_tolerance: - doc: Maximal fragment mass tolerance which is allowed for MS/MS spectra, used for the calculation of matching ions. - type: double? - number_of_bins: - doc: Number of bins that should be used to calculate the histograms for the fitting. - type: long? - out_precursor_fit: - doc: Gaussian fit to the histogram of mass deviations from the precursors. - type: string? - out_fragment_fit: - doc: Gaussian fit to the histogram of mass deviations from the fragments. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out_precursor: - type: File? - outputBinding: - glob: $(inputs.out_precursor) - out_fragment: - type: File? - outputBinding: - glob: $(inputs.out_fragment) - out_precursor_fit: - type: File? - outputBinding: - glob: $(inputs.out_precursor_fit) - out_fragment_fit: - type: File? - outputBinding: - glob: $(inputs.out_fragment_fit) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - IDMassAccuracy -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/IDMerger.cwl b/workflow/cwl/IDMerger.cwl deleted file mode 100644 index f9e2ad103c9..00000000000 --- a/workflow/cwl/IDMerger.cwl +++ /dev/null @@ -1,62 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: IDMerger -doc: Merges several protein/peptide identification files into one file. -inputs: - in: - doc: Input files separated by blanks (all must have the same type) - type: File[] - out: - doc: Output file (must have the same type as the input files) - type: string - out_type: - doc: "Output file type (default: determined from file extension)" - type: string? - add_to: - doc: Optional input file. IDs from 'in' are added to this file, but only if the (modified) peptide sequences are not present yet (considering only best hits per spectrum). - type: File? - annotate_file_origin: - doc: "Store the original filename in each protein/peptide identification (meta value: 'file_origin') - idXML input/output only" - type: string? - pepxml_protxml: - doc: "Merge idXML files derived from a pepXML and corresponding protXML file.\nExactly two input files are expected in this case. Not compatible with 'add_to'." - type: boolean? - merge_proteins_add_PSMs: - doc: Merge all identified proteins by accession into one protein identification run but keep all the PSMs with updated links to potential new protein ID#s. Not compatible with 'add_to'. - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - IDMerger -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/IDPosteriorErrorProbability.cwl b/workflow/cwl/IDPosteriorErrorProbability.cwl deleted file mode 100644 index 760612b8463..00000000000 --- a/workflow/cwl/IDPosteriorErrorProbability.cwl +++ /dev/null @@ -1,84 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: IDPosteriorErrorProbability -doc: Estimates probabilities for incorrectly assigned peptide sequences and a set of search engine scores using a mixture model. -inputs: - in: - doc: "input file " - type: File - out: - doc: "output file " - type: string - out_plot: - doc: txt file (if gnuplot is available, a corresponding PDF will be created as well.) - type: string? - split_charge: - doc: The search engine scores are split by charge if this flag is set. Thus, for each charge state a new model will be computed. - type: boolean? - top_hits_only: - doc: If set only the top hits of every PeptideIdentification will be used - type: boolean? - fdr_for_targets_smaller: - doc: Only used, when top_hits_only set. Additionally, target/decoy information should be available. The score_type must be q-value from an previous False Discovery Rate run. - type: double? - ignore_bad_data: - doc: If set errors will be written but ignored. Useful for pipelines with many datasets where only a few are bad, but the pipeline should run through. - type: boolean? - prob_correct: - doc: If set scores will be calculated as '1 - ErrorProbabilities' and can be interpreted as probabilities for correct identifications. - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - fit_algorithm__number_of_bins: - doc: Number of bins used for visualization. Only needed if each iteration step of the EM-Algorithm will be visualized - type: long? - fit_algorithm__incorrectly_assigned: - doc: for 'Gumbel', the Gumbel distribution is used to plot incorrectly assigned sequences. For 'Gauss', the Gauss distribution is used. - type: string? - fit_algorithm__max_nr_iterations: - doc: Bounds the number of iterations for the EM algorithm when convergence is slow. - type: long? - fit_algorithm__neg_log_delta: - doc: The negative logarithm of the convergence threshold for the likelihood increase. - type: long? - fit_algorithm__outlier_handling: - doc: "What to do with outliers:\n- ignore_iqr_outliers: ignore outliers outside of 3*IQR from Q1/Q3 for fitting\n- set_iqr_to_closest_valid: set IQR-based outliers to the last valid value for fitting\n- ignore_extreme_percentiles: ignore everything outside 99th and 1st percentile (also removes equal values like potential censored max values in XTandem)\n- none: do nothing" - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - out_plot: - type: File? - outputBinding: - glob: $(inputs.out_plot) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - IDPosteriorErrorProbability -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/IDRTCalibration.cwl b/workflow/cwl/IDRTCalibration.cwl deleted file mode 100644 index 6df635aecd7..00000000000 --- a/workflow/cwl/IDRTCalibration.cwl +++ /dev/null @@ -1,59 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: IDRTCalibration -doc: Calibrate RTs of peptide hits linearly to standards. -inputs: - in: - doc: "input file " - type: File - out: - doc: "output file " - type: string - calibrant_1_reference: - doc: The RT of the first calibrant in the reference file. - type: double? - calibrant_2_reference: - doc: The RT of the second calibrant in the reference file. - type: double? - calibrant_1_input: - doc: The RT of the first calibrant in the input file. Please note that this value needs to be set. The default value -1.0 is not allowed. - type: double? - calibrant_2_input: - doc: The RT of the second calibrant in the input file. Please note that this value needs to be set. The default value -1.0 is not allowed. - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - IDRTCalibration -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/IDRipper.cwl b/workflow/cwl/IDRipper.cwl deleted file mode 100644 index 96a655d8df2..00000000000 --- a/workflow/cwl/IDRipper.cwl +++ /dev/null @@ -1,53 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: IDRipper -doc: Split protein/peptide identification file into several files according to identification run and annotated file origin. -inputs: - in: - doc: Input file, in which the protein/peptide identifications must be tagged with 'file_origin' - type: File - out: - doc: Path to the output directory to write the ripped files to. - type: string - numeric_filenames: - doc: Do not infer output filenames from spectra_data or file_origin but use the input filename with numeric suffixes. - type: boolean? - split_ident_runs: - doc: Split different identification runs into separate files. - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out)* -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - IDRipper -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/IDScoreSwitcher.cwl b/workflow/cwl/IDScoreSwitcher.cwl deleted file mode 100644 index ac72922c7f3..00000000000 --- a/workflow/cwl/IDScoreSwitcher.cwl +++ /dev/null @@ -1,62 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: IDScoreSwitcher -doc: Switches between different scores of peptide or protein hits in identification data -inputs: - in: - doc: Input file - type: File - out: - doc: Output file - type: string - new_score: - doc: Name of the meta value to use as the new score - type: string? - new_score_orientation: - doc: Orientation of the new score (are higher or lower values better?) - type: string? - new_score_type: - doc: "Name to use as the type of the new score (default: same as 'new_score')" - type: string? - old_score: - doc: "Name to use for the meta value storing the old score (default: old score type)" - type: string? - proteins: - doc: Apply to protein scores instead of PSM scores - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - IDScoreSwitcher -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/IDSplitter.cwl b/workflow/cwl/IDSplitter.cwl deleted file mode 100644 index 71935352b71..00000000000 --- a/workflow/cwl/IDSplitter.cwl +++ /dev/null @@ -1,54 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: IDSplitter -doc: Splits protein/peptide identifications off of annotated data files -inputs: - in: - doc: Input file (data annotated with identifications) - type: File - out: - doc: Output file (data without identifications). Either 'out' or 'id_out' are required. They can be used together. - type: string? - id_out: - doc: Output file (identifications). Either 'out' or 'id_out' are required. They can be used together. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File? - outputBinding: - glob: $(inputs.out) - id_out: - type: File? - outputBinding: - glob: $(inputs.id_out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - IDSplitter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/INIUpdater.cwl b/workflow/cwl/INIUpdater.cwl deleted file mode 100644 index c03d77b004e..00000000000 --- a/workflow/cwl/INIUpdater.cwl +++ /dev/null @@ -1,44 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: INIUpdater -doc: Update INI and TOPPAS files to new OpenMS version. -inputs: - in: - doc: INI/TOPPAS files that need updating. - type: File[] - i: - doc: "in-place: Override given INI/TOPPAS files with new content (not compatible with -out)" - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - [] -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - INIUpdater -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/ImageCreator.cwl b/workflow/cwl/ImageCreator.cwl deleted file mode 100644 index 01643bdb446..00000000000 --- a/workflow/cwl/ImageCreator.cwl +++ /dev/null @@ -1,92 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: ImageCreator -doc: Transforms an LC-MS map into an image. -inputs: - in: - doc: "input file " - type: File - in_featureXML: - doc: "input file " - type: File? - out: - doc: output file - type: string - out_type: - doc: The image format. Set this if you want to force a format not reflected by the 'out' filename. - type: string? - rt: - doc: Retention time range to extract - type: string? - mz: - doc: Mass-to-charge range to extract - type: string? - width: - doc: "Number of pixels in m/z dimension.\nIf 0, one pixel per Th." - type: long? - height: - doc: "Number of pixels in RT dimension.\nIf 0, one pixel per spectrum." - type: long? - background_color: - doc: "Background color e.g.: \"#FF0000\" to choose red as background color" - type: string? - feature_color: - doc: "Feature color e.g.: \"#00FF00\" to choose green as feature color" - type: string? - gradient: - doc: "Intensity gradient that defines colors for the range between 0 and 100.\nExample: '0,#FFFFFF;50,#FF0000;100,#000000'" - type: string? - max_intensity: - doc: "Maximum peak intensity used to determine range for colors.\nIf 0, this is determined from the data." - type: double? - log_intensity: - doc: Apply logarithm to intensity values - type: boolean? - transpose: - doc: "Flag to transpose the resampled matrix (RT vs. m/z).\nPer default, dimensions run bottom-up in RT and left-right in m/z." - type: boolean? - precursors: - doc: "Mark locations of MS2 precursors.\n" - type: boolean? - precursor_color: - doc: Color for precursor marks (color code or word, e.g. 'black') (requires 'precursors' flag to be active) - type: string? - precursor_size: - doc: Size of the precursor marks (requires 'precursors' flag to be active) - type: long? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - ImageCreator -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/InternalCalibration.cwl b/workflow/cwl/InternalCalibration.cwl deleted file mode 100644 index aa3cd4ba2b7..00000000000 --- a/workflow/cwl/InternalCalibration.cwl +++ /dev/null @@ -1,134 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: InternalCalibration -doc: Applies an internal mass recalibration. -inputs: - in: - doc: Input peak file - type: File - out: - doc: "Output file " - type: string - rscript_executable: - doc: "Path to the Rscript executable (default: 'Rscript')." - type: File? - ppm_match_tolerance: - doc: Finding calibrants in raw data uses this tolerance (for lock masses and ID's). - type: double? - ms_level: - doc: Target MS levels to apply the transformation onto. Does not affect calibrant collection. - type: long[]? - RT_chunking: - doc: RT window (one-sided, i.e. left->center, or center->right) around an MS scan in which calibrants are collected to build a model. Set to -1 to use ALL calibrants for all scans, i.e. a global model. - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - cal__id_in: - doc: Identifications or features whose peptide ID's serve as calibration masses. - type: File? - cal__lock_in: - doc: "Input file containing reference m/z values (text file with each line as: m/z ms-level charge) which occur in all scans." - type: File? - cal__lock_out: - doc: Optional output file containing peaks from 'in' which were matched to reference m/z values. Useful to see which peaks were used for calibration. - type: string? - cal__lock_fail_out: - doc: Optional output file containing lock masses which were NOT found or accepted(!) in data from 'in'. Useful to see which peaks were used for calibration. - type: string? - cal__lock_require_mono: - doc: Require all lock masses to be monoisotopic, i.e. not the iso1, iso2 etc ('charge' column is used to determine the spacing). Peaks which are not mono-isotopic are not used. - type: boolean? - cal__lock_require_iso: - doc: Require all lock masses to have at least the +1 isotope. Peaks without isotope pattern are not used. - type: boolean? - cal__model_type: - doc: Type of function to be fitted to the calibration points. - type: string? - RANSAC__enabled: - doc: Apply RANSAC to calibration points to remove outliers before fitting a model. - type: boolean? - RANSAC__threshold: - doc: Threshold for accepting inliers (instrument precision (not accuracy!) as ppm^2 distance) - type: double? - RANSAC__pc_inliers: - doc: Minimum percentage (of available data) of inliers (/<-1Da>/<+1Da>/<+2Da>; e.g. '0/0.3/4/0', '0.1/0.3/3/0.2'" - type: string[]? - itraq8plex__channel_113_description: - doc: Description for the content of the 113 channel. - type: string? - itraq8plex__channel_114_description: - doc: Description for the content of the 114 channel. - type: string? - itraq8plex__channel_115_description: - doc: Description for the content of the 115 channel. - type: string? - itraq8plex__channel_116_description: - doc: Description for the content of the 116 channel. - type: string? - itraq8plex__channel_117_description: - doc: Description for the content of the 117 channel. - type: string? - itraq8plex__channel_118_description: - doc: Description for the content of the 118 channel. - type: string? - itraq8plex__channel_119_description: - doc: Description for the content of the 119 channel. - type: string? - itraq8plex__channel_121_description: - doc: Description for the content of the 121 channel. - type: string? - itraq8plex__reference_channel: - doc: Number of the reference channel (113-121). Please note that 120 is not valid. - type: long? - itraq8plex__correction_matrix: - doc: "Correction matrix for isotope distributions (see documentation); use the following format: <-2Da>/<-1Da>/<+1Da>/<+2Da>; e.g. '0/0.3/4/0', '0.1/0.3/3/0.2'" - type: string[]? - quantification__isotope_correction: - doc: Enable isotope correction (highly recommended). Note that you need to provide a correct isotope correction matrix otherwise the tool will fail or produce invalid results. - type: string? - quantification__normalization: - doc: Enable normalization of channel intensities with respect to the reference channel. The normalization is done by using the Median of Ratios (every channel / Reference). Also the ratio of medians (from any channel and reference) is provided as control measure! - type: boolean? - tmt10plex__channel_126_description: - doc: Description for the content of the 126 channel. - type: string? - tmt10plex__channel_127N_description: - doc: Description for the content of the 127N channel. - type: string? - tmt10plex__channel_127C_description: - doc: Description for the content of the 127C channel. - type: string? - tmt10plex__channel_128N_description: - doc: Description for the content of the 128N channel. - type: string? - tmt10plex__channel_128C_description: - doc: Description for the content of the 128C channel. - type: string? - tmt10plex__channel_129N_description: - doc: Description for the content of the 129N channel. - type: string? - tmt10plex__channel_129C_description: - doc: Description for the content of the 129C channel. - type: string? - tmt10plex__channel_130N_description: - doc: Description for the content of the 130N channel. - type: string? - tmt10plex__channel_130C_description: - doc: Description for the content of the 130C channel. - type: string? - tmt10plex__channel_131_description: - doc: Description for the content of the 131 channel. - type: string? - tmt10plex__reference_channel: - doc: The reference channel (126, 127N, 127C, 128N, 128C, 129N, 129C, 130N, 130C, 131). - type: string? - tmt10plex__correction_matrix: - doc: "Correction matrix for isotope distributions (see documentation); use the following format: <-2Da>/<-1Da>/<+1Da>/<+2Da>; e.g. '0/0.3/4/0', '0.1/0.3/3/0.2'" - type: string[]? - tmt11plex__channel_126_description: - doc: Description for the content of the 126 channel. - type: string? - tmt11plex__channel_127N_description: - doc: Description for the content of the 127N channel. - type: string? - tmt11plex__channel_127C_description: - doc: Description for the content of the 127C channel. - type: string? - tmt11plex__channel_128N_description: - doc: Description for the content of the 128N channel. - type: string? - tmt11plex__channel_128C_description: - doc: Description for the content of the 128C channel. - type: string? - tmt11plex__channel_129N_description: - doc: Description for the content of the 129N channel. - type: string? - tmt11plex__channel_129C_description: - doc: Description for the content of the 129C channel. - type: string? - tmt11plex__channel_130N_description: - doc: Description for the content of the 130N channel. - type: string? - tmt11plex__channel_130C_description: - doc: Description for the content of the 130C channel. - type: string? - tmt11plex__channel_131N_description: - doc: Description for the content of the 131N channel. - type: string? - tmt11plex__channel_131C_description: - doc: Description for the content of the 131C channel. - type: string? - tmt11plex__reference_channel: - doc: The reference channel (126, 127N, 127C, 128N, 128C, 129N, 129C, 130N, 130C, 131N, 131C). - type: string? - tmt11plex__correction_matrix: - doc: "Correction matrix for isotope distributions (see documentation); use the following format: <-2Da>/<-1Da>/<+1Da>/<+2Da>; e.g. '0/0.3/4/0', '0.1/0.3/3/0.2'" - type: string[]? - tmt16plex__channel_126_description: - doc: Description for the content of the 126 channel. - type: string? - tmt16plex__channel_127N_description: - doc: Description for the content of the 127N channel. - type: string? - tmt16plex__channel_127C_description: - doc: Description for the content of the 127C channel. - type: string? - tmt16plex__channel_128N_description: - doc: Description for the content of the 128N channel. - type: string? - tmt16plex__channel_128C_description: - doc: Description for the content of the 128C channel. - type: string? - tmt16plex__channel_129N_description: - doc: Description for the content of the 129N channel. - type: string? - tmt16plex__channel_129C_description: - doc: Description for the content of the 129C channel. - type: string? - tmt16plex__channel_130N_description: - doc: Description for the content of the 130N channel. - type: string? - tmt16plex__channel_130C_description: - doc: Description for the content of the 130C channel. - type: string? - tmt16plex__channel_131N_description: - doc: Description for the content of the 131N channel. - type: string? - tmt16plex__channel_131C_description: - doc: Description for the content of the 131C channel. - type: string? - tmt16plex__channel_132N_description: - doc: Description for the content of the 132N channel. - type: string? - tmt16plex__channel_132C_description: - doc: Description for the content of the 132C channel. - type: string? - tmt16plex__channel_133N_description: - doc: Description for the content of the 133N channel. - type: string? - tmt16plex__channel_133C_description: - doc: Description for the content of the 133C channel. - type: string? - tmt16plex__channel_134N_description: - doc: Description for the content of the 134N channel. - type: string? - tmt16plex__reference_channel: - doc: The reference channel (126, 127N, 127C, 128N, 128C, 129N, 129C, 130N, 130C, 131N, 131C, 132N, 132C, 133N, 133C, 134N). - type: string? - tmt16plex__correction_matrix: - doc: "Correction matrix for isotope distributions in percent from the Thermo data sheet (see documentation); Please provide 16 entries (rows), separated by comma, where each entry contains 8 values in the following format: <-2C13>/<-N15-C13>/<-C13>/<-N15>/<+N15>/<+C13>/<+N15+C13>/<+2C13> e.g. one row may look like this: 'NA/0.00 / 0.82/0.65 / NA/8.13 / NA/0.26'. You may use whitespaces at your leisure to ease reading." - type: string[]? - tmt18plex__channel_126_description: - doc: Description for the content of the 126 channel. - type: string? - tmt18plex__channel_127N_description: - doc: Description for the content of the 127N channel. - type: string? - tmt18plex__channel_127C_description: - doc: Description for the content of the 127C channel. - type: string? - tmt18plex__channel_128N_description: - doc: Description for the content of the 128N channel. - type: string? - tmt18plex__channel_128C_description: - doc: Description for the content of the 128C channel. - type: string? - tmt18plex__channel_129N_description: - doc: Description for the content of the 129N channel. - type: string? - tmt18plex__channel_129C_description: - doc: Description for the content of the 129C channel. - type: string? - tmt18plex__channel_130N_description: - doc: Description for the content of the 130N channel. - type: string? - tmt18plex__channel_130C_description: - doc: Description for the content of the 130C channel. - type: string? - tmt18plex__channel_131N_description: - doc: Description for the content of the 131N channel. - type: string? - tmt18plex__channel_131C_description: - doc: Description for the content of the 131C channel. - type: string? - tmt18plex__channel_132N_description: - doc: Description for the content of the 132N channel. - type: string? - tmt18plex__channel_132C_description: - doc: Description for the content of the 132C channel. - type: string? - tmt18plex__channel_133N_description: - doc: Description for the content of the 133N channel. - type: string? - tmt18plex__channel_133C_description: - doc: Description for the content of the 133C channel. - type: string? - tmt18plex__channel_134N_description: - doc: Description for the content of the 134N channel. - type: string? - tmt18plex__channel_134C_description: - doc: Description for the content of the 134C channel. - type: string? - tmt18plex__channel_135N_description: - doc: Description for the content of the 135N channel. - type: string? - tmt18plex__reference_channel: - doc: The reference channel (126, 127N, 127C, 128N, 128C, 129N, 129C, 130N, 130C, 131N, 131C, 132N, 132C, 133N, 133C, 134N, 134C, 135N). - type: string? - tmt18plex__correction_matrix: - doc: "Correction matrix for isotope distributions in percent from the Thermo data sheet (see documentation); Please provide 18 entries (rows), separated by comma, where each entry contains 8 values in the following format: <-2C13>/<-N15-C13>/<-C13>/<-N15>/<+N15>/<+C13>/<+N15+C13>/<+2C13> e.g. one row may look like this: 'NA/0.00 / 0.82/0.65 / NA/8.13 / NA/0.26'. You may use whitespaces at your leisure to ease reading." - type: string[]? - tmt6plex__channel_126_description: - doc: Description for the content of the 126 channel. - type: string? - tmt6plex__channel_127_description: - doc: Description for the content of the 127 channel. - type: string? - tmt6plex__channel_128_description: - doc: Description for the content of the 128 channel. - type: string? - tmt6plex__channel_129_description: - doc: Description for the content of the 129 channel. - type: string? - tmt6plex__channel_130_description: - doc: Description for the content of the 130 channel. - type: string? - tmt6plex__channel_131_description: - doc: Description for the content of the 131 channel. - type: string? - tmt6plex__reference_channel: - doc: Number of the reference channel (126-131). - type: long? - tmt6plex__correction_matrix: - doc: "Correction matrix for isotope distributions (see documentation); use the following format: <-2Da>/<-1Da>/<+1Da>/<+2Da>; e.g. '0/0.3/4/0', '0.1/0.3/3/0.2'" - type: string[]? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - IsobaricAnalyzer -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/JSONExporter.cwl b/workflow/cwl/JSONExporter.cwl deleted file mode 100644 index df79ae976c8..00000000000 --- a/workflow/cwl/JSONExporter.cwl +++ /dev/null @@ -1,47 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: JSONExporter -doc: Exports .oms (SQLite) files in JSON format -inputs: - in: - doc: Input file - type: File - out: - doc: Output file - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - JSONExporter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/LuciphorAdapter.cwl b/workflow/cwl/LuciphorAdapter.cwl deleted file mode 100644 index b51a2804697..00000000000 --- a/workflow/cwl/LuciphorAdapter.cwl +++ /dev/null @@ -1,113 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: LuciphorAdapter -doc: Modification site localisation using LuciPHOr2. -inputs: - in: - doc: Input spectrum file - type: File - id: - doc: Protein/peptide identifications file - type: File - out: - doc: Output file - type: string - executable: - doc: LuciPHOr2 .jar file. Provide a full or relative path, or make sure it can be found in your PATH environment. - type: File - fragment_method: - doc: Fragmentation method - type: string? - fragment_mass_tolerance: - doc: Tolerance of the peaks in the fragment spectrum - type: double? - fragment_error_units: - doc: Unit of fragment mass tolerance - type: string? - min_mz: - doc: Do not consider peaks below this value for matching fragment ions - type: double? - target_modifications: - doc: List the amino acids to be searched for and their mass modifications, specified using UniMod (www.unimod.org) terms, e.g. 'Carbamidomethyl (C)' - type: string[]? - neutral_losses: - doc: "List the types of neutral losses that you want to consider. The residue field is case sensitive. For example: lower case 'sty' implies that the neutral loss can only occur if the specified modification is present. Syntax: NL = - " - type: string[]? - decoy_mass: - doc: How much to add to an amino acid to make it a decoy - type: double? - decoy_neutral_losses: - doc: "For handling the neutral loss from a decoy sequence. The syntax for this is identical to that of the normal neutral losses given above except that the residue is always 'X'. Syntax: DECOY_NL = X - " - type: string[]? - max_charge_state: - doc: Do not consider PSMs with a charge state above this value - type: long? - max_peptide_length: - doc: Restrict scoring to peptides with a length shorter than this value - type: long? - max_num_perm: - doc: Maximum number of permutations a sequence can have - type: long? - modeling_score_threshold: - doc: Minimum score a PSM needs to be considered for modeling - type: double? - scoring_threshold: - doc: PSMs below this value will be discarded - type: double? - min_num_psms_model: - doc: The minimum number of PSMs you need for any charge state in order to build a model for it - type: long? - num_threads: - doc: For multi-threading, 0 = use all CPU found by JAVA - type: long? - run_mode: - doc: "Determines how Luciphor will run: 0 = calculate FLR then rerun scoring without decoys (two iterations), 1 = Report Decoys: calculate FLR but don't rescore PSMs, all decoy hits will be reported" - type: string? - rt_tolerance: - doc: Set the retention time tolerance (for the mapping of identifications to spectra in case multiple search engines were used) - type: double? - java_executable: - doc: The Java executable. Usually Java is on the system PATH. If Java is not found, use this parameter to specify the full path to Java - type: File? - java_memory: - doc: Maximum Java heap size (in MB) - type: long? - java_permgen: - doc: Maximum Java permanent generation space (in MB); only for Java 7 and below - type: long? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - LuciphorAdapter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MRMMapper.cwl b/workflow/cwl/MRMMapper.cwl deleted file mode 100644 index 0078cda4fd8..00000000000 --- a/workflow/cwl/MRMMapper.cwl +++ /dev/null @@ -1,62 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MRMMapper -doc: MRMMapper maps measured chromatograms (mzML) and the transitions used (TraML) -inputs: - in: - doc: Input file containing chromatograms (converted mzXML file) - type: File - tr: - doc: transition file - type: File - out: - doc: Output file containing mapped chromatograms - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__precursor_tolerance: - doc: Precursor tolerance when mapping (in Th) - type: double? - algorithm__product_tolerance: - doc: Product tolerance when mapping (in Th) - type: double? - algorithm__map_multiple_assays: - doc: Allow to map multiple assays to chromatograms and duplicate these chromatograms in the output. - type: boolean? - algorithm__error_on_unmapped: - doc: Treat remaining, unmapped chromatograms as an error - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MRMMapper -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MRMPairFinder.cwl b/workflow/cwl/MRMPairFinder.cwl deleted file mode 100644 index 4ba5e692253..00000000000 --- a/workflow/cwl/MRMPairFinder.cwl +++ /dev/null @@ -1,66 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MRMPairFinder -doc: Util which can be used to evaluate labeled pair ratios on MRM features. -inputs: - in: - doc: Input featureXML file containing the features of the MRM experiment spectra. - type: File - pair_in: - doc: "Pair-file in the format: prec-m/z-light prec-m/z-heavy frag-m/z-light frag-m/z-heavy rt" - type: File - out: - doc: Output consensusXML file were the pairs of the features will be written to. - type: string - feature_out: - doc: Output featureXML file, only written if given, skipped otherwise. - type: string? - mass_tolerance: - doc: Precursor mass tolerance which is used for the pair finding and the matching of the given pair m/z values to the features. - type: double? - RT_tolerance: - doc: Maximal deviation in RT dimension in seconds a feature can have when comparing to the RT values given in the pair file. - type: double? - RT_pair_tolerance: - doc: Maximal deviation in RT dimension in seconds the two partners of a pair is allowed to have. - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - feature_out: - type: File? - outputBinding: - glob: $(inputs.feature_out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MRMPairFinder -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MRMTransitionGroupPicker.cwl b/workflow/cwl/MRMTransitionGroupPicker.cwl deleted file mode 100644 index 8319930bed7..00000000000 --- a/workflow/cwl/MRMTransitionGroupPicker.cwl +++ /dev/null @@ -1,137 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MRMTransitionGroupPicker -doc: Picks peaks in SRM/MRM chromatograms. -inputs: - in: - doc: Input file - type: File - tr: - doc: transition file ('TraML' or 'csv') - type: File - out: - doc: output file - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__stop_after_feature: - doc: Stop finding after feature (ordered by intensity; -1 means do not stop). - type: long? - algorithm__stop_after_intensity_ratio: - doc: Stop after reaching intensity ratio - type: double? - algorithm__min_peak_width: - doc: Minimal peak width (s), discard all peaks below this value (-1 means no action). - type: double? - algorithm__peak_integration: - doc: Calculate the peak area and height either the smoothed or the raw chromatogram data. - type: string? - algorithm__background_subtraction: - doc: "Remove background from peak signal using estimated noise levels. The 'original' method is only provided for historical purposes, please use the 'exact' method and set parameters using the PeakIntegrator: settings. The same original or smoothed chromatogram specified by peak_integration will be used for background estimation." - type: string? - algorithm__recalculate_peaks: - doc: Tries to get better peak picking by looking at peak consistency of all picked peaks. Tries to use the consensus (median) peak border if the variation within the picked peaks is too large. - type: boolean? - algorithm__use_precursors: - doc: Use precursor chromatogram for peak picking (note that this may lead to precursor signal driving the peak picking) - type: boolean? - algorithm__use_consensus: - doc: Use consensus peak boundaries when computing transition group picking (if false, compute independent peak boundaries for each transition) - type: string? - algorithm__recalculate_peaks_max_z: - doc: Determines the maximal Z-Score (difference measured in standard deviations) that is considered too large for peak boundaries. If the Z-Score is above this value, the median is used for peak boundaries (default value 1.0). - type: double? - algorithm__minimal_quality: - doc: Only if compute_peak_quality is set, this parameter will not consider peaks below this quality threshold - type: double? - algorithm__resample_boundary: - doc: For computing peak quality, how many extra seconds should be sample left and right of the actual peak - type: double? - algorithm__compute_peak_quality: - doc: Tries to compute a quality value for each peakgroup and detect outlier transitions. The resulting score is centered around zero and values above 0 are generally good and below -1 or -2 are usually bad. - type: boolean? - algorithm__compute_peak_shape_metrics: - doc: Calculates various peak shape metrics (e.g., tailing) that can be used for downstream QC/QA. - type: boolean? - algorithm__compute_total_mi: - doc: Compute mutual information metrics for individual transitions that can be used for OpenSWATH/IPF scoring. - type: boolean? - algorithm__boundary_selection_method: - doc: Method to use when selecting the best boundaries for peaks. - type: string? - algorithm__PeakPickerChromatogram__sgolay_frame_length: - doc: "The number of subsequent data points used for smoothing.\nThis number has to be uneven. If it is not, 1 will be added." - type: long? - algorithm__PeakPickerChromatogram__sgolay_polynomial_order: - doc: Order of the polynomial that is fitted. - type: long? - algorithm__PeakPickerChromatogram__gauss_width: - doc: Gaussian width in seconds, estimated peak size. - type: double? - algorithm__PeakPickerChromatogram__use_gauss: - doc: Use Gaussian filter for smoothing (alternative is Savitzky-Golay filter) - type: string? - algorithm__PeakPickerChromatogram__peak_width: - doc: Force a certain minimal peak_width on the data (e.g. extend the peak at least by this amount on both sides) in seconds. -1 turns this feature off. - type: double? - algorithm__PeakPickerChromatogram__signal_to_noise: - doc: Signal-to-noise threshold at which a peak will not be extended any more. Note that setting this too high (e.g. 1.0) can lead to peaks whose flanks are not fully captured. - type: double? - algorithm__PeakPickerChromatogram__sn_win_len: - doc: Signal to noise window length. - type: double? - algorithm__PeakPickerChromatogram__sn_bin_count: - doc: Signal to noise bin count. - type: long? - algorithm__PeakPickerChromatogram__write_sn_log_messages: - doc: Write out log messages of the signal-to-noise estimator in case of sparse windows or median in rightmost histogram bin - type: boolean? - algorithm__PeakPickerChromatogram__remove_overlapping_peaks: - doc: Try to remove overlapping peaks during peak picking - type: string? - algorithm__PeakPickerChromatogram__method: - doc: Which method to choose for chromatographic peak-picking (OpenSWATH legacy on raw data, corrected picking on smoothed chromatogram or Crawdad on smoothed chromatogram). - type: string? - algorithm__PeakIntegrator__integration_type: - doc: The integration technique to use in integratePeak() and estimateBackground() which uses either the summed intensity, integration by Simpson's rule or trapezoidal integration. - type: string? - algorithm__PeakIntegrator__baseline_type: - doc: The baseline type to use in estimateBackground() based on the peak boundaries. A rectangular baseline shape is computed based either on the minimal intensity of the peak boundaries, the maximum intensity or the average intensity (base_to_base). - type: string? - algorithm__PeakIntegrator__fit_EMG: - doc: Fit the chromatogram/spectrum to the EMG peak model. - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MRMTransitionGroupPicker -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MSFraggerAdapter.cwl b/workflow/cwl/MSFraggerAdapter.cwl deleted file mode 100644 index 78ef71e126b..00000000000 --- a/workflow/cwl/MSFraggerAdapter.cwl +++ /dev/null @@ -1,315 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MSFraggerAdapter -doc: "Peptide Identification with MSFragger.\nImportant note:\nThe Regents of the University of Michigan (\"Michigan\") grants us permission to redistribute \nthe MS Fragger application developed by Michigan within the OpenMS Pipeline and make available \nfor use on related service offerings supported by the University of Tubingen and the Center for\nIntegrative Bioinformatics. \nPer the license agreement the use of the pipeline and associated materials is for academic \nresearch, non-commercial or educational purposes. Any commercial use inquiries \nmust be directed to the University of Michigan Technology Transfer Office at \ntechtransfer@umich.edu. All right title and interest in MS Fragger shall remain with the \nUniversity of Michigan.\n\nFor details, please see the supplied license file or \nhttps://raw.githubusercontent.com/OpenMS/THIRDPARTY/master/All/MSFragger/License.txt \n" -inputs: - license: - doc: Set to yes, if you have read and agreed to the MSFragger license terms. - type: string - java_executable: - doc: The Java executable. Usually Java is on the system PATH. If Java is not found, use this parameter to specify the full path to Java - type: File? - java_heapmemory: - doc: Maximum Java heap size (in MB) - type: long? - executable: - doc: Path to the MSFragger executable to use; may be empty if the executable is globally available. - type: File - in: - doc: Input File with specta for MSFragger - type: File - out: - doc: MSFragger output file - type: string - opt_out: - doc: MSFragger optional output file - type: string? - database: - doc: Protein FASTA database file path - type: File - reindex: - doc: Recalculate peptide to protein association using OpenMS. Annotates target-decoy information. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - tolerance__precursor_mass_tolerance_lower: - doc: Lower precursor mass tolerance - type: double? - tolerance__precursor_mass_tolerance_upper: - doc: Upper precursor mass tolerance - type: double? - tolerance__precursor_mass_unit: - doc: Unit of precursor mass tolerance - type: string? - tolerance__precursor_true_tolerance: - doc: True precursor mass tolerance (window is +/- this value). Used for tie breaker of results (in spectrally ambiguous cases) and zero bin boosting in open searches (0 disables these features). This option is STRONGLY recommended for open searches. - type: double? - tolerance__precursor_true_unit: - doc: Unit of precursor true tolerance - type: string? - tolerance__fragment_mass_tolerance: - doc: Fragment mass tolerance (window is +/- this value) - type: double? - tolerance__fragment_mass_unit: - doc: Unit of fragment mass tolerance - type: string? - tolerance__isotope_error: - doc: Isotope correction for MS/MS events triggered on isotopic peaks. Should be set to 0 (disabled) for open search or 0/1/2 for correction of narrow window searches. Shifts the precursor mass window to multiples of this value multiplied by the mass of C13-C12. - type: string? - digest__search_enzyme_name: - doc: Name of the enzyme to be written to the pepXML file - type: string? - digest__search_enzyme_cutafter: - doc: Residues after which the enzyme cuts (specified as a string of amino acids) - type: string? - digest__search_enzyme_nocutbefore: - doc: Residues that the enzyme will not cut before - type: string? - digest__num_enzyme_termini: - doc: Number of enzyme termini (non-enzymatic (0), semi (1), fully (2) - type: string? - digest__allowed_missed_cleavage: - doc: Allowed number of missed cleavages - type: string? - digest__min_length: - doc: Minimum length of peptides to be generated during in-silico digestion - type: long? - digest__max_length: - doc: Maximum length of peptides to be generated during in-silico digestion - type: long? - digest__mass_range_min: - doc: Min mass of peptides to be generated (Da) - type: double? - digest__mass_range_max: - doc: Max mass of peptides to be generated (Da) - type: double? - varmod__clip_nterm_m: - doc: Specifies the trimming of a protein N-terminal methionine as a variable modification - type: boolean? - varmod__masses: - doc: Masses for variable modifications - type: double[]? - varmod__syntaxes: - doc: Syntax Strings for variable modifications - type: string[]? - varmod__unimod: - doc: Variable modifications in unimod syntax, is added to mass+syntax varmod list - type: string[]? - varmod__enable_common: - doc: Enable common variable modifications (15.9949 M and 42.0106 [^) - type: boolean? - varmod__not_allow_multiple_variable_mods_on_residue: - doc: Do not allow any one amino acid to be modified by multiple variable modifications - type: boolean? - varmod__max_variable_mods_per_peptide: - doc: Maximum total number of variable modifications per peptide - type: string? - varmod__max_variable_mods_combinations: - doc: Maximum allowed number of modified variably modified peptides from each peptide sequence, (maximum of 65534). If a greater number than the maximum is generated, only the unmodified peptide is considered - type: long? - spectrum__minimum_peaks: - doc: Minimum number of peaks in experimental spectrum for matching - type: long? - spectrum__use_topn_peaks: - doc: Pre-process experimental spectrum to only use top N peaks - type: long? - spectrum__minimum_ratio: - doc: Filters out all peaks in experimental spectrum less intense than this multiple of the base peak intensity - type: double? - spectrum__clear_mz_range_min: - doc: Removes peaks in this m/z range prior to matching (minimum value). Useful for iTRAQ/TMT experiments (i.e. 0.0 150.0) - type: double? - spectrum__clear_mz_range_max: - doc: Removes peaks in this m/z range prior to matching (maximum value). Useful for iTRAQ/TMT experiments (i.e. 0.0 150.0) - type: double? - spectrum__max_fragment_charge: - doc: Maximum charge state for theoretical fragments to match - type: string? - spectrum__override_charge: - doc: "Ignores precursor charge and uses charge state specified in precursor_charge range (parameters: spectrum:precursor_charge_min and spectrum:precursor_charge_max)" - type: boolean? - spectrum__precursor_charge_min: - doc: Min charge of precursor charge range to consider. If specified, also spectrum:override_charge must be set) - type: long? - spectrum__precursor_charge_max: - doc: Max charge of precursor charge range to consider. If specified, also spectrum:override_charge must be set) - type: long? - search__track_zero_topn: - doc: Track top N unmodified peptide results separately from main results internally for boosting features. Should be set to a number greater than search:output_report_topN if zero bin boosting is desired - type: long? - search__zero_bin_accept_expect: - doc: Ranks a zero-bin hit above all non-zero-bin hit if it has expectation less than this value - type: double? - search__zero_bin_mult_expect: - doc: Multiplies expect value of PSMs in the zero-bin during results ordering (set to less than 1 for boosting) - type: double? - search__add_topn_complementary: - doc: Inserts complementary ions corresponding to the top N most intense fragments in each experimental spectrum. Useful for recovery of modified peptides near C-terminus in open search. 