✨ Parse MSFragger parameter files

proteobench/io/params/fragger.py

@@ -0,0 +1,60 @@
+"""Functionality to parse MSFragger fragger.params parameter files.
+
+MSFragger has a text based paramter file format which 
+separates paramters and their value using an equal sign. Optional comments are 
+expressed with a hash sign.
+"""
+from __future__ import annotations
+
+import logging
+from collections import namedtuple
+
+logger = logging.getLogger(__name__)
+
+Parameter = namedtuple("Parameter", ["name", "value", "comment"])
+
+
+def read_file(file: str) -> list[Parameter]:
+    """Read MSFragger parameter file as list of records."""
+    with open(file) as f:
+        data = []
+        for line in f:
+            line = line.strip()
+            logger.debug(line)
+            # ! logic below also allows to keep the comments as comments
+            if line.startswith("#"):
+                continue
+            if not line:
+                continue
+            if "#" in line:
+                res = line.split("#")
+                if len(res) == 1:
+                    comment = res[0]
+                    data.append(Parameter(None, None, comment.strip()))
+                    continue
+                param, comment = [x.strip() for x in res]
+            else:
+                param = line
+                comment = None
+            res = param.strip().split(" = ")
+            if len(res) == 1:
+                param = res[0].strip()
+                data.append(Parameter(param, None, comment))
+                continue
+            param, value = [x.strip() for x in res]
+            data.append(Parameter(param, value, comment))
+    return data
+
+
+if __name__ == "__main__":
+    import pathlib
+
+    import pandas as pd
+
+    file = pathlib.Path("../../../test/params/fragger.params")
+    data = read_file(file)
+    df = pd.DataFrame.from_records(data, columns=Parameter._fields).set_index(
+        Parameter._fields[0]
+    )
+    df
+    df.to_csv(file.with_suffix(".csv"))

test/params/fragger.csv

@@ -0,0 +1,105 @@
+name,value,comment
+database_name,Q:\MISC_PERSONAL\Bart\Benchmark_experiment_EuBIC\Shared\2023-01-30-decoys-BenchmarkFASTAModule1_DDA.fasta.fas,Path to the protein database file in FASTA format.
+num_threads,47,Number of CPU threads to use.
+precursor_mass_lower,-10,Lower bound of the precursor mass window.
+precursor_mass_upper,10,Upper bound of the precursor mass window.
+precursor_mass_units,1,"Precursor mass tolerance units (0 for Da, 1 for ppm)."
+data_type,0,"Data type (0 for DDA, 1 for DIA, 2 for gas-phase fractionation DIA)."
+precursor_true_tolerance,20,True precursor mass tolerance (window is +/- this value).
+precursor_true_units,1,"True precursor mass tolerance units (0 for Da, 1 for ppm)."
+fragment_mass_tolerance,20,Fragment mass tolerance (window is +/- this value).
+fragment_mass_units,1,"Fragment mass tolerance units (0 for Da, 1 for ppm)."
+calibrate_mass,2,"Perform mass calibration (0 for OFF, 1 for ON, 2 for ON and find optimal parameters)."
+use_all_mods_in_first_search,0,"Use all variable modifications in first search (0 for No, 1 for Yes)."
+decoy_prefix,rev_,Prefix of the decoy protein entries. Used for parameter optimization only.
+deisotope,1,"Perform deisotoping or not (0=no, 1=yes and assume singleton peaks single charged, 2=yes and assume singleton peaks single or double charged)."
+deneutralloss,1,"Perform deneutrallossing or not (0=no, 1=yes)."
+isotope_error,0/1/2,Also search for MS/MS events triggered on specified isotopic peaks.
+mass_offsets,0.0,Creates multiple precursor tolerance windows with specified mass offsets.
+precursor_mass_mode,selected,One of isolated/selected/corrected.
+remove_precursor_peak,1,Remove precursor peaks from tandem mass spectra. 0 = not remove; 1 = remove the peak with precursor charge; 2 = remove the peaks with all charge states (only for DDA mode).
+remove_precursor_range,"-1.500000,1.500000",m/z range in removing precursor peaks. Only for DDA mode. Unit: Th.
+intensity_transform,0,Transform peaks intensities with sqrt root. 0 = not transform; 1 = transform using sqrt root.
+activation_types,all,"Filter to only search scans of provided activation type(s). Allowed: All, HCD, CID, ETD, ECD."
+write_calibrated_mzml,0,"Write calibrated MS2 scan to a mzML file (0 for No, 1 for Yes)."
+write_uncalibrated_mgf,0,"Write uncalibrated MS2 scan to a MGF file (0 for No, 1 for Yes). Only for .raw and .d formats."
+mass_diff_to_variable_mod,0,Put mass diff as a variable modification. 0 for no; 1 for yes and remove delta mass; 2 for yes