0 disables this option - type: long? - search__min_fragments_modeling: - doc: Minimum number of matched peaks in PSM for inclusion in statistical modeling - type: long? - search__min_matched_fragments: - doc: Minimum number of matched peaks for PSM to be reported. MSFragger recommends a minimum of 4 for narrow window searching and 6 for open searches - type: long? - search__output_report_topn: - doc: Reports top N PSMs per input spectrum - type: long? - search__output_max_expect: - doc: Suppresses reporting of PSM if top hit has expectation greater than this threshold - type: double? - search__localize_delta_mass: - doc: Include fragment ions mass-shifted by unknown modifications (recommended for open and mass offset searches) (0 for OFF, 1 for ON) - type: long? - statmod__add_cterm_peptide: - doc: Statically add mass in Da to C-terminal of peptide - type: double? - statmod__add_nterm_peptide: - doc: Statically add mass in Da to N-terminal of peptide - type: double? - statmod__add_cterm_protein: - doc: Statically add mass in Da to C-terminal of protein - type: double? - statmod__add_nterm_protein: - doc: Statically add mass in Da to N-terminal of protein - type: double? - statmod__add_G_glycine: - doc: Statically add mass to glycine - type: double? - statmod__add_A_alanine: - doc: Statically add mass to alanine - type: double? - statmod__add_S_serine: - doc: Statically add mass to serine - type: double? - statmod__add_P_proline: - doc: Statically add mass to proline - type: double? - statmod__add_V_valine: - doc: Statically add mass to valine - type: double? - statmod__add_T_threonine: - doc: Statically add mass to threonine - type: double? - statmod__add_C_cysteine: - doc: Statically add mass to cysteine - type: double? - statmod__add_L_leucine: - doc: Statically add mass to leucine - type: double? - statmod__add_I_isoleucine: - doc: Statically add mass to isoleucine - type: double? - statmod__add_N_asparagine: - doc: Statically add mass to asparagine - type: double? - statmod__add_D_aspartic_acid: - doc: Statically add mass to aspartic_acid - type: double? - statmod__add_Q_glutamine: - doc: Statically add mass to glutamine - type: double? - statmod__add_K_lysine: - doc: Statically add mass to lysine - type: double? - statmod__add_E_glutamic_acid: - doc: Statically add mass to glutamic_acid - type: double? - statmod__add_M_methionine: - doc: Statically add mass to methionine - type: double? - statmod__add_H_histidine: - doc: Statically add mass to histidine - type: double? - statmod__add_F_phenylalanine: - doc: Statically add mass to phenylalanine - type: double? - statmod__add_R_arginine: - doc: Statically add mass to arginine - type: double? - statmod__add_Y_tyrosine: - doc: Statically add mass to tyrosine - type: double? - statmod__add_W_tryptophan: - doc: Statically add mass to tryptophan - type: double? - statmod__unimod: - doc: Fixed modifications in unimod syntax if specific mass is unknown, e.g. Carbamidomethylation (C). When multiple different masses are given for one aminoacid this parameter (unimod) will have priority. - type: string[]? - PeptideIndexing__decoy_string: - doc: String that was appended (or prefixed - see 'decoy_string_position' flag below) to the accessions in the protein database to indicate decoy proteins. If empty (default), it's determined automatically (checking for common terms, both as prefix and suffix). - type: string? - PeptideIndexing__decoy_string_position: - doc: Is the 'decoy_string' prepended (prefix) or appended (suffix) to the protein accession? (ignored if decoy_string is empty) - type: string? - PeptideIndexing__missing_decoy_action: - doc: "Action to take if NO peptide was assigned to a decoy protein (which indicates wrong database or decoy string): 'error' (exit with error, no output), 'warn' (exit with success, warning message), 'silent' (no action is taken, not even a warning)" - type: string? - PeptideIndexing__write_protein_sequence: - doc: If set, the protein sequences are stored as well. - type: boolean? - PeptideIndexing__write_protein_description: - doc: If set, the protein description is stored as well. - type: boolean? - PeptideIndexing__keep_unreferenced_proteins: - doc: If set, protein hits which are not referenced by any peptide are kept. - type: boolean? - PeptideIndexing__unmatched_action: - doc: "If peptide sequences cannot be matched to any protein: 1) raise an error; 2) warn (unmatched PepHits will miss target/decoy annotation with downstream problems); 3) remove the hit." - type: string? - PeptideIndexing__aaa_max: - doc: Maximal number of ambiguous amino acids (AAAs) allowed when matching to a protein database with AAAs. AAAs are 'B', 'J', 'Z' and 'X'. - type: long? - PeptideIndexing__mismatches_max: - doc: Maximal number of mismatched (mm) amino acids allowed when matching to a protein database. The required runtime is exponential in the number of mm's; apply with care. MM's are allowed in addition to AAA's. - type: long? - PeptideIndexing__IL_equivalent: - doc: Treat the isobaric amino acids isoleucine ('I') and leucine ('L') as equivalent (indistinguishable). Also occurrences of 'J' will be treated as 'I' thus avoiding ambiguous matching. - type: boolean? - PeptideIndexing__allow_nterm_protein_cleavage: - doc: Allow the protein N-terminus amino acid to clip. - type: string? - PeptideIndexing__enzyme__name: - doc: "Enzyme which determines valid cleavage sites - e.g. trypsin cleaves after lysine (K) or arginine (R), but not before proline (P). Default: deduce from input" - type: string? - PeptideIndexing__enzyme__specificity: - doc: "Specificity of the enzyme. Default: deduce from input.\n 'full': both internal cleavage sites must match.\n 'semi': one of two internal cleavage sites must match.\n 'none': allow all peptide hits no matter their context (enzyme is irrelevant)." - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - opt_out: - type: File? - outputBinding: - glob: $(inputs.opt_out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MSFraggerAdapter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MSGFPlusAdapter.cwl b/workflow/cwl/MSGFPlusAdapter.cwl deleted file mode 100644 index 61742a71260..00000000000 --- a/workflow/cwl/MSGFPlusAdapter.cwl +++ /dev/null @@ -1,174 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MSGFPlusAdapter -doc: MS/MS database search using MS-GF+. -inputs: - in: - doc: Input file (MS-GF+ parameter '-s') - type: File - out: - doc: Output file - type: string? - mzid_out: - doc: "Alternative output file (MS-GF+ parameter '-o')\nEither 'out' or 'mzid_out' are required. They can be used together." - type: string? - executable: - doc: The MSGFPlus Java archive file. Provide a full or relative path, or make sure it can be found in your PATH environment. - type: File - database: - doc: Protein sequence database (FASTA file; MS-GF+ parameter '-d'). Non-existing relative filenames are looked up via 'OpenMS.ini:id_db_dir'. - type: File - precursor_mass_tolerance: - doc: Precursor monoisotopic mass tolerance (MS-GF+ parameter '-t') - type: double? - precursor_error_units: - doc: Unit of precursor mass tolerance (MS-GF+ parameter '-t') - type: string? - isotope_error_range: - doc: Range of allowed isotope peak errors (MS-GF+ parameter '-ti'). Takes into account the error introduced by choosing a non-monoisotopic peak for fragmentation. Combined with 'precursor_mass_tolerance'/'precursor_error_units', this determines the actual precursor mass tolerance. E.g. for experimental mass 'exp' and calculated mass 'calc', '-precursor_mass_tolerance 20 -precursor_error_units ppm -isotope_error_range -1,2' tests '|exp - calc - n * 1.00335 Da| < 20 ppm' for n = -1, 0, 1, 2. - type: string? - fragment_method: - doc: Fragmentation method ('from_spectrum' relies on spectrum meta data and uses CID as fallback option; MS-GF+ parameter '-m') - type: string? - instrument: - doc: Instrument that generated the data ('low_res'/'high_res' refer to LCQ and LTQ instruments; MS-GF+ parameter '-inst') - type: string? - enzyme: - doc: "Enzyme used for digestion, or type of cleavage. Note: MS-GF+ does not support blocking rules. (MS-GF+ parameter '-e')" - type: string? - protocol: - doc: Labeling or enrichment protocol used, if any (MS-GF+ parameter '-p') - type: string? - tryptic: - doc: Level of cleavage specificity required (MS-GF+ parameter '-ntt') - type: string? - min_precursor_charge: - doc: Minimum precursor ion charge (only used for spectra without charge information; MS-GF+ parameter '-minCharge') - type: long? - max_precursor_charge: - doc: Maximum precursor ion charge (only used for spectra without charge information; MS-GF+ parameter '-maxCharge') - type: long? - min_peptide_length: - doc: Minimum peptide length to consider (MS-GF+ parameter '-minLength') - type: long? - max_peptide_length: - doc: Maximum peptide length to consider (MS-GF+ parameter '-maxLength') - type: long? - matches_per_spec: - doc: Number of matches per spectrum to be reported (MS-GF+ parameter '-n') - type: long? - add_features: - doc: Output additional features (MS-GF+ parameter '-addFeatures'). This is required by Percolator and hence by default enabled. - type: string? - max_mods: - doc: Maximum number of modifications per peptide. If this value is large, the search may take very long. - type: long? - max_missed_cleavages: - doc: "Maximum number of missed cleavages allowed for a peptide to be considered for scoring. (default: -1 meaning unlimited)" - type: long? - tasks: - doc: "(Override the number of tasks to use on the threads; Default: (internally calculated based on inputs))\n More tasks than threads will reduce the memory requirements of the search, but will be slower (how much depends on the inputs).\n 1 <= tasks <= numThreads: will create one task per thread, which is the original behavior.\n tasks = 0: use default calculation - minimum of: (threads*3) and (numSpectra/250).\n tasks < 0: multiply number of threads by abs(tasks) to determine number of tasks (i.e., -2 means \"2 * numThreads\" tasks).\n One task per thread will use the most memory, but will usually finish the fastest.\n 2-3 tasks per thread will use comparably less memory, but may cause the search to take 1.5 to 2 times as long." - type: long? - fixed_modifications: - doc: Fixed modifications, specified using Unimod (www.unimod.org) terms, e.g. 'Carbamidomethyl (C)' or 'Oxidation (M)' - type: string[]? - variable_modifications: - doc: Variable modifications, specified using Unimod (www.unimod.org) terms, e.g. 'Carbamidomethyl (C)' or 'Oxidation (M)' - type: string[]? - legacy_conversion: - doc: Use the indirect conversion of MS-GF+ results to idXML via export to TSV. Try this only if the default conversion takes too long or uses too much memory. - type: boolean? - conf: - doc: Optional MSGF+ configuration file (passed as -conf to MSGF+). See documentation for examples. Parameters of the adapter take precedence. Use conf file only for settings not available here (for example, any fixed/var modifications, in the conf file will be ignored, since they are provided via -mod flag) - type: File? - java_executable: - doc: The Java executable. Usually Java is on the system PATH. If Java is not found, use this parameter to specify the full path to Java - type: File? - java_memory: - doc: Maximum Java heap size (in MB) - type: long? - java_permgen: - doc: Maximum Java permanent generation space (in MB); only for Java 7 and below - type: long? - reindex: - doc: Recalculate peptide to protein association using OpenMS. Annotates target-decoy information. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - PeptideIndexing__decoy_string: - doc: String that was appended (or prefixed - see 'decoy_string_position' flag below) to the accessions in the protein database to indicate decoy proteins. If empty (default), it's determined automatically (checking for common terms, both as prefix and suffix). - type: string? - PeptideIndexing__decoy_string_position: - doc: Is the 'decoy_string' prepended (prefix) or appended (suffix) to the protein accession? (ignored if decoy_string is empty) - type: string? - PeptideIndexing__missing_decoy_action: - doc: "Action to take if NO peptide was assigned to a decoy protein (which indicates wrong database or decoy string): 'error' (exit with error, no output), 'warn' (exit with success, warning message), 'silent' (no action is taken, not even a warning)" - type: string? - PeptideIndexing__write_protein_sequence: - doc: If set, the protein sequences are stored as well. - type: boolean? - PeptideIndexing__write_protein_description: - doc: If set, the protein description is stored as well. - type: boolean? - PeptideIndexing__keep_unreferenced_proteins: - doc: If set, protein hits which are not referenced by any peptide are kept. - type: boolean? - PeptideIndexing__unmatched_action: - doc: "If peptide sequences cannot be matched to any protein: 1) raise an error; 2) warn (unmatched PepHits will miss target/decoy annotation with downstream problems); 3) remove the hit." - type: string? - PeptideIndexing__aaa_max: - doc: Maximal number of ambiguous amino acids (AAAs) allowed when matching to a protein database with AAAs. AAAs are 'B', 'J', 'Z' and 'X'. - type: long? - PeptideIndexing__mismatches_max: - doc: Maximal number of mismatched (mm) amino acids allowed when matching to a protein database. The required runtime is exponential in the number of mm's; apply with care. MM's are allowed in addition to AAA's. - type: long? - PeptideIndexing__IL_equivalent: - doc: Treat the isobaric amino acids isoleucine ('I') and leucine ('L') as equivalent (indistinguishable). Also occurrences of 'J' will be treated as 'I' thus avoiding ambiguous matching. - type: boolean? - PeptideIndexing__allow_nterm_protein_cleavage: - doc: Allow the protein N-terminus amino acid to clip. - type: string? - PeptideIndexing__enzyme__name: - doc: "Enzyme which determines valid cleavage sites - e.g. trypsin cleaves after lysine (K) or arginine (R), but not before proline (P). Default: deduce from input" - type: string? - PeptideIndexing__enzyme__specificity: - doc: "Specificity of the enzyme. Default: deduce from input.\n 'full': both internal cleavage sites must match.\n 'semi': one of two internal cleavage sites must match.\n 'none': allow all peptide hits no matter their context (enzyme is irrelevant)." - type: string? -outputs: - out: - type: File? - outputBinding: - glob: $(inputs.out) - mzid_out: - type: File? - outputBinding: - glob: $(inputs.mzid_out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MSGFPlusAdapter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MSstatsConverter.cwl b/workflow/cwl/MSstatsConverter.cwl deleted file mode 100644 index 6902e1b7d07..00000000000 --- a/workflow/cwl/MSstatsConverter.cwl +++ /dev/null @@ -1,71 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MSstatsConverter -doc: Converter to input for MSstats -inputs: - in: - doc: Input consensusXML with peptide intensities - type: File - in_design: - doc: Experimental Design file - type: File - method: - doc: Method used in the experiment(label free [LFQ], isobaric labeling [ISO])) - type: string? - msstats_bioreplicate: - doc: Which column in the condition table should be used for MSstats 'BioReplicate' - type: string? - msstats_condition: - doc: Which column in the condition table should be used for MSstats 'Condition' - type: string? - msstats_mixture: - doc: Which column in the condition table should be used for MSstats 'Mixture' - type: string? - reannotate_filenames: - doc: Overwrite MS file names in consensusXML - type: File[]? - labeled_reference_peptides: - doc: If set, IsotopeLabelType is 'H', else 'L' - type: boolean? - retention_time_summarization_method: - doc: How indistinguishable peptidoforms at different retention times should be treated. This is usually necessary for LFQ experiments and therefore defaults to 'max'. In case of TMT/iTRAQ, MSstatsTMT does the aggregation itself later and the parameter always resets to manual (i.e. is unused). - type: string? - out: - doc: Input CSV file for MSstats. - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MSstatsConverter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MaRaClusterAdapter.cwl b/workflow/cwl/MaRaClusterAdapter.cwl deleted file mode 100644 index bbed54e29df..00000000000 --- a/workflow/cwl/MaRaClusterAdapter.cwl +++ /dev/null @@ -1,78 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MaRaClusterAdapter -doc: Facilitate input to MaRaCluster and reintegrate. -inputs: - in: - doc: Input file(s) - type: File[] - id_in: - doc: Optional idXML Input file(s) in the same order as mzML files - for Maracluster Cluster annotation - type: File[]? - out: - doc: Output file in idXML format - type: string? - consensus_out: - doc: Consensus spectra in mzML format - type: string? - output_directory: - doc: Output directory for MaRaCluster original consensus output - type: string? - pcut: - doc: "log(p-value) cutoff, has to be < 0.0. Default: -10.0." - type: double? - min_cluster_size: - doc: minimum number of spectra in a cluster for consensus spectra - type: long? - maracluster_executable: - doc: The maracluster executable. Provide a full or relative path, or make sure it can be found in your PATH environment. - type: File - verbose: - doc: "Set verbosity of output: 0=no processing info, 5=all." - type: long? - precursor_tolerance: - doc: Precursor monoisotopic mass tolerance - type: double? - precursor_tolerance_units: - doc: tolerance_mass_units 0=ppm, 1=Da - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File? - outputBinding: - glob: $(inputs.out) - consensus_out: - type: File? - outputBinding: - glob: $(inputs.consensus_out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MaRaClusterAdapter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MapAlignerIdentification.cwl b/workflow/cwl/MapAlignerIdentification.cwl deleted file mode 100644 index b4f31005baf..00000000000 --- a/workflow/cwl/MapAlignerIdentification.cwl +++ /dev/null @@ -1,134 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MapAlignerIdentification -doc: Corrects retention time distortions between maps based on common peptide identifications. -inputs: - in: - doc: Input files to align (all must have the same file type) - type: File[] - design: - doc: Input file containing the experimental design - type: File? - store_original_rt: - doc: Store the original retention times (before transformation) as meta data in the output? - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - reference__file: - doc: File to use as reference - type: File? - reference__index: - doc: "Use one of the input files as reference ('1' for the first file, etc.).\nIf '0', no explicit reference is set - the algorithm will select a reference." - type: long? - algorithm__score_type: - doc: Name of the score type to use for ranking and filtering (.oms input only). If left empty, a score type is picked automatically. - type: string? - algorithm__score_cutoff: - doc: Use only IDs above a score cut-off (parameter 'min_score') for alignment? - type: boolean? - algorithm__min_score: - doc: "If 'score_cutoff' is 'true': Minimum score for an ID to be considered.\nUnless you have very few runs or identifications, increase this value to focus on more informative peptides." - type: double? - algorithm__min_run_occur: - doc: "Minimum number of runs (incl. reference, if any) in which a peptide must occur to be used for the alignment.\nUnless you have very few runs or identifications, increase this value to focus on more informative peptides." - type: long? - algorithm__max_rt_shift: - doc: "Maximum realistic RT difference for a peptide (median per run vs. reference). Peptides with higher shifts (outliers) are not used to compute the alignment.\nIf 0, no limit (disable filter); if > 1, the final value in seconds; if <= 1, taken as a fraction of the range of the reference RT scale." - type: double? - algorithm__use_unassigned_peptides: - doc: Should unassigned peptide identifications be used when computing an alignment of feature or consensus maps? If 'false', only peptide IDs assigned to features will be used. - type: string? - algorithm__use_feature_rt: - doc: "When aligning feature or consensus maps, don't use the retention time of a peptide identification directly; instead, use the retention time of the centroid of the feature (apex of the elution profile) that the peptide was matched to. If different identifications are matched to one feature, only the peptide closest to the centroid in RT is used.\nPrecludes 'use_unassigned_peptides'." - type: boolean? - algorithm__use_adducts: - doc: If IDs contain adducts, treat differently adducted variants of the same molecule as different. - type: string? - model__type: - doc: Type of model - type: string? - model__linear__symmetric_regression: - doc: Perform linear regression on 'y - x' vs. 'y + x', instead of on 'y' vs. 'x'. - type: boolean? - model__linear__x_weight: - doc: Weight x values - type: string? - model__linear__y_weight: - doc: Weight y values - type: string? - model__linear__x_datum_min: - doc: Minimum x value - type: double? - model__linear__x_datum_max: - doc: Maximum x value - type: double? - model__linear__y_datum_min: - doc: Minimum y value - type: double? - model__linear__y_datum_max: - doc: Maximum y value - type: double? - model__b_spline__wavelength: - doc: Determines the amount of smoothing by setting the number of nodes for the B-spline. The number is chosen so that the spline approximates a low-pass filter with this cutoff wavelength. The wavelength is given in the same units as the data; a higher value means more smoothing. '0' sets the number of nodes to twice the number of input points. - type: double? - model__b_spline__num_nodes: - doc: Number of nodes for B-spline fitting. Overrides 'wavelength' if set (to two or greater). A lower value means more smoothing. - type: long? - model__b_spline__extrapolate: - doc: "Method to use for extrapolation beyond the original data range. 'linear': Linear extrapolation using the slope of the B-spline at the corresponding endpoint. 'b_spline': Use the B-spline (as for interpolation). 'constant': Use the constant value of the B-spline at the corresponding endpoint. 'global_linear': Use a linear fit through the data (which will most probably introduce discontinuities at the ends of the data range)." - type: string? - model__b_spline__boundary_condition: - doc: "Boundary condition at B-spline endpoints: 0 (value zero), 1 (first derivative zero) or 2 (second derivative zero)" - type: long? - model__lowess__span: - doc: Fraction of datapoints (f) to use for each local regression (determines the amount of smoothing). Choosing this parameter in the range .2 to .8 usually results in a good fit. - type: double? - model__lowess__num_iterations: - doc: Number of robustifying iterations for lowess fitting. - type: long? - model__lowess__delta: - doc: Nonnegative parameter which may be used to save computations (recommended value is 0.01 of the range of the input, e.g. for data ranging from 1000 seconds to 2000 seconds, it could be set to 10). Setting a negative value will automatically do this. - type: double? - model__lowess__interpolation_type: - doc: "Method to use for interpolation between datapoints computed by lowess. 'linear': Linear interpolation. 'cspline': Use the cubic spline for interpolation. 'akima': Use an akima spline for interpolation" - type: string? - model__lowess__extrapolation_type: - doc: "Method to use for extrapolation outside the data range. 'two-point-linear': Uses a line through the first and last point to extrapolate. 'four-point-linear': Uses a line through the first and second point to extrapolate in front and and a line through the last and second-to-last point in the end. 'global-linear': Uses a linear regression to fit a line through all data points and use it for interpolation." - type: string? - model__interpolated__interpolation_type: - doc: Type of interpolation to apply. - type: string? - model__interpolated__extrapolation_type: - doc: "Type of extrapolation to apply: two-point-linear: use the first and last data point to build a single linear model, four-point-linear: build two linear models on both ends using the first two / last two points, global-linear: use all points to build a single linear model. Note that global-linear may not be continuous at the border." - type: string? -outputs: - [] -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MapAlignerIdentification -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MapAlignerPoseClustering.cwl b/workflow/cwl/MapAlignerPoseClustering.cwl deleted file mode 100644 index 5db85aac34f..00000000000 --- a/workflow/cwl/MapAlignerPoseClustering.cwl +++ /dev/null @@ -1,119 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MapAlignerPoseClustering -doc: Corrects retention time distortions between maps using a pose clustering approach. -inputs: - in: - doc: Input files to align (all must have the same file type) - type: File[] - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - reference__file: - doc: File to use as reference (same file format as input files required) - type: File? - reference__index: - doc: "Use one of the input files as reference ('1' for the first file, etc.).\nIf '0', no explicit reference is set - the algorithm will select a reference." - type: long? - algorithm__max_num_peaks_considered: - doc: The maximal number of peaks/features to be considered per map. To use all, set to '-1'. - type: long? - algorithm__superimposer__mz_pair_max_distance: - doc: Maximum of m/z deviation of corresponding elements in different maps. This condition applies to the pairs considered in hashing. - type: double? - algorithm__superimposer__rt_pair_distance_fraction: - doc: "Within each of the two maps, the pairs considered for pose clustering must be separated by at least this fraction of the total elution time interval (i.e., max - min). " - type: double? - algorithm__superimposer__num_used_points: - doc: Maximum number of elements considered in each map (selected by intensity). Use this to reduce the running time and to disregard weak signals during alignment. For using all points, set this to -1. - type: long? - algorithm__superimposer__scaling_bucket_size: - doc: The scaling of the retention time interval is being hashed into buckets of this size during pose clustering. A good choice for this would be a bit smaller than the error you would expect from repeated runs. - type: double? - algorithm__superimposer__shift_bucket_size: - doc: The shift at the lower (respectively, higher) end of the retention time interval is being hashed into buckets of this size during pose clustering. A good choice for this would be about the time between consecutive MS scans. - type: double? - algorithm__superimposer__max_shift: - doc: Maximal shift which is considered during histogramming (in seconds). This applies for both directions. - type: double? - algorithm__superimposer__max_scaling: - doc: Maximal scaling which is considered during histogramming. The minimal scaling is the reciprocal of this. - type: double? - algorithm__superimposer__dump_buckets: - doc: "[DEBUG] If non-empty, base filename where hash table buckets will be dumped to. A serial number for each invocation will be appended automatically." - type: string? - algorithm__superimposer__dump_pairs: - doc: "[DEBUG] If non-empty, base filename where the individual hashed pairs will be dumped to (large!). A serial number for each invocation will be appended automatically." - type: string? - algorithm__pairfinder__second_nearest_gap: - doc: Only link features whose distance to the second nearest neighbors (for both sides) is larger by 'second_nearest_gap' than the distance between the matched pair itself. - type: double? - algorithm__pairfinder__use_identifications: - doc: Never link features that are annotated with different peptides (features without ID's always match; only the best hit per peptide identification is considered). - type: boolean? - algorithm__pairfinder__ignore_charge: - doc: "false [default]: pairing requires equal charge state (or at least one unknown charge '0'); true: Pairing irrespective of charge state" - type: boolean? - algorithm__pairfinder__ignore_adduct: - doc: "true [default]: pairing requires equal adducts (or at least one without adduct annotation); true: Pairing irrespective of adducts" - type: string? - algorithm__pairfinder__distance_RT__max_difference: - doc: Never pair features with a larger RT distance (in seconds). - type: double? - algorithm__pairfinder__distance_RT__exponent: - doc: Normalized RT differences ([0-1], relative to 'max_difference') are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow) - type: double? - algorithm__pairfinder__distance_RT__weight: - doc: Final RT distances are weighted by this factor - type: double? - algorithm__pairfinder__distance_MZ__max_difference: - doc: Never pair features with larger m/z distance (unit defined by 'unit') - type: double? - algorithm__pairfinder__distance_MZ__unit: - doc: Unit of the 'max_difference' parameter - type: string? - algorithm__pairfinder__distance_MZ__exponent: - doc: Normalized ([0-1], relative to 'max_difference') m/z differences are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow) - type: double? - algorithm__pairfinder__distance_MZ__weight: - doc: Final m/z distances are weighted by this factor - type: double? - algorithm__pairfinder__distance_intensity__exponent: - doc: Differences in relative intensity ([0-1]) are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow) - type: double? - algorithm__pairfinder__distance_intensity__weight: - doc: Final intensity distances are weighted by this factor - type: double? - algorithm__pairfinder__distance_intensity__log_transform: - doc: Log-transform intensities? If disabled, d = |int_f2 - int_f1| / int_max. If enabled, d = |log(int_f2 + 1) - log(int_f1 + 1)| / log(int_max + 1)) - type: string? -outputs: - [] -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MapAlignerPoseClustering -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MapAlignerSpectrum.cwl b/workflow/cwl/MapAlignerSpectrum.cwl deleted file mode 100644 index bd6567a8f79..00000000000 --- a/workflow/cwl/MapAlignerSpectrum.cwl +++ /dev/null @@ -1,122 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MapAlignerSpectrum -doc: Corrects retention time distortions between maps by spectrum alignment. -inputs: - in: - doc: Input files to align (all must have the same file type) - type: File[] - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__gapcost: - doc: This Parameter stands for the cost of opening a gap in the Alignment. A gap means that one spectrum can not be aligned directly to another spectrum in the Map. This happens, when the similarity of both spectra a too low or even not present. Imagine it as a insert or delete of the spectrum in the map (similar to sequence alignment). The gap is necessary for aligning, if we open a gap there is a possibility that an another spectrum can be correct aligned with a higher score as before without gap. But to open a gap is a negative event and needs to carry a punishment, so a gap should only be opened if the benefits outweigh the downsides. The Parameter is to giving as a positive number, the implementation convert it to a negative number. - type: double? - algorithm__affinegapcost: - doc: This Parameter controls the cost of extension a already open gap. The idea behind the affine gapcost lies under the assumption, that it is better to get a long distance of connected gaps than to have a structure of gaps interspersed with matches (gap match gap match etc.). Therefore the punishment for the extension of a gap generally should be lower than the normal gapcost. If the result of the alignment shows high compression, it is a good idea to lower either the affine gapcost or gap opening cost. - type: double? - algorithm__cutoff_score: - doc: The Parameter defines the threshold which filtered spectra, these spectra are high potential candidate for deciding the interval of a sub-alignment. Only those pair of spectra are selected, which has a score higher or same of the threshold. - type: double? - algorithm__bucketsize: - doc: Defines the numbers of buckets. It is a quantize of the interval of those points, which defines the main alignment (match points). These points have to filtered, to reduce the amount of points for the calculating a smoother spline curve. - type: long? - algorithm__anchorpoints: - doc: Defines the percent of numbers of match points which a selected from one bucket. The high score pairs are previously selected. The reduction of match points helps to get a smoother spline curve. - type: long? - algorithm__debug: - doc: Activate the debug mode, there a files written starting with debug prefix. - type: boolean? - algorithm__mismatchscore: - doc: "Defines the score of two spectra if they have no similarity to each other. " - type: double? - algorithm__scorefunction: - doc: The score function is the core of an alignment. The success of an alignment depends mostly of the elected score function. The score function return the similarity of two spectra. The score influence defines later the way of possible traceback. There are multiple spectra similarity scores available.. - type: string? - model__type: - doc: Type of model - type: string? - model__linear__symmetric_regression: - doc: Perform linear regression on 'y - x' vs. 'y + x', instead of on 'y' vs. 'x'. - type: boolean? - model__linear__x_weight: - doc: Weight x values - type: string? - model__linear__y_weight: - doc: Weight y values - type: string? - model__linear__x_datum_min: - doc: Minimum x value - type: double? - model__linear__x_datum_max: - doc: Maximum x value - type: double? - model__linear__y_datum_min: - doc: Minimum y value - type: double? - model__linear__y_datum_max: - doc: Maximum y value - type: double? - model__b_spline__wavelength: - doc: Determines the amount of smoothing by setting the number of nodes for the B-spline. The number is chosen so that the spline approximates a low-pass filter with this cutoff wavelength. The wavelength is given in the same units as the data; a higher value means more smoothing. '0' sets the number of nodes to twice the number of input points. - type: double? - model__b_spline__num_nodes: - doc: Number of nodes for B-spline fitting. Overrides 'wavelength' if set (to two or greater). A lower value means more smoothing. - type: long? - model__b_spline__extrapolate: - doc: "Method to use for extrapolation beyond the original data range. 'linear': Linear extrapolation using the slope of the B-spline at the corresponding endpoint. 'b_spline': Use the B-spline (as for interpolation). 'constant': Use the constant value of the B-spline at the corresponding endpoint. 'global_linear': Use a linear fit through the data (which will most probably introduce discontinuities at the ends of the data range)." - type: string? - model__b_spline__boundary_condition: - doc: "Boundary condition at B-spline endpoints: 0 (value zero), 1 (first derivative zero) or 2 (second derivative zero)" - type: long? - model__lowess__span: - doc: Fraction of datapoints (f) to use for each local regression (determines the amount of smoothing). Choosing this parameter in the range .2 to .8 usually results in a good fit. - type: double? - model__lowess__num_iterations: - doc: Number of robustifying iterations for lowess fitting. - type: long? - model__lowess__delta: - doc: Nonnegative parameter which may be used to save computations (recommended value is 0.01 of the range of the input, e.g. for data ranging from 1000 seconds to 2000 seconds, it could be set to 10). Setting a negative value will automatically do this. - type: double? - model__lowess__interpolation_type: - doc: "Method to use for interpolation between datapoints computed by lowess. 'linear': Linear interpolation. 'cspline': Use the cubic spline for interpolation. 'akima': Use an akima spline for interpolation" - type: string? - model__lowess__extrapolation_type: - doc: "Method to use for extrapolation outside the data range. 'two-point-linear': Uses a line through the first and last point to extrapolate. 'four-point-linear': Uses a line through the first and second point to extrapolate in front and and a line through the last and second-to-last point in the end. 'global-linear': Uses a linear regression to fit a line through all data points and use it for interpolation." - type: string? - model__interpolated__interpolation_type: - doc: Type of interpolation to apply. - type: string? - model__interpolated__extrapolation_type: - doc: "Type of extrapolation to apply: two-point-linear: use the first and last data point to build a single linear model, four-point-linear: build two linear models on both ends using the first two / last two points, global-linear: use all points to build a single linear model. Note that global-linear may not be continuous at the border." - type: string? -outputs: - [] -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MapAlignerSpectrum -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MapAlignerTreeGuided.cwl b/workflow/cwl/MapAlignerTreeGuided.cwl deleted file mode 100644 index 3a8bcaa6812..00000000000 --- a/workflow/cwl/MapAlignerTreeGuided.cwl +++ /dev/null @@ -1,128 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MapAlignerTreeGuided -doc: Tree guided correction of retention time distortions between maps. -inputs: - in: - doc: Input files to align (all must have the same file type) - type: File[] - copy_data: - doc: Copy data (faster, more memory required) or reload data (slower, less memory required) when aligning many files. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__model_type: - doc: Options to control the modeling of retention time transformations from data - type: string? - algorithm__model__type: - doc: Type of model - type: string? - algorithm__model__linear__symmetric_regression: - doc: Perform linear regression on 'y - x' vs. 'y + x', instead of on 'y' vs. 'x'. - type: boolean? - algorithm__model__linear__x_weight: - doc: Weight x values - type: string? - algorithm__model__linear__y_weight: - doc: Weight y values - type: string? - algorithm__model__linear__x_datum_min: - doc: Minimum x value - type: double? - algorithm__model__linear__x_datum_max: - doc: Maximum x value - type: double? - algorithm__model__linear__y_datum_min: - doc: Minimum y value - type: double? - algorithm__model__linear__y_datum_max: - doc: Maximum y value - type: double? - algorithm__model__b_spline__wavelength: - doc: Determines the amount of smoothing by setting the number of nodes for the B-spline. The number is chosen so that the spline approximates a low-pass filter with this cutoff wavelength. The wavelength is given in the same units as the data; a higher value means more smoothing. '0' sets the number of nodes to twice the number of input points. - type: double? - algorithm__model__b_spline__num_nodes: - doc: Number of nodes for B-spline fitting. Overrides 'wavelength' if set (to two or greater). A lower value means more smoothing. - type: long? - algorithm__model__b_spline__extrapolate: - doc: "Method to use for extrapolation beyond the original data range. 'linear': Linear extrapolation using the slope of the B-spline at the corresponding endpoint. 'b_spline': Use the B-spline (as for interpolation). 'constant': Use the constant value of the B-spline at the corresponding endpoint. 'global_linear': Use a linear fit through the data (which will most probably introduce discontinuities at the ends of the data range)." - type: string? - algorithm__model__b_spline__boundary_condition: - doc: "Boundary condition at B-spline endpoints: 0 (value zero), 1 (first derivative zero) or 2 (second derivative zero)" - type: long? - algorithm__model__lowess__span: - doc: Fraction of datapoints (f) to use for each local regression (determines the amount of smoothing). Choosing this parameter in the range .2 to .8 usually results in a good fit. - type: double? - algorithm__model__lowess__num_iterations: - doc: Number of robustifying iterations for lowess fitting. - type: long? - algorithm__model__lowess__delta: - doc: Nonnegative parameter which may be used to save computations (recommended value is 0.01 of the range of the input, e.g. for data ranging from 1000 seconds to 2000 seconds, it could be set to 10). Setting a negative value will automatically do this. - type: double? - algorithm__model__lowess__interpolation_type: - doc: "Method to use for interpolation between datapoints computed by lowess. 'linear': Linear interpolation. 'cspline': Use the cubic spline for interpolation. 'akima': Use an akima spline for interpolation" - type: string? - algorithm__model__lowess__extrapolation_type: - doc: "Method to use for extrapolation outside the data range. 'two-point-linear': Uses a line through the first and last point to extrapolate. 'four-point-linear': Uses a line through the first and second point to extrapolate in front and and a line through the last and second-to-last point in the end. 'global-linear': Uses a linear regression to fit a line through all data points and use it for interpolation." - type: string? - algorithm__model__interpolated__interpolation_type: - doc: Type of interpolation to apply. - type: string? - algorithm__model__interpolated__extrapolation_type: - doc: "Type of extrapolation to apply: two-point-linear: use the first and last data point to build a single linear model, four-point-linear: build two linear models on both ends using the first two / last two points, global-linear: use all points to build a single linear model. Note that global-linear may not be continuous at the border." - type: string? - algorithm__align_algorithm__score_type: - doc: Name of the score type to use for ranking and filtering (.oms input only). If left empty, a score type is picked automatically. - type: string? - algorithm__align_algorithm__score_cutoff: - doc: Use only IDs above a score cut-off (parameter 'min_score') for alignment? - type: boolean? - algorithm__align_algorithm__min_score: - doc: "If 'score_cutoff' is 'true': Minimum score for an ID to be considered.\nUnless you have very few runs or identifications, increase this value to focus on more informative peptides." - type: double? - algorithm__align_algorithm__min_run_occur: - doc: "Minimum number of runs (incl. reference, if any) in which a peptide must occur to be used for the alignment.\nUnless you have very few runs or identifications, increase this value to focus on more informative peptides." - type: long? - algorithm__align_algorithm__max_rt_shift: - doc: "Maximum realistic RT difference for a peptide (median per run vs. reference). Peptides with higher shifts (outliers) are not used to compute the alignment.\nIf 0, no limit (disable filter); if > 1, the final value in seconds; if <= 1, taken as a fraction of the range of the reference RT scale." - type: double? - algorithm__align_algorithm__use_unassigned_peptides: - doc: Should unassigned peptide identifications be used when computing an alignment of feature or consensus maps? If 'false', only peptide IDs assigned to features will be used. - type: string? - algorithm__align_algorithm__use_feature_rt: - doc: "When aligning feature or consensus maps, don't use the retention time of a peptide identification directly; instead, use the retention time of the centroid of the feature (apex of the elution profile) that the peptide was matched to. If different identifications are matched to one feature, only the peptide closest to the centroid in RT is used.\nPrecludes 'use_unassigned_peptides'." - type: string? - algorithm__align_algorithm__use_adducts: - doc: If IDs contain adducts, treat differently adducted variants of the same molecule as different. - type: string? -outputs: - [] -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MapAlignerTreeGuided -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MapNormalizer.cwl b/workflow/cwl/MapNormalizer.cwl deleted file mode 100644 index 27fcd78b5b7..00000000000 --- a/workflow/cwl/MapNormalizer.cwl +++ /dev/null @@ -1,47 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MapNormalizer -doc: Normalizes peak intensities in an MS run. -inputs: - in: - doc: "input file " - type: File - out: - doc: "output file " - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MapNormalizer -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MapRTTransformer.cwl b/workflow/cwl/MapRTTransformer.cwl deleted file mode 100644 index ae9a15139bb..00000000000 --- a/workflow/cwl/MapRTTransformer.cwl +++ /dev/null @@ -1,120 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MapRTTransformer -doc: Applies retention time transformations to maps. -inputs: - in: - doc: Input file to transform (separated by blanks) - type: File? - out: - doc: Output file (same file type as 'in'). This option or 'trafo_out' has to be provided; they can be used together. - type: string? - trafo_in: - doc: Transformation to apply - type: File - trafo_out: - doc: Transformation output file. This option or 'out' has to be provided; they can be used together. - type: string? - invert: - doc: Invert transformation (approximatively) before applying it - type: boolean? - store_original_rt: - doc: Store the original retention times (before transformation) as meta data in the output file - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - model__type: - doc: Type of model - type: string? - model__linear__symmetric_regression: - doc: Perform linear regression on 'y - x' vs. 'y + x', instead of on 'y' vs. 'x'. - type: boolean? - model__linear__x_weight: - doc: Weight x values - type: string? - model__linear__y_weight: - doc: Weight y values - type: string? - model__linear__x_datum_min: - doc: Minimum x value - type: double? - model__linear__x_datum_max: - doc: Maximum x value - type: double? - model__linear__y_datum_min: - doc: Minimum y value - type: double? - model__linear__y_datum_max: - doc: Maximum y value - type: double? - model__b_spline__wavelength: - doc: Determines the amount of smoothing by setting the number of nodes for the B-spline. The number is chosen so that the spline approximates a low-pass filter with this cutoff wavelength. The wavelength is given in the same units as the data; a higher value means more smoothing. '0' sets the number of nodes to twice the number of input points. - type: double? - model__b_spline__num_nodes: - doc: Number of nodes for B-spline fitting. Overrides 'wavelength' if set (to two or greater). A lower value means more smoothing. - type: long? - model__b_spline__extrapolate: - doc: "Method to use for extrapolation beyond the original data range. 'linear': Linear extrapolation using the slope of the B-spline at the corresponding endpoint. 'b_spline': Use the B-spline (as for interpolation). 'constant': Use the constant value of the B-spline at the corresponding endpoint. 'global_linear': Use a linear fit through the data (which will most probably introduce discontinuities at the ends of the data range)." - type: string? - model__b_spline__boundary_condition: - doc: "Boundary condition at B-spline endpoints: 0 (value zero), 1 (first derivative zero) or 2 (second derivative zero)" - type: long? - model__lowess__span: - doc: Fraction of datapoints (f) to use for each local regression (determines the amount of smoothing). Choosing this parameter in the range .2 to .8 usually results in a good fit. - type: double? - model__lowess__num_iterations: - doc: Number of robustifying iterations for lowess fitting. - type: long? - model__lowess__delta: - doc: Nonnegative parameter which may be used to save computations (recommended value is 0.01 of the range of the input, e.g. for data ranging from 1000 seconds to 2000 seconds, it could be set to 10). Setting a negative value will automatically do this. - type: double? - model__lowess__interpolation_type: - doc: "Method to use for interpolation between datapoints computed by lowess. 'linear': Linear interpolation. 'cspline': Use the cubic spline for interpolation. 'akima': Use an akima spline for interpolation" - type: string? - model__lowess__extrapolation_type: - doc: "Method to use for extrapolation outside the data range. 'two-point-linear': Uses a line through the first and last point to extrapolate. 'four-point-linear': Uses a line through the first and second point to extrapolate in front and and a line through the last and second-to-last point in the end. 'global-linear': Uses a linear regression to fit a line through all data points and use it for interpolation." - type: string? - model__interpolated__interpolation_type: - doc: Type of interpolation to apply. - type: string? - model__interpolated__extrapolation_type: - doc: "Type of extrapolation to apply: two-point-linear: use the first and last data point to build a single linear model, four-point-linear: build two linear models on both ends using the first two / last two points, global-linear: use all points to build a single linear model. Note that global-linear may not be continuous at the border." - type: string? -outputs: - out: - type: File? - outputBinding: - glob: $(inputs.out) - trafo_out: - type: File? - outputBinding: - glob: $(inputs.trafo_out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MapRTTransformer -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MapStatistics.cwl b/workflow/cwl/MapStatistics.cwl deleted file mode 100644 index cc009933083..00000000000 --- a/workflow/cwl/MapStatistics.cwl +++ /dev/null @@ -1,62 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MapStatistics -doc: Extract extended statistics on the features of a map for quality control. -inputs: - in: - doc: Input file - type: File - in_type: - doc: "Input file type -- default: determined from file extension or content" - type: string? - out: - doc: Optional output txt file. If empty, the output is written to the command line. - type: string? - n: - doc: Report separate statistics for each of n RT slices of the map. - type: long? - m: - doc: Show meta information about the whole experiment - type: boolean? - p: - doc: Shows data processing information - type: boolean? - s: - doc: Computes a summary statistics of intensities, qualities, and widths - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File? - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MapStatistics -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MascotAdapter.cwl b/workflow/cwl/MascotAdapter.cwl deleted file mode 100644 index 3b0bf52d633..00000000000 --- a/workflow/cwl/MascotAdapter.cwl +++ /dev/null @@ -1,122 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MascotAdapter -doc: Annotates MS/MS spectra using Mascot. -inputs: - in: - doc: "input file in mzData format.\nNote: In mode 'mascot_out' a Mascot results file (.mascotXML) is read" - type: File - out: - doc: "output file in idXML format.\nNote: In mode 'mascot_in' Mascot generic format is written." - type: string - out_type: - doc: output file type (for TOPPAS) - type: string? - instrument: - doc: the instrument that was used to measure the spectra - type: string? - precursor_mass_tolerance: - doc: the precursor mass tolerance - type: double? - peak_mass_tolerance: - doc: the peak mass tolerance - type: double? - taxonomy: - doc: the taxonomy - type: string? - modifications: - doc: the modifications i.e. Carboxymethyl (C) - type: string[]? - variable_modifications: - doc: the variable modifications i.e. Carboxymethyl (C) - type: string[]? - charges: - doc: the different charge states - type: string[]? - db: - doc: the database to search in - type: string? - hits: - doc: the number of hits to report - type: string? - cleavage: - doc: The enzyme descriptor to the enzyme used for digestion. (Trypsin is default, None would be best for peptide input or unspecific digestion, for more please refer to your mascot server). - type: string? - missed_cleavages: - doc: number of allowed missed cleavages - type: long? - sig_threshold: - doc: significance threshold - type: double? - pep_homol: - doc: peptide homology threshold - type: double? - pep_ident: - doc: peptide ident threshold - type: double? - pep_rank: - doc: peptide rank - type: long? - prot_score: - doc: protein score - type: double? - pep_score: - doc: peptide score - type: double? - pep_exp_z: - doc: peptide expected charge - type: long? - show_unassigned: - doc: show_unassigned - type: long? - first_dim_rt: - doc: additional information which is added to every peptide identification as metavalue if set > 0 - type: double? - boundary: - doc: MIME boundary for mascot output format - type: string? - mass_type: - doc: mass type - type: string? - mascot_directory: - doc: the directory in which mascot is located - type: string? - temp_data_directory: - doc: a directory in which some temporary files can be stored - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MascotAdapter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MascotAdapterOnline.cwl b/workflow/cwl/MascotAdapterOnline.cwl deleted file mode 100644 index 61c2f862c76..00000000000 --- a/workflow/cwl/MascotAdapterOnline.cwl +++ /dev/null @@ -1,161 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MascotAdapterOnline -doc: Annotates MS/MS spectra using Mascot. -inputs: - in: - doc: "input file in mzML format.\n" - type: File - out: - doc: "output file in idXML format.\n" - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - Mascot_parameters__database: - doc: Name of the sequence database - type: string? - Mascot_parameters__search_type: - doc: Name of the search type for the query - type: string? - Mascot_parameters__enzyme: - doc: The enzyme descriptor to the enzyme used for digestion. (Trypsin is default, None would be best for peptide input or unspecific digestion, for more please refer to your mascot server). - type: string? - Mascot_parameters__instrument: - doc: Instrument definition which specifies the fragmentation rules - type: string? - Mascot_parameters__missed_cleavages: - doc: Number of missed cleavages allowed for the enzyme - type: long? - Mascot_parameters__precursor_mass_tolerance: - doc: Tolerance of the precursor peaks - type: double? - Mascot_parameters__precursor_error_units: - doc: Units of the precursor mass tolerance - type: string? - Mascot_parameters__fragment_mass_tolerance: - doc: Tolerance of the peaks in the fragment spectrum - type: double? - Mascot_parameters__fragment_error_units: - doc: Units of the fragment peaks tolerance - type: string? - Mascot_parameters__charges: - doc: Charge states to consider, given as a comma separated list of integers (only used for spectra without precursor charge information) - type: string? - Mascot_parameters__taxonomy: - doc: Taxonomy specification of the sequences - type: string? - Mascot_parameters__fixed_modifications: - doc: List of fixed modifications, according to UniMod definitions. - type: string[]? - Mascot_parameters__variable_modifications: - doc: Variable modifications given as UniMod definitions. - type: string[]? - Mascot_parameters__special_modifications: - doc: Modifications with specificity groups that are used by Mascot and have to be treated specially - type: string? - Mascot_parameters__mass_type: - doc: Defines the mass type, either monoisotopic or average - type: string? - Mascot_parameters__number_of_hits: - doc: Number of hits which should be returned, if 0 AUTO mode is enabled. - type: long? - Mascot_parameters__skip_spectrum_charges: - doc: Sometimes precursor charges are given for each spectrum but are wrong, setting this to 'true' does not write any charge information to the spectrum, the general charge information is however kept. - type: boolean? - Mascot_parameters__decoy: - doc: Set to true if mascot should generate the decoy database. - type: boolean? - Mascot_parameters__search_title: - doc: Sets the title of the search. - type: string? - Mascot_parameters__username: - doc: Sets the username which is mentioned in the results file. - type: string? - Mascot_parameters__email: - doc: "Sets the email which is mentioned in the results file. Note: Some server require that a proper email is provided." - type: string? - Mascot_server__hostname: - doc: Address of the host where Mascot listens, e.g. 'mascot-server' or '127.0.0.1' - type: string? - Mascot_server__host_port: - doc: Port where the Mascot server listens, 80 should be a good guess - type: long? - Mascot_server__server_path: - doc: Path on the server where Mascot server listens, 'mascot' should be a good guess - type: string? - Mascot_server__timeout: - doc: Timeout in seconds, after which the query is declared as failed.This is NOT the whole time the search takes, but the time in between two progress steps. Some Mascot servers freeze during this (unstable network etc) and idle forever, the connection is killed. Set this to 0 to disable timeout! - type: long? - Mascot_server__boundary: - doc: Boundary for the MIME section - type: string? - Mascot_server__use_proxy: - doc: Flag which enables the proxy usage for the HTTP requests, please specify at least 'proxy_host' and 'proxy_port' - type: boolean? - Mascot_server__proxy_host: - doc: Host where the proxy server runs on - type: string? - Mascot_server__proxy_port: - doc: Port where the proxy server listens - type: long? - Mascot_server__proxy_username: - doc: Login name for the proxy server, if needed - type: string? - Mascot_server__proxy_password: - doc: Login password for the proxy server, if needed - type: string? - Mascot_server__login: - doc: Flag which should be set 'true' if Mascot security is enabled; also set 'username' and 'password' then. - type: boolean? - Mascot_server__username: - doc: Name of the user if login is used (Mascot security must be enabled!) - type: string? - Mascot_server__password: - doc: Password of the user if login is used (Mascot security must be enabled!) - type: string? - Mascot_server__use_ssl: - doc: Flag indicating whether you want to send requests to an HTTPS server or not (HTTP). Requires OpenSSL to be installed (see openssl.org) - type: boolean? - Mascot_server__export_params: - doc: Adjustable export parameters (passed to Mascot's 'export_dat_2.pl' script). Generally only parameters that control which hits to export are safe to adjust/add. Many settings that govern what types of information to include are required by OpenMS and cannot be changed. Note that setting 'query_master' to 1 may lead to incorrect protein references for peptides. - type: string? - Mascot_server__skip_export: - doc: "For use with an external Mascot Percolator (via GenericWrapper): Run the Mascot search, but do not export the results. The output file produced by MascotAdapterOnline will contain only the Mascot search number." - type: boolean? - Mascot_server__batch_size: - doc: Number of spectra processed in one batch by Mascot (default 50000) - type: long? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MascotAdapterOnline -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MassCalculator.cwl b/workflow/cwl/MassCalculator.cwl deleted file mode 100644 index 153d5681cf1..00000000000 --- a/workflow/cwl/MassCalculator.cwl +++ /dev/null @@ -1,65 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MassCalculator -doc: Calculates masses and mass-to-charge ratios of peptide sequences -inputs: - in: - doc: Input file with peptide sequences and optionally charge numbers (mutually exclusive to 'in_seq') - type: File? - in_seq: - doc: List of peptide sequences (mutually exclusive to 'in') - type: string[]? - out: - doc: Output file; if empty, output is written to the screen - type: string? - charge: - doc: List of charge states; required if 'in_seq' is given - type: long[]? - format: - doc: "Output format ('list': human-readable list, 'table': CSV-like table, 'mass_only': mass values only, 'mz_only': m/z values only)\n" - type: string? - average_mass: - doc: Compute average (instead of monoisotopic) peptide masses - type: boolean? - fragment_type: - doc: "For what type of sequence/fragment the mass should be computed\n" - type: string? - separator: - doc: Field separator for 'table' output format; by default, the 'tab' character is used - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File? - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MassCalculator -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MassTraceExtractor.cwl b/workflow/cwl/MassTraceExtractor.cwl deleted file mode 100644 index 70163c7e007..00000000000 --- a/workflow/cwl/MassTraceExtractor.cwl +++ /dev/null @@ -1,98 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MassTraceExtractor -doc: Detects mass traces in centroided LC-MS data. -inputs: - in: - doc: input centroided mzML file - type: File - out: - doc: output featureXML file with mass traces - type: string - out_type: - doc: "output file type -- default: determined from file extension or content" - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__common__noise_threshold_int: - doc: Intensity threshold below which peaks are regarded as noise. - type: double? - algorithm__common__chrom_peak_snr: - doc: Minimum signal-to-noise a mass trace should have. - type: double? - algorithm__common__chrom_fwhm: - doc: Expected chromatographic peak width (in seconds). - type: double? - algorithm__mtd__mass_error_ppm: - doc: Allowed mass deviation (in ppm). - type: double? - algorithm__mtd__reestimate_mt_sd: - doc: Enables dynamic re-estimation of m/z variance during mass trace collection stage. - type: string? - algorithm__mtd__quant_method: - doc: Method of quantification for mass traces. For LC data 'area' is recommended, 'median' for direct injection data. 'max_height' simply uses the most intense peak in the trace. - type: string? - algorithm__mtd__trace_termination_criterion: - doc: Termination criterion for the extension of mass traces. In 'outlier' mode, trace extension cancels if a predefined number of consecutive outliers are found (see trace_termination_outliers parameter). In 'sample_rate' mode, trace extension in both directions stops if ratio of found peaks versus visited spectra falls below the 'min_sample_rate' threshold. - type: string? - algorithm__mtd__trace_termination_outliers: - doc: Mass trace extension in one direction cancels if this number of consecutive spectra with no detectable peaks is reached. - type: long? - algorithm__mtd__min_sample_rate: - doc: Minimum fraction of scans along the mass trace that must contain a peak. - type: double? - algorithm__mtd__min_trace_length: - doc: Minimum expected length of a mass trace (in seconds). - type: double? - algorithm__mtd__max_trace_length: - doc: Maximum expected length of a mass trace (in seconds). Set to a negative value to disable maximal length check during mass trace detection. - type: double? - algorithm__epd__width_filtering: - doc: Enable filtering of unlikely peak widths. The fixed setting filters out mass traces outside the [min_fwhm, max_fwhm] interval (set parameters accordingly!). The auto setting filters with the 5 and 95% quantiles of the peak width distribution. - type: string? - algorithm__epd__min_fwhm: - doc: Minimum full-width-at-half-maximum of chromatographic peaks (in seconds). Ignored if parameter width_filtering is off or auto. - type: double? - algorithm__epd__max_fwhm: - doc: Maximum full-width-at-half-maximum of chromatographic peaks (in seconds). Ignored if parameter width_filtering is off or auto. - type: double? - algorithm__epd__masstrace_snr_filtering: - doc: Apply post-filtering by signal-to-noise ratio after smoothing. - type: boolean? - algorithm__epd__enabled: - doc: Enables/disables the chromatographic peak detection of mass traces - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MassTraceExtractor -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MetaProSIP.cwl b/workflow/cwl/MetaProSIP.cwl deleted file mode 100644 index d9cd5ccadd2..00000000000 --- a/workflow/cwl/MetaProSIP.cwl +++ /dev/null @@ -1,141 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MetaProSIP -doc: Performs proteinSIP on peptide features for elemental flux analysis. -inputs: - in_mzML: - doc: Centroided MS1 data - type: File - in_fasta: - doc: Protein sequence database - type: File - out_csv: - doc: Column separated file with feature fitting result. - type: string - out_peptide_centric_csv: - doc: Column separated file with peptide centric result. - type: string - in_featureXML: - doc: Feature data annotated with identifications (IDMapper) - type: File - r_executable: - doc: "Path to the R executable (default: 'R')" - type: File? - mz_tolerance_ppm: - doc: Tolerance in ppm - type: double? - rt_tolerance_s: - doc: Tolerance window around feature rt for XIC extraction - type: double? - intensity_threshold: - doc: Intensity threshold to collect peaks in the MS1 spectrum. - type: double? - correlation_threshold: - doc: Correlation threshold for reporting a RIA - type: double? - xic_threshold: - doc: Minimum correlation to mono-isotopic peak for retaining a higher isotopic peak. If featureXML from reference file is used it should be disabled (set to -1) as no mono-isotopic peak is expected to be present. - type: double? - decomposition_threshold: - doc: Minimum R-squared of decomposition that must be achieved for a peptide to be reported. - type: double? - weight_merge_window: - doc: Decomposition coefficients within +- this rate window will be combined - type: double? - min_correlation_distance_to_averagine: - doc: Minimum difference in correlation between incorporation pattern and averagine pattern. Positive values filter all RIAs passing the correlation threshold but that also show a better correlation to an averagine peptide. Disabled for values <= -1 - type: double? - pattern_15N_TIC_threshold: - doc: The most intense peaks of the theoretical pattern contributing to at least this TIC fraction are taken into account. - type: double? - pattern_13C_TIC_threshold: - doc: The most intense peaks of the theoretical pattern contributing to at least this TIC fraction are taken into account. - type: double? - pattern_2H_TIC_threshold: - doc: The most intense peaks of the theoretical pattern contributing to at least this TIC fraction are taken into account. - type: double? - pattern_18O_TIC_threshold: - doc: The most intense peaks of the theoretical pattern contributing to at least this TIC fraction are taken into account. - type: double? - heatmap_bins: - doc: Number of RIA bins for heat map generation. - type: long? - plot_extension: - doc: Extension used for plots (png|svg|pdf). - type: string? - qc_output_directory: - doc: Output directory for the quality report - type: string? - labeling_element: - doc: Which element (single letter code) is labeled. - type: string? - use_unassigned_ids: - doc: Include identifications not assigned to a feature in pattern detection. - type: boolean? - use_averagine_ids: - doc: Use averagine peptides as model to perform pattern detection on unidentified peptides. - type: boolean? - report_natural_peptides: - doc: Whether purely natural peptides are reported in the quality report. - type: boolean? - filter_monoisotopic: - doc: Try to filter out mono-isotopic patterns to improve detection of low RIA patterns - type: boolean? - cluster: - doc: Perform grouping - type: boolean? - observed_peak_fraction: - doc: Fraction of observed/expected peaks. - type: double? - min_consecutive_isotopes: - doc: Minimum number of consecutive isotopic intensities needed. - type: long? - score_plot_yaxis_min: - doc: The minimum value of the score axis. Values smaller than zero usually only make sense if the observed peak fraction is set to 0. - type: double? - collect_method: - doc: How RIAs are collected. - type: string? - lowRIA_correlation_threshold: - doc: Correlation threshold for reporting low RIA patterns. Disable and take correlation_threshold value for negative values. - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out_csv: - type: File - outputBinding: - glob: $(inputs.out_csv) - out_peptide_centric_csv: - type: File - outputBinding: - glob: $(inputs.out_peptide_centric_csv) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MetaProSIP -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MetaboliteAdductDecharger.cwl b/workflow/cwl/MetaboliteAdductDecharger.cwl deleted file mode 100644 index d73bc399c8e..00000000000 --- a/workflow/cwl/MetaboliteAdductDecharger.cwl +++ /dev/null @@ -1,112 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MetaboliteAdductDecharger -doc: Decharges and merges different feature charge variants of the same metabolite. -inputs: - in: - doc: "input file " - type: File - out_cm: - doc: output consensus map - type: string? - out_fm: - doc: output feature map - type: string? - outpairs: - doc: output file - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__MetaboliteFeatureDeconvolution__charge_min: - doc: Minimal possible charge - type: long? - algorithm__MetaboliteFeatureDeconvolution__charge_max: - doc: Maximal possible charge - type: long? - algorithm__MetaboliteFeatureDeconvolution__charge_span_max: - doc: Maximal range of charges for a single analyte, i.e. observing q1=[5,6,7] implies span=3. Setting this to 1 will only find adduct variants of the same charge - type: long? - algorithm__MetaboliteFeatureDeconvolution__q_try: - doc: Try different values of charge for each feature according to the above settings ('heuristic' [does not test all charges, just the likely ones] or 'all' ), or leave feature charge untouched ('feature'). - type: string? - algorithm__MetaboliteFeatureDeconvolution__retention_max_diff: - doc: Maximum allowed RT difference between any two features if their relation shall be determined - type: double? - algorithm__MetaboliteFeatureDeconvolution__retention_max_diff_local: - doc: Maximum allowed RT difference between between two co-features, after adduct shifts have been accounted for (if you do not have any adduct shifts, this value should be equal to 'retention_max_diff', otherwise it should be smaller!) - type: double? - algorithm__MetaboliteFeatureDeconvolution__mass_max_diff: - doc: Maximum allowed mass tolerance per feature. Defines a symmetric tolerance window around the feature. When looking at possible feature pairs, the allowed feature-wise errors are combined for consideration of possible adduct shifts. For ppm tolerances, each window is based on the respective observed feature mz (instead of putative experimental mzs causing the observed one)! - type: double? - algorithm__MetaboliteFeatureDeconvolution__unit: - doc: Unit of the 'max_difference' parameter - type: string? - algorithm__MetaboliteFeatureDeconvolution__potential_adducts: - doc: "Adducts used to explain mass differences in format: 'Elements:Charge(+/-/0):Probability[:RTShift[:Label]]', i.e. the number of '+' or '-' indicate the charge ('0' if neutral adduct), e.g. 'Ca:++:0.5' indicates +2. Probabilites have to be in (0,1]. The optional RTShift param indicates the expected RT shift caused by this adduct, e.g. '(2)H4H-4:0:1:-3' indicates a 4 deuterium label, which causes early elution by 3 seconds. As fifth parameter you can add a label for every feature with this adduct. This also determines the map number in the consensus file. Adduct element losses are written in the form 'H-2'. All provided adducts need to have the same charge sign or be neutral! Mixing of adducts with different charge directions is only allowed as neutral complexes. For example, 'H-1Na:0:0.05' can be used to model Sodium gains (with balancing deprotonation) in negative mode." - type: string[]? - algorithm__MetaboliteFeatureDeconvolution__max_neutrals: - doc: Maximal number of neutral adducts(q=0) allowed. Add them in the 'potential_adducts' section! - type: long? - algorithm__MetaboliteFeatureDeconvolution__use_minority_bound: - doc: Prune the considered adduct transitions by transition probabilities. - type: string? - algorithm__MetaboliteFeatureDeconvolution__max_minority_bound: - doc: "Limits allowed adduct compositions and changes between compositions in the underlying graph optimization problem by introducing a probability-based threshold: the minority bound sets the maximum count of the least probable adduct (according to 'potential_adducts' param) within a charge variant with maximum charge only containing the most likely adduct otherwise. E.g., for 'charge_max' 4 and 'max_minority_bound' 2 with most probable adduct being H+ and least probable adduct being Na+, this will allow adduct compositions of '2(H+),2(Na+)' but not of '1(H+),3(Na+)'. Further, adduct compositions/changes less likely than '2(H+),2(Na+)' will be discarded as well." - type: long? - algorithm__MetaboliteFeatureDeconvolution__min_rt_overlap: - doc: Minimum overlap of the convex hull' RT intersection measured against the union from two features (if CHs are given) - type: double? - algorithm__MetaboliteFeatureDeconvolution__intensity_filter: - doc: Enable the intensity filter, which will only allow edges between two equally charged features if the intensity of the feature with less likely adducts is smaller than that of the other feature. It is not used for features of different charge. - type: boolean? - algorithm__MetaboliteFeatureDeconvolution__negative_mode: - doc: Enable negative ionization mode. - type: boolean? - algorithm__MetaboliteFeatureDeconvolution__default_map_label: - doc: Label of map in output consensus file where all features are put by default - type: string? - algorithm__MetaboliteFeatureDeconvolution__verbose_level: - doc: Amount of debug information given during processing. - type: long? -outputs: - out_cm: - type: File? - outputBinding: - glob: $(inputs.out_cm) - out_fm: - type: File? - outputBinding: - glob: $(inputs.out_fm) - outpairs: - type: File? - outputBinding: - glob: $(inputs.outpairs) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MetaboliteAdductDecharger -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MetaboliteSpectralMatcher.cwl b/workflow/cwl/MetaboliteSpectralMatcher.cwl deleted file mode 100644 index 0adff5ef8ed..00000000000 --- a/workflow/cwl/MetaboliteSpectralMatcher.cwl +++ /dev/null @@ -1,75 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MetaboliteSpectralMatcher -doc: Perform a spectral library search. -inputs: - in: - doc: Input spectra. - type: File - database: - doc: Default spectral database. - type: File - out: - doc: mzTab file - type: string - out_spectra: - doc: Output spectra as mzML file. Can be useful to inspect the peak map after spectra merging. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__prec_mass_error_value: - doc: Error allowed for precursor ion mass. - type: double? - algorithm__frag_mass_error_value: - doc: Error allowed for product ions. - type: double? - algorithm__mass_error_unit: - doc: Unit of mass error (ppm or Da) - type: string? - algorithm__report_mode: - doc: "Which results shall be reported: the top-three scoring ones or the best scoring one?" - type: string? - algorithm__ionization_mode: - doc: Positive or negative ionization mode? - type: string? - algorithm__merge_spectra: - doc: Merge MS2 spectra with the same precursor mass. - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - out_spectra: - type: File? - outputBinding: - glob: $(inputs.out_spectra) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MetaboliteSpectralMatcher -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MultiplexResolver.cwl b/workflow/cwl/MultiplexResolver.cwl deleted file mode 100644 index f6b4c2addca..00000000000 --- a/workflow/cwl/MultiplexResolver.cwl +++ /dev/null @@ -1,114 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MultiplexResolver -doc: Completes peptide multiplets and resolves conflicts within them. -inputs: - in: - doc: Peptide multiplets with assigned sequence information - type: File - in_blacklist: - doc: Optional input containing spectral peaks blacklisted during feature detection. Needed for generation of dummy features. - type: File? - out: - doc: Complete peptide multiplets. - type: string - out_conflicts: - doc: Optional output containing peptide multiplets without ID annotation or with conflicting quant/ID information. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__labels: - doc: "Labels used for labelling the samples. [...] specifies the labels for a single sample. For example\n\n[][Lys8,Arg10] ... SILAC\n[][Lys4,Arg6][Lys8,Arg10] ... triple-SILAC\n[Dimethyl0][Dimethyl6] ... Dimethyl\n[Dimethyl0][Dimethyl4][Dimethyl8] ... triple Dimethyl\n[ICPL0][ICPL4][ICPL6][ICPL10] ... ICPL" - type: string? - algorithm__missed_cleavages: - doc: Maximum number of missed cleavages due to incomplete digestion. (Only relevant if enzymatic cutting site coincides with labelling site. For example, Arg/Lys in the case of trypsin digestion and SILAC labelling.) - type: long? - algorithm__mass_tolerance: - doc: Mass tolerance in Da for matching the mass shifts in the detected peptide multiplet to the theoretical mass shift pattern. - type: double? - algorithm__mz_tolerance: - doc: m/z tolerance in ppm for checking if dummy feature vicinity was blacklisted. - type: long? - algorithm__rt_tolerance: - doc: Retention time tolerance in seconds for checking if dummy feature vicinity was blacklisted. - type: long? - labels__Arg6: - doc: "Label:13C(6) | C(-6) 13C(6) | unimod #188" - type: double? - labels__Arg10: - doc: "Label:13C(6)15N(4) | C(-6) 13C(6) N(-4) 15N(4) | unimod #267" - type: double? - labels__Lys4: - doc: "Label:2H(4) | H(-4) 2H(4) | unimod #481" - type: double? - labels__Lys6: - doc: "Label:13C(6) | C(-6) 13C(6) | unimod #188" - type: double? - labels__Lys8: - doc: "Label:13C(6)15N(2) | C(-6) 13C(6) N(-2) 15N(2) | unimod #259" - type: double? - labels__Leu3: - doc: "Label:2H(3) | H(-3) 2H(3) | unimod #262" - type: double? - labels__Dimethyl0: - doc: "Dimethyl | H(4) C(2) | unimod #36" - type: double? - labels__Dimethyl4: - doc: "Dimethyl:2H(4) | 2H(4) C(2) | unimod #199" - type: double? - labels__Dimethyl6: - doc: "Dimethyl:2H(4)13C(2) | 2H(4) 13C(2) | unimod #510" - type: double? - labels__Dimethyl8: - doc: "Dimethyl:2H(6)13C(2) | H(-2) 2H(6) 13C(2) | unimod #330" - type: double? - labels__ICPL0: - doc: "ICPL | H(3) C(6) N O | unimod #365" - type: double? - labels__ICPL4: - doc: "ICPL:2H(4) | H(-1) 2H(4) C(6) N O | unimod #687" - type: double? - labels__ICPL6: - doc: "ICPL:13C(6) | H(3) 13C(6) N O | unimod #364" - type: double? - labels__ICPL10: - doc: "ICPL:13C(6)2H(4) | H(-1) 2H(4) 13C(6) N O | unimod #866" - type: double? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - out_conflicts: - type: File? - outputBinding: - glob: $(inputs.out_conflicts) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MultiplexResolver -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MzMLSplitter.cwl b/workflow/cwl/MzMLSplitter.cwl deleted file mode 100644 index 04b9e355ab4..00000000000 --- a/workflow/cwl/MzMLSplitter.cwl +++ /dev/null @@ -1,62 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MzMLSplitter -doc: Splits an mzML file into multiple parts -inputs: - in: - doc: Input file - type: File - out: - doc: "Prefix for output files ('_part1of2.mzML' etc. will be appended; default: same as 'in' without the file extension)" - type: string? - parts: - doc: Number of parts to split into (takes precedence over 'size' if set) - type: long? - size: - doc: Approximate upper limit for resulting file sizes (in 'unit') - type: long? - unit: - doc: Unit for 'size' (base 1024) - type: string? - no_chrom: - doc: Remove chromatograms, keep only spectra. - type: boolean? - no_spec: - doc: Remove spectra, keep only chromatograms. - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File? - outputBinding: - glob: $(inputs.out)* -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MzMLSplitter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/MzTabExporter.cwl b/workflow/cwl/MzTabExporter.cwl deleted file mode 100644 index 3a8715b781e..00000000000 --- a/workflow/cwl/MzTabExporter.cwl +++ /dev/null @@ -1,56 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: MzTabExporter -doc: Exports various XML formats to an mzTab file. -inputs: - in: - doc: Input files used to generate the mzTab file. - type: File? - out: - doc: Output file (mzTab) - type: string - first_run_inference_only: - doc: Does the first IdentificationRun in the file only represent (protein) inference results? If so, read peptide information only from second to last runs. - type: boolean? - export_all_psms: - doc: Export all PSMs instead of only the best per spectrum - type: boolean? - opt_columns: - doc: Add optional columns which are not part of the mzTab standard. - type: string[]? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - MzTabExporter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/NoiseFilterGaussian.cwl b/workflow/cwl/NoiseFilterGaussian.cwl deleted file mode 100644 index bfe196543bd..00000000000 --- a/workflow/cwl/NoiseFilterGaussian.cwl +++ /dev/null @@ -1,62 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: NoiseFilterGaussian -doc: Removes noise from profile spectra by using Gaussian filter (on uniform as well as non-uniform data). -inputs: - in: - doc: "input raw data file " - type: File - out: - doc: "output raw data file " - type: string - processOption: - doc: Whether to load all data and process them in-memory or whether to process the data on the fly (lowmemory) without loading the whole file into memory first - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__gaussian_width: - doc: Use a gaussian filter width which has approximately the same width as your mass peaks (FWHM in m/z). - type: double? - algorithm__ppm_tolerance: - doc: "Gaussian width, depending on the m/z position.\nThe higher the value, the wider the peak and therefore the wider the gaussian." - type: double? - algorithm__use_ppm_tolerance: - doc: If true, instead of the gaussian_width value, the ppm_tolerance is used. The gaussian is calculated in each step anew, so this is much slower. - type: boolean? - algorithm__write_log_messages: - doc: "true: Warn if no signal was found by the Gauss filter algorithm." - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - NoiseFilterGaussian -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/NoiseFilterSGolay.cwl b/workflow/cwl/NoiseFilterSGolay.cwl deleted file mode 100644 index 5a4d8610f75..00000000000 --- a/workflow/cwl/NoiseFilterSGolay.cwl +++ /dev/null @@ -1,56 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: NoiseFilterSGolay -doc: Removes noise from profile spectra by using a Savitzky Golay filter (on uniform (equidistant) data). -inputs: - in: - doc: "input raw data file " - type: File - out: - doc: "output raw data file " - type: string - processOption: - doc: Whether to load all data and process them in-memory or whether to process the data on the fly (lowmemory) without loading the whole file into memory first - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__frame_length: - doc: "The number of subsequent data points used for smoothing.\nThis number has to be uneven. If it is not, 1 will be added." - type: long? - algorithm__polynomial_order: - doc: Order or the polynomial that is fitted. - type: long? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - NoiseFilterSGolay -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/NovorAdapter.cwl b/workflow/cwl/NovorAdapter.cwl deleted file mode 100644 index 73d33cfd4d7..00000000000 --- a/workflow/cwl/NovorAdapter.cwl +++ /dev/null @@ -1,86 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: NovorAdapter -doc: Performs de novo sequencing of peptides from MS/MS data with Novor. -inputs: - executable: - doc: novor.jar - type: File? - in: - doc: MzML Input file - type: File - out: - doc: Novor idXML output - type: string - enzyme: - doc: "Digestion enzyme - currently only Trypsin is supported " - type: string? - fragmentation: - doc: Fragmentation method - type: string? - massAnalyzer: - doc: MassAnalyzer e.g. (Oritrap CID-Trap, CID-FT, HCD-FT; QTof CID-TOF) - type: string? - fragment_mass_tolerance: - doc: Fragmentation error tolerance (Da) - type: double? - precursor_mass_tolerance: - doc: Precursor error tolerance (ppm or Da) - type: double? - precursor_error_units: - doc: Unit of precursor mass tolerance - type: string? - variable_modifications: - doc: Variable modifications - type: string[]? - fixed_modifications: - doc: Fixed modifications - type: string[]? - forbiddenResidues: - doc: Forbidden Resiudes - type: string[]? - novorFile: - doc: File to introduce customized algorithm parameters for advanced users (otional .novor file) - type: File? - java_executable: - doc: The Java executable. Usually Java is on the system PATH. If Java is not found, use this parameter to specify the full path to Java - type: File? - java_memory: - doc: Maximum Java heap size (in MB) - type: long? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - NovorAdapter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/NucleicAcidSearchEngine.cwl b/workflow/cwl/NucleicAcidSearchEngine.cwl deleted file mode 100644 index 3fa1c916dc8..00000000000 --- a/workflow/cwl/NucleicAcidSearchEngine.cwl +++ /dev/null @@ -1,167 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: NucleicAcidSearchEngine -doc: Annotate nucleic acid identifications to MS/MS spectra. -inputs: - in: - doc: "Input file: spectra" - type: File - database: - doc: "Input file: sequence database. Required unless 'digest' is set." - type: File? - digest: - doc: "Input file: pre-digested sequence database. Can be used instead of 'database'. Sets all 'oligo:...' parameters." - type: File? - out: - doc: "Output file: mzTab" - type: string - id_out: - doc: "Output file: idXML (for visualization in TOPPView)" - type: string? - db_out: - doc: "Output file: oms (SQLite database)" - type: string? - digest_out: - doc: "Output file: sequence database digest. Ignored if 'digest' input is used." - type: string? - lfq_out: - doc: "Output file: targets for label-free quantification using FeatureFinderMetaboIdent ('id' input)" - type: string? - theo_ms2_out: - doc: "Output file: theoretical MS2 spectra for precursor mass matches" - type: string? - exp_ms2_out: - doc: "Output file: experimental MS2 spectra for precursor mass matches" - type: string? - decharge_ms2: - doc: Decharge the MS2 spectra for scoring - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - precursor__mass_tolerance: - doc: Precursor mass tolerance (+/- around uncharged precursor mass) - type: double? - precursor__mass_tolerance_unit: - doc: Unit of precursor mass tolerance - type: string? - precursor__min_charge: - doc: Minimum precursor charge to be considered - type: long? - precursor__max_charge: - doc: Maximum precursor charge to be considered - type: long? - precursor__include_unknown_charge: - doc: Include MS2 spectra with unknown precursor charge - try to match them in any possible charge between 'min_charge' and 'max_charge', at the risk of a higher error rate - type: boolean? - precursor__use_avg_mass: - doc: Use average instead of monoisotopic precursor masses (appropriate for low-resolution instruments) - type: boolean? - precursor__use_adducts: - doc: Consider possible salt adducts (see 'precursor:potential_adducts') when matching precursor masses - type: boolean? - precursor__potential_adducts: - doc: "Adducts considered to explain mass differences. Format: 'Element:Charge(+/-)', i.e. the number of '+' or '-' indicates the charge, e.g. 'Ca:++' indicates +2. Only used if 'precursor:use_adducts' is set." - type: string[]? - precursor__isotopes: - doc: "Correct for mono-isotopic peak misassignments. E.g.: 1 = precursor may be misassigned to the first isotopic peak. Ignored if 'use_avg_mass' is set." - type: long[]? - fragment__mass_tolerance: - doc: Fragment mass tolerance (+/- around fragment m/z) - type: double? - fragment__mass_tolerance_unit: - doc: Unit of fragment mass tolerance - type: string? - fragment__ions: - doc: Fragment ions to include in theoretical spectra - type: string[]? - modifications__variable: - doc: Variable modifications - type: string[]? - modifications__variable_max_per_oligo: - doc: Maximum number of residues carrying a variable modification per candidate oligonucleotide - type: long? - modifications__resolve_ambiguities: - doc: "Attempt to resolve ambiguous modifications (e.g. 'mA?' for 'mA'/'Am') based on a-B ions.\nThis incurs a performance cost because two modifications have to be considered for each case.\nRequires a-B ions to be enabled in parameter 'fragment:ions'." - type: boolean? - oligo__min_size: - doc: Minimum size an oligonucleotide must have after digestion to be considered in the search - type: long? - oligo__max_size: - doc: Maximum size an oligonucleotide must have after digestion to be considered in the search, leave at 0 for no limit - type: long? - oligo__missed_cleavages: - doc: Number of missed cleavages - type: long? - oligo__enzyme: - doc: The enzyme used for RNA digestion - type: string? - report__top_hits: - doc: Maximum number of top-scoring hits per spectrum that are reported ('0' for all hits) - type: long? - fdr__decoy_pattern: - doc: String used as part of the accession to annotate decoy sequences (e.g. 'DECOY_'). Leave empty to skip the FDR/q-value calculation. - type: string? - fdr__cutoff: - doc: Cut-off for FDR filtering; search hits with higher q-values will be removed - type: double? - fdr__remove_decoys: - doc: Do not score hits to decoy sequences and remove them when filtering - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - id_out: - type: File? - outputBinding: - glob: $(inputs.id_out) - db_out: - type: File? - outputBinding: - glob: $(inputs.db_out) - digest_out: - type: File? - outputBinding: - glob: $(inputs.digest_out) - lfq_out: - type: File? - outputBinding: - glob: $(inputs.lfq_out) - theo_ms2_out: - type: File? - outputBinding: - glob: $(inputs.theo_ms2_out) - exp_ms2_out: - type: File? - outputBinding: - glob: $(inputs.exp_ms2_out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - NucleicAcidSearchEngine -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenMSDatabasesInfo.cwl b/workflow/cwl/OpenMSDatabasesInfo.cwl deleted file mode 100644 index e617299510d..00000000000 --- a/workflow/cwl/OpenMSDatabasesInfo.cwl +++ /dev/null @@ -1,51 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenMSDatabasesInfo -doc: Prints the content of OpenMS' enzyme and modification databases to TSV -inputs: - enzymes_out: - doc: Currently supported enzymes as TSV - type: string - mods_out: - doc: Currently supported modifications as TSV - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - enzymes_out: - type: File - outputBinding: - glob: $(inputs.enzymes_out) - mods_out: - type: File - outputBinding: - glob: $(inputs.mods_out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenMSDatabasesInfo -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenMSInfo.cwl b/workflow/cwl/OpenMSInfo.cwl deleted file mode 100644 index fa4a29243f7..00000000000 --- a/workflow/cwl/OpenMSInfo.cwl +++ /dev/null @@ -1,44 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenMSInfo -doc: Prints configurations details of OpenMS. -inputs: - p: - doc: Print information (flag can also be omitted) - type: boolean? - dummy: - doc: A fake input file, which is needed for some workflow systems to call this tool - type: File? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - [] -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenMSInfo -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenPepXL.cwl b/workflow/cwl/OpenPepXL.cwl deleted file mode 100644 index d357cb49745..00000000000 --- a/workflow/cwl/OpenPepXL.cwl +++ /dev/null @@ -1,170 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenPepXL -doc: Protein-protein cross-linking identification using labeled linkers. -inputs: - in: - doc: Input file containing the spectra. - type: File - consensus: - doc: Input file containing the linked mass peaks. - type: File - database: - doc: Input file containing the protein database. - type: File - decoy_database: - doc: Input file containing the decoy protein database. Decoys can also be included in the normal database file instead (or additionally). - type: File? - decoy_string: - doc: String that was appended (or prefixed - see 'prefix' flag below) to the accessions in the protein database to indicate decoy proteins. - type: string? - decoy_prefix: - doc: Set to true, if the decoy_string is a prefix of accessions in the protein database. Otherwise it is a suffix. - type: string? - out_idXML: - doc: Results in idXML format (at least one of these output parameters should be set, otherwise you will not have any results) - type: string? - out_mzIdentML: - doc: Results in mzIdentML (.mzid) format (at least one of these output parameters should be set, otherwise you will not have any results) - type: string? - out_xquestxml: - doc: Results in the xquest.xml format (at least one of these output parameters should be set, otherwise you will not have any results). - type: string? - out_xquest_specxml: - doc: Matched spectra in the xQuest .spec.xml format for spectra visualization in the xQuest results manager. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - precursor__mass_tolerance: - doc: Width of precursor mass tolerance window - type: double? - precursor__mass_tolerance_unit: - doc: Unit of precursor mass tolerance. - type: string? - precursor__min_charge: - doc: Minimum precursor charge to be considered. - type: long? - precursor__max_charge: - doc: Maximum precursor charge to be considered. - type: long? - precursor__corrections: - doc: Monoisotopic peak correction. Matches candidates for possible monoisotopic precursor peaks for experimental mass m and given numbers n at masses (m - n * (C13-C12)). These should be ordered from more extreme to less extreme corrections. Numbers later in the list will be preferred in case of ambiguities. - type: long[]? - fragment__mass_tolerance: - doc: Fragment mass tolerance - type: double? - fragment__mass_tolerance_xlinks: - doc: Fragment mass tolerance for cross-link ions - type: double? - fragment__mass_tolerance_unit: - doc: Unit of fragment m - type: string? - modifications__fixed: - doc: Fixed modifications, specified using UniMod (www.unimod.org) terms, e.g. 'Carbamidomethyl (C)' - type: string[]? - modifications__variable: - doc: Variable modifications, specified using UniMod (www.unimod.org) terms, e.g. 'Oxidation (M)' - type: string[]? - modifications__variable_max_per_peptide: - doc: Maximum number of residues carrying a variable modification per candidate peptide - type: long? - peptide__min_size: - doc: Minimum size a peptide must have after digestion to be considered in the search. - type: long? - peptide__missed_cleavages: - doc: Number of missed cleavages. - type: long? - peptide__enzyme: - doc: The enzyme used for peptide digestion. - type: string? - cross_linker__residue1: - doc: Comma separated residues, that the first side of a bifunctional cross-linker can attach to - type: string[]? - cross_linker__residue2: - doc: Comma separated residues, that the second side of a bifunctional cross-linker can attach to - type: string[]? - cross_linker__mass_light: - doc: Mass of the light cross-linker, linking two residues on one or two peptides - type: double? - cross_linker__mass_iso_shift: - doc: Mass of the isotopic shift between the light and heavy linkers - type: double? - cross_linker__mass_mono_link: - doc: Possible masses of the linker, when attached to only one peptide - type: double[]? - cross_linker__name: - doc: Name of the searched cross-link, used to resolve ambiguity of equal masses (e.g. DSS or BS3) - type: string? - algorithm__number_top_hits: - doc: Number of top hits reported for each spectrum pair - type: long? - algorithm__deisotope: - doc: Set to true, if the input spectra should be deisotoped before any other processing steps. If set to auto the spectra will be deisotoped, if the fragment mass tolerance is < 0.1 Da or < 100 ppm (0.1 Da at a mass of 1000) - type: string? - ions__b_ions: - doc: Search for peaks of b-ions. - type: string? - ions__y_ions: - doc: Search for peaks of y-ions. - type: string? - ions__a_ions: - doc: Search for peaks of a-ions. - type: boolean? - ions__x_ions: - doc: Search for peaks of x-ions. - type: boolean? - ions__c_ions: - doc: Search for peaks of c-ions. - type: boolean? - ions__z_ions: - doc: Search for peaks of z-ions. - type: boolean? - ions__neutral_losses: - doc: Search for neutral losses of H2O and H3N. - type: string? -outputs: - out_idXML: - type: File? - outputBinding: - glob: $(inputs.out_idXML) - out_mzIdentML: - type: File? - outputBinding: - glob: $(inputs.out_mzIdentML) - out_xquestxml: - type: File? - outputBinding: - glob: $(inputs.out_xquestxml) - out_xquest_specxml: - type: File? - outputBinding: - glob: $(inputs.out_xquest_specxml) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenPepXL -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenPepXLLF.cwl b/workflow/cwl/OpenPepXLLF.cwl deleted file mode 100644 index 9017adcc479..00000000000 --- a/workflow/cwl/OpenPepXLLF.cwl +++ /dev/null @@ -1,170 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenPepXLLF -doc: Protein-protein cross linking with label-free linkers. -inputs: - in: - doc: Input file containing the spectra. - type: File - database: - doc: Input file containing the protein database. - type: File - decoy_database: - doc: Input file containing the decoy protein database. Decoys can also be included in the normal database file instead (or additionally). - type: File? - decoy_string: - doc: String that was appended (or prefixed - see 'prefix' flag below) to the accessions in the protein database to indicate decoy proteins. - type: string? - decoy_prefix: - doc: Set to true, if the decoy_string is a prefix of accessions in the protein database. Otherwise it is a suffix. - type: string? - out_idXML: - doc: Results in idXML format (at least one of these output parameters should be set, otherwise you will not have any results). - type: string? - out_mzIdentML: - doc: Results in mzIdentML (.mzid) format (at least one of these output parameters should be set, otherwise you will not have any results) - type: string? - out_xquestxml: - doc: Results in the xquest.xml format (at least one of these output parameters should be set, otherwise you will not have any results). - type: string? - out_xquest_specxml: - doc: Matched spectra in the xQuest .spec.xml format for spectra visualization in the xQuest results manager. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - precursor__mass_tolerance: - doc: Width of precursor mass tolerance window - type: double? - precursor__mass_tolerance_unit: - doc: Unit of precursor mass tolerance. - type: string? - precursor__min_charge: - doc: Minimum precursor charge to be considered. - type: long? - precursor__max_charge: - doc: Maximum precursor charge to be considered. - type: long? - precursor__corrections: - doc: Monoisotopic peak correction. Matches candidates for possible monoisotopic precursor peaks for experimental mass m and given numbers n at masses (m - n * (C13-C12)). These should be ordered from more extreme to less extreme corrections. Numbers later in the list will be preferred in case of ambiguities. - type: long[]? - fragment__mass_tolerance: - doc: Fragment mass tolerance - type: double? - fragment__mass_tolerance_xlinks: - doc: Fragment mass tolerance for cross-link ions - type: double? - fragment__mass_tolerance_unit: - doc: Unit of fragment m - type: string? - modifications__fixed: - doc: Fixed modifications, specified using UniMod (www.unimod.org) terms, e.g. 'Carbamidomethyl (C)' - type: string[]? - modifications__variable: - doc: Variable modifications, specified using UniMod (www.unimod.org) terms, e.g. 'Oxidation (M)' - type: string[]? - modifications__variable_max_per_peptide: - doc: Maximum number of residues carrying a variable modification per candidate peptide - type: long? - peptide__min_size: - doc: Minimum size a peptide must have after digestion to be considered in the search. - type: long? - peptide__missed_cleavages: - doc: Number of missed cleavages. - type: long? - peptide__enzyme: - doc: The enzyme used for peptide digestion. - type: string? - cross_linker__residue1: - doc: Comma separated residues, that the first side of a bifunctional cross-linker can attach to - type: string[]? - cross_linker__residue2: - doc: Comma separated residues, that the second side of a bifunctional cross-linker can attach to - type: string[]? - cross_linker__mass: - doc: Mass of the light cross-linker, linking two residues on one or two peptides - type: double? - cross_linker__mass_mono_link: - doc: Possible masses of the linker, when attached to only one peptide - type: double[]? - cross_linker__name: - doc: Name of the searched cross-link, used to resolve ambiguity of equal masses (e.g. DSS or BS3) - type: string? - algorithm__number_top_hits: - doc: Number of top hits reported for each spectrum pair - type: long? - algorithm__deisotope: - doc: Set to true, if the input spectra should be deisotoped before any other processing steps. If set to auto the spectra will be deisotoped, if the fragment mass tolerance is < 0.1 Da or < 100 ppm (0.1 Da at a mass of 1000) - type: string? - algorithm__use_sequence_tags: - doc: Use sequence tags (de novo sequencing of short fragments) to filter out candidates before scoring. This will make the search faster, but can impact the sensitivity positively or negatively, depending on the dataset. - type: boolean? - algorithm__sequence_tag_min_length: - doc: Minimal length of sequence tags to use for filtering candidates. Longer tags will make the search faster but much less sensitive. Ignored if 'algorithm:use_sequence_tags' is false. - type: long? - ions__b_ions: - doc: Search for peaks of b-ions. - type: string? - ions__y_ions: - doc: Search for peaks of y-ions. - type: string? - ions__a_ions: - doc: Search for peaks of a-ions. - type: boolean? - ions__x_ions: - doc: Search for peaks of x-ions. - type: boolean? - ions__c_ions: - doc: Search for peaks of c-ions. - type: boolean? - ions__z_ions: - doc: Search for peaks of z-ions. - type: boolean? - ions__neutral_losses: - doc: Search for neutral losses of H2O and H3N. - type: string? -outputs: - out_idXML: - type: File? - outputBinding: - glob: $(inputs.out_idXML) - out_mzIdentML: - type: File? - outputBinding: - glob: $(inputs.out_mzIdentML) - out_xquestxml: - type: File? - outputBinding: - glob: $(inputs.out_xquestxml) - out_xquest_specxml: - type: File? - outputBinding: - glob: $(inputs.out_xquest_specxml) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenPepXLLF -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenSwathAnalyzer.cwl b/workflow/cwl/OpenSwathAnalyzer.cwl deleted file mode 100644 index 615ae32bd29..00000000000 --- a/workflow/cwl/OpenSwathAnalyzer.cwl +++ /dev/null @@ -1,299 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenSwathAnalyzer -doc: Picks peaks and finds features in an SWATH-MS or SRM experiment. -inputs: - in: - doc: input file containing the chromatograms. - type: File - tr: - doc: transition file - type: File - rt_norm: - doc: RT normalization file (how to map the RTs of this run to the ones stored in the library) - type: File? - out: - doc: output file - type: string - no-strict: - doc: run in non-strict mode and allow some chromatograms to not be mapped. - type: boolean? - swath_files: - doc: "[applies only if you have full MS2 spectra maps] Swath files that were used to extract the transitions. If present, SWATH specific scoring will be used." - type: File[]? - min_upper_edge_dist: - doc: "[applies only if you have full MS2 spectra maps] Minimal distance to the edge to still consider a precursor, in Thomson (only in SWATH)" - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - model__type: - doc: Type of model - type: string? - model__symmetric_regression: - doc: "Only for 'linear' model: Perform linear regression on 'y - x' vs. 'y + x', instead of on 'y' vs. 'x'." - type: boolean? - algorithm__stop_report_after_feature: - doc: Stop reporting after feature (ordered by quality; -1 means do not stop). - type: long? - algorithm__rt_extraction_window: - doc: Only extract RT around this value (-1 means extract over the whole range, a value of 500 means to extract around +/- 500 s of the expected elution). For this to work, the TraML input file needs to contain normalized RT values. - type: double? - algorithm__rt_normalization_factor: - doc: The normalized RT is expected to be between 0 and 1. If your normalized RT has a different range, pass this here (e.g. it goes from 0 to 100, set this value to 100) - type: double? - algorithm__quantification_cutoff: - doc: Cutoff in m/z below which peaks should not be used for quantification any more - type: double? - algorithm__write_convex_hull: - doc: Whether to write out all points of all features into the featureXML - type: boolean? - algorithm__spectrum_addition_method: - doc: For spectrum addition, either use simple concatenation or use peak resampling - type: string? - algorithm__add_up_spectra: - doc: Add up spectra around the peak apex (needs to be a non-even integer) - type: long? - algorithm__spacing_for_spectra_resampling: - doc: If spectra are to be added, use this spacing to add them up - type: double? - algorithm__uis_threshold_sn: - doc: S/N threshold to consider identification transition (set to -1 to consider all) - type: long? - algorithm__uis_threshold_peak_area: - doc: Peak area threshold to consider identification transition (set to -1 to consider all) - type: long? - algorithm__scoring_model: - doc: Scoring model to use - type: string? - algorithm__im_extra_drift: - doc: Extra drift time to extract for IM scoring (as a fraction, e.g. 0.25 means 25% extra on each side) - type: double? - algorithm__strict: - doc: Whether to error (true) or skip (false) if a transition in a transition group does not have a corresponding chromatogram. - type: string? - algorithm__use_ms1_ion_mobility: - doc: Performs ion mobility extraction in MS1. Set to false if MS1 spectra do not contain ion mobility - type: string? - algorithm__TransitionGroupPicker__stop_after_feature: - doc: Stop finding after feature (ordered by intensity; -1 means do not stop). - type: long? - algorithm__TransitionGroupPicker__stop_after_intensity_ratio: - doc: Stop after reaching intensity ratio - type: double? - algorithm__TransitionGroupPicker__min_peak_width: - doc: Minimal peak width (s), discard all peaks below this value (-1 means no action). - type: double? - algorithm__TransitionGroupPicker__peak_integration: - doc: Calculate the peak area and height either the smoothed or the raw chromatogram data. - type: string? - algorithm__TransitionGroupPicker__background_subtraction: - doc: "Remove background from peak signal using estimated noise levels. The 'original' method is only provided for historical purposes, please use the 'exact' method and set parameters using the PeakIntegrator: settings. The same original or smoothed chromatogram specified by peak_integration will be used for background estimation." - type: string? - algorithm__TransitionGroupPicker__recalculate_peaks: - doc: Tries to get better peak picking by looking at peak consistency of all picked peaks. Tries to use the consensus (median) peak border if the variation within the picked peaks is too large. - type: boolean? - algorithm__TransitionGroupPicker__use_precursors: - doc: Use precursor chromatogram for peak picking (note that this may lead to precursor signal driving the peak picking) - type: boolean? - algorithm__TransitionGroupPicker__use_consensus: - doc: Use consensus peak boundaries when computing transition group picking (if false, compute independent peak boundaries for each transition) - type: string? - algorithm__TransitionGroupPicker__recalculate_peaks_max_z: - doc: Determines the maximal Z-Score (difference measured in standard deviations) that is considered too large for peak boundaries. If the Z-Score is above this value, the median is used for peak boundaries (default value 1.0). - type: double? - algorithm__TransitionGroupPicker__minimal_quality: - doc: Only if compute_peak_quality is set, this parameter will not consider peaks below this quality threshold - type: double? - algorithm__TransitionGroupPicker__resample_boundary: - doc: For computing peak quality, how many extra seconds should be sample left and right of the actual peak - type: double? - algorithm__TransitionGroupPicker__compute_peak_quality: - doc: Tries to compute a quality value for each peakgroup and detect outlier transitions. The resulting score is centered around zero and values above 0 are generally good and below -1 or -2 are usually bad. - type: boolean? - algorithm__TransitionGroupPicker__compute_peak_shape_metrics: - doc: Calculates various peak shape metrics (e.g., tailing) that can be used for downstream QC/QA. - type: boolean? - algorithm__TransitionGroupPicker__compute_total_mi: - doc: Compute mutual information metrics for individual transitions that can be used for OpenSWATH/IPF scoring. - type: boolean? - algorithm__TransitionGroupPicker__boundary_selection_method: - doc: Method to use when selecting the best boundaries for peaks. - type: string? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__sgolay_frame_length: - doc: "The number of subsequent data points used for smoothing.\nThis number has to be uneven. If it is not, 1 will be added." - type: long? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__sgolay_polynomial_order: - doc: Order of the polynomial that is fitted. - type: long? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__gauss_width: - doc: Gaussian width in seconds, estimated peak size. - type: double? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__use_gauss: - doc: Use Gaussian filter for smoothing (alternative is Savitzky-Golay filter) - type: string? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__peak_width: - doc: Force a certain minimal peak_width on the data (e.g. extend the peak at least by this amount on both sides) in seconds. -1 turns this feature off. - type: double? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__signal_to_noise: - doc: Signal-to-noise threshold at which a peak will not be extended any more. Note that setting this too high (e.g. 1.0) can lead to peaks whose flanks are not fully captured. - type: double? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__sn_win_len: - doc: Signal to noise window length. - type: double? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__sn_bin_count: - doc: Signal to noise bin count. - type: long? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__write_sn_log_messages: - doc: Write out log messages of the signal-to-noise estimator in case of sparse windows or median in rightmost histogram bin - type: boolean? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__remove_overlapping_peaks: - doc: Try to remove overlapping peaks during peak picking - type: string? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__method: - doc: Which method to choose for chromatographic peak-picking (OpenSWATH legacy on raw data, corrected picking on smoothed chromatogram or Crawdad on smoothed chromatogram). - type: string? - algorithm__TransitionGroupPicker__PeakIntegrator__integration_type: - doc: The integration technique to use in integratePeak() and estimateBackground() which uses either the summed intensity, integration by Simpson's rule or trapezoidal integration. - type: string? - algorithm__TransitionGroupPicker__PeakIntegrator__baseline_type: - doc: The baseline type to use in estimateBackground() based on the peak boundaries. A rectangular baseline shape is computed based either on the minimal intensity of the peak boundaries, the maximum intensity or the average intensity (base_to_base). - type: string? - algorithm__TransitionGroupPicker__PeakIntegrator__fit_EMG: - doc: Fit the chromatogram/spectrum to the EMG peak model. - type: string? - algorithm__DIAScoring__dia_extraction_window: - doc: DIA extraction window in Th or ppm. - type: double? - algorithm__DIAScoring__dia_extraction_unit: - doc: DIA extraction window unit - type: string? - algorithm__DIAScoring__dia_centroided: - doc: Use centroided DIA data. - type: boolean? - algorithm__DIAScoring__dia_byseries_intensity_min: - doc: DIA b/y series minimum intensity to consider. - type: double? - algorithm__DIAScoring__dia_byseries_ppm_diff: - doc: DIA b/y series minimal difference in ppm to consider. - type: double? - algorithm__DIAScoring__dia_nr_isotopes: - doc: DIA number of isotopes to consider. - type: long? - algorithm__DIAScoring__dia_nr_charges: - doc: DIA number of charges to consider. - type: long? - algorithm__DIAScoring__peak_before_mono_max_ppm_diff: - doc: DIA maximal difference in ppm to count a peak at lower m/z when searching for evidence that a peak might not be monoisotopic. - type: double? - algorithm__EMGScoring__interpolation_step: - doc: Sampling rate for the interpolation of the model function. - type: double? - algorithm__EMGScoring__tolerance_stdev_bounding_box: - doc: Bounding box has range [minimim of data, maximum of data] enlarged by tolerance_stdev_bounding_box times the standard deviation of the data. - type: double? - algorithm__EMGScoring__max_iteration: - doc: Maximum number of iterations using by Levenberg-Marquardt algorithm. - type: long? - algorithm__EMGScoring__init_mom: - doc: Initialize parameters using method of moments estimators. - type: boolean? - algorithm__EMGScoring__statistics__mean: - doc: Centroid position of the model. - type: double? - algorithm__EMGScoring__statistics__variance: - doc: Variance of the model. - type: double? - algorithm__Scores__use_shape_score: - doc: Use the shape score (this score measures the similarity in shape of the transitions using a cross-correlation) - type: string? - algorithm__Scores__use_coelution_score: - doc: Use the coelution score (this score measures the similarity in coelution of the transitions using a cross-correlation) - type: string? - algorithm__Scores__use_rt_score: - doc: Use the retention time score (this score measure the difference in retention time) - type: string? - algorithm__Scores__use_library_score: - doc: Use the library score - type: string? - algorithm__Scores__use_elution_model_score: - doc: Use the elution model (EMG) score (this score fits a gaussian model to the peak and checks the fit) - type: string? - algorithm__Scores__use_intensity_score: - doc: Use the intensity score - type: string? - algorithm__Scores__use_nr_peaks_score: - doc: Use the number of peaks score - type: string? - algorithm__Scores__use_total_xic_score: - doc: Use the total XIC score - type: string? - algorithm__Scores__use_total_mi_score: - doc: Use the total MI score - type: boolean? - algorithm__Scores__use_sn_score: - doc: Use the SN (signal to noise) score - type: string? - algorithm__Scores__use_mi_score: - doc: Use the MI (mutual information) score - type: boolean? - algorithm__Scores__use_dia_scores: - doc: Use the DIA (SWATH) scores. If turned off, will not use fragment ion spectra for scoring. - type: string? - algorithm__Scores__use_ms1_correlation: - doc: Use the correlation scores with the MS1 elution profiles - type: boolean? - algorithm__Scores__use_sonar_scores: - doc: Use the scores for SONAR scans (scanning swath) - type: boolean? - algorithm__Scores__use_ion_mobility_scores: - doc: Use the scores for Ion Mobility scans - type: boolean? - algorithm__Scores__use_ms1_fullscan: - doc: Use the full MS1 scan at the peak apex for scoring (ppm accuracy of precursor and isotopic pattern) - type: boolean? - algorithm__Scores__use_ms1_mi: - doc: Use the MS1 MI score - type: boolean? - algorithm__Scores__use_uis_scores: - doc: Use UIS scores for peptidoform identification - type: boolean? - algorithm__Scores__use_ionseries_scores: - doc: Use MS2-level b/y ion-series scores for peptidoform identification - type: string? - algorithm__Scores__use_ms2_isotope_scores: - doc: "Use MS2-level isotope scores (pearson & manhattan) across product transitions (based on ID if annotated or averagine)" - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenSwathAnalyzer -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenSwathAssayGenerator.cwl b/workflow/cwl/OpenSwathAssayGenerator.cwl deleted file mode 100644 index 01fa722ae07..00000000000 --- a/workflow/cwl/OpenSwathAssayGenerator.cwl +++ /dev/null @@ -1,113 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenSwathAssayGenerator -doc: Generates assays according to different models for a specific TraML -inputs: - in: - doc: Input file - type: File - in_type: - doc: "Input file type -- default: determined from file extension or content\n" - type: string? - out: - doc: Output file - type: string - out_type: - doc: "Output file type -- default: determined from file extension or content\n" - type: string? - min_transitions: - doc: minimal number of transitions - type: long? - max_transitions: - doc: maximal number of transitions - type: long? - allowed_fragment_types: - doc: allowed fragment types - type: string? - allowed_fragment_charges: - doc: allowed fragment charge states - type: string? - enable_detection_specific_losses: - doc: set this flag if specific neutral losses for detection fragment ions should be allowed - type: boolean? - enable_detection_unspecific_losses: - doc: set this flag if unspecific neutral losses (H2O1, H3N1, C1H2N2, C1H2N1O1) for detection fragment ions should be allowed - type: boolean? - precursor_mz_threshold: - doc: MZ threshold in Thomson for precursor ion selection - type: double? - precursor_lower_mz_limit: - doc: lower MZ limit for precursor ions - type: double? - precursor_upper_mz_limit: - doc: upper MZ limit for precursor ions - type: double? - product_mz_threshold: - doc: MZ threshold in Thomson for fragment ion annotation - type: double? - product_lower_mz_limit: - doc: lower MZ limit for fragment ions - type: double? - product_upper_mz_limit: - doc: upper MZ limit for fragment ions - type: double? - swath_windows_file: - doc: "Tab separated file containing the SWATH windows for exclusion of fragment ions falling into the precursor isolation window: lower_offset upper_offset \\newline 400 425 \\newline ... Note that the first line is a header and will be skipped." - type: File? - unimod_file: - doc: (Modified) Unimod XML file (http://www.unimod.org/xml/unimod.xml) describing residue modifiability - type: File? - enable_ipf: - doc: "IPF: set this flag if identification transitions should be generated for IPF. Note: Requires setting 'unimod_file'." - type: boolean? - max_num_alternative_localizations: - doc: "IPF: maximum number of site-localization permutations" - type: long? - disable_identification_ms2_precursors: - doc: "IPF: set this flag if MS2-level precursor ions for identification should not be allowed for extraction of the precursor signal from the fragment ion data (MS2-level)." - type: boolean? - disable_identification_specific_losses: - doc: "IPF: set this flag if specific neutral losses for identification fragment ions should not be allowed" - type: boolean? - enable_identification_unspecific_losses: - doc: "IPF: set this flag if unspecific neutral losses (H2O1, H3N1, C1H2N2, C1H2N1O1) for identification fragment ions should be allowed" - type: boolean? - enable_swath_specifity: - doc: "IPF: set this flag if identification transitions without precursor specificity (i.e. across whole precursor isolation window instead of precursor MZ) should be generated." - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenSwathAssayGenerator -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenSwathChromatogramExtractor.cwl b/workflow/cwl/OpenSwathChromatogramExtractor.cwl deleted file mode 100644 index 887b3a11089..00000000000 --- a/workflow/cwl/OpenSwathChromatogramExtractor.cwl +++ /dev/null @@ -1,83 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenSwathChromatogramExtractor -doc: Extract chromatograms (XIC) from a MS2 map file. -inputs: - in: - doc: Input files separated by blank - type: File[] - tr: - doc: transition file ('TraML' or 'csv') - type: File - rt_norm: - doc: RT normalization file (how to map the RTs of this run to the ones stored in the library) - type: File? - out: - doc: output file - type: string - min_upper_edge_dist: - doc: Minimal distance to the edge to still consider a precursor, in Thomson - type: double? - rt_window: - doc: Extraction window in RT dimension (-1 means extract over the whole range). This is the full window size, e.g. a value of 1000 seconds would extract 500 seconds on either side. - type: double? - ion_mobility_window: - doc: Extraction window in ion mobility dimension (in milliseconds). This is the full window size, e.g. a value of 10 milliseconds would extract 5 milliseconds on either side. - type: double? - mz_window: - doc: Extraction window in m/z dimension (in Thomson, to use ppm see -ppm flag). This is the full window size, e.g. 100 ppm would extract 50 ppm on either side. - type: double? - ppm: - doc: m/z extraction_window is in ppm - type: boolean? - is_swath: - doc: Set this flag if the data is SWATH data - type: boolean? - extract_MS1: - doc: Extract the MS1 transitions based on the precursor values in the TraML file (useful for extracting MS1 XIC) - type: boolean? - extraction_function: - doc: Function used to extract the signal - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - model__type: - doc: Type of model - type: string? - model__symmetric_regression: - doc: "Only for 'linear' model: Perform linear regression on 'y - x' vs. 'y + x', instead of on 'y' vs. 'x'." - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenSwathChromatogramExtractor -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenSwathConfidenceScoring.cwl b/workflow/cwl/OpenSwathConfidenceScoring.cwl deleted file mode 100644 index 57409d55409..00000000000 --- a/workflow/cwl/OpenSwathConfidenceScoring.cwl +++ /dev/null @@ -1,68 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenSwathConfidenceScoring -doc: Compute confidence scores for OpenSwath results -inputs: - in: - doc: Input file (OpenSwath results) - type: File - lib: - doc: Assay library - type: File - out: - doc: Output file (results with confidence scores) - type: string - trafo: - doc: Retention time transformation - type: File? - decoys: - doc: Number of decoy assays to select from the library for every true assay (0 for "all") - type: long? - transitions: - doc: Number of transitions per feature to consider (highest intensities first; 0 for "all") - type: long? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - GLM__intercept: - doc: Intercept term - type: double? - GLM__delta_rt: - doc: Coefficient of retention time difference - type: double? - GLM__dist_int: - doc: Coefficient of intensity distance - type: double? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenSwathConfidenceScoring -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenSwathDIAPreScoring.cwl b/workflow/cwl/OpenSwathDIAPreScoring.cwl deleted file mode 100644 index 13b8fd0a796..00000000000 --- a/workflow/cwl/OpenSwathDIAPreScoring.cwl +++ /dev/null @@ -1,47 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenSwathDIAPreScoring -doc: Scoring spectra using the DIA scores. -inputs: - tr: - doc: transition file - type: File - swath_files: - doc: Swath files that were used to extract the transitions. If present, SWATH specific scoring will be applied. - type: File[] - min_upper_edge_dist: - doc: Minimal distance to the edge to still consider a precursor, in Thomson (only in SWATH) - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - [] -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenSwathDIAPreScoring -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenSwathDecoyGenerator.cwl b/workflow/cwl/OpenSwathDecoyGenerator.cwl deleted file mode 100644 index 06b2bc97dd2..00000000000 --- a/workflow/cwl/OpenSwathDecoyGenerator.cwl +++ /dev/null @@ -1,98 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenSwathDecoyGenerator -doc: Generates decoys according to different models for a specific TraML -inputs: - in: - doc: Input file - type: File - in_type: - doc: "Input file type -- default: determined from file extension or content\n" - type: string? - out: - doc: Output file - type: string - out_type: - doc: "Output file type -- default: determined from file extension or content\n" - type: string? - method: - doc: Decoy generation method - type: string? - decoy_tag: - doc: decoy tag - type: string? - min_decoy_fraction: - doc: Minimum fraction of decoy / target peptides and proteins - type: double? - aim_decoy_fraction: - doc: Number of decoys the algorithm should generate (if unequal to 1, the algorithm will randomly select N peptides for decoy generation) - type: double? - shuffle_max_attempts: - doc: "shuffle: maximum attempts to lower the amino acid sequence identity between target and decoy for the shuffle algorithm" - type: long? - shuffle_sequence_identity_threshold: - doc: "shuffle: target-decoy amino acid sequence identity threshold for the shuffle algorithm" - type: double? - shift_precursor_mz_shift: - doc: "shift: precursor ion MZ shift in Thomson for shift decoy method" - type: double? - shift_product_mz_shift: - doc: "shift: fragment ion MZ shift in Thomson for shift decoy method" - type: double? - product_mz_threshold: - doc: MZ threshold in Thomson for fragment ion annotation - type: double? - allowed_fragment_types: - doc: allowed fragment types - type: string? - allowed_fragment_charges: - doc: allowed fragment charge states - type: string? - enable_detection_specific_losses: - doc: set this flag if specific neutral losses for detection fragment ions should be allowed - type: boolean? - enable_detection_unspecific_losses: - doc: set this flag if unspecific neutral losses (H2O1, H3N1, C1H2N2, C1H2N1O1) for detection fragment ions should be allowed - type: boolean? - switchKR: - doc: Whether to switch terminal K and R (to achieve different precursor mass) - type: string? - separate: - doc: set this flag if decoys should not be appended to targets. - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenSwathDecoyGenerator -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenSwathFeatureXMLToTSV.cwl b/workflow/cwl/OpenSwathFeatureXMLToTSV.cwl deleted file mode 100644 index 16244987ae4..00000000000 --- a/workflow/cwl/OpenSwathFeatureXMLToTSV.cwl +++ /dev/null @@ -1,56 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenSwathFeatureXMLToTSV -doc: Converts a featureXML to a mProphet tsv. -inputs: - in: - doc: Input files separated by blank - type: File[] - tr: - doc: TraML transition file - type: File - out: - doc: tsv output file (mProphet compatible) - type: string - short_format: - doc: Whether to write short (one peptide per line) or long format (one transition per line). - type: boolean? - best_scoring_peptide: - doc: If only the best scoring feature per peptide should be printed, give the variable name - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenSwathFeatureXMLToTSV -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenSwathFileSplitter.cwl b/workflow/cwl/OpenSwathFileSplitter.cwl deleted file mode 100644 index 1c6f2a016c3..00000000000 --- a/workflow/cwl/OpenSwathFileSplitter.cwl +++ /dev/null @@ -1,54 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenSwathFileSplitter -doc: Splits SWATH files into n files, each containing one window. -inputs: - in: - doc: Input file (SWATH/DIA file) - type: File - outputDirectory: - doc: Output file prefix - type: string? - out_qc: - doc: Optional QC meta data (charge distribution in MS1). Only works with mzML input files. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - outputDirectory: - type: File? - outputBinding: - glob: $(inputs.outputDirectory)* - out_qc: - type: File? - outputBinding: - glob: $(inputs.out_qc) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenSwathFileSplitter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenSwathMzMLFileCacher.cwl b/workflow/cwl/OpenSwathMzMLFileCacher.cwl deleted file mode 100644 index 95e063fabe1..00000000000 --- a/workflow/cwl/OpenSwathMzMLFileCacher.cwl +++ /dev/null @@ -1,71 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenSwathMzMLFileCacher -doc: Caches the spectra and chromatogram data of an mzML to disk. -inputs: - in: - doc: Input mzML file - type: File - in_type: - doc: "input file type -- default: determined from file extension or content\n" - type: string? - out: - doc: Output file - type: string - out_type: - doc: "Output file type -- default: determined from file extension or content\nNote: that not all conversion paths work or make sense." - type: string? - convert_back: - doc: Convert back to mzML - type: boolean? - lossy_compression: - doc: "Use numpress compression to achieve optimally small file size (attention: may cause small loss of precision; only for mzML data)." - type: string? - full_meta: - doc: Write full meta information into sqMass file (may require large amounts of memory) - type: string? - lossy_mass_accuracy: - doc: Desired (absolute) m/z accuracy for lossy compression (e.g. use 0.0001 for a mass accuracy of 0.2 ppm at 500 m/z, default uses -1.0 for maximal accuracy). - type: double? - process_lowmemory: - doc: "Whether to process the file on the fly without loading the whole file into memory first (only for conversions of mzXML/mzML to mzML).\nNote: this flag will prevent conversion from spectra to chromatograms." - type: boolean? - lowmem_batchsize: - doc: The batch size of the low memory conversion - type: long? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenSwathMzMLFileCacher -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenSwathRTNormalizer.cwl b/workflow/cwl/OpenSwathRTNormalizer.cwl deleted file mode 100644 index 51706994abb..00000000000 --- a/workflow/cwl/OpenSwathRTNormalizer.cwl +++ /dev/null @@ -1,323 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenSwathRTNormalizer -doc: Generate a transformation file on how to transform the RT space into the normalized space given a description of RT peptides and their normalized retention time. -inputs: - in: - doc: Input files separated by blank - type: File[] - tr: - doc: transition file with the RT peptides ('TraML' or 'csv') - type: File - out: - doc: output file - type: string - rt_norm: - doc: RT normalization file (how to map the RTs of this run to the ones stored in the library) - type: File? - min_rsq: - doc: Minimum r-squared of RT peptides regression - type: double? - min_coverage: - doc: Minimum relative amount of RT peptides to keep - type: double? - estimateBestPeptides: - doc: Whether the algorithms should try to choose the best peptides based on their peak shape for normalization. Use this option you do not expect all your peptides to be detected in a sample and too many 'bad' peptides enter the outlier removal step (e.g. due to them being endogenous peptides or using a less curated list of peptides). - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - RTNormalization__outlierMethod: - doc: "Which outlier detection method to use (valid: 'iter_residual', 'iter_jackknife', 'ransac', 'none'). Iterative methods remove one outlier at a time. Jackknife approach optimizes for maximum r-squared improvement while 'iter_residual' removes the datapoint with the largest residual error (removal by residual is computationally cheaper, use this with lots of peptides)." - type: string? - RTNormalization__useIterativeChauvenet: - doc: Whether to use Chauvenet's criterion when using iterative methods. This should be used if the algorithm removes too many datapoints but it may lead to true outliers being retained. - type: boolean? - RTNormalization__RANSACMaxIterations: - doc: Maximum iterations for the RANSAC outlier detection algorithm. - type: long? - RTNormalization__RANSACMaxPercentRTThreshold: - doc: Maximum threshold in RT dimension for the RANSAC outlier detection algorithm (in percent of the total gradient). Default is set to 3% which is around +/- 4 minutes on a 120 gradient. - type: long? - RTNormalization__RANSACSamplingSize: - doc: Sampling size of data points per iteration for the RANSAC outlier detection algorithm. - type: long? - algorithm__stop_report_after_feature: - doc: Stop reporting after feature (ordered by quality; -1 means do not stop). - type: long? - algorithm__rt_extraction_window: - doc: Only extract RT around this value (-1 means extract over the whole range, a value of 500 means to extract around +/- 500 s of the expected elution). For this to work, the TraML input file needs to contain normalized RT values. - type: double? - algorithm__rt_normalization_factor: - doc: The normalized RT is expected to be between 0 and 1. If your normalized RT has a different range, pass this here (e.g. it goes from 0 to 100, set this value to 100) - type: double? - algorithm__quantification_cutoff: - doc: Cutoff in m/z below which peaks should not be used for quantification any more - type: double? - algorithm__write_convex_hull: - doc: Whether to write out all points of all features into the featureXML - type: boolean? - algorithm__spectrum_addition_method: - doc: For spectrum addition, either use simple concatenation or use peak resampling - type: string? - algorithm__add_up_spectra: - doc: Add up spectra around the peak apex (needs to be a non-even integer) - type: long? - algorithm__spacing_for_spectra_resampling: - doc: If spectra are to be added, use this spacing to add them up - type: double? - algorithm__uis_threshold_sn: - doc: S/N threshold to consider identification transition (set to -1 to consider all) - type: long? - algorithm__uis_threshold_peak_area: - doc: Peak area threshold to consider identification transition (set to -1 to consider all) - type: long? - algorithm__scoring_model: - doc: Scoring model to use - type: string? - algorithm__im_extra_drift: - doc: Extra drift time to extract for IM scoring (as a fraction, e.g. 0.25 means 25% extra on each side) - type: double? - algorithm__strict: - doc: Whether to error (true) or skip (false) if a transition in a transition group does not have a corresponding chromatogram. - type: string? - algorithm__use_ms1_ion_mobility: - doc: Performs ion mobility extraction in MS1. Set to false if MS1 spectra do not contain ion mobility - type: string? - algorithm__TransitionGroupPicker__stop_after_feature: - doc: Stop finding after feature (ordered by intensity; -1 means do not stop). - type: long? - algorithm__TransitionGroupPicker__stop_after_intensity_ratio: - doc: Stop after reaching intensity ratio - type: double? - algorithm__TransitionGroupPicker__min_peak_width: - doc: Minimal peak width (s), discard all peaks below this value (-1 means no action). - type: double? - algorithm__TransitionGroupPicker__peak_integration: - doc: Calculate the peak area and height either the smoothed or the raw chromatogram data. - type: string? - algorithm__TransitionGroupPicker__background_subtraction: - doc: "Remove background from peak signal using estimated noise levels. The 'original' method is only provided for historical purposes, please use the 'exact' method and set parameters using the PeakIntegrator: settings. The same original or smoothed chromatogram specified by peak_integration will be used for background estimation." - type: string? - algorithm__TransitionGroupPicker__recalculate_peaks: - doc: Tries to get better peak picking by looking at peak consistency of all picked peaks. Tries to use the consensus (median) peak border if the variation within the picked peaks is too large. - type: boolean? - algorithm__TransitionGroupPicker__use_precursors: - doc: Use precursor chromatogram for peak picking (note that this may lead to precursor signal driving the peak picking) - type: boolean? - algorithm__TransitionGroupPicker__use_consensus: - doc: Use consensus peak boundaries when computing transition group picking (if false, compute independent peak boundaries for each transition) - type: string? - algorithm__TransitionGroupPicker__recalculate_peaks_max_z: - doc: Determines the maximal Z-Score (difference measured in standard deviations) that is considered too large for peak boundaries. If the Z-Score is above this value, the median is used for peak boundaries (default value 1.0). - type: double? - algorithm__TransitionGroupPicker__minimal_quality: - doc: Only if compute_peak_quality is set, this parameter will not consider peaks below this quality threshold - type: double? - algorithm__TransitionGroupPicker__resample_boundary: - doc: For computing peak quality, how many extra seconds should be sample left and right of the actual peak - type: double? - algorithm__TransitionGroupPicker__compute_peak_quality: - doc: Tries to compute a quality value for each peakgroup and detect outlier transitions. The resulting score is centered around zero and values above 0 are generally good and below -1 or -2 are usually bad. - type: boolean? - algorithm__TransitionGroupPicker__compute_peak_shape_metrics: - doc: Calculates various peak shape metrics (e.g., tailing) that can be used for downstream QC/QA. - type: boolean? - algorithm__TransitionGroupPicker__compute_total_mi: - doc: Compute mutual information metrics for individual transitions that can be used for OpenSWATH/IPF scoring. - type: boolean? - algorithm__TransitionGroupPicker__boundary_selection_method: - doc: Method to use when selecting the best boundaries for peaks. - type: string? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__sgolay_frame_length: - doc: "The number of subsequent data points used for smoothing.\nThis number has to be uneven. If it is not, 1 will be added." - type: long? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__sgolay_polynomial_order: - doc: Order of the polynomial that is fitted. - type: long? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__gauss_width: - doc: Gaussian width in seconds, estimated peak size. - type: double? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__use_gauss: - doc: Use Gaussian filter for smoothing (alternative is Savitzky-Golay filter) - type: string? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__peak_width: - doc: Force a certain minimal peak_width on the data (e.g. extend the peak at least by this amount on both sides) in seconds. -1 turns this feature off. - type: double? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__signal_to_noise: - doc: Signal-to-noise threshold at which a peak will not be extended any more. Note that setting this too high (e.g. 1.0) can lead to peaks whose flanks are not fully captured. - type: double? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__sn_win_len: - doc: Signal to noise window length. - type: double? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__sn_bin_count: - doc: Signal to noise bin count. - type: long? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__write_sn_log_messages: - doc: Write out log messages of the signal-to-noise estimator in case of sparse windows or median in rightmost histogram bin - type: boolean? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__remove_overlapping_peaks: - doc: Try to remove overlapping peaks during peak picking - type: string? - algorithm__TransitionGroupPicker__PeakPickerChromatogram__method: - doc: Which method to choose for chromatographic peak-picking (OpenSWATH legacy on raw data, corrected picking on smoothed chromatogram or Crawdad on smoothed chromatogram). - type: string? - algorithm__TransitionGroupPicker__PeakIntegrator__integration_type: - doc: The integration technique to use in integratePeak() and estimateBackground() which uses either the summed intensity, integration by Simpson's rule or trapezoidal integration. - type: string? - algorithm__TransitionGroupPicker__PeakIntegrator__baseline_type: - doc: The baseline type to use in estimateBackground() based on the peak boundaries. A rectangular baseline shape is computed based either on the minimal intensity of the peak boundaries, the maximum intensity or the average intensity (base_to_base). - type: string? - algorithm__TransitionGroupPicker__PeakIntegrator__fit_EMG: - doc: Fit the chromatogram/spectrum to the EMG peak model. - type: string? - algorithm__DIAScoring__dia_extraction_window: - doc: DIA extraction window in Th or ppm. - type: double? - algorithm__DIAScoring__dia_extraction_unit: - doc: DIA extraction window unit - type: string? - algorithm__DIAScoring__dia_centroided: - doc: Use centroided DIA data. - type: boolean? - algorithm__DIAScoring__dia_byseries_intensity_min: - doc: DIA b/y series minimum intensity to consider. - type: double? - algorithm__DIAScoring__dia_byseries_ppm_diff: - doc: DIA b/y series minimal difference in ppm to consider. - type: double? - algorithm__DIAScoring__dia_nr_isotopes: - doc: DIA number of isotopes to consider. - type: long? - algorithm__DIAScoring__dia_nr_charges: - doc: DIA number of charges to consider. - type: long? - algorithm__DIAScoring__peak_before_mono_max_ppm_diff: - doc: DIA maximal difference in ppm to count a peak at lower m/z when searching for evidence that a peak might not be monoisotopic. - type: double? - algorithm__EMGScoring__interpolation_step: - doc: Sampling rate for the interpolation of the model function. - type: double? - algorithm__EMGScoring__tolerance_stdev_bounding_box: - doc: Bounding box has range [minimim of data, maximum of data] enlarged by tolerance_stdev_bounding_box times the standard deviation of the data. - type: double? - algorithm__EMGScoring__max_iteration: - doc: Maximum number of iterations using by Levenberg-Marquardt algorithm. - type: long? - algorithm__EMGScoring__init_mom: - doc: Initialize parameters using method of moments estimators. - type: boolean? - algorithm__EMGScoring__statistics__mean: - doc: Centroid position of the model. - type: double? - algorithm__EMGScoring__statistics__variance: - doc: Variance of the model. - type: double? - algorithm__Scores__use_shape_score: - doc: Use the shape score (this score measures the similarity in shape of the transitions using a cross-correlation) - type: string? - algorithm__Scores__use_coelution_score: - doc: Use the coelution score (this score measures the similarity in coelution of the transitions using a cross-correlation) - type: string? - algorithm__Scores__use_rt_score: - doc: Use the retention time score (this score measure the difference in retention time) - type: string? - algorithm__Scores__use_library_score: - doc: Use the library score - type: string? - algorithm__Scores__use_elution_model_score: - doc: Use the elution model (EMG) score (this score fits a gaussian model to the peak and checks the fit) - type: string? - algorithm__Scores__use_intensity_score: - doc: Use the intensity score - type: string? - algorithm__Scores__use_nr_peaks_score: - doc: Use the number of peaks score - type: string? - algorithm__Scores__use_total_xic_score: - doc: Use the total XIC score - type: string? - algorithm__Scores__use_total_mi_score: - doc: Use the total MI score - type: boolean? - algorithm__Scores__use_sn_score: - doc: Use the SN (signal to noise) score - type: string? - algorithm__Scores__use_mi_score: - doc: Use the MI (mutual information) score - type: boolean? - algorithm__Scores__use_dia_scores: - doc: Use the DIA (SWATH) scores. If turned off, will not use fragment ion spectra for scoring. - type: string? - algorithm__Scores__use_ms1_correlation: - doc: Use the correlation scores with the MS1 elution profiles - type: boolean? - algorithm__Scores__use_sonar_scores: - doc: Use the scores for SONAR scans (scanning swath) - type: boolean? - algorithm__Scores__use_ion_mobility_scores: - doc: Use the scores for Ion Mobility scans - type: boolean? - algorithm__Scores__use_ms1_fullscan: - doc: Use the full MS1 scan at the peak apex for scoring (ppm accuracy of precursor and isotopic pattern) - type: boolean? - algorithm__Scores__use_ms1_mi: - doc: Use the MS1 MI score - type: boolean? - algorithm__Scores__use_uis_scores: - doc: Use UIS scores for peptidoform identification - type: boolean? - algorithm__Scores__use_ionseries_scores: - doc: Use MS2-level b/y ion-series scores for peptidoform identification - type: string? - algorithm__Scores__use_ms2_isotope_scores: - doc: "Use MS2-level isotope scores (pearson & manhattan) across product transitions (based on ID if annotated or averagine)" - type: string? - peptideEstimation__InitialQualityCutoff: - doc: The initial overall quality cutoff for a peak to be scored (range ca. -2 to 2) - type: double? - peptideEstimation__OverallQualityCutoff: - doc: The overall quality cutoff for a peak to go into the retention time estimation (range ca. 0 to 10) - type: double? - peptideEstimation__NrRTBins: - doc: Number of RT bins to use to compute coverage. This option should be used to ensure that there is a complete coverage of the RT space (this should detect cases where only a part of the RT gradient is actually covered by normalization peptides) - type: long? - peptideEstimation__MinPeptidesPerBin: - doc: Minimal number of peptides that are required for a bin to counted as 'covered' - type: long? - peptideEstimation__MinBinsFilled: - doc: Minimal number of bins required to be covered - type: long? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenSwathRTNormalizer -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenSwathRewriteToFeatureXML.cwl b/workflow/cwl/OpenSwathRewriteToFeatureXML.cwl deleted file mode 100644 index 750d8f6aab5..00000000000 --- a/workflow/cwl/OpenSwathRewriteToFeatureXML.cwl +++ /dev/null @@ -1,53 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenSwathRewriteToFeatureXML -doc: Combines featureXML and mProphet tsv to FDR filtered featureXML. -inputs: - csv: - doc: "mProphet tsv output file: \"all_peakgroups.xls\"" - type: File? - featureXML: - doc: input featureXML file - type: File - out: - doc: output featureXML file - type: string - FDR_cutoff: - doc: FDR cutoff (e.g. to remove all features with a an m_score above 0.05 use 0.05 here) - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenSwathRewriteToFeatureXML -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/OpenSwathWorkflow.cwl b/workflow/cwl/OpenSwathWorkflow.cwl deleted file mode 100644 index eb69f9b56de..00000000000 --- a/workflow/cwl/OpenSwathWorkflow.cwl +++ /dev/null @@ -1,464 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: OpenSwathWorkflow -doc: Complete workflow to run OpenSWATH -inputs: - in: - doc: Input files separated by blank - type: File[] - tr: - doc: transition file ('TraML','tsv','pqp') - type: File - tr_type: - doc: "input file type -- default: determined from file extension or content\n" - type: string? - tr_irt: - doc: transition file ('TraML') - type: File? - tr_irt_nonlinear: - doc: additional nonlinear transition file ('TraML') - type: File? - rt_norm: - doc: RT normalization file (how to map the RTs of this run to the ones stored in the library). If set, tr_irt may be omitted. - type: File? - swath_windows_file: - doc: "Optional, tab-separated file containing the SWATH windows for extraction: lower_offset upper_offset. Note that the first line is a header and will be skipped." - type: File? - sort_swath_maps: - doc: Sort input SWATH files when matching to SWATH windows from swath_windows_file - type: boolean? - enable_ms1: - doc: Extract the precursor ion trace(s) and use for scoring if present - type: string? - enable_ipf: - doc: Enable additional scoring of identification assays using IPF (see online documentation) - type: string? - out_features: - doc: output file - type: string? - out_tsv: - doc: TSV output file (mProphet-compatible TSV file) - type: string? - out_osw: - doc: OSW output file (PyProphet-compatible SQLite file) - type: string? - out_chrom: - doc: Also output all computed chromatograms output in mzML (chrom.mzML) or sqMass (SQLite format) - type: string? - out_qc: - doc: Optional QC meta data (charge distribution in MS1). Only works with mzML input files. - type: string? - min_upper_edge_dist: - doc: Minimal distance to the upper edge of a Swath window to still consider a precursor, in Thomson - type: double? - sonar: - doc: data is scanning SWATH data - type: boolean? - pasef: - doc: data is PASEF data - type: boolean? - rt_extraction_window: - doc: Only extract RT around this value (-1 means extract over the whole range, a value of 600 means to extract around +/- 300 s of the expected elution). - type: double? - extra_rt_extraction_window: - doc: Output an XIC with a RT-window by this much larger (e.g. to visually inspect a larger area of the chromatogram) - type: double? - ion_mobility_window: - doc: "Extraction window in ion mobility dimension (in 1/k0 or milliseconds depending on library). This is the full window size, e.g. a value of 10 milliseconds would extract 5 milliseconds on either side. -1 means extract over the whole range or ion mobility is not present. (Default for diaPASEF data: 0.06 1/k0)" - type: double? - mz_extraction_window: - doc: Extraction window in Thomson or ppm (see mz_extraction_window_unit) - type: double? - mz_extraction_window_unit: - doc: Unit for mz extraction - type: string? - mz_extraction_window_ms1: - doc: Extraction window used in MS1 in Thomson or ppm (see mz_extraction_window_ms1_unit) - type: double? - mz_extraction_window_ms1_unit: - doc: Unit of the MS1 m/z extraction window - type: string? - im_extraction_window_ms1: - doc: Extraction window in ion mobility dimension for MS1 (in 1/k0 or milliseconds depending on library). -1 means this is not ion mobility data. - type: double? - use_ms1_ion_mobility: - doc: Also perform precursor extraction using the same ion mobility window as for fragment ion extraction - type: string? - matching_window_only: - doc: Assume the input data is targeted / PRM-like data with potentially overlapping DIA windows. Will only attempt to extract each assay from the *best* matching DIA window (instead of all matching windows). - type: boolean? - irt_mz_extraction_window: - doc: Extraction window used for iRT and m/z correction in Thomson or ppm (see irt_mz_extraction_window_unit) - type: double? - irt_mz_extraction_window_unit: - doc: Unit for mz extraction - type: string? - irt_im_extraction_window: - doc: Ion mobility extraction window used for iRT (in 1/K0 or milliseconds depending on library). -1 means do not perform ion mobility calibration - type: double? - min_rsq: - doc: Minimum r-squared of RT peptides regression - type: double? - min_coverage: - doc: Minimum relative amount of RT peptides to keep - type: double? - split_file_input: - doc: "The input files each contain one single SWATH (alternatively: all SWATH are in separate files)" - type: boolean? - use_elution_model_score: - doc: Turn on elution model score (EMG fit to peak) - type: boolean? - readOptions: - doc: Whether to run OpenSWATH directly on the input data, cache data to disk first or to perform a datareduction step first. If you choose cache, make sure to also set tempDirectory - type: string? - mz_correction_function: - doc: Use the retention time normalization peptide MS2 masses to perform a mass correction (linear, weighted by intensity linear or quadratic) of all spectra. - type: string? - tempDirectory: - doc: Temporary directory to store cached files for example - type: string? - extraction_function: - doc: Function used to extract the signal - type: string? - batchSize: - doc: The batch size of chromatograms to process (0 means to only have one batch, sensible values are around 250-1000) - type: long? - outer_loop_threads: - doc: How many threads should be used for the outer loop (-1 use all threads, use 4 to analyze 4 SWATH windows in memory at once). - type: long? - ms1_isotopes: - doc: The number of MS1 isotopes used for extraction - type: long? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - Debugging__irt_mzml: - doc: Chromatogram mzML containing the iRT peptides - type: string? - Debugging__irt_trafo: - doc: Transformation file for RT transform - type: string? - Calibration__ms1_im_calibration: - doc: Whether to use MS1 precursor data for the ion mobility calibration (default = false, uses MS2 / fragment ions for calibration) - type: boolean? - Calibration__im_correction_function: - doc: Type of normalization function for IM calibration. - type: string? - Calibration__debug_im_file: - doc: Debug file for Ion Mobility calibration. - type: string? - Calibration__debug_mz_file: - doc: Debug file for m/z calibration. - type: string? - Library__retentionTimeInterpretation: - doc: How to interpret the provided retention time (the retention time column can either be interpreted to be in iRT, minutes or seconds) - type: string? - Library__override_group_label_check: - doc: Override an internal check that assures that all members of the same PeptideGroupLabel have the same PeptideSequence (this ensures that only different isotopic forms of the same peptide can be grouped together in the same label group). Only turn this off if you know what you are doing. - type: boolean? - Library__force_invalid_mods: - doc: Force reading even if invalid modifications are encountered (OpenMS may not recognize the modification) - type: boolean? - RTNormalization__alignmentMethod: - doc: "How to perform the alignment to the normalized RT space using anchor points. 'linear': perform linear regression (for few anchor points). 'interpolated': Interpolate between anchor points (for few, noise-free anchor points). 'lowess' Use local regression (for many, noisy anchor points). 'b_spline' use b splines for smoothing." - type: string? - RTNormalization__outlierMethod: - doc: "Which outlier detection method to use (valid: 'iter_residual', 'iter_jackknife', 'ransac', 'none'). Iterative methods remove one outlier at a time. Jackknife approach optimizes for maximum r-squared improvement while 'iter_residual' removes the datapoint with the largest residual error (removal by residual is computationally cheaper, use this with lots of peptides)." - type: string? - RTNormalization__useIterativeChauvenet: - doc: Whether to use Chauvenet's criterion when using iterative methods. This should be used if the algorithm removes too many datapoints but it may lead to true outliers being retained. - type: boolean? - RTNormalization__RANSACMaxIterations: - doc: Maximum iterations for the RANSAC outlier detection algorithm. - type: long? - RTNormalization__RANSACMaxPercentRTThreshold: - doc: Maximum threshold in RT dimension for the RANSAC outlier detection algorithm (in percent of the total gradient). Default is set to 3% which is around +/- 4 minutes on a 120 gradient. - type: long? - RTNormalization__RANSACSamplingSize: - doc: Sampling size of data points per iteration for the RANSAC outlier detection algorithm. - type: long? - RTNormalization__estimateBestPeptides: - doc: Whether the algorithms should try to choose the best peptides based on their peak shape for normalization. Use this option you do not expect all your peptides to be detected in a sample and too many 'bad' peptides enter the outlier removal step (e.g. due to them being endogenous peptides or using a less curated list of peptides). - type: boolean? - RTNormalization__InitialQualityCutoff: - doc: The initial overall quality cutoff for a peak to be scored (range ca. -2 to 2) - type: double? - RTNormalization__OverallQualityCutoff: - doc: The overall quality cutoff for a peak to go into the retention time estimation (range ca. 0 to 10) - type: double? - RTNormalization__NrRTBins: - doc: Number of RT bins to use to compute coverage. This option should be used to ensure that there is a complete coverage of the RT space (this should detect cases where only a part of the RT gradient is actually covered by normalization peptides) - type: long? - RTNormalization__MinPeptidesPerBin: - doc: Minimal number of peptides that are required for a bin to counted as 'covered' - type: long? - RTNormalization__MinBinsFilled: - doc: Minimal number of bins required to be covered - type: long? - RTNormalization__lowess__span: - doc: Span parameter for lowess - type: double? - RTNormalization__b_spline__num_nodes: - doc: Number of nodes for b spline - type: long? - Scoring__stop_report_after_feature: - doc: Stop reporting after feature (ordered by quality; -1 means do not stop). - type: long? - Scoring__rt_normalization_factor: - doc: The normalized RT is expected to be between 0 and 1. If your normalized RT has a different range, pass this here (e.g. it goes from 0 to 100, set this value to 100) - type: double? - Scoring__quantification_cutoff: - doc: Cutoff in m/z below which peaks should not be used for quantification any more - type: double? - Scoring__write_convex_hull: - doc: Whether to write out all points of all features into the featureXML - type: boolean? - Scoring__spectrum_addition_method: - doc: For spectrum addition, either use simple concatenation or use peak resampling - type: string? - Scoring__add_up_spectra: - doc: Add up spectra around the peak apex (needs to be a non-even integer) - type: long? - Scoring__spacing_for_spectra_resampling: - doc: If spectra are to be added, use this spacing to add them up - type: double? - Scoring__uis_threshold_sn: - doc: S/N threshold to consider identification transition (set to -1 to consider all) - type: long? - Scoring__uis_threshold_peak_area: - doc: Peak area threshold to consider identification transition (set to -1 to consider all) - type: long? - Scoring__scoring_model: - doc: Scoring model to use - type: string? - Scoring__im_extra_drift: - doc: Extra drift time to extract for IM scoring (as a fraction, e.g. 0.25 means 25% extra on each side) - type: double? - Scoring__strict: - doc: Whether to error (true) or skip (false) if a transition in a transition group does not have a corresponding chromatogram. - type: string? - Scoring__use_ms1_ion_mobility: - doc: Performs ion mobility extraction in MS1. Set to false if MS1 spectra do not contain ion mobility - type: string? - Scoring__TransitionGroupPicker__stop_after_feature: - doc: Stop finding after feature (ordered by intensity; -1 means do not stop). - type: long? - Scoring__TransitionGroupPicker__min_peak_width: - doc: Minimal peak width (s), discard all peaks below this value (-1 means no action). - type: double? - Scoring__TransitionGroupPicker__peak_integration: - doc: Calculate the peak area and height either the smoothed or the raw chromatogram data. - type: string? - Scoring__TransitionGroupPicker__background_subtraction: - doc: "Remove background from peak signal using estimated noise levels. The 'original' method is only provided for historical purposes, please use the 'exact' method and set parameters using the PeakIntegrator: settings. The same original or smoothed chromatogram specified by peak_integration will be used for background estimation." - type: string? - Scoring__TransitionGroupPicker__recalculate_peaks: - doc: Tries to get better peak picking by looking at peak consistency of all picked peaks. Tries to use the consensus (median) peak border if the variation within the picked peaks is too large. - type: string? - Scoring__TransitionGroupPicker__use_precursors: - doc: Use precursor chromatogram for peak picking (note that this may lead to precursor signal driving the peak picking) - type: boolean? - Scoring__TransitionGroupPicker__use_consensus: - doc: Use consensus peak boundaries when computing transition group picking (if false, compute independent peak boundaries for each transition) - type: string? - Scoring__TransitionGroupPicker__recalculate_peaks_max_z: - doc: Determines the maximal Z-Score (difference measured in standard deviations) that is considered too large for peak boundaries. If the Z-Score is above this value, the median is used for peak boundaries (default value 1.0). - type: double? - Scoring__TransitionGroupPicker__minimal_quality: - doc: Only if compute_peak_quality is set, this parameter will not consider peaks below this quality threshold - type: double? - Scoring__TransitionGroupPicker__resample_boundary: - doc: For computing peak quality, how many extra seconds should be sample left and right of the actual peak - type: double? - Scoring__TransitionGroupPicker__compute_peak_quality: - doc: Tries to compute a quality value for each peakgroup and detect outlier transitions. The resulting score is centered around zero and values above 0 are generally good and below -1 or -2 are usually bad. - type: boolean? - Scoring__TransitionGroupPicker__compute_peak_shape_metrics: - doc: Calculates various peak shape metrics (e.g., tailing) that can be used for downstream QC/QA. - type: boolean? - Scoring__TransitionGroupPicker__compute_total_mi: - doc: Compute mutual information metrics for individual transitions that can be used for OpenSWATH/IPF scoring. - type: boolean? - Scoring__TransitionGroupPicker__boundary_selection_method: - doc: Method to use when selecting the best boundaries for peaks. - type: string? - Scoring__TransitionGroupPicker__PeakPickerChromatogram__sgolay_frame_length: - doc: "The number of subsequent data points used for smoothing.\nThis number has to be uneven. If it is not, 1 will be added." - type: long? - Scoring__TransitionGroupPicker__PeakPickerChromatogram__sgolay_polynomial_order: - doc: Order of the polynomial that is fitted. - type: long? - Scoring__TransitionGroupPicker__PeakPickerChromatogram__gauss_width: - doc: Gaussian width in seconds, estimated peak size. - type: double? - Scoring__TransitionGroupPicker__PeakPickerChromatogram__use_gauss: - doc: Use Gaussian filter for smoothing (alternative is Savitzky-Golay filter) - type: string? - Scoring__TransitionGroupPicker__PeakPickerChromatogram__peak_width: - doc: Force a certain minimal peak_width on the data (e.g. extend the peak at least by this amount on both sides) in seconds. -1 turns this feature off. - type: double? - Scoring__TransitionGroupPicker__PeakPickerChromatogram__signal_to_noise: - doc: Signal-to-noise threshold at which a peak will not be extended any more. Note that setting this too high (e.g. 1.0) can lead to peaks whose flanks are not fully captured. - type: double? - Scoring__TransitionGroupPicker__PeakPickerChromatogram__write_sn_log_messages: - doc: Write out log messages of the signal-to-noise estimator in case of sparse windows or median in rightmost histogram bin - type: boolean? - Scoring__TransitionGroupPicker__PeakPickerChromatogram__remove_overlapping_peaks: - doc: Try to remove overlapping peaks during peak picking - type: string? - Scoring__TransitionGroupPicker__PeakPickerChromatogram__method: - doc: Which method to choose for chromatographic peak-picking (OpenSWATH legacy on raw data, corrected picking on smoothed chromatogram or Crawdad on smoothed chromatogram). - type: string? - Scoring__TransitionGroupPicker__PeakIntegrator__integration_type: - doc: The integration technique to use in integratePeak() and estimateBackground() which uses either the summed intensity, integration by Simpson's rule or trapezoidal integration. - type: string? - Scoring__TransitionGroupPicker__PeakIntegrator__baseline_type: - doc: The baseline type to use in estimateBackground() based on the peak boundaries. A rectangular baseline shape is computed based either on the minimal intensity of the peak boundaries, the maximum intensity or the average intensity (base_to_base). - type: string? - Scoring__TransitionGroupPicker__PeakIntegrator__fit_EMG: - doc: Fit the chromatogram/spectrum to the EMG peak model. - type: string? - Scoring__DIAScoring__dia_extraction_window: - doc: DIA extraction window in Th or ppm. - type: double? - Scoring__DIAScoring__dia_extraction_unit: - doc: DIA extraction window unit - type: string? - Scoring__DIAScoring__dia_centroided: - doc: Use centroided DIA data. - type: boolean? - Scoring__DIAScoring__dia_byseries_intensity_min: - doc: DIA b/y series minimum intensity to consider. - type: double? - Scoring__DIAScoring__dia_byseries_ppm_diff: - doc: DIA b/y series minimal difference in ppm to consider. - type: double? - Scoring__DIAScoring__dia_nr_isotopes: - doc: DIA number of isotopes to consider. - type: long? - Scoring__DIAScoring__dia_nr_charges: - doc: DIA number of charges to consider. - type: long? - Scoring__DIAScoring__peak_before_mono_max_ppm_diff: - doc: DIA maximal difference in ppm to count a peak at lower m/z when searching for evidence that a peak might not be monoisotopic. - type: double? - Scoring__EMGScoring__max_iteration: - doc: Maximum number of iterations using by Levenberg-Marquardt algorithm. - type: long? - Scoring__EMGScoring__init_mom: - doc: Initialize parameters using method of moments estimators. - type: boolean? - Scoring__Scores__use_shape_score: - doc: Use the shape score (this score measures the similarity in shape of the transitions using a cross-correlation) - type: string? - Scoring__Scores__use_coelution_score: - doc: Use the coelution score (this score measures the similarity in coelution of the transitions using a cross-correlation) - type: string? - Scoring__Scores__use_rt_score: - doc: Use the retention time score (this score measure the difference in retention time) - type: string? - Scoring__Scores__use_library_score: - doc: Use the library score - type: string? - Scoring__Scores__use_intensity_score: - doc: Use the intensity score - type: string? - Scoring__Scores__use_nr_peaks_score: - doc: Use the number of peaks score - type: string? - Scoring__Scores__use_total_xic_score: - doc: Use the total XIC score - type: string? - Scoring__Scores__use_total_mi_score: - doc: Use the total MI score - type: boolean? - Scoring__Scores__use_sn_score: - doc: Use the SN (signal to noise) score - type: string? - Scoring__Scores__use_mi_score: - doc: Use the MI (mutual information) score - type: string? - Scoring__Scores__use_dia_scores: - doc: Use the DIA (SWATH) scores. If turned off, will not use fragment ion spectra for scoring. - type: string? - Scoring__Scores__use_ms1_correlation: - doc: Use the correlation scores with the MS1 elution profiles - type: boolean? - Scoring__Scores__use_sonar_scores: - doc: Use the scores for SONAR scans (scanning swath) - type: boolean? - Scoring__Scores__use_ion_mobility_scores: - doc: Use the scores for Ion Mobility scans - type: boolean? - Scoring__Scores__use_ms1_fullscan: - doc: Use the full MS1 scan at the peak apex for scoring (ppm accuracy of precursor and isotopic pattern) - type: boolean? - Scoring__Scores__use_ms1_mi: - doc: Use the MS1 MI score - type: string? - Scoring__Scores__use_uis_scores: - doc: Use UIS scores for peptidoform identification - type: boolean? - Scoring__Scores__use_ionseries_scores: - doc: Use MS2-level b/y ion-series scores for peptidoform identification - type: string? - Scoring__Scores__use_ms2_isotope_scores: - doc: "Use MS2-level isotope scores (pearson & manhattan) across product transitions (based on ID if annotated or averagine)" - type: string? -outputs: - out_features: - type: File? - outputBinding: - glob: $(inputs.out_features) - out_tsv: - type: File? - outputBinding: - glob: $(inputs.out_tsv) - out_osw: - type: File? - outputBinding: - glob: $(inputs.out_osw) - out_chrom: - type: File? - outputBinding: - glob: $(inputs.out_chrom) - out_qc: - type: File? - outputBinding: - glob: $(inputs.out_qc) - Debugging__irt_mzml: - type: File? - outputBinding: - glob: $(inputs.Debugging__irt_mzml) - Debugging__irt_trafo: - type: File? - outputBinding: - glob: $(inputs.Debugging__irt_trafo) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - OpenSwathWorkflow -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/PSMFeatureExtractor.cwl b/workflow/cwl/PSMFeatureExtractor.cwl deleted file mode 100644 index eb2285977b4..00000000000 --- a/workflow/cwl/PSMFeatureExtractor.cwl +++ /dev/null @@ -1,68 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: PSMFeatureExtractor -doc: Computes extra features for each input PSM. -inputs: - in: - doc: Input file(s) - type: File[] - out: - doc: Output file in mzid or idXML format - type: string - out_type: - doc: "Output file type -- default: determined from file extension or content." - type: string? - extra: - doc: List of the MetaData parameters to be included in a feature set for precolator. - type: string[]? - multiple_search_engines: - doc: Combine PSMs from different search engines by merging on scan level. - type: boolean? - skip_db_check: - doc: Manual override to skip the check if same settings for multiple search engines were applied. Only valid together with -multiple_search_engines flag. - type: boolean? - concat: - doc: "Naive merging of PSMs from different search engines: concatenate multiple search results instead of merging on scan level. Only valid together with -multiple_search_engines flag." - type: boolean? - impute: - doc: Will instead of discarding all PSM not unanimously detected by all SE, impute missing values by their respective scores min/max observed. Only valid together with -multiple_search_engines flag. - type: boolean? - limit_imputation: - doc: Will impute missing scores with the worst numerical limit (instead of min/max observed) of the respective score. Only valid together with -multiple_search_engines flag. - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - PSMFeatureExtractor -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/PeakPickerHiRes.cwl b/workflow/cwl/PeakPickerHiRes.cwl deleted file mode 100644 index c6d914bc731..00000000000 --- a/workflow/cwl/PeakPickerHiRes.cwl +++ /dev/null @@ -1,98 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: PeakPickerHiRes -doc: Finds mass spectrometric peaks in profile mass spectra. -inputs: - in: - doc: "input profile data file " - type: File - out: - doc: "output peak file " - type: string - processOption: - doc: Whether to load all data and process them in-memory or whether to process the data on the fly (lowmemory) without loading the whole file into memory first - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__signal_to_noise: - doc: Minimal signal-to-noise ratio for a peak to be picked (0.0 disables SNT estimation!) - type: double? - algorithm__spacing_difference_gap: - doc: The extension of a peak is stopped if the spacing between two subsequent data points exceeds 'spacing_difference_gap * min_spacing'. 'min_spacing' is the smaller of the two spacings from the peak apex to its two neighboring points. '0' to disable the constraint. Not applicable to chromatograms. - type: double? - algorithm__spacing_difference: - doc: Maximum allowed difference between points during peak extension, in multiples of the minimal difference between the peak apex and its two neighboring points. If this difference is exceeded a missing point is assumed (see parameter 'missing'). A higher value implies a less stringent peak definition, since individual signals within the peak are allowed to be further apart. '0' to disable the constraint. Not applicable to chromatograms. - type: double? - algorithm__missing: - doc: Maximum number of missing points allowed when extending a peak to the left or to the right. A missing data point occurs if the spacing between two subsequent data points exceeds 'spacing_difference * min_spacing'. 'min_spacing' is the smaller of the two spacings from the peak apex to its two neighboring points. Not applicable to chromatograms. - type: long? - algorithm__ms_levels: - doc: List of MS levels for which the peak picking is applied. If empty, auto mode is enabled, all peaks which aren't picked yet will get picked. Other scans are copied to the output without changes. - type: long[]? - algorithm__report_FWHM: - doc: Add metadata for FWHM (as floatDataArray named 'FWHM' or 'FWHM_ppm', depending on param 'report_FWHM_unit') for each picked peak. - type: boolean? - algorithm__report_FWHM_unit: - doc: Unit of FWHM. Either absolute in the unit of input, e.g. 'm/z' for spectra, or relative as ppm (only sensible for spectra, not chromatograms). - type: string? - algorithm__SignalToNoise__max_intensity: - doc: maximal intensity considered for histogram construction. By default, it will be calculated automatically (see auto_mode). Only provide this parameter if you know what you are doing (and change 'auto_mode' to '-1')! All intensities EQUAL/ABOVE 'max_intensity' will be added to the LAST histogram bin. If you choose 'max_intensity' too small, the noise estimate might be too small as well. If chosen too big, the bins become quite large (which you could counter by increasing 'bin_count', which increases runtime). In general, the Median-S/N estimator is more robust to a manual max_intensity than the MeanIterative-S/N. - type: long? - algorithm__SignalToNoise__auto_max_stdev_factor: - doc: "parameter for 'max_intensity' estimation (if 'auto_mode' == 0): mean + 'auto_max_stdev_factor' * stdev" - type: double? - algorithm__SignalToNoise__auto_max_percentile: - doc: "parameter for 'max_intensity' estimation (if 'auto_mode' == 1): auto_max_percentile th percentile" - type: long? - algorithm__SignalToNoise__auto_mode: - doc: "method to use to determine maximal intensity: -1 --> use 'max_intensity'; 0 --> 'auto_max_stdev_factor' method (default); 1 --> 'auto_max_percentile' method" - type: long? - algorithm__SignalToNoise__win_len: - doc: window length in Thomson - type: double? - algorithm__SignalToNoise__bin_count: - doc: number of bins for intensity values - type: long? - algorithm__SignalToNoise__min_required_elements: - doc: minimum number of elements required in a window (otherwise it is considered sparse) - type: long? - algorithm__SignalToNoise__noise_for_empty_window: - doc: noise value used for sparse windows - type: double? - algorithm__SignalToNoise__write_log_messages: - doc: Write out log messages in case of sparse windows or median in rightmost histogram bin - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - PeakPickerHiRes -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/PeakPickerIterative.cwl b/workflow/cwl/PeakPickerIterative.cwl deleted file mode 100644 index 9cb98d0f37e..00000000000 --- a/workflow/cwl/PeakPickerIterative.cwl +++ /dev/null @@ -1,74 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: PeakPickerIterative -doc: Finds mass spectrometric peaks in profile mass spectra. -inputs: - in: - doc: "input file " - type: File - out: - doc: output file - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__signal_to_noise_: - doc: Signal to noise value, each peak is required to be above this value (turn off by setting it to 0.0) - type: double? - algorithm__peak_width: - doc: Expected peak width half width in Dalton - peaks will be extended until this half width is reached (even if the intensitity is increasing). In conjunction with check_width_internally it will also be used to remove peaks whose spacing is larger than this value. - type: double? - algorithm__spacing_difference: - doc: Difference between peaks in multiples of the minimal difference to continue. The higher this value is set, the further apart peaks are allowed to be to still extend a peak. E.g. if the value is set to 1.5 and in a current peak the minimal spacing between peaks is 10 mDa, then only peaks at most 15 mDa apart will be added to the peak. - type: double? - algorithm__sn_bin_count_: - doc: Bin count for the Signal to Noise estimation. - type: long? - algorithm__nr_iterations_: - doc: Nr of iterations to perform (how many times the peaks are re-centered). - type: long? - algorithm__sn_win_len_: - doc: Window length for the Signal to Noise estimation. - type: double? - algorithm__check_width_internally: - doc: Delete peaks where the spacing is larger than the peak width (should be set to true to avoid artefacts) - type: boolean? - algorithm__ms1_only: - doc: Only do MS1 - type: boolean? - algorithm__clear_meta_data: - doc: Delete meta data about peak width - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - PeakPickerIterative -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/PeakPickerWavelet.cwl b/workflow/cwl/PeakPickerWavelet.cwl deleted file mode 100644 index cb8c7b2181b..00000000000 --- a/workflow/cwl/PeakPickerWavelet.cwl +++ /dev/null @@ -1,176 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: PeakPickerWavelet -doc: Finds mass spectrometric peaks in profile mass spectra. -inputs: - in: - doc: "input profile data file " - type: File - out: - doc: "output peak file " - type: string - write_peak_meta_data: - doc: "Write additional information about the picked peaks (maximal intensity, left and right area...) into the mzML-file. Attention: this can blow up files, since seven arrays are stored per spectrum!" - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__signal_to_noise: - doc: Minimal signal to noise ratio for a peak to be picked. - type: double? - algorithm__centroid_percentage: - doc: Percentage of the maximum height that the raw data points must exceed to be taken into account for the calculation of the centroid. If it is 1 the centroid position corresponds to the position of the highest intensity. - type: double? - algorithm__peak_width: - doc: Approximate fwhm of the peaks. - type: double? - algorithm__estimate_peak_width: - doc: "Flag if the average peak width shall be estimated. Attention: when this flag is set, the peak_width is ignored." - type: boolean? - algorithm__fwhm_lower_bound_factor: - doc: Factor that calculates the minimal fwhm value from the peak_width. All peaks with width smaller than fwhm_bound_factor * peak_width are discarded. - type: double? - algorithm__fwhm_upper_bound_factor: - doc: Factor that calculates the maximal fwhm value from the peak_width. All peaks with width greater than fwhm_upper_bound_factor * peak_width are discarded. - type: double? - algorithm__thresholds__peak_bound: - doc: Minimal peak intensity. - type: double? - algorithm__thresholds__peak_bound_ms2_level: - doc: Minimal peak intensity for MS/MS peaks. - type: double? - algorithm__thresholds__correlation: - doc: minimal correlation of a peak and the raw signal. If a peak has a lower correlation it is skipped. - type: double? - algorithm__thresholds__noise_level: - doc: noise level for the search of the peak endpoints. - type: double? - algorithm__thresholds__search_radius: - doc: search radius for the search of the maximum in the signal after a maximum in the cwt was found - type: long? - algorithm__wavelet_transform__spacing: - doc: Spacing of the CWT. Note that the accuracy of the picked peak's centroid position depends in the Raw data spacing, i.e., 50% of raw peak distance at most. - type: double? - algorithm__optimization__type: - doc: If the peak parameters position, intensity and left/right widthshall be optimized set optimization to one_dimensional or two_dimensional. - type: string? - algorithm__optimization__iterations: - doc: maximal number of iterations for the fitting step - type: long? - algorithm__optimization__penalties__position: - doc: "penalty term for the fitting of the position:If it differs too much from the initial one it can be penalized " - type: double? - algorithm__optimization__penalties__left_width: - doc: penalty term for the fitting of the left width:If the left width differs too much from the initial one during the fitting it can be penalized. - type: double? - algorithm__optimization__penalties__right_width: - doc: penalty term for the fitting of the right width:If the right width differs too much from the initial one during the fitting it can be penalized. - type: double? - algorithm__optimization__penalties__height: - doc: penalty term for the fitting of the intensity (only used in 2D Optimization):If it gets negative during the fitting it can be penalized. - type: double? - algorithm__optimization__2d__tolerance_mz: - doc: mz tolerance for cluster construction - type: double? - algorithm__optimization__2d__max_peak_distance: - doc: maximal peak distance in mz in a cluster - type: double? - algorithm__deconvolution__deconvolution: - doc: If you want heavily overlapping peaks to be separated set this value to "true" - type: boolean? - algorithm__deconvolution__asym_threshold: - doc: If the symmetry of a peak is smaller than asym_thresholds it is assumed that it consists of more than one peak and the deconvolution procedure is started. - type: double? - algorithm__deconvolution__left_width: - doc: 1/left_width is the initial value for the left width of the peaks found in the deconvolution step. - type: double? - algorithm__deconvolution__right_width: - doc: 1/right_width is the initial value for the right width of the peaks found in the deconvolution step. - type: double? - algorithm__deconvolution__scaling: - doc: Initial scaling of the cwt used in the separation of heavily overlapping peaks. The initial value is used for charge 1, for higher charges it is adapted to scaling/charge. - type: double? - algorithm__deconvolution__fitting__fwhm_threshold: - doc: If the FWHM of a peak is higher than 'fwhm_thresholds' it is assumed that it consists of more than one peak and the deconvolution procedure is started. - type: double? - algorithm__deconvolution__fitting__eps_abs: - doc: if the absolute error gets smaller than this value the fitting is stopped. - type: double? - algorithm__deconvolution__fitting__eps_rel: - doc: if the relative error gets smaller than this value the fitting is stopped. - type: double? - algorithm__deconvolution__fitting__max_iteration: - doc: maximal number of iterations for the fitting step - type: long? - algorithm__deconvolution__fitting__penalties__position: - doc: penalty term for the fitting of the peak position:If the position changes more than 0.5Da during the fitting it can be penalized as well as discrepancies of the peptide mass rule. - type: double? - algorithm__deconvolution__fitting__penalties__height: - doc: penalty term for the fitting of the intensity:If it gets negative during the fitting it can be penalized. - type: double? - algorithm__deconvolution__fitting__penalties__left_width: - doc: penalty term for the fitting of the left width:If the left width gets too broad or negative during the fitting it can be penalized. - type: double? - algorithm__deconvolution__fitting__penalties__right_width: - doc: penalty term for the fitting of the right width:If the right width gets too broad or negative during the fitting it can be penalized. - type: double? - algorithm__SignalToNoiseEstimationParameter__max_intensity: - doc: maximal intensity considered for histogram construction. By default, it will be calculated automatically (see auto_mode). Only provide this parameter if you know what you are doing (and change 'auto_mode' to '-1')! All intensities EQUAL/ABOVE 'max_intensity' will not be added to the histogram. If you choose 'max_intensity' too small, the noise estimate might be too small as well. If chosen too big, the bins become quite large (which you could counter by increasing 'bin_count', which increases runtime). - type: long? - algorithm__SignalToNoiseEstimationParameter__auto_max_stdev_factor: - doc: "parameter for 'max_intensity' estimation (if 'auto_mode' == 0): mean + 'auto_max_stdev_factor' * stdev" - type: double? - algorithm__SignalToNoiseEstimationParameter__auto_max_percentile: - doc: "parameter for 'max_intensity' estimation (if 'auto_mode' == 1): auto_max_percentile th percentile" - type: long? - algorithm__SignalToNoiseEstimationParameter__auto_mode: - doc: "method to use to determine maximal intensity: -1 --> use 'max_intensity'; 0 --> 'auto_max_stdev_factor' method (default); 1 --> 'auto_max_percentile' method" - type: long? - algorithm__SignalToNoiseEstimationParameter__win_len: - doc: window length in Thomson - type: double? - algorithm__SignalToNoiseEstimationParameter__bin_count: - doc: number of bins for intensity values - type: long? - algorithm__SignalToNoiseEstimationParameter__stdev_mp: - doc: multiplier for stdev - type: double? - algorithm__SignalToNoiseEstimationParameter__min_required_elements: - doc: minimum number of elements required in a window (otherwise it is considered sparse) - type: long? - algorithm__SignalToNoiseEstimationParameter__noise_for_empty_window: - doc: noise value used for sparse windows - type: double? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - PeakPickerWavelet -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/PeptideIndexer.cwl b/workflow/cwl/PeptideIndexer.cwl deleted file mode 100644 index 88c620043eb..00000000000 --- a/workflow/cwl/PeptideIndexer.cwl +++ /dev/null @@ -1,89 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: PeptideIndexer -doc: Refreshes the protein references for all peptide hits. -inputs: - in: - doc: Input idXML file containing the identifications. - type: File - fasta: - doc: Input sequence database in FASTA format. Leave empty for using the same DB as used for the input idXML (this might fail). Non-existing relative filenames are looked up via 'OpenMS.ini:id_db_dir' - type: File? - out: - doc: Output idXML file. - type: string - decoy_string: - doc: String that was appended (or prefixed - see 'decoy_string_position' flag below) to the accessions in the protein database to indicate decoy proteins. If empty (default), it's determined automatically (checking for common terms, both as prefix and suffix). - type: string? - decoy_string_position: - doc: Is the 'decoy_string' prepended (prefix) or appended (suffix) to the protein accession? (ignored if decoy_string is empty) - type: string? - missing_decoy_action: - doc: "Action to take if NO peptide was assigned to a decoy protein (which indicates wrong database or decoy string): 'error' (exit with error, no output), 'warn' (exit with success, warning message), 'silent' (no action is taken, not even a warning)" - type: string? - write_protein_sequence: - doc: If set, the protein sequences are stored as well. - type: boolean? - write_protein_description: - doc: If set, the protein description is stored as well. - type: boolean? - keep_unreferenced_proteins: - doc: If set, protein hits which are not referenced by any peptide are kept. - type: boolean? - unmatched_action: - doc: "If peptide sequences cannot be matched to any protein: 1) raise an error; 2) warn (unmatched PepHits will miss target/decoy annotation with downstream problems); 3) remove the hit." - type: string? - aaa_max: - doc: Maximal number of ambiguous amino acids (AAAs) allowed when matching to a protein database with AAAs. AAAs are 'B', 'J', 'Z' and 'X'. - type: long? - mismatches_max: - doc: Maximal number of mismatched (mm) amino acids allowed when matching to a protein database. The required runtime is exponential in the number of mm's; apply with care. MM's are allowed in addition to AAA's. - type: long? - IL_equivalent: - doc: Treat the isobaric amino acids isoleucine ('I') and leucine ('L') as equivalent (indistinguishable). Also occurrences of 'J' will be treated as 'I' thus avoiding ambiguous matching. - type: boolean? - allow_nterm_protein_cleavage: - doc: Allow the protein N-terminus amino acid to clip. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - enzyme__name: - doc: "Enzyme which determines valid cleavage sites - e.g. trypsin cleaves after lysine (K) or arginine (R), but not before proline (P). Default: deduce from input" - type: string? - enzyme__specificity: - doc: "Specificity of the enzyme. Default: deduce from input.\n 'full': both internal cleavage sites must match.\n 'semi': one of two internal cleavage sites must match.\n 'none': allow all peptide hits no matter their context (enzyme is irrelevant)." - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - PeptideIndexer -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/PercolatorAdapter.cwl b/workflow/cwl/PercolatorAdapter.cwl deleted file mode 100644 index 5b0319cb042..00000000000 --- a/workflow/cwl/PercolatorAdapter.cwl +++ /dev/null @@ -1,194 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: PercolatorAdapter -doc: Facilitate input to Percolator and reintegrate. -inputs: - in: - doc: Input file(s) - type: File[]? - in_decoy: - doc: Input decoy file(s) in case of separate searches - type: File[]? - in_osw: - doc: Input file in OSW format - type: File? - out: - doc: Output file - type: string - out_pin: - doc: Write pin file (e.g., for debugging) - type: string? - out_pout_target: - doc: Write pout file (e.g., for debugging) - type: string? - out_pout_decoy: - doc: Write pout file (e.g., for debugging) - type: string? - out_pout_target_proteins: - doc: Write pout file (e.g., for debugging) - type: string? - out_pout_decoy_proteins: - doc: Write pout file (e.g., for debugging) - type: string? - out_type: - doc: "Output file type -- default: determined from file extension or content." - type: string? - enzyme: - doc: "Type of enzyme: no_enzyme,elastase,pepsin,proteinasek,thermolysin,chymotrypsin,lys-n,lys-c,arg-c,asp-n,glu-c,trypsin,trypsinp" - type: string? - percolator_executable: - doc: The Percolator executable. Provide a full or relative path, or make sure it can be found in your PATH environment. - type: File - peptide_level_fdrs: - doc: Calculate peptide-level FDRs instead of PSM-level FDRs. - type: boolean? - protein_level_fdrs: - doc: Use the picked protein-level FDR to infer protein probabilities. Use the -fasta option and -decoy_pattern to set the Fasta file and decoy pattern. - type: boolean? - osw_level: - doc: "OSW: the data level selected for scoring." - type: string? - score_type: - doc: Type of the peptide main score - type: string? - generic_feature_set: - doc: Use only generic (i.e. not search engine specific) features. Generating search engine specific features for common search engines by PSMFeatureExtractor will typically boost the identification rate significantly. - type: boolean? - subset_max_train: - doc: Only train an SVM on a subset of PSMs, and use the resulting score vector to evaluate the other PSMs. Recommended when analyzing huge numbers (>1 million) of PSMs. When set to 0, all PSMs are used for training as normal. - type: long? - cpos: - doc: Cpos, penalty for mistakes made on positive examples. Set by cross validation if not specified. - type: double? - cneg: - doc: Cneg, penalty for mistakes made on negative examples. Set by cross validation if not specified. - type: double? - testFDR: - doc: False discovery rate threshold for evaluating best cross validation result and the reported end result. - type: double? - trainFDR: - doc: False discovery rate threshold to define positive examples in training. Set to testFDR if 0. - type: double? - maxiter: - doc: Maximal number of iterations - type: long? - nested_xval_bins: - doc: Number of nested cross-validation bins in the 3 splits. - type: long? - quick_validation: - doc: Quicker execution by reduced internal cross-validation. - type: boolean? - weights: - doc: Output final weights to the given file - type: string? - init_weights: - doc: Read initial weights to the given file - type: File? - static: - doc: Use static model (requires init-weights parameter to be set) - type: boolean? - default_direction: - doc: The most informative feature given as the feature name, can be negated to indicate that a lower value is better. - type: string? - verbose: - doc: "Set verbosity of output: 0=no processing info, 5=all." - type: long? - unitnorm: - doc: Use unit normalization [0-1] instead of standard deviation normalization - type: boolean? - test_each_iteration: - doc: Measure performance on test set each iteration - type: boolean? - override: - doc: Override error check and do not fall back on default score vector in case of suspect score vector - type: boolean? - seed: - doc: Setting seed of the random number generator. - type: long? - doc: - doc: Include description of correct features - type: long? - klammer: - doc: Retention time features calculated as in Klammer et al. Only available if -doc is set - type: boolean? - fasta: - doc: Provide the fasta file as the argument to this flag, which will be used for protein grouping based on an in-silico digest (only valid if option -protein_level_fdrs is active). - type: File? - decoy_pattern: - doc: Define the text pattern to identify the decoy proteins and/or PSMs, set this up if the label that identifies the decoys in the database is not the default (Only valid if option -protein_level_fdrs is active). - type: string? - post_processing_tdc: - doc: Use target-decoy competition to assign q-values and PEPs. - type: boolean? - train_best_positive: - doc: Enforce that, for each spectrum, at most one PSM is included in the positive set during each training iteration. If the user only provides one PSM per spectrum, this filter will have no effect. - type: boolean? - ipf_max_peakgroup_pep: - doc: "OSW/IPF: Assess transitions only for candidate peak groups until maximum posterior error probability." - type: double? - ipf_max_transition_isotope_overlap: - doc: "OSW/IPF: Maximum isotope overlap to consider transitions in IPF." - type: double? - ipf_min_transition_sn: - doc: "OSW/IPF: Minimum log signal-to-noise level to consider transitions in IPF. Set -1 to disable this filter." - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - out_pin: - type: File? - outputBinding: - glob: $(inputs.out_pin) - out_pout_target: - type: File? - outputBinding: - glob: $(inputs.out_pout_target) - out_pout_decoy: - type: File? - outputBinding: - glob: $(inputs.out_pout_decoy) - out_pout_target_proteins: - type: File? - outputBinding: - glob: $(inputs.out_pout_target_proteins) - out_pout_decoy_proteins: - type: File? - outputBinding: - glob: $(inputs.out_pout_decoy_proteins) - weights: - type: File? - outputBinding: - glob: $(inputs.weights) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - PercolatorAdapter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/PhosphoScoring.cwl b/workflow/cwl/PhosphoScoring.cwl deleted file mode 100644 index 4b19880fa06..00000000000 --- a/workflow/cwl/PhosphoScoring.cwl +++ /dev/null @@ -1,65 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: PhosphoScoring -doc: Scores potential phosphorylation sites in order to localize the most probable sites. -inputs: - in: - doc: Input file with MS/MS spectra - type: File - id: - doc: Identification input file which contains a search against a concatenated sequence database - type: File - out: - doc: Identification output annotated with phosphorylation scores - type: string - fragment_mass_tolerance: - doc: Fragment mass tolerance for spectrum comparisons - type: double? - fragment_mass_unit: - doc: Unit of fragment mass tolerance - type: string? - max_peptide_length: - doc: Restrict scoring to peptides with a length no greater than this value ('0' for 'no restriction') - type: long? - max_num_perm: - doc: Maximum number of permutations a sequence can have to be processed ('0' for 'no restriction') - type: long? - unambiguous_score: - doc: "Score to use for unambiguous assignments, where all sites on a peptide are phosphorylated. (Note: If a peptide is not phosphorylated at all, its score is set to '-1'.)" - type: long? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - PhosphoScoring -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/PrecursorMassCorrector.cwl b/workflow/cwl/PrecursorMassCorrector.cwl deleted file mode 100644 index 81bd2198ac8..00000000000 --- a/workflow/cwl/PrecursorMassCorrector.cwl +++ /dev/null @@ -1,59 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: PrecursorMassCorrector -doc: Corrects the precursor entries of MS/MS spectra, by using MS1 information. -inputs: - in: - doc: Input mzML file containing the spectra. - type: File - out: - doc: Output mzML file. - type: string - feature_in: - doc: "Input featureXML file, containing features; if set, the MS/MS spectra precursor entries \nwill be matched to the feature m/z values if possible." - type: File? - precursor_mass_tolerance: - doc: "Maximal deviation in Th which is acceptable to be corrected;\nthis value should be set to the instruments selection window." - type: double? - max_charge: - doc: Maximal charge that should be assumed for precursor peaks - type: long? - intensity_threshold: - doc: Intensity threshold value for isotope wavelet feature finder, please look at the documentation of the class for details. - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - PrecursorMassCorrector -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/ProteinInference.cwl b/workflow/cwl/ProteinInference.cwl deleted file mode 100644 index 139e8476e02..00000000000 --- a/workflow/cwl/ProteinInference.cwl +++ /dev/null @@ -1,98 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: ProteinInference -doc: Protein inference based on an aggregation of the scores of the identified peptides. -inputs: - in: - doc: input file(s) - type: File[] - out: - doc: output file - type: string - out_type: - doc: output file type - type: string? - merge_runs: - doc: If your idXML contains multiple runs, merge them beforehand? Otherwise performs inference separately per run. - type: string? - protein_fdr: - doc: Additionally calculate the target-decoy FDR on protein-level after inference - type: boolean? - conservative_fdr: - doc: Use (D+1)/(T) instead of (D+1)/(T+D) for reporting protein FDRs. - type: string? - picked_fdr: - doc: Use picked protein FDRs. - type: string? - picked_decoy_string: - doc: If using picked protein FDRs, which decoy string was used? Leave blank for auto-detection. - type: string? - picked_decoy_prefix: - doc: If using picked protein FDRs, was the decoy string a prefix or suffix? Ignored during auto-detection. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - Merging__annotate_origin: - doc: If true, adds a map_index MetaValue to the PeptideIDs to annotate the IDRun they came from. - type: string? - Merging__allow_disagreeing_settings: - doc: Force merging of disagreeing runs. Use at your own risk. - type: boolean? - Algorithm__min_peptides_per_protein: - doc: Minimal number of peptides needed for a protein identification. If set to zero, unmatched proteins get a score of -Infinity. If bigger than zero, proteins with less peptides are filtered and evidences removed from the PSMs. PSMs that do not reference any proteins anymore are removed but the spectrum info is kept. - type: long? - Algorithm__score_aggregation_method: - doc: How to aggregate scores of peptides matching to the same protein? - type: string? - Algorithm__treat_charge_variants_separately: - doc: If this is true, different charge variants of the same peptide sequence count as individual evidences. - type: string? - Algorithm__treat_modification_variants_separately: - doc: If this is true, different modification variants of the same peptide sequence count as individual evidences. - type: string? - Algorithm__use_shared_peptides: - doc: "If this is true, shared peptides are used as evidences. Note: shared_peptides are not deleted and potentially resolved in postprocessing as well." - type: string? - Algorithm__skip_count_annotation: - doc: If this is set, peptide counts won't be annotated at the proteins. - type: boolean? - Algorithm__annotate_indistinguishable_groups: - doc: If this is true, calculates and annotates indistinguishable protein groups. - type: string? - Algorithm__greedy_group_resolution: - doc: If this is true, shared peptides will be associated to best proteins only (i.e. become potentially quantifiable razor peptides). - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - ProteinInference -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/ProteinQuantifier.cwl b/workflow/cwl/ProteinQuantifier.cwl deleted file mode 100644 index dfe43a5d9b0..00000000000 --- a/workflow/cwl/ProteinQuantifier.cwl +++ /dev/null @@ -1,106 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: ProteinQuantifier -doc: Compute peptide and protein abundances -inputs: - in: - doc: Input file - type: File - protein_groups: - doc: "Protein inference results for the identification runs that were used to annotate the input (e.g. via the ProteinInference tool).\nInformation about indistinguishable proteins will be used for protein quantification." - type: File? - design: - doc: input file containing the experimental design - type: File? - out: - doc: Output file for protein abundances - type: string? - peptide_out: - doc: Output file for peptide abundances - type: string? - mztab: - doc: Output file (mzTab) - type: string? - method: - doc: "- top - quantify based on three most abundant peptides (number can be changed in 'top').\n- iBAQ (intensity based absolute quantification), calculate the sum of all peptide peak intensities divided by the number of theoretically observable tryptic peptides (https://rdcu.be/cND1J). Warning: only consensusXML or featureXML input is allowed!" - type: string? - best_charge_and_fraction: - doc: "Distinguish between fraction and charge states of a peptide. For peptides, abundances will be reported separately for each fraction and charge;\nfor proteins, abundances will be computed based only on the most prevalent charge observed of each peptide (over all fractions).\nBy default, abundances are summed over all charge states." - type: boolean? - greedy_group_resolution: - doc: Pre-process identifications with greedy resolution of shared peptides based on the protein group probabilities. (Only works with an idXML file given as protein_groups parameter). - type: boolean? - ratios: - doc: "Add the log2 ratios of the abundance values to the output. Format: log_2(x_0/x_0) log_2(x_1/x_0) log_2(x_2/x_0) ..." - type: boolean? - ratiosSILAC: - doc: "Add the log2 ratios for a triple SILAC experiment to the output. Only applicable to consensus maps of exactly three sub-maps. Format: log_2(heavy/light) log_2(heavy/middle) log_2(middle/light)" - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - top__N: - doc: Calculate protein abundance from this number of proteotypic peptides (most abundant first; '0' for all) - type: long? - top__aggregate: - doc: Aggregation method used to compute protein abundances from peptide abundances - type: string? - top__include_all: - doc: Include results for proteins with fewer proteotypic peptides than indicated by 'N' (no effect if 'N' is 0 or 1) - type: boolean? - consensus__normalize: - doc: Scale peptide abundances so that medians of all samples are equal - type: boolean? - consensus__fix_peptides: - doc: "Use the same peptides for protein quantification across all samples.\nWith 'N 0',all peptides that occur in every sample are considered.\nOtherwise ('N'), the N peptides that occur in the most samples (independently of each other) are selected,\nbreaking ties by total abundance (there is no guarantee that the best co-ocurring peptides are chosen!)." - type: boolean? - format__separator: - doc: Character(s) used to separate fields; by default, the 'tab' character is used - type: string? - format__quoting: - doc: "Method for quoting of strings: 'none' for no quoting, 'double' for quoting with doubling of embedded quotes,\n'escape' for quoting with backslash-escaping of embedded quotes" - type: string? - format__replacement: - doc: If 'quoting' is 'none', used to replace occurrences of the separator in strings before writing - type: string? -outputs: - out: - type: File? - outputBinding: - glob: $(inputs.out) - peptide_out: - type: File? - outputBinding: - glob: $(inputs.peptide_out) - mztab: - type: File? - outputBinding: - glob: $(inputs.mztab) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - ProteinQuantifier -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/ProteinResolver.cwl b/workflow/cwl/ProteinResolver.cwl deleted file mode 100644 index 90c2c97c259..00000000000 --- a/workflow/cwl/ProteinResolver.cwl +++ /dev/null @@ -1,95 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: ProteinResolver -doc: protein inference -inputs: - fasta: - doc: Input database file - type: File - in: - doc: Input file(s) holding experimental data - type: File[]? - in_path: - doc: Path to idXMLs or consensusXMLs files. Ignored if 'in' is given. - type: string? - design: - doc: Text file containing the experimental design. See documentation for specific format requirements - type: File? - protein_groups: - doc: output file. Contains all protein groups - type: string? - peptide_table: - doc: output file. Contains one peptide per line and all proteins which contain that peptide - type: string? - protein_table: - doc: output file. Contains one protein per line - type: string? - additional_info: - doc: output file for additional info - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - resolver__missed_cleavages: - doc: Number of allowed missed cleavages - type: long? - resolver__min_length: - doc: Minimum length of peptide - type: long? - resolver__enzyme: - doc: Digestion enzyme - type: string? - designer__experiment: - doc: Identifier for the experimental design. - type: string? - designer__file: - doc: Identifier for the file name. - type: string? - designer__separator: - doc: Separator, which should be used to split a row into columns - type: string? -outputs: - protein_groups: - type: File? - outputBinding: - glob: $(inputs.protein_groups) - peptide_table: - type: File? - outputBinding: - glob: $(inputs.peptide_table) - protein_table: - type: File? - outputBinding: - glob: $(inputs.protein_table) - additional_info: - type: File? - outputBinding: - glob: $(inputs.additional_info) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - ProteinResolver -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/ProteomicsLFQ.cwl b/workflow/cwl/ProteomicsLFQ.cwl deleted file mode 100644 index c4038426a12..00000000000 --- a/workflow/cwl/ProteomicsLFQ.cwl +++ /dev/null @@ -1,448 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: ProteomicsLFQ -doc: A standard proteomics LFQ pipeline. -inputs: - in: - doc: Input files - type: File[] - ids: - doc: "Identifications filtered at PSM level (e.g., q-value < 0.01).And annotated with PEP as main score.\nWe suggest using:\n1. PSMFeatureExtractor to annotate percolator features.\n2. PercolatorAdapter tool (score_type = 'q-value', -post-processing-tdc)\n3. IDFilter (pep:score = 0.05)\nTo obtain well calibrated PEPs and an initial reduction of PSMs\nID files must be provided in same order as spectra files." - type: File[] - design: - doc: design file - type: File? - fasta: - doc: fasta file - type: File? - out: - doc: output mzTab file - type: string - out_msstats: - doc: output MSstats input file - type: string? - out_triqler: - doc: output Triqler input file - type: string? - out_cxml: - doc: output consensusXML file - type: string? - proteinFDR: - doc: Protein FDR threshold (0.05=5%). - type: double? - picked_proteinFDR: - doc: Use a picked protein FDR? - type: boolean? - psmFDR: - doc: FDR threshold for sub-protein level (e.g. 0.05=5%). Use -FDR_type to choose the level. Cutoff is applied at the highest level. If Bayesian inference was chosen, it is equivalent with a peptide FDR - type: double? - FDR_type: - doc: Sub-protein FDR level. PSM, PSM+peptide (best PSM q-value). - type: string? - protein_inference: - doc: "Infer proteins:\naggregation = aggregates all peptide scores across a protein (using the best score) \nbayesian = computes a posterior probability for every protein based on a Bayesian network.\n Note: 'bayesian' only uses and reports the best PSM per peptide." - type: string? - protein_quantification: - doc: "Quantify proteins based on:\nunique_peptides = use peptides mapping to single proteins or a group of indistinguishable proteins(according to the set of experimentally identified peptides).\nstrictly_unique_peptides = use peptides mapping to a unique single protein only.\nshared_peptides = use shared peptides only for its best group (by inference score)" - type: string? - quantification_method: - doc: "feature_intensity: MS1 signal.\nspectral_counting: PSM counts." - type: string? - targeted_only: - doc: "true: Only ID based quantification.\nfalse: include unidentified features so they can be linked to identified ones (=match between runs)." - type: boolean? - feature_with_id_min_score: - doc: "The minimum probability (e.g.: 0.25) an identified (=id targeted) feature must have to be kept for alignment and linking (0=no filter)." - type: double? - feature_without_id_min_score: - doc: "The minimum probability (e.g.: 0.75) an unidentified feature must have to be kept for alignment and linking (0=no filter)." - type: double? - mass_recalibration: - doc: Mass recalibration. - type: boolean? - alignment_order: - doc: If star, aligns all maps to the reference with most IDs. - type: string? - keep_feature_top_psm_only: - doc: If false, also keeps lower ranked PSMs that have the top-scoring sequence as a candidate per feature in the same file. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - Seeding__intThreshold: - doc: Peak intensity threshold applied in seed detection. - type: double? - Seeding__charge: - doc: Charge range considered for untargeted feature seeds. - type: string? - Seeding__traceRTTolerance: - doc: Combines all spectra in the tolerance window to stabilize identification of isotope patterns. Controls sensitivity (low value) vs. specificity (high value) of feature seeds. - type: double? - Centroiding__signal_to_noise: - doc: Minimal signal-to-noise ratio for a peak to be picked (0.0 disables SNT estimation!) - type: double? - Centroiding__spacing_difference_gap: - doc: The extension of a peak is stopped if the spacing between two subsequent data points exceeds 'spacing_difference_gap * min_spacing'. 'min_spacing' is the smaller of the two spacings from the peak apex to its two neighboring points. '0' to disable the constraint. Not applicable to chromatograms. - type: double? - Centroiding__spacing_difference: - doc: Maximum allowed difference between points during peak extension, in multiples of the minimal difference between the peak apex and its two neighboring points. If this difference is exceeded a missing point is assumed (see parameter 'missing'). A higher value implies a less stringent peak definition, since individual signals within the peak are allowed to be further apart. '0' to disable the constraint. Not applicable to chromatograms. - type: double? - Centroiding__missing: - doc: Maximum number of missing points allowed when extending a peak to the left or to the right. A missing data point occurs if the spacing between two subsequent data points exceeds 'spacing_difference * min_spacing'. 'min_spacing' is the smaller of the two spacings from the peak apex to its two neighboring points. Not applicable to chromatograms. - type: long? - Centroiding__ms_levels: - doc: List of MS levels for which the peak picking is applied. If empty, auto mode is enabled, all peaks which aren't picked yet will get picked. Other scans are copied to the output without changes. - type: long[]? - Centroiding__report_FWHM: - doc: Add metadata for FWHM (as floatDataArray named 'FWHM' or 'FWHM_ppm', depending on param 'report_FWHM_unit') for each picked peak. - type: boolean? - Centroiding__report_FWHM_unit: - doc: Unit of FWHM. Either absolute in the unit of input, e.g. 'm/z' for spectra, or relative as ppm (only sensible for spectra, not chromatograms). - type: string? - Centroiding__SignalToNoise__max_intensity: - doc: maximal intensity considered for histogram construction. By default, it will be calculated automatically (see auto_mode). Only provide this parameter if you know what you are doing (and change 'auto_mode' to '-1')! All intensities EQUAL/ABOVE 'max_intensity' will be added to the LAST histogram bin. If you choose 'max_intensity' too small, the noise estimate might be too small as well. If chosen too big, the bins become quite large (which you could counter by increasing 'bin_count', which increases runtime). In general, the Median-S/N estimator is more robust to a manual max_intensity than the MeanIterative-S/N. - type: long? - Centroiding__SignalToNoise__auto_max_stdev_factor: - doc: "parameter for 'max_intensity' estimation (if 'auto_mode' == 0): mean + 'auto_max_stdev_factor' * stdev" - type: double? - Centroiding__SignalToNoise__auto_max_percentile: - doc: "parameter for 'max_intensity' estimation (if 'auto_mode' == 1): auto_max_percentile th percentile" - type: long? - Centroiding__SignalToNoise__auto_mode: - doc: "method to use to determine maximal intensity: -1 --> use 'max_intensity'; 0 --> 'auto_max_stdev_factor' method (default); 1 --> 'auto_max_percentile' method" - type: long? - Centroiding__SignalToNoise__win_len: - doc: window length in Thomson - type: double? - Centroiding__SignalToNoise__bin_count: - doc: number of bins for intensity values - type: long? - Centroiding__SignalToNoise__min_required_elements: - doc: minimum number of elements required in a window (otherwise it is considered sparse) - type: long? - Centroiding__SignalToNoise__noise_for_empty_window: - doc: noise value used for sparse windows - type: double? - Centroiding__SignalToNoise__write_log_messages: - doc: Write out log messages in case of sparse windows or median in rightmost histogram bin - type: string? - PeptideQuantification__candidates_out: - doc: Optional output file with feature candidates. - type: string? - PeptideQuantification__debug: - doc: Debug level for feature detection. - type: long? - PeptideQuantification__quantify_decoys: - doc: Whether decoy peptides should be quantified (true) or skipped (false). - type: boolean? - PeptideQuantification__min_psm_cutoff: - doc: Minimum score for the best PSM of a spectrum to be used as seed. Use 'none' for no cutoff. - type: string? - PeptideQuantification__add_mass_offset_peptides: - doc: If for every peptide (or seed) also an offset peptide is extracted (true). Can be used to downstream to determine MBR false transfer rates. (0.0 = disabled) - type: double? - PeptideQuantification__extract__batch_size: - doc: Nr of peptides used in each batch of chromatogram extraction. Smaller values decrease memory usage but increase runtime. - type: long? - PeptideQuantification__extract__mz_window: - doc: "m/z window size for chromatogram extraction (unit: ppm if 1 or greater, else Da/Th)" - type: double? - PeptideQuantification__extract__n_isotopes: - doc: Number of isotopes to include in each peptide assay. - type: long? - PeptideQuantification__extract__isotope_pmin: - doc: Minimum probability for an isotope to be included in the assay for a peptide. If set, this parameter takes precedence over 'extract:n_isotopes'. - type: double? - PeptideQuantification__extract__rt_quantile: - doc: Quantile of the RT deviations between aligned internal and external IDs to use for scaling the RT extraction window - type: double? - PeptideQuantification__extract__rt_window: - doc: RT window size (in sec.) for chromatogram extraction. If set, this parameter takes precedence over 'extract:rt_quantile'. - type: double? - PeptideQuantification__detect__min_peak_width: - doc: Minimum elution peak width. Absolute value in seconds if 1 or greater, else relative to 'peak_width'. - type: double? - PeptideQuantification__detect__signal_to_noise: - doc: Signal-to-noise threshold for OpenSWATH feature detection - type: double? - PeptideQuantification__detect__mapping_tolerance: - doc: RT tolerance (plus/minus) for mapping peptide IDs to features. Absolute value in seconds if 1 or greater, else relative to the RT span of the feature. - type: double? - PeptideQuantification__svm__samples: - doc: Number of observations to use for training ('0' for all) - type: long? - PeptideQuantification__svm__no_selection: - doc: By default, roughly the same number of positive and negative observations, with the same intensity distribution, are selected for training. This aims to reduce biases, but also reduces the amount of training data. Set this flag to skip this procedure and consider all available observations (subject to 'svm:samples'). - type: boolean? - PeptideQuantification__svm__xval_out: - doc: "Output file: SVM cross-validation (parameter optimization) results" - type: string? - PeptideQuantification__svm__kernel: - doc: SVM kernel - type: string? - PeptideQuantification__svm__xval: - doc: Number of partitions for cross-validation (parameter optimization) - type: long? - PeptideQuantification__svm__log2_C: - doc: Values to try for the SVM parameter 'C' during parameter optimization. A value 'x' is used as 'C = 2^x'. - type: double[]? - PeptideQuantification__svm__log2_gamma: - doc: Values to try for the SVM parameter 'gamma' during parameter optimization (RBF kernel only). A value 'x' is used as 'gamma = 2^x'. - type: double[]? - PeptideQuantification__svm__log2_p: - doc: Values to try for the SVM parameter 'epsilon' during parameter optimization (epsilon-SVR only). A value 'x' is used as 'epsilon = 2^x'. - type: double[]? - PeptideQuantification__svm__epsilon: - doc: Stopping criterion - type: double? - PeptideQuantification__svm__cache_size: - doc: Size of the kernel cache (in MB) - type: double? - PeptideQuantification__svm__no_shrinking: - doc: Disable the shrinking heuristics - type: boolean? - PeptideQuantification__svm__predictors: - doc: Names of OpenSWATH scores to use as predictors for the SVM (comma-separated list) - type: string? - PeptideQuantification__svm__min_prob: - doc: Minimum probability of correctness, as predicted by the SVM, required to retain a feature candidate - type: double? - PeptideQuantification__model__type: - doc: Type of elution model to fit to features - type: string? - PeptideQuantification__model__add_zeros: - doc: Add zero-intensity points outside the feature range to constrain the model fit. This parameter sets the weight given to these points during model fitting; '0' to disable. - type: double? - PeptideQuantification__model__unweighted_fit: - doc: Suppress weighting of mass traces according to theoretical intensities when fitting elution models - type: boolean? - PeptideQuantification__model__no_imputation: - doc: If fitting the elution model fails for a feature, set its intensity to zero instead of imputing a value from the initial intensity estimate - type: boolean? - PeptideQuantification__model__each_trace: - doc: Fit elution model to each individual mass trace - type: boolean? - PeptideQuantification__model__check__min_area: - doc: Lower bound for the area under the curve of a valid elution model - type: double? - PeptideQuantification__model__check__boundaries: - doc: Time points corresponding to this fraction of the elution model height have to be within the data region used for model fitting - type: double? - PeptideQuantification__model__check__width: - doc: Upper limit for acceptable widths of elution models (Gaussian or EGH), expressed in terms of modified (median-based) z-scores. '0' to disable. Not applied to individual mass traces (parameter 'each_trace'). - type: double? - PeptideQuantification__model__check__asymmetry: - doc: Upper limit for acceptable asymmetry of elution models (EGH only), expressed in terms of modified (median-based) z-scores. '0' to disable. Not applied to individual mass traces (parameter 'each_trace'). - type: double? - PeptideQuantification__EMGScoring__max_iteration: - doc: Maximum number of iterations for EMG fitting. - type: long? - PeptideQuantification__EMGScoring__init_mom: - doc: Alternative initial parameters for fitting through method of moments. - type: boolean? - Alignment__model_type: - doc: Options to control the modeling of retention time transformations from data - type: string? - Alignment__model__type: - doc: Type of model - type: string? - Alignment__model__linear__symmetric_regression: - doc: Perform linear regression on 'y - x' vs. 'y + x', instead of on 'y' vs. 'x'. - type: boolean? - Alignment__model__linear__x_weight: - doc: Weight x values - type: string? - Alignment__model__linear__y_weight: - doc: Weight y values - type: string? - Alignment__model__linear__x_datum_min: - doc: Minimum x value - type: double? - Alignment__model__linear__x_datum_max: - doc: Maximum x value - type: double? - Alignment__model__linear__y_datum_min: - doc: Minimum y value - type: double? - Alignment__model__linear__y_datum_max: - doc: Maximum y value - type: double? - Alignment__model__b_spline__wavelength: - doc: Determines the amount of smoothing by setting the number of nodes for the B-spline. The number is chosen so that the spline approximates a low-pass filter with this cutoff wavelength. The wavelength is given in the same units as the data; a higher value means more smoothing. '0' sets the number of nodes to twice the number of input points. - type: double? - Alignment__model__b_spline__num_nodes: - doc: Number of nodes for B-spline fitting. Overrides 'wavelength' if set (to two or greater). A lower value means more smoothing. - type: long? - Alignment__model__b_spline__extrapolate: - doc: "Method to use for extrapolation beyond the original data range. 'linear': Linear extrapolation using the slope of the B-spline at the corresponding endpoint. 'b_spline': Use the B-spline (as for interpolation). 'constant': Use the constant value of the B-spline at the corresponding endpoint. 'global_linear': Use a linear fit through the data (which will most probably introduce discontinuities at the ends of the data range)." - type: string? - Alignment__model__b_spline__boundary_condition: - doc: "Boundary condition at B-spline endpoints: 0 (value zero), 1 (first derivative zero) or 2 (second derivative zero)" - type: long? - Alignment__model__lowess__span: - doc: Fraction of datapoints (f) to use for each local regression (determines the amount of smoothing). Choosing this parameter in the range .2 to .8 usually results in a good fit. - type: double? - Alignment__model__lowess__num_iterations: - doc: Number of robustifying iterations for lowess fitting. - type: long? - Alignment__model__lowess__delta: - doc: Nonnegative parameter which may be used to save computations (recommended value is 0.01 of the range of the input, e.g. for data ranging from 1000 seconds to 2000 seconds, it could be set to 10). Setting a negative value will automatically do this. - type: double? - Alignment__model__lowess__interpolation_type: - doc: "Method to use for interpolation between datapoints computed by lowess. 'linear': Linear interpolation. 'cspline': Use the cubic spline for interpolation. 'akima': Use an akima spline for interpolation" - type: string? - Alignment__model__lowess__extrapolation_type: - doc: "Method to use for extrapolation outside the data range. 'two-point-linear': Uses a line through the first and last point to extrapolate. 'four-point-linear': Uses a line through the first and second point to extrapolate in front and and a line through the last and second-to-last point in the end. 'global-linear': Uses a linear regression to fit a line through all data points and use it for interpolation." - type: string? - Alignment__model__interpolated__interpolation_type: - doc: Type of interpolation to apply. - type: string? - Alignment__model__interpolated__extrapolation_type: - doc: "Type of extrapolation to apply: two-point-linear: use the first and last data point to build a single linear model, four-point-linear: build two linear models on both ends using the first two / last two points, global-linear: use all points to build a single linear model. Note that global-linear may not be continuous at the border." - type: string? - Alignment__align_algorithm__score_type: - doc: Name of the score type to use for ranking and filtering (.oms input only). If left empty, a score type is picked automatically. - type: string? - Alignment__align_algorithm__score_cutoff: - doc: Use only IDs above a score cut-off (parameter 'min_score') for alignment? - type: boolean? - Alignment__align_algorithm__min_score: - doc: "If 'score_cutoff' is 'true': Minimum score for an ID to be considered.\nUnless you have very few runs or identifications, increase this value to focus on more informative peptides." - type: double? - Alignment__align_algorithm__min_run_occur: - doc: "Minimum number of runs (incl. reference, if any) in which a peptide must occur to be used for the alignment.\nUnless you have very few runs or identifications, increase this value to focus on more informative peptides." - type: long? - Alignment__align_algorithm__max_rt_shift: - doc: "Maximum realistic RT difference for a peptide (median per run vs. reference). Peptides with higher shifts (outliers) are not used to compute the alignment.\nIf 0, no limit (disable filter); if > 1, the final value in seconds; if <= 1, taken as a fraction of the range of the reference RT scale." - type: double? - Alignment__align_algorithm__use_unassigned_peptides: - doc: Should unassigned peptide identifications be used when computing an alignment of feature or consensus maps? If 'false', only peptide IDs assigned to features will be used. - type: boolean? - Alignment__align_algorithm__use_feature_rt: - doc: "When aligning feature or consensus maps, don't use the retention time of a peptide identification directly; instead, use the retention time of the centroid of the feature (apex of the elution profile) that the peptide was matched to. If different identifications are matched to one feature, only the peptide closest to the centroid in RT is used.\nPrecludes 'use_unassigned_peptides'." - type: string? - Alignment__align_algorithm__use_adducts: - doc: If IDs contain adducts, treat differently adducted variants of the same molecule as different. - type: string? - Linking__use_identifications: - doc: Never link features that are annotated with different peptides (only the best hit per peptide identification is taken into account). - type: string? - Linking__nr_partitions: - doc: How many partitions in m/z space should be used for the algorithm (more partitions means faster runtime and more memory efficient execution). - type: long? - Linking__min_nr_diffs_per_bin: - doc: "If IDs are used: How many differences from matching IDs should be used to calculate a linking tolerance for unIDed features in an RT region. RT regions will be extended until that number is reached." - type: long? - Linking__min_IDscore_forTolCalc: - doc: "If IDs are used: What is the minimum score of an ID to assume a reliable match for tolerance calculation. Check your current score type!" - type: double? - Linking__noID_penalty: - doc: "If IDs are used: For the normalized distances, how high should the penalty for missing IDs be? 0 = no bias, 1 = IDs inside the max tolerances always preferred (even if much further away)." - type: double? - Linking__ignore_charge: - doc: "false [default]: pairing requires equal charge state (or at least one unknown charge '0'); true: Pairing irrespective of charge state" - type: boolean? - Linking__ignore_adduct: - doc: "true [default]: pairing requires equal adducts (or at least one without adduct annotation); true: Pairing irrespective of adducts" - type: string? - Linking__distance_RT__exponent: - doc: Normalized RT differences ([0-1], relative to 'max_difference') are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow) - type: double? - Linking__distance_RT__weight: - doc: Final RT distances are weighted by this factor - type: double? - Linking__distance_MZ__max_difference: - doc: Never pair features with larger m/z distance (unit defined by 'unit') - type: double? - Linking__distance_MZ__unit: - doc: Unit of the 'max_difference' parameter - type: string? - Linking__distance_MZ__exponent: - doc: Normalized ([0-1], relative to 'max_difference') m/z differences are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow) - type: double? - Linking__distance_MZ__weight: - doc: Final m/z distances are weighted by this factor - type: double? - Linking__distance_intensity__exponent: - doc: Differences in relative intensity ([0-1]) are raised to this power (using 1 or 2 will be fast, everything else is REALLY slow) - type: double? - Linking__distance_intensity__weight: - doc: Final intensity distances are weighted by this factor - type: double? - Linking__distance_intensity__log_transform: - doc: Log-transform intensities? If disabled, d = |int_f2 - int_f1| / int_max. If enabled, d = |log(int_f2 + 1) - log(int_f1 + 1)| / log(int_max + 1)) - type: string? - ProteinQuantification__method: - doc: "- top - quantify based on three most abundant peptides (number can be changed in 'top').\n- iBAQ (intensity based absolute quantification), calculate the sum of all peptide peak intensities divided by the number of theoretically observable tryptic peptides (https://rdcu.be/cND1J). Warning: only consensusXML or featureXML input is allowed!" - type: string? - ProteinQuantification__best_charge_and_fraction: - doc: "Distinguish between fraction and charge states of a peptide. For peptides, abundances will be reported separately for each fraction and charge;\nfor proteins, abundances will be computed based only on the most prevalent charge observed of each peptide (over all fractions).\nBy default, abundances are summed over all charge states." - type: boolean? - ProteinQuantification__top__N: - doc: Calculate protein abundance from this number of proteotypic peptides (most abundant first; '0' for all) - type: long? - ProteinQuantification__top__aggregate: - doc: Aggregation method used to compute protein abundances from peptide abundances - type: string? - ProteinQuantification__top__include_all: - doc: Include results for proteins with fewer proteotypic peptides than indicated by 'N' (no effect if 'N' is 0 or 1) - type: string? - ProteinQuantification__consensus__normalize: - doc: Scale peptide abundances so that medians of all samples are equal - type: boolean? - ProteinQuantification__consensus__fix_peptides: - doc: "Use the same peptides for protein quantification across all samples.\nWith 'N 0',all peptides that occur in every sample are considered.\nOtherwise ('N'), the N peptides that occur in the most samples (independently of each other) are selected,\nbreaking ties by total abundance (there is no guarantee that the best co-ocurring peptides are chosen!)." - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - out_msstats: - type: File? - outputBinding: - glob: $(inputs.out_msstats) - out_triqler: - type: File? - outputBinding: - glob: $(inputs.out_triqler) - out_cxml: - type: File? - outputBinding: - glob: $(inputs.out_cxml) - PeptideQuantification__candidates_out: - type: File? - outputBinding: - glob: $(inputs.PeptideQuantification__candidates_out) - PeptideQuantification__svm__xval_out: - type: File? - outputBinding: - glob: $(inputs.PeptideQuantification__svm__xval_out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - ProteomicsLFQ -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/QCCalculator.cwl b/workflow/cwl/QCCalculator.cwl deleted file mode 100644 index 02a01cf7145..00000000000 --- a/workflow/cwl/QCCalculator.cwl +++ /dev/null @@ -1,74 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: QCCalculator -doc: Calculates basic quality parameters from MS experiments and subsequent analysis data as identification or feature detection. -inputs: - in: - doc: raw data input file (this is relevant if you want to look at MS1, MS2 and precursor peak information) - type: File - out: - doc: Your QC file. - type: string - out_type: - doc: "Output file type -- default: determined from file extension or content" - type: string? - label: - doc: unique name for the run that can be used in a figure label - type: string? - name: - doc: name of the person creating this mzQC file - type: string? - address: - doc: contact address (mail/e-mail or phone) - type: string? - description: - doc: description and comments about the mzQC file contents - type: string? - id: - doc: Input idXML file containing the identifications. Your identifications will be exported in an easy-to-read format - type: File? - feature: - doc: feature input file (this is relevant for most QC issues) - type: File? - consensus: - doc: consensus input file (this is only used for charge state deconvoluted output. Use the consensusXML output form the DeCharger) - type: File? - remove_duplicate_features: - doc: This flag should be set, if you work with a set of merged features. - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - QCCalculator -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/QCEmbedder.cwl b/workflow/cwl/QCEmbedder.cwl deleted file mode 100644 index 0fb270756a8..00000000000 --- a/workflow/cwl/QCEmbedder.cwl +++ /dev/null @@ -1,65 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: QCEmbedder -doc: Attaches a table or an image to a given qc parameter. -inputs: - in: - doc: Input qcml file - type: File? - qp_att_acc: - doc: Defines the qp cv accession of the qp to which the table/image is attached. - type: string? - cv_acc: - doc: Defines the cv accession of the attachment. - type: string - run: - doc: The file that defined the run under which the qp for the attachment is aggregated as mzML file. The file is only used to extract the run name from the file name. - type: File? - name: - doc: If no file for the run was given (or if the target qp is contained in a set), at least a name of the target run/set containing the the qp for the attachment has to be given. - type: string? - plot: - doc: If a plot image is to be attached to a qp, this has to be specified here. - type: File? - table: - doc: If a table is to be attached to a qp, this has to be specified here. - type: File? - out: - doc: Output extended qcML file - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - QCEmbedder -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/QCExporter.cwl b/workflow/cwl/QCExporter.cwl deleted file mode 100644 index 61be7da5623..00000000000 --- a/workflow/cwl/QCExporter.cwl +++ /dev/null @@ -1,53 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: QCExporter -doc: Will extract several qp from several run/sets in a tabular format. -inputs: - in: - doc: Input qcml file - type: File - names: - doc: The name of the target runs or sets to be exported from. If empty, from all will be exported. - type: string[]? - mapping: - doc: The mapping of the exported table's headers to the according qp cvs. The first row is considered containing the headers as for the exported the table. The second row is considered the according qp cv accessions of the qp to be exported. - type: File - out_csv: - doc: Output csv formatted quality parameter. - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out_csv: - type: File - outputBinding: - glob: $(inputs.out_csv) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - QCExporter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/QCExtractor.cwl b/workflow/cwl/QCExtractor.cwl deleted file mode 100644 index c6a269ca54c..00000000000 --- a/workflow/cwl/QCExtractor.cwl +++ /dev/null @@ -1,56 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: QCExtractor -doc: Extracts a table attachment to a given qc parameter. -inputs: - in: - doc: Input qcml file - type: File - qp: - doc: Target attachment qp. - type: string - run: - doc: The file that defined the run under which the qp for the attachment is aggregated as mzML file. The file is only used to extract the run name from the file name. - type: File? - name: - doc: If no file for the run was given (or if the target qp is contained in a set), at least a name of the target run/set containing the the qp for the attachment has to be given. - type: string? - out_csv: - doc: Output csv formatted table. - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out_csv: - type: File - outputBinding: - glob: $(inputs.out_csv) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - QCExtractor -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/QCImporter.cwl b/workflow/cwl/QCImporter.cwl deleted file mode 100644 index e0e97099193..00000000000 --- a/workflow/cwl/QCImporter.cwl +++ /dev/null @@ -1,53 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: QCImporter -doc: Imports tables with quality control parameters into qcml files. -inputs: - in: - doc: Input qcml file - type: File? - table: - doc: The table containing the additional qp values in the columns. First row is considered containing the header. The target run or set names/ids are indicated by column "raw data file", so each row after the header will contain the values of qps for that run. (csv without "!) - type: File - mapping: - doc: The mapping of the table header to the according qp cvs, also in csv format. The first row is considered containing the headers as in the table. The second row is considered the according qp cv accessions. (csv without "!) - type: File - out: - doc: Output extended qcML file - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - QCImporter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/QCMerger.cwl b/workflow/cwl/QCMerger.cwl deleted file mode 100644 index fc39bda254d..00000000000 --- a/workflow/cwl/QCMerger.cwl +++ /dev/null @@ -1,50 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: QCMerger -doc: Merges two qcml files together. -inputs: - in: - doc: List of qcml files to be merged. - type: File[] - out: - doc: Output extended/reduced qcML file - type: string - setname: - doc: Use only when all given qcml files belong to one set, which will be held under the given name. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - QCMerger -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/QCShrinker.cwl b/workflow/cwl/QCShrinker.cwl deleted file mode 100644 index 37677dc5108..00000000000 --- a/workflow/cwl/QCShrinker.cwl +++ /dev/null @@ -1,56 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: QCShrinker -doc: Remove unneeded or verbose table attachments from a qcml file. -inputs: - in: - doc: Input qcml file - type: File - qp_accessions: - doc: A list of cv accessions that should be removed. If empty, the usual suspects will be removed! - type: string[]? - name: - doc: The name of the target run or set that contains the requested quality parameter. - type: string? - run: - doc: The file from which the name of the target run that contains the requested quality parameter is taken. This overrides the name parameter! - type: File? - out: - doc: Output extended/reduced qcML file - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - QCShrinker -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/QualityControl.cwl b/workflow/cwl/QualityControl.cwl deleted file mode 100644 index d20aee4f0e2..00000000000 --- a/workflow/cwl/QualityControl.cwl +++ /dev/null @@ -1,84 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: QualityControl -doc: "Computes various QC metrics.\nMany input formats are supported only the consensusXML is required.\nThe more optional files you provide, the more metrics you get." -inputs: - in_cm: - doc: ConsensusXML input, generated by FeatureLinker. - type: File - in_raw: - doc: MzML input (after InternalCalibration, if available) - type: File[]? - in_postFDR: - doc: FeatureXMLs after FDR filtering - type: File[]? - out: - doc: Output mzTab with QC information - type: string? - out_cm: - doc: ConsensusXML with QC information (as metavalues) - type: string? - in_contaminants: - doc: Proteins considered contaminants - type: File? - in_fasta: - doc: FASTA file used during MS/MS identification (including decoys). If the protein description contains 'GN=...' then gene names will be extracted - type: File? - in_trafo: - doc: trafoXMLs from MapAligners - type: File[]? - out_evd: - doc: If a Path is given, a MQEvidence txt-file will be created in this directory. If the directory does not exist, it will be created as well. - type: string? - out_msms: - doc: If a Path is given, a MQMsms txt-file will be created in this directory. If the directory does not exist, it will be created as well. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - FragmentMassError__unit: - doc: Unit for mass tolerance. 'auto' uses information from FeatureXML - type: string? - FragmentMassError__tolerance: - doc: m/z search window for matching peaks in two spectra - type: double? - MS2_id_rate__assume_all_target: - doc: Forces the metric to run even if target/decoy annotation is missing (accepts all pep_ids as target hits). - type: boolean? -outputs: - out: - type: File? - outputBinding: - glob: $(inputs.out) - out_cm: - type: File? - outputBinding: - glob: $(inputs.out_cm) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - QualityControl -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/RNADigestor.cwl b/workflow/cwl/RNADigestor.cwl deleted file mode 100644 index c158a0d7852..00000000000 --- a/workflow/cwl/RNADigestor.cwl +++ /dev/null @@ -1,65 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: RNADigestor -doc: Digests an RNA sequence database in-silico. -inputs: - in: - doc: Input file containing RNA sequences - type: File - out: - doc: Output file containing sequence fragments - type: string - missed_cleavages: - doc: The number of allowed missed cleavages - type: long? - min_length: - doc: Minimum length of a fragment - type: long? - max_length: - doc: Maximum length of a fragment - type: long? - enzyme: - doc: Digestion enzyme (RNase) - type: string? - unique: - doc: Report each unique sequence fragment only once - type: boolean? - cdna: - doc: Input file contains cDNA sequences - replace 'T' with 'U') - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - RNADigestor -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/RNAMassCalculator.cwl b/workflow/cwl/RNAMassCalculator.cwl deleted file mode 100644 index 40c734ec99a..00000000000 --- a/workflow/cwl/RNAMassCalculator.cwl +++ /dev/null @@ -1,65 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: RNAMassCalculator -doc: Calculates masses, mass-to-charge ratios and sum formulas of RNA sequences -inputs: - in: - doc: Input file with RNA sequences and optionally charge numbers (mutually exclusive to 'in_seq') - type: File? - in_seq: - doc: List of RNA sequences (mutually exclusive to 'in') - type: string[]? - out: - doc: Output file; if empty, output is written to the screen - type: string? - charge: - doc: List of charge states; required if 'in_seq' is given - type: long[]? - format: - doc: "Output format ('list': human-readable list, 'table': CSV-like table, 'mass_only': mass values only, 'mz_only': m/z values only, 'formula_only': sum formula only)\n" - type: string? - average_mass: - doc: Compute average (instead of monoisotopic) oligonucleotide masses - type: boolean? - fragment_type: - doc: "For what type of sequence/fragment the mass should be computed\n" - type: string? - separator: - doc: Field separator for 'table' output format; by default, the 'tab' character is used - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File? - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - RNAMassCalculator -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/RNPxlXICFilter.cwl b/workflow/cwl/RNPxlXICFilter.cwl deleted file mode 100644 index fe8a5ef8f0d..00000000000 --- a/workflow/cwl/RNPxlXICFilter.cwl +++ /dev/null @@ -1,59 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: RNPxlXICFilter -doc: Remove MS2 spectra from treatment based on the fold change between control and treatment. -inputs: - control: - doc: input mzML file - type: File - treatment: - doc: input mzML file - type: File - fold_change: - doc: fold change between XICs - type: double? - rt_tol: - doc: RT tolerance in [s] for finding max peak (whole RT range around RT middle) - type: double? - mz_tol: - doc: m/z tolerance in [ppm] for finding a peak - type: double? - out: - doc: output of the treatment file after XIC filtering. - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - RNPxlXICFilter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/Resampler.cwl b/workflow/cwl/Resampler.cwl deleted file mode 100644 index ccc0a064a79..00000000000 --- a/workflow/cwl/Resampler.cwl +++ /dev/null @@ -1,59 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: Resampler -doc: Transforms an LC/MS map into a resampled map or a PNG image. -inputs: - in: - doc: "input file " - type: File - out: - doc: output file in mzML format - type: string - sampling_rate: - doc: New sampling rate in m/z dimension (in Th unless ppm flag is set) - type: double? - ppm: - doc: sampling_rate is given in ppm - type: boolean? - align_sampling: - doc: Ensures that sampling is performed equally across the map (same raster is used for all spectra) - type: boolean? - min_int_cutoff: - doc: Intensity cutoff for peaks to be stored in output spectrum (only peaks above this cutoff will be stored, -1 means store all data) - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - Resampler -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SageAdapter.cwl b/workflow/cwl/SageAdapter.cwl deleted file mode 100644 index 16ae149c1b3..00000000000 --- a/workflow/cwl/SageAdapter.cwl +++ /dev/null @@ -1,176 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SageAdapter -doc: Annotates MS/MS spectra using Sage. -inputs: - in: - doc: Input files separated by blank - type: File[] - out: - doc: Single output file containing all search results. - type: string - database: - doc: FASTA file - type: File - sage_executable: - doc: The Sage executable. Provide a full or relative path, or make sure it can be found in your PATH environment. - type: File - decoy_prefix: - doc: "Prefix on protein accession used to distinguish decoy from target proteins. NOTE: Decoy suffix is currently not supported by sage." - type: string? - batch_size: - doc: "Number of files to load and search in parallel (default = # of CPUs/2)" - type: long? - precursor_tol_left: - doc: Start (left side) of the precursor tolerance window w.r.t. precursor location. Usually used with negative values smaller or equal to the 'right' counterpart. - type: double? - precursor_tol_right: - doc: End (right side) of the precursor tolerance window w.r.t. precursor location. Usually used with positive values larger or equal to the 'left' counterpart. - type: double? - precursor_tol_unit: - doc: Unit of precursor tolerance (ppm or Da) - type: string? - fragment_tol_left: - doc: Start (left side) of the fragment tolerance window w.r.t. precursor location. Usually used with negative values smaller or equal to the 'right' counterpart. - type: double? - fragment_tol_right: - doc: End (right side) of the fragment tolerance window w.r.t. precursor location. Usually used with positive values larger or equal to the 'left' counterpart. - type: double? - fragment_tol_unit: - doc: Unit of fragment tolerance (ppm or Da) - type: string? - min_matched_peaks: - doc: Minimum number of b+y ions required to match for PSM to be reported - type: long? - min_peaks: - doc: Minimum number of peaks required for a spectrum to be considered - type: long? - max_peaks: - doc: Take the top N most intense MS2 peaks only for matching - type: long? - report_psms: - doc: Number of hits (PSMs) to report for each spectrum - type: long? - bucket_size: - doc: "How many fragments are in each internal mass bucket (default: 8192 for hi-res data). Try increasing it to 32k or 64k for low-res. See also: fragment_tol_*" - type: long? - min_len: - doc: Minimum peptide length - type: long? - max_len: - doc: Maximum peptide length - type: long? - missed_cleavages: - doc: Number of missed cleavages - type: long? - fragment_min_mz: - doc: Minimum fragment m/z - type: double? - fragment_max_mz: - doc: Maximum fragment m/z - type: double? - peptide_min_mass: - doc: Minimum monoisotopic peptide mass to consider a peptide from the DB - type: double? - peptide_max_mass: - doc: Maximum monoisotopic peptide mass to consider a peptide from the DB - type: double? - min_ion_index: - doc: Minimum ion index to consider for preliminary scoring. Default = 2 to skip b1/y1 AND (sic) b2/y2 ions that are often missing. - type: long? - max_variable_mods: - doc: Maximum number of variable modifications - type: long? - isotope_error_range: - doc: Range of (C13) isotope errors to consider for precursor.Can be negative. E.g. '-1,3' for considering '-1/0/1/2/3' - type: string? - charges: - doc: Range of precursor charges to consider if not annotated in the file. - type: string? - enzyme: - doc: The enzyme used for peptide digestion. - type: string? - fixed_modifications: - doc: Fixed modifications, specified using Unimod (www.unimod.org) terms, e.g. 'Carbamidomethyl (C)' or 'Oxidation (M)' - type: string[]? - variable_modifications: - doc: Variable modifications, specified using Unimod (www.unimod.org) terms, e.g. 'Carbamidomethyl (C)' or 'Oxidation (M)' - type: string[]? - reindex: - doc: Recalculate peptide to protein association using OpenMS. Annotates target-decoy information. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - PeptideIndexing__decoy_string: - doc: String that was appended (or prefixed - see 'decoy_string_position' flag below) to the accessions in the protein database to indicate decoy proteins. If empty (default), it's determined automatically (checking for common terms, both as prefix and suffix). - type: string? - PeptideIndexing__decoy_string_position: - doc: Is the 'decoy_string' prepended (prefix) or appended (suffix) to the protein accession? (ignored if decoy_string is empty) - type: string? - PeptideIndexing__missing_decoy_action: - doc: "Action to take if NO peptide was assigned to a decoy protein (which indicates wrong database or decoy string): 'error' (exit with error, no output), 'warn' (exit with success, warning message), 'silent' (no action is taken, not even a warning)" - type: string? - PeptideIndexing__write_protein_sequence: - doc: If set, the protein sequences are stored as well. - type: boolean? - PeptideIndexing__write_protein_description: - doc: If set, the protein description is stored as well. - type: boolean? - PeptideIndexing__keep_unreferenced_proteins: - doc: If set, protein hits which are not referenced by any peptide are kept. - type: boolean? - PeptideIndexing__unmatched_action: - doc: "If peptide sequences cannot be matched to any protein: 1) raise an error; 2) warn (unmatched PepHits will miss target/decoy annotation with downstream problems); 3) remove the hit." - type: string? - PeptideIndexing__aaa_max: - doc: Maximal number of ambiguous amino acids (AAAs) allowed when matching to a protein database with AAAs. AAAs are 'B', 'J', 'Z' and 'X'. - type: long? - PeptideIndexing__mismatches_max: - doc: Maximal number of mismatched (mm) amino acids allowed when matching to a protein database. The required runtime is exponential in the number of mm's; apply with care. MM's are allowed in addition to AAA's. - type: long? - PeptideIndexing__IL_equivalent: - doc: Treat the isobaric amino acids isoleucine ('I') and leucine ('L') as equivalent (indistinguishable). Also occurrences of 'J' will be treated as 'I' thus avoiding ambiguous matching. - type: boolean? - PeptideIndexing__allow_nterm_protein_cleavage: - doc: Allow the protein N-terminus amino acid to clip. - type: string? - PeptideIndexing__enzyme__name: - doc: "Enzyme which determines valid cleavage sites - e.g. trypsin cleaves after lysine (K) or arginine (R), but not before proline (P). Default: deduce from input" - type: string? - PeptideIndexing__enzyme__specificity: - doc: "Specificity of the enzyme. Default: deduce from input.\n 'full': both internal cleavage sites must match.\n 'semi': one of two internal cleavage sites must match.\n 'none': allow all peptide hits no matter their context (enzyme is irrelevant)." - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SageAdapter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SeedListGenerator.cwl b/workflow/cwl/SeedListGenerator.cwl deleted file mode 100644 index 4db18cc425f..00000000000 --- a/workflow/cwl/SeedListGenerator.cwl +++ /dev/null @@ -1,50 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SeedListGenerator -doc: Generates seed lists for feature detection. -inputs: - in: - doc: Input file (see below for details) - type: File - out_prefix: - doc: Output file prefix - type: string - use_peptide_mass: - doc: "[idXML input only] Use the monoisotopic mass of the best peptide hit for the m/z position (default: use precursor m/z)" - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out_prefix: - type: File - outputBinding: - glob: $(inputs.out_prefix)* -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SeedListGenerator -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SemanticValidator.cwl b/workflow/cwl/SemanticValidator.cwl deleted file mode 100644 index ef31e764009..00000000000 --- a/workflow/cwl/SemanticValidator.cwl +++ /dev/null @@ -1,47 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SemanticValidator -doc: SemanticValidator for semantically validating certain XML files. -inputs: - in: - doc: Input file (any xml file) - type: File - mapping_file: - doc: Mapping file which is used to semantically validate the given XML file against this mapping file (see 'share/OpenMS/MAPPING' for templates). - type: File - cv: - doc: Controlled Vocabulary files containg the CV terms (if left empty, a set of default files are used) - type: File[]? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - [] -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SemanticValidator -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SequenceCoverageCalculator.cwl b/workflow/cwl/SequenceCoverageCalculator.cwl deleted file mode 100644 index 66cad68562c..00000000000 --- a/workflow/cwl/SequenceCoverageCalculator.cwl +++ /dev/null @@ -1,50 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SequenceCoverageCalculator -doc: Prints information about idXML files. -inputs: - in_database: - doc: input file containing the database in FASTA format - type: File - in_peptides: - doc: input file containing the identified peptides - type: File - out: - doc: Optional text output file. If left out, the output is written to the command line. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File? - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SequenceCoverageCalculator -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SimpleSearchEngine.cwl b/workflow/cwl/SimpleSearchEngine.cwl deleted file mode 100644 index 9f6ea93d85f..00000000000 --- a/workflow/cwl/SimpleSearchEngine.cwl +++ /dev/null @@ -1,104 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SimpleSearchEngine -doc: Annotates MS/MS spectra using SimpleSearchEngine. -inputs: - in: - doc: "input file " - type: File - database: - doc: "input file " - type: File - out: - doc: "output file " - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - Search__enzyme: - doc: The enzyme used for peptide digestion. - type: string? - Search__decoys: - doc: Should decoys be generated? - type: boolean? - Search__precursor__mass_tolerance: - doc: +/- tolerance for precursor mass. - type: double? - Search__precursor__mass_tolerance_unit: - doc: Unit of precursor mass tolerance. - type: string? - Search__precursor__min_charge: - doc: Minimum precursor charge to be considered. - type: long? - Search__precursor__max_charge: - doc: Maximum precursor charge to be considered. - type: long? - Search__precursor__isotopes: - doc: "Corrects for mono-isotopic peak misassignments. (E.g.: 1 = prec. may be misassigned to first isotopic peak)" - type: long[]? - Search__fragment__mass_tolerance: - doc: Fragment mass tolerance - type: double? - Search__fragment__mass_tolerance_unit: - doc: Unit of fragment m - type: string? - Search__modifications__fixed: - doc: Fixed modifications, specified using UniMod (www.unimod.org) terms, e.g. 'Carbamidomethyl (C)' - type: string[]? - Search__modifications__variable: - doc: Variable modifications, specified using UniMod (www.unimod.org) terms, e.g. 'Oxidation (M)' - type: string[]? - Search__modifications__variable_max_per_peptide: - doc: Maximum number of residues carrying a variable modification per candidate peptide - type: long? - Search__annotate__PSM: - doc: Annotations added to each PSM. - type: string[]? - Search__peptide__min_size: - doc: Minimum size a peptide must have after digestion to be considered in the search. - type: long? - Search__peptide__max_size: - doc: Maximum size a peptide must have after digestion to be considered in the search (0 = disabled). - type: long? - Search__peptide__missed_cleavages: - doc: Number of missed cleavages. - type: long? - Search__peptide__motif: - doc: If set, only peptides that contain this motif (provided as RegEx) will be considered. - type: string? - Search__report__top_hits: - doc: Maximum number of top scoring hits per spectrum that are reported. - type: long? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SimpleSearchEngine -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SiriusAdapter.cwl b/workflow/cwl/SiriusAdapter.cwl deleted file mode 100644 index fdb4a5f4662..00000000000 --- a/workflow/cwl/SiriusAdapter.cwl +++ /dev/null @@ -1,176 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SiriusAdapter -doc: Metabolite identification using single and tandem mass spectrometry -inputs: - sirius_executable: - doc: The Sirius executable. Provide a full or relative path, or make sure it can be found in your PATH environment. - type: File? - in: - doc: MzML Input file - type: File - in_featureinfo: - doc: FeatureXML input with feature and adduct information - type: File? - out_sirius: - doc: MzTab output file for SIRIUS results - type: string? - out_fingerid: - doc: MzTab output file for CSI:FingerID, if this parameter is given, SIRIUS will search for a molecular structure using CSI:FingerID after determining the sum formula - type: string? - out_ms: - doc: Internal SIRIUS .ms format after OpenMS preprocessing - type: string? - out_annotated_spectra: - doc: Export spectra with fragment annotations from SIRIUS - type: string? - out_project_space: - doc: Output directory for SIRIUS project space - type: string? - sirius_user_email: - doc: E-mail for your SIRIUS account. - type: string? - sirius_user_password: - doc: Password for your SIRIUS account. - type: string? - converter_mode: - doc: Use this flag in combination with the out_ms file to convert the input mzML and featureXML to a .ms file. Without further SIRIUS processing. - type: boolean? - read_sirius_stdout: - doc: Read and print the standard output and error of the Sirius executable, even if it succeeds. - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - preprocessing__filter_by_num_masstraces: - doc: Number of mass traces each feature has to have to be included. To use this parameter, setting the feature_only flag is necessary - type: long? - preprocessing__precursor_mz_tolerance: - doc: Tolerance window for precursor selection (Feature selection in regard to the precursor) - type: double? - preprocessing__precursor_mz_tolerance_unit: - doc: Unit of the precursor_mz_tolerance - type: string? - preprocessing__precursor_rt_tolerance: - doc: Tolerance window (left and right) for precursor selection [seconds] - type: double? - preprocessing__isotope_pattern_iterations: - doc: Number of iterations that should be performed to extract the C13 isotope pattern. If no peak is found (C13 distance) the function will abort. Be careful with noisy data - since this can lead to wrong isotope patterns - type: long? - preprocessing__feature_only: - doc: Uses the feature information from in_featureinfo to reduce the search space to MS2 associated with a feature - type: boolean? - preprocessing__no_masstrace_info_isotope_pattern: - doc: Use this flag if the masstrace information from a feature should be discarded and the isotope_pattern_iterations should be used instead - type: boolean? - project__maxmz: - doc: "Just consider compounds with a precursor mz lower or equal\nthis maximum mz. All other compounds in the input file\nare ignored." - type: long? - project__loglevel: - doc: "Set logging level of the Jobs SIRIUS will execute.\nValid values: SEVERE, WARNING, INFO, FINER, ALL\nDefault: WARNING" - type: string? - project__ignore_formula: - doc: Ignore given molecular formula in internal .ms format, while processing. - type: boolean? - project__q: - doc: Suppress shell output - type: boolean? - sirius__ppm_max: - doc: Maximum allowed mass deviation in ppm for decomposing masses [ppm]. - type: double? - sirius__ppm_max_ms2: - doc: "Maximum allowed mass deviation in ppm for decomposing masses in MS2 [ppm].If not specified, the same value as for the MS1 is used. " - type: double? - sirius__tree_timeout: - doc: Time out in seconds per fragmentation tree computations. 0 for an infinite amount of time - type: long? - sirius__compound_timeout: - doc: Maximal computation time in seconds for a single compound. 0 for an infinite amount of time. - type: long? - sirius__no_recalibration: - doc: Disable recalibration of input spectra - type: boolean? - sirius__profile: - doc: Name of the configuration profile - type: string? - sirius__formulas: - doc: Specify the neutral molecular formula of the measured compound to compute its tree or a list of candidate formulas the method should discriminate. Omit this option if you want to consider all possible molecular formulas - type: string? - sirius__ions_enforced: - doc: "The iontype/adduct of the MS/MS data. Example: [M+H]+, \n[M-H]-, [M+Cl]-, [M+Na]+, [M]+. You can also provide a \ncomma separated list of adducts." - type: string? - sirius__candidates: - doc: The number of formula candidates in the SIRIUS output - type: long? - sirius__candidates_per_ion: - doc: Minimum number of candidates in the output for each ionization. Set to force output of results for each possible ionization, even if not part of highest ranked results. - type: long? - sirius__elements_considered: - doc: Set the allowed elements for rare element detection. Write SBrClBSe to allow the elements S,Br,Cl,B and Se. - type: string? - sirius__elements_enforced: - doc: "Enforce elements for molecular formula determination. Write CHNOPSCl to allow the elements C, H, N, O, P, S and Cl. Add numbers in brackets to restrict the minimal and maximal allowed occurrence of these elements: CHNOP[5]S[8]Cl[1-2]. When one number is given then it is interpreted as upper bound." - type: string? - sirius__no_isotope_score: - doc: Disable isotope pattern score. - type: boolean? - sirius__no_isotope_filter: - doc: Disable molecular formula filter. When filtering is enabled, molecular formulas are excluded if their theoretical isotope pattern does not match the theoretical one, even if their MS/MS pattern has high score. - type: boolean? - sirius__ions_considered: - doc: "the iontype/adduct of the MS/MS data. Example: [M+H]+, [M-H]-, [M+Cl]-, [M+Na]+, [M]+. You can also provide a comma separated list of adducts." - type: string? - sirius__db: - doc: "Search formulas in the Union of the given databases db-name1,db-name2,db-name3. If no database is given all possible molecular formulas will be respected (no database is used). Example: possible DBs: ALL,BIO,PUBCHEM,MESH,HMDB,KNAPSACK,CHEBI,PUBMED,KEGG,HSDB,MACONDA,METACYC,GNPS,ZINCBIO,UNDP,YMDB,PLANTCYC,NORMAN,ADDITIONAL,PUBCHEMANNOTATIONBIO,PUBCHEMANNOTATIONDRUG,PUBCHEMANNOTATIONSAFETYANDTOXIC,PUBCHEMANNOTATIONFOOD,KEGGMINE,ECOCYCMINE,YMDBMINE" - type: string? - sirius__solver: - doc: "For GUROBI and CPLEX environment variables need to be configured. \n(see SIRIUS manual: https://boecker-lab.github.io/docs.sirius.github.io/install/)." - type: string? - fingerid__db: - doc: "Search structures in the Union of the given databases db-name1,db-name2,db-name3. If no database is given all possible molecular formulas will be respected (no database is used). Example: possible DBs: ALL,BIO,PUBCHEM,MESH,HMDB,KNAPSACK,CHEBI,PUBMED,KEGG,HSDB,MACONDA,METACYC,GNPS,ZINCBIO,UNDP,YMDB,PLANTCYC,NORMAN,ADDITIONAL,PUBCHEMANNOTATIONBIO,PUBCHEMANNOTATIONDRUG,PUBCHEMANNOTATIONSAFETYANDTOXIC,PUBCHEMANNOTATIONFOOD,KEGGMINE,ECOCYCMINE,YMDBMINE" - type: string? -outputs: - out_sirius: - type: File? - outputBinding: - glob: $(inputs.out_sirius) - out_fingerid: - type: File? - outputBinding: - glob: $(inputs.out_fingerid) - out_ms: - type: File? - outputBinding: - glob: $(inputs.out_ms) - out_annotated_spectra: - type: File? - outputBinding: - glob: $(inputs.out_annotated_spectra) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SiriusAdapter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SpecLibCreator.cwl b/workflow/cwl/SpecLibCreator.cwl deleted file mode 100644 index 561dc2caf3b..00000000000 --- a/workflow/cwl/SpecLibCreator.cwl +++ /dev/null @@ -1,56 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SpecLibCreator -doc: Creates an MSP formatted spectral library. -inputs: - info: - doc: Holds id, peptide, retention time etc. - type: File - itemseperator: - doc: " Separator between items. e.g. ," - type: string? - itemenclosed: - doc: "'true' or 'false' if true every item is enclosed e.g. '$peptide$,$run$..." - type: boolean? - spec: - doc: spectra - type: File - out: - doc: output MSP formatted spectra library - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SpecLibCreator -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SpecLibSearcher.cwl b/workflow/cwl/SpecLibSearcher.cwl deleted file mode 100644 index 4620450b222..00000000000 --- a/workflow/cwl/SpecLibSearcher.cwl +++ /dev/null @@ -1,89 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SpecLibSearcher -doc: Identifies peptide MS/MS spectra by spectral matching with a searchable spectral library. -inputs: - in: - doc: Input files - type: File[] - lib: - doc: searchable spectral library (MSP format) - type: File - compare_function: - doc: function for similarity comparison - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - precursor__mass_tolerance: - doc: Width of precursor mass tolerance window - type: double? - precursor__mass_tolerance_unit: - doc: Unit of precursor mass tolerance. - type: string? - precursor__min_charge: - doc: Minimum precursor charge to be considered. - type: long? - precursor__max_charge: - doc: Maximum precursor charge to be considered. - type: long? - precursor__isotopes: - doc: "Corrects for mono-isotopic peak misassignments. (E.g.: 1 = prec. may be misassigned to first isotopic peak)" - type: long[]? - fragment__mass_tolerance: - doc: Fragment mass tolerance - type: double? - report__top_hits: - doc: Maximum number of top scoring hits per spectrum that are reported. - type: long? - filter__remove_peaks_below_threshold: - doc: All peaks of a query spectrum with intensities below will be zeroed. - type: double? - filter__min_peaks: - doc: required minimum number of peaks for a query spectrum - type: long? - filter__max_peaks: - doc: Use only the top of peaks. - type: long? - filter__cut_peaks_below: - doc: Remove all peaks which are lower than 1/ of the highest peaks. Default equals all peaks which are lower than 0.001 of the maximum intensity peak - type: long? - modifications__fixed: - doc: Fixed modifications, specified using UniMod (www.unimod.org) terms, e.g. 'Carbamidomethyl (C)' - type: string[]? - modifications__variable: - doc: Variable modifications, specified using UniMod (www.unimod.org) terms, e.g. 'Oxidation (M)' - type: string[]? - modifications__variable_max_per_peptide: - doc: Maximum number of residues carrying a variable modification per candidate peptide - type: long? -outputs: - [] -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SpecLibSearcher -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SpectraFilterBernNorm.cwl b/workflow/cwl/SpectraFilterBernNorm.cwl deleted file mode 100644 index 05187fd59f1..00000000000 --- a/workflow/cwl/SpectraFilterBernNorm.cwl +++ /dev/null @@ -1,56 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SpectraFilterBernNorm -doc: Scales and filters spectra according using the Bern norm. -inputs: - in: - doc: "input file " - type: File - out: - doc: "output file " - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__C1: - doc: C1 value of the normalization. - type: double? - algorithm__C2: - doc: C2 value of the normalization. - type: double? - algorithm__threshold: - doc: Threshold of the Bern et al. normalization. - type: double? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SpectraFilterBernNorm -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SpectraFilterMarkerMower.cwl b/workflow/cwl/SpectraFilterMarkerMower.cwl deleted file mode 100644 index 4d127f1d641..00000000000 --- a/workflow/cwl/SpectraFilterMarkerMower.cwl +++ /dev/null @@ -1,45 +0,0 @@ -label: SpectraFilterMarkerMower -doc: Applies thresholdfilter to peak spectra. -inputs: - in: - doc: "input file " - type: File - out: - doc: "output file " - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SpectraFilterMarkerMower -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json \ No newline at end of file diff --git a/workflow/cwl/SpectraFilterNLargest.cwl b/workflow/cwl/SpectraFilterNLargest.cwl deleted file mode 100644 index e34e8fef260..00000000000 --- a/workflow/cwl/SpectraFilterNLargest.cwl +++ /dev/null @@ -1,50 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SpectraFilterNLargest -doc: Keeps only the n largest peaks per spectrum. -inputs: - in: - doc: "input file " - type: File - out: - doc: "output file " - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__n: - doc: The number of peaks to keep - type: long? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SpectraFilterNLargest -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SpectraFilterNormalizer.cwl b/workflow/cwl/SpectraFilterNormalizer.cwl deleted file mode 100644 index c5bfa353bc7..00000000000 --- a/workflow/cwl/SpectraFilterNormalizer.cwl +++ /dev/null @@ -1,50 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SpectraFilterNormalizer -doc: Scale intensities per spectrum to either sum to 1 or have a maximum of 1. -inputs: - in: - doc: input file - type: File - out: - doc: output file - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__method: - doc: Normalize via dividing by TIC ('to_TIC') per spectrum (i.e. all peaks sum to 1) or normalize to max. intensity to one ('to_one') per spectrum. - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SpectraFilterNormalizer -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SpectraFilterParentPeakMower.cwl b/workflow/cwl/SpectraFilterParentPeakMower.cwl deleted file mode 100644 index e93871c1e12..00000000000 --- a/workflow/cwl/SpectraFilterParentPeakMower.cwl +++ /dev/null @@ -1,71 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SpectraFilterParentPeakMower -doc: Applies thresholdfilter to peak spectra. -inputs: - in: - doc: "input file " - type: File - out: - doc: "output file " - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__window_size: - doc: The size of the m/z window where the peaks are removed, +/- window_size. - type: double? - algorithm__default_charge: - doc: If the precursor has no charge set, the default charge is assumed. - type: long? - algorithm__clean_all_charge_states: - doc: Set to 1 if precursor ions of all possible charge states should be removed. - type: long? - algorithm__consider_NH3_loss: - doc: Whether NH3 loss peaks from the precursor should be removed. - type: long? - algorithm__consider_H2O_loss: - doc: Whether H2O loss peaks from the precursor should be removed. - type: long? - algorithm__reduce_by_factor: - doc: Reduce the intensities of the precursor and related ions by a given factor (set 'set_to_zero' to 0). - type: long? - algorithm__factor: - doc: Factor which is used to reduce the intensities if 'reduce_by_factor' is selected. - type: double? - algorithm__set_to_zero: - doc: Reduce the intensities of the precursor and related ions to zero. - type: long? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SpectraFilterParentPeakMower -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SpectraFilterScaler.cwl b/workflow/cwl/SpectraFilterScaler.cwl deleted file mode 100644 index ae21a4c1db8..00000000000 --- a/workflow/cwl/SpectraFilterScaler.cwl +++ /dev/null @@ -1,47 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SpectraFilterScaler -doc: Applies thresholdfilter to peak spectra. -inputs: - in: - doc: "input file " - type: File - out: - doc: "output file " - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SpectraFilterScaler -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SpectraFilterSqrtMower.cwl b/workflow/cwl/SpectraFilterSqrtMower.cwl deleted file mode 100644 index b6bf3f87912..00000000000 --- a/workflow/cwl/SpectraFilterSqrtMower.cwl +++ /dev/null @@ -1,47 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SpectraFilterSqrtMower -doc: Applies thresholdfilter to peak spectra. -inputs: - in: - doc: "input file " - type: File - out: - doc: "output file " - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SpectraFilterSqrtMower -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SpectraFilterThresholdMower.cwl b/workflow/cwl/SpectraFilterThresholdMower.cwl deleted file mode 100644 index 349546a68a0..00000000000 --- a/workflow/cwl/SpectraFilterThresholdMower.cwl +++ /dev/null @@ -1,50 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SpectraFilterThresholdMower -doc: Applies thresholdfilter to peak spectra. -inputs: - in: - doc: "input file " - type: File - out: - doc: "output file " - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__threshold: - doc: Intensity threshold, peaks below this threshold are discarded - type: double? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SpectraFilterThresholdMower -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SpectraFilterWindowMower.cwl b/workflow/cwl/SpectraFilterWindowMower.cwl deleted file mode 100644 index fb65760b38e..00000000000 --- a/workflow/cwl/SpectraFilterWindowMower.cwl +++ /dev/null @@ -1,56 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SpectraFilterWindowMower -doc: Applies thresholdfilter to peak spectra. -inputs: - in: - doc: "input file " - type: File - out: - doc: "output file " - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__windowsize: - doc: The size of the sliding window along the m/z axis. - type: double? - algorithm__peakcount: - doc: The number of peaks that should be kept. - type: long? - algorithm__movetype: - doc: Whether sliding window (one peak steps) or jumping window (window size steps) should be used. - type: string? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SpectraFilterWindowMower -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SpectraMerger.cwl b/workflow/cwl/SpectraMerger.cwl deleted file mode 100644 index b756323ba03..00000000000 --- a/workflow/cwl/SpectraMerger.cwl +++ /dev/null @@ -1,107 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SpectraMerger -doc: Merges spectra (each MS level separately), increasing S/N ratios. -inputs: - in: - doc: Input mzML file. - type: File - out: - doc: Output mzML file with merged spectra. - type: string - merging_method: - doc: Method of merging which should be used. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__mz_binning_width: - doc: minimum m/z distance for two data points (profile data) or peaks (centroided data) to be considered distinct. Closer data points or peaks will be merged. - type: double? - algorithm__mz_binning_width_unit: - doc: Unit in which the distance between two data points or peaks is given. - type: string? - algorithm__sort_blocks: - doc: Sort blocks by before merging them (useful for precursor order) - type: string? - algorithm__average_gaussian__spectrum_type: - doc: Spectrum type of the MS level to be averaged - type: string? - algorithm__average_gaussian__ms_level: - doc: If set to be 0, each MS level will be merged from 1 to max. Otherwise, average spectra of this level. All other spectra remain unchanged. - type: long? - algorithm__average_gaussian__rt_FWHM: - doc: FWHM of Gauss curve in seconds to be averaged over. - type: double? - algorithm__average_gaussian__cutoff: - doc: Intensity cutoff for Gaussian. The Gaussian RT profile decreases from 1 at its apex to 0 at infinity. Spectra for which the intensity of the Gaussian drops below the cutoff do not contribute to the average. - type: double? - algorithm__average_gaussian__precursor_mass_tol: - doc: PPM mass tolerance for precursor mass. If set, MSn (n>2) spectra of precursor masses within the tolerance are averaged. - type: double? - algorithm__average_gaussian__precursor_max_charge: - doc: Possible maximum precursor ion charge. Effective only when average_gaussian:precursor_mass_tol option is active. - type: long? - algorithm__average_tophat__spectrum_type: - doc: Spectrum type of the MS level to be averaged - type: string? - algorithm__average_tophat__ms_level: - doc: If set to be 0, each MS level will be merged from 1 to max. Otherwise, average spectra of this level. All other spectra remain unchanged. - type: long? - algorithm__average_tophat__rt_range: - doc: RT range to be averaged over, i.e. +/-(RT range)/2 from each spectrum. - type: double? - algorithm__average_tophat__rt_unit: - doc: Unit for RT range. - type: string? - algorithm__block_method__ms_levels: - doc: Merge spectra of this level. All spectra with other MS levels remain untouched. - type: long[]? - algorithm__block_method__rt_block_size: - doc: Maximum number of scans to be summed up. - type: long? - algorithm__block_method__rt_max_length: - doc: Maximum RT size of the block in seconds (0.0 = no size restriction). - type: double? - algorithm__precursor_method__mz_tolerance: - doc: Max m/z distance of the precursor entries of two spectra to be merged in [Da]. - type: double? - algorithm__precursor_method__mass_tolerance: - doc: Max mass distance of the precursor entries of two spectra to be merged in [Da]. Active when set to a positive value. - type: double? - algorithm__precursor_method__rt_tolerance: - doc: Max RT distance of the precursor entries of two spectra to be merged in [s]. - type: double? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SpectraMerger -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/SpectraSTSearchAdapter.cwl b/workflow/cwl/SpectraSTSearchAdapter.cwl deleted file mode 100644 index 59c6ec5ecd1..00000000000 --- a/workflow/cwl/SpectraSTSearchAdapter.cwl +++ /dev/null @@ -1,71 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: SpectraSTSearchAdapter -doc: Interface to the SEARCH Mode of the SpectraST executable -inputs: - executable: - doc: Path to the SpectraST executable to use; may be empty if the executable is globally available. - type: File - spectra_files: - doc: File names(s) of spectra to be searched. - type: File[] - library_file: - doc: Specify library file. - type: File - sequence_database_file: - doc: The sequence database. - type: File? - sequence_database_type: - doc: Specify type of sequence database - type: string? - search_file: - doc: Only search a subset of the query spectra in the search file - type: File? - params_file: - doc: Read search options from file. All options set in the file will be overridden by command-line options, if specified. - type: File? - precursor_mz_tolerance: - doc: m/z (in Th) tolerance within which candidate entries are compared to the query. Monoisotopic mass is assumed. - type: double? - use_isotopically_averaged_mass: - doc: Use isotopically averaged mass instead of monoisotopic mass - type: boolean? - use_all_charge_states: - doc: Search library spectra of all charge states, i.e., ignore specified charge state (if any) of the query spectrum - type: boolean? - user_mod_file: - doc: Specify name of user-defined modifications file. Default is "spectrast.usermods". - type: File? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - [] -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - SpectraSTSearchAdapter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/StaticModification.cwl b/workflow/cwl/StaticModification.cwl deleted file mode 100644 index cfbf8760da9..00000000000 --- a/workflow/cwl/StaticModification.cwl +++ /dev/null @@ -1,53 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: StaticModification -doc: Applies a set of modifications to all PeptideIDs in an idXML file. -inputs: - in: - doc: "Input: identification results" - type: File - out: - doc: "Output: identification results with modifications applied" - type: string - mods: - doc: List of manual modifications, specified using Unimod (www.unimod.org) terms, e.g. 'Carbamidomethyl (C)' or 'Oxidation (M)'. - type: string[]? - presets: - doc: Add predefined sets, as shortcut to manually specifying a lot of modifications. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - StaticModification -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/TICCalculator.cwl b/workflow/cwl/TICCalculator.cwl deleted file mode 100644 index b89039713f1..00000000000 --- a/workflow/cwl/TICCalculator.cwl +++ /dev/null @@ -1,50 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: TICCalculator -doc: Calculates the TIC from a mass spectrometric raw file (useful for benchmarking). -inputs: - in: - doc: Input file to convert. - type: File - in_type: - doc: "Input file type -- default: determined from file extension or content\n" - type: string? - read_method: - doc: Method to read the file - type: string? - loadData: - doc: Whether to actually load and decode the binary data (or whether to skip decoding the binary data) - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - [] -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - TICCalculator -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/TOFCalibration.cwl b/workflow/cwl/TOFCalibration.cwl deleted file mode 100644 index 9cd03b2c440..00000000000 --- a/workflow/cwl/TOFCalibration.cwl +++ /dev/null @@ -1,185 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: TOFCalibration -doc: Applies time of flight calibration. -inputs: - in: - doc: "input peak or raw data file " - type: File - out: - doc: "output file " - type: string - ext_calibrants: - doc: "input file containing the external calibrant spectra (peak or raw data)\n" - type: File - ref_masses: - doc: input file containing reference masses of the external calibrant spectra (one per line) - type: File - tof_const: - doc: "File containing TOF conversion constants. These can be either two or three constants\nper set, depending on the conversion type. Either one set for all calibrant spectra \n(tab separated), or one for each spectrum.\nFor a detailed description, please have a look at the doxygen documentation.(one set, tab separated, per line)" - type: File - peak_data: - doc: set this flag, if you have peak data, not raw data (the picking parameters are accessible only from the INI file). - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__PeakPicker__signal_to_noise: - doc: Minimal signal to noise ratio for a peak to be picked. - type: double? - algorithm__PeakPicker__centroid_percentage: - doc: Percentage of the maximum height that the raw data points must exceed to be taken into account for the calculation of the centroid. If it is 1 the centroid position corresponds to the position of the highest intensity. - type: double? - algorithm__PeakPicker__peak_width: - doc: Approximate fwhm of the peaks. - type: double? - algorithm__PeakPicker__estimate_peak_width: - doc: "Flag if the average peak width shall be estimated. Attention: when this flag is set, the peak_width is ignored." - type: boolean? - algorithm__PeakPicker__fwhm_lower_bound_factor: - doc: Factor that calculates the minimal fwhm value from the peak_width. All peaks with width smaller than fwhm_bound_factor * peak_width are discarded. - type: double? - algorithm__PeakPicker__fwhm_upper_bound_factor: - doc: Factor that calculates the maximal fwhm value from the peak_width. All peaks with width greater than fwhm_upper_bound_factor * peak_width are discarded. - type: double? - algorithm__PeakPicker__thresholds__peak_bound: - doc: Minimal peak intensity. - type: double? - algorithm__PeakPicker__thresholds__peak_bound_ms2_level: - doc: Minimal peak intensity for MS/MS peaks. - type: double? - algorithm__PeakPicker__thresholds__correlation: - doc: minimal correlation of a peak and the raw signal. If a peak has a lower correlation it is skipped. - type: double? - algorithm__PeakPicker__thresholds__noise_level: - doc: noise level for the search of the peak endpoints. - type: double? - algorithm__PeakPicker__thresholds__search_radius: - doc: search radius for the search of the maximum in the signal after a maximum in the cwt was found - type: long? - algorithm__PeakPicker__wavelet_transform__spacing: - doc: Spacing of the CWT. Note that the accuracy of the picked peak's centroid position depends in the Raw data spacing, i.e., 50% of raw peak distance at most. - type: double? - algorithm__PeakPicker__optimization__type: - doc: If the peak parameters position, intensity and left/right widthshall be optimized set optimization to one_dimensional or two_dimensional. - type: string? - algorithm__PeakPicker__optimization__iterations: - doc: maximal number of iterations for the fitting step - type: long? - algorithm__PeakPicker__optimization__penalties__position: - doc: "penalty term for the fitting of the position:If it differs too much from the initial one it can be penalized " - type: double? - algorithm__PeakPicker__optimization__penalties__left_width: - doc: penalty term for the fitting of the left width:If the left width differs too much from the initial one during the fitting it can be penalized. - type: double? - algorithm__PeakPicker__optimization__penalties__right_width: - doc: penalty term for the fitting of the right width:If the right width differs too much from the initial one during the fitting it can be penalized. - type: double? - algorithm__PeakPicker__optimization__penalties__height: - doc: penalty term for the fitting of the intensity (only used in 2D Optimization):If it gets negative during the fitting it can be penalized. - type: double? - algorithm__PeakPicker__optimization__2d__tolerance_mz: - doc: mz tolerance for cluster construction - type: double? - algorithm__PeakPicker__optimization__2d__max_peak_distance: - doc: maximal peak distance in mz in a cluster - type: double? - algorithm__PeakPicker__deconvolution__deconvolution: - doc: If you want heavily overlapping peaks to be separated set this value to "true" - type: boolean? - algorithm__PeakPicker__deconvolution__asym_threshold: - doc: If the symmetry of a peak is smaller than asym_thresholds it is assumed that it consists of more than one peak and the deconvolution procedure is started. - type: double? - algorithm__PeakPicker__deconvolution__left_width: - doc: 1/left_width is the initial value for the left width of the peaks found in the deconvolution step. - type: double? - algorithm__PeakPicker__deconvolution__right_width: - doc: 1/right_width is the initial value for the right width of the peaks found in the deconvolution step. - type: double? - algorithm__PeakPicker__deconvolution__scaling: - doc: Initial scaling of the cwt used in the separation of heavily overlapping peaks. The initial value is used for charge 1, for higher charges it is adapted to scaling/charge. - type: double? - algorithm__PeakPicker__deconvolution__fitting__fwhm_threshold: - doc: If the FWHM of a peak is higher than 'fwhm_thresholds' it is assumed that it consists of more than one peak and the deconvolution procedure is started. - type: double? - algorithm__PeakPicker__deconvolution__fitting__eps_abs: - doc: if the absolute error gets smaller than this value the fitting is stopped. - type: double? - algorithm__PeakPicker__deconvolution__fitting__eps_rel: - doc: if the relative error gets smaller than this value the fitting is stopped. - type: double? - algorithm__PeakPicker__deconvolution__fitting__max_iteration: - doc: maximal number of iterations for the fitting step - type: long? - algorithm__PeakPicker__deconvolution__fitting__penalties__position: - doc: penalty term for the fitting of the peak position:If the position changes more than 0.5Da during the fitting it can be penalized as well as discrepancies of the peptide mass rule. - type: double? - algorithm__PeakPicker__deconvolution__fitting__penalties__height: - doc: penalty term for the fitting of the intensity:If it gets negative during the fitting it can be penalized. - type: double? - algorithm__PeakPicker__deconvolution__fitting__penalties__left_width: - doc: penalty term for the fitting of the left width:If the left width gets too broad or negative during the fitting it can be penalized. - type: double? - algorithm__PeakPicker__deconvolution__fitting__penalties__right_width: - doc: penalty term for the fitting of the right width:If the right width gets too broad or negative during the fitting it can be penalized. - type: double? - algorithm__PeakPicker__SignalToNoiseEstimationParameter__max_intensity: - doc: maximal intensity considered for histogram construction. By default, it will be calculated automatically (see auto_mode). Only provide this parameter if you know what you are doing (and change 'auto_mode' to '-1')! All intensities EQUAL/ABOVE 'max_intensity' will not be added to the histogram. If you choose 'max_intensity' too small, the noise estimate might be too small as well. If chosen too big, the bins become quite large (which you could counter by increasing 'bin_count', which increases runtime). - type: long? - algorithm__PeakPicker__SignalToNoiseEstimationParameter__auto_max_stdev_factor: - doc: "parameter for 'max_intensity' estimation (if 'auto_mode' == 0): mean + 'auto_max_stdev_factor' * stdev" - type: double? - algorithm__PeakPicker__SignalToNoiseEstimationParameter__auto_max_percentile: - doc: "parameter for 'max_intensity' estimation (if 'auto_mode' == 1): auto_max_percentile th percentile" - type: long? - algorithm__PeakPicker__SignalToNoiseEstimationParameter__auto_mode: - doc: "method to use to determine maximal intensity: -1 --> use 'max_intensity'; 0 --> 'auto_max_stdev_factor' method (default); 1 --> 'auto_max_percentile' method" - type: long? - algorithm__PeakPicker__SignalToNoiseEstimationParameter__win_len: - doc: window length in Thomson - type: double? - algorithm__PeakPicker__SignalToNoiseEstimationParameter__bin_count: - doc: number of bins for intensity values - type: long? - algorithm__PeakPicker__SignalToNoiseEstimationParameter__stdev_mp: - doc: multiplier for stdev - type: double? - algorithm__PeakPicker__SignalToNoiseEstimationParameter__min_required_elements: - doc: minimum number of elements required in a window (otherwise it is considered sparse) - type: long? - algorithm__PeakPicker__SignalToNoiseEstimationParameter__noise_for_empty_window: - doc: noise value used for sparse windows - type: double? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - TOFCalibration -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/TargetedFileConverter.cwl b/workflow/cwl/TargetedFileConverter.cwl deleted file mode 100644 index 5d93b96a0b9..00000000000 --- a/workflow/cwl/TargetedFileConverter.cwl +++ /dev/null @@ -1,65 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: TargetedFileConverter -doc: Converts different transition files for targeted proteomics / metabolomics analysis. -inputs: - in: - doc: "Input file to convert.\n See http://www.openms.de/current_doxygen/html/TOPP_TargetedFileConverter.html for format of OpenSWATH transition TSV file or SpectraST MRM file." - type: File - in_type: - doc: "input file type -- default: determined from file extension or content\n" - type: string? - out: - doc: Output file - type: string - out_type: - doc: "Output file type -- default: determined from file extension or content\nNote: not all conversion paths work or make sense." - type: string? - legacy_traml_id: - doc: "PQP to TraML: Should legacy TraML IDs be used?" - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - algorithm__retentionTimeInterpretation: - doc: How to interpret the provided retention time (the retention time column can either be interpreted to be in iRT, minutes or seconds) - type: string? - algorithm__override_group_label_check: - doc: Override an internal check that assures that all members of the same PeptideGroupLabel have the same PeptideSequence (this ensures that only different isotopic forms of the same peptide can be grouped together in the same label group). Only turn this off if you know what you are doing. - type: boolean? - algorithm__force_invalid_mods: - doc: Force reading even if invalid modifications are encountered (OpenMS may not recognize the modification) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - TargetedFileConverter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/TextExporter.cwl b/workflow/cwl/TextExporter.cwl deleted file mode 100644 index 1b759823df6..00000000000 --- a/workflow/cwl/TextExporter.cwl +++ /dev/null @@ -1,119 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: TextExporter -doc: Exports various XML formats to a text file. -inputs: - in: - doc: "Input file " - type: File - out: - doc: Output file. - type: string - out_type: - doc: "Output file type -- default: determined from file extension, ambiguous file extensions are interpreted as tsv" - type: string? - replacement: - doc: Used to replace occurrences of the separator in strings before writing, if 'quoting' is 'none' - type: string? - quoting: - doc: "Method for quoting of strings: 'none' for no quoting, 'double' for quoting with doubling of embedded quotes,\n'escape' for quoting with backslash-escaping of embedded quotes" - type: string? - no_ids: - doc: Suppresses output of identification data. - type: boolean? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - feature__minimal: - doc: "Set this flag to write only three attributes: RT, m/z, and intensity." - type: boolean? - feature__add_metavalues: - doc: Add columns for meta values which occur with a certain frequency (0-100%). Set to -1 to omit meta values (default). - type: long? - id__proteins_only: - doc: Set this flag if you want only protein information from an idXML file - type: boolean? - id__peptides_only: - doc: Set this flag if you want only peptide information from an idXML file - type: boolean? - id__protein_groups: - doc: Set this flag if you want to also write indist. group information from an idXML file - type: boolean? - id__first_dim_rt: - doc: If this flag is set the first_dim RT of the peptide hits will also be printed (if present). - type: boolean? - id__add_metavalues: - doc: Add columns for meta values of PeptideID (=spectrum) entries which occur with a certain frequency (0-100%). Set to -1 to omit meta values (default). - type: long? - id__add_hit_metavalues: - doc: Add columns for meta values of PeptideHit (=PSM) entries which occur with a certain frequency (0-100%). Set to -1 to omit meta values (default). - type: long? - id__add_protein_hit_metavalues: - doc: Add columns for meta values on protein level which occur with a certain frequency (0-100%). Set to -1 to omit meta values (default). - type: long? - consensus__centroids: - doc: Output file for centroids of consensus features - type: string? - consensus__elements: - doc: Output file for elements of consensus features - type: string? - consensus__features: - doc: Output file for consensus features and contained elements from all maps (writes 'nan's if elements are missing) - type: string? - consensus__sorting_method: - doc: "Sorting options can be combined. The precedence is: sort_by_size, sort_by_maps, sorting_method" - type: string? - consensus__sort_by_maps: - doc: Apply a stable sort by the covered maps, lexicographically - type: boolean? - consensus__sort_by_size: - doc: Apply a stable sort by decreasing size (i.e., the number of elements) - type: boolean? - consensus__add_metavalues: - doc: Add columns for ConsensusFeature meta values. - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) - consensus__centroids: - type: File? - outputBinding: - glob: $(inputs.consensus__centroids) - consensus__elements: - type: File? - outputBinding: - glob: $(inputs.consensus__elements) - consensus__features: - type: File? - outputBinding: - glob: $(inputs.consensus__features) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - TextExporter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/TriqlerConverter.cwl b/workflow/cwl/TriqlerConverter.cwl deleted file mode 100644 index ddfaa5ad02c..00000000000 --- a/workflow/cwl/TriqlerConverter.cwl +++ /dev/null @@ -1,56 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: TriqlerConverter -doc: Converter to input for Triqler -inputs: - in: - doc: Input consensusXML with peptide intensities - type: File - in_design: - doc: Experimental Design file - type: File - Triqler_condition: - doc: Which column in the condition table should be used for Triqler 'Condition' - type: string? - reannotate_filenames: - doc: Overwrite MS file names in consensusXML - type: File[]? - out: - doc: Input CSV file for Triqler. - type: string - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out: - type: File - outputBinding: - glob: $(inputs.out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - TriqlerConverter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/XFDR.cwl b/workflow/cwl/XFDR.cwl deleted file mode 100644 index d422c145551..00000000000 --- a/workflow/cwl/XFDR.cwl +++ /dev/null @@ -1,91 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: XFDR -doc: Calculates false discovery rate estimates on crosslink identifications -inputs: - in: - doc: Crosslink Identifications in either xquest.xml, idXML, or mzIdentML format (as produced by OpenPepXL) - type: File? - in_type: - doc: Type of input file provided with -in. If omitted, the file type is guessed from the file extension. - type: string? - out_idXML: - doc: Output as idXML file - type: string? - out_mzIdentML: - doc: Output as mzIdentML file - type: string? - out_xquest: - doc: Output as xquest.xml file - type: string? - decoy_string: - doc: Prefix of decoy protein ids. The correspondig target protein id should be retrievable by deleting this prefix. - type: string? - minborder: - doc: Filter for minimum precursor mass error (ppm) before FDR estimation. Values outside of the tolerance window of the original search will effectively disable this filter. - type: double? - maxborder: - doc: Filter for maximum precursor mass error (ppm) before FDR estimation. Values outside of the tolerance window of the original search will effectively disable this filter. - type: double? - mindeltas: - doc: Filter for delta score, 0 disables the filter. Minimum delta score required, hits are rejected if larger or equal. The delta score is a ratio of the score of a hit and the score of the next best hit to the same spectrum, so the value range is between 0 and 1 with 1.0 meaning the scores are equal and 0.5 meaning the next best score is half as high as the current one. - type: double? - minionsmatched: - doc: Filter for minimum matched ions per peptide. - type: long? - uniquexl: - doc: Calculate statistics based only on unique IDs. For a set of IDs from equal candidates (same pair of peptides, modifications and cross-linked positions), only the highest scoring hit will be considered. By default the score distribution will be estimated using all 1st ranked candidates. - type: boolean? - no_qvalues: - doc: Do not transform simple FDR to q-values - type: boolean? - minscore: - doc: Minimum score to be considered for FDR calculation. A number lower than the lowest score will effectively disable this filter. - type: double? - binsize: - doc: Bin size for the cumulative histograms for score distributions. Should be about the same size as the smallest expected difference between scores. Smaller numbers will make XFDR more robust, but much slower. Negative numbers are not allowed. Should only be changed if the range of the main score changes or another score than the OpenPepXL score is used. - type: double? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - out_idXML: - type: File? - outputBinding: - glob: $(inputs.out_idXML) - out_mzIdentML: - type: File? - outputBinding: - glob: $(inputs.out_mzIdentML) - out_xquest: - type: File? - outputBinding: - glob: $(inputs.out_xquest) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - XFDR -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/XMLValidator.cwl b/workflow/cwl/XMLValidator.cwl deleted file mode 100644 index 9cd8477233c..00000000000 --- a/workflow/cwl/XMLValidator.cwl +++ /dev/null @@ -1,44 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: XMLValidator -doc: Validates XML files against an XSD schema. -inputs: - in: - doc: file to validate - type: File - schema: - doc: "schema to validate against.\nIf no schema is given, the file is validated against the latest schema of the file type." - type: File? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? -outputs: - [] -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - XMLValidator -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json diff --git a/workflow/cwl/XTandemAdapter.cwl b/workflow/cwl/XTandemAdapter.cwl deleted file mode 100644 index e9bbb07e1e7..00000000000 --- a/workflow/cwl/XTandemAdapter.cwl +++ /dev/null @@ -1,150 +0,0 @@ -# Copyright (c) 2002-2023, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin -# SPDX-License-Identifier: Apache-2.0 -label: XTandemAdapter -doc: Annotates MS/MS spectra using X! Tandem. -inputs: - in: - doc: Input file containing MS2 spectra - type: File - out: - doc: Output file containing search results - type: string? - xml_out: - doc: Raw output file directly from X! Tandem. Either 'out' or 'xml_out' are required. They can be used together. - type: string? - database: - doc: FASTA file or pro file. Non-existing relative file-names are looked up via'OpenMS.ini:id_db_dir' - type: File - xtandem_executable: - doc: X! Tandem executable. Provide a full or relative path, or make sure it can be found in your PATH environment. - type: File - default_config_file: - doc: Default X! Tandem configuration file. All parameters of this adapter take precedence over the file - use it for parameters not available here. A template file can be found at 'OpenMS/share/CHEMISTRY/XTandem_default_config.xml'. - type: File? - ignore_adapter_param: - doc: Set this to use the configuration given in 'default_config_file' exclusively, ignoring other parameters (apart from 'in', 'out', 'database', 'xtandem_executable') set via this adapter. - type: boolean? - precursor_mass_tolerance: - doc: Precursor mass tolerance - type: double? - fragment_mass_tolerance: - doc: Fragment mass error - type: double? - precursor_error_units: - doc: Parent monoisotopic mass error units - type: string? - fragment_error_units: - doc: Fragment monoisotopic mass error units - type: string? - max_precursor_charge: - doc: Maximum precursor charge ('0' to use X! Tandem default) - type: long? - no_isotope_error: - doc: By default, misassignment to the first and second isotopic 13C peak are also considered. Set this flag to disable. - type: boolean? - fixed_modifications: - doc: Fixed modifications, specified using Unimod (www.unimod.org) terms, e.g. 'Carbamidomethyl (C)' or 'Oxidation (M)' - type: string[]? - variable_modifications: - doc: Variable modifications, specified using Unimod (www.unimod.org) terms, e.g. 'Carbamidomethyl (C)' or 'Oxidation (M)' - type: string[]? - minimum_fragment_mz: - doc: Minimum fragment m/z - type: double? - enzyme: - doc: The enzyme used for peptide digestion. - type: string? - missed_cleavages: - doc: Number of possible cleavage sites missed by the enzyme - type: long? - semi_cleavage: - doc: Require only peptide end to have a valid cleavage site, not both. - type: boolean? - output_results: - doc: Which hits should be reported. All, valid ones (passing the E-Value threshold), or stochastic (failing the threshold) - type: string? - max_valid_expect: - doc: Maximal E-Value of a hit to be reported (only evaluated if 'output_result' is 'valid' or 'stochastic') - type: double? - reindex: - doc: Recalculate peptide to protein association using OpenMS. Annotates target-decoy information. - type: string? - log: - doc: Name of log file (created only when specified) - type: string? - debug: - doc: Sets the debug level - type: long? - threads: - doc: Sets the number of threads allowed to be used by the TOPP tool - type: long? - no_progress: - doc: Disables progress logging to command line - type: boolean? - force: - doc: Overrides tool-specific checks - type: boolean? - test: - doc: Enables the test mode (needed for internal use only) - type: boolean? - PeptideIndexing__decoy_string: - doc: String that was appended (or prefixed - see 'decoy_string_position' flag below) to the accessions in the protein database to indicate decoy proteins. If empty (default), it's determined automatically (checking for common terms, both as prefix and suffix). - type: string? - PeptideIndexing__decoy_string_position: - doc: Is the 'decoy_string' prepended (prefix) or appended (suffix) to the protein accession? (ignored if decoy_string is empty) - type: string? - PeptideIndexing__missing_decoy_action: - doc: "Action to take if NO peptide was assigned to a decoy protein (which indicates wrong database or decoy string): 'error' (exit with error, no output), 'warn' (exit with success, warning message), 'silent' (no action is taken, not even a warning)" - type: string? - PeptideIndexing__write_protein_sequence: - doc: If set, the protein sequences are stored as well. - type: boolean? - PeptideIndexing__write_protein_description: - doc: If set, the protein description is stored as well. - type: boolean? - PeptideIndexing__keep_unreferenced_proteins: - doc: If set, protein hits which are not referenced by any peptide are kept. - type: boolean? - PeptideIndexing__unmatched_action: - doc: "If peptide sequences cannot be matched to any protein: 1) raise an error; 2) warn (unmatched PepHits will miss target/decoy annotation with downstream problems); 3) remove the hit." - type: string? - PeptideIndexing__aaa_max: - doc: Maximal number of ambiguous amino acids (AAAs) allowed when matching to a protein database with AAAs. AAAs are 'B', 'J', 'Z' and 'X'. - type: long? - PeptideIndexing__mismatches_max: - doc: Maximal number of mismatched (mm) amino acids allowed when matching to a protein database. The required runtime is exponential in the number of mm's; apply with care. MM's are allowed in addition to AAA's. - type: long? - PeptideIndexing__IL_equivalent: - doc: Treat the isobaric amino acids isoleucine ('I') and leucine ('L') as equivalent (indistinguishable). Also occurrences of 'J' will be treated as 'I' thus avoiding ambiguous matching. - type: boolean? - PeptideIndexing__allow_nterm_protein_cleavage: - doc: Allow the protein N-terminus amino acid to clip. - type: string? - PeptideIndexing__enzyme__name: - doc: "Enzyme which determines valid cleavage sites - e.g. trypsin cleaves after lysine (K) or arginine (R), but not before proline (P). Default: deduce from input" - type: string? - PeptideIndexing__enzyme__specificity: - doc: "Specificity of the enzyme. Default: deduce from input.\n 'full': both internal cleavage sites must match.\n 'semi': one of two internal cleavage sites must match.\n 'none': allow all peptide hits no matter their context (enzyme is irrelevant)." - type: string? -outputs: - out: - type: File? - outputBinding: - glob: $(inputs.out) - xml_out: - type: File? - outputBinding: - glob: $(inputs.xml_out) -cwlVersion: v1.2 -class: CommandLineTool -baseCommand: - - XTandemAdapter -requirements: - InlineJavascriptRequirement: {} - InitialWorkDirRequirement: - listing: - - entryname: cwl_inputs.json - entry: $(JSON.stringify(inputs)) -arguments: - - -ini - - cwl_inputs.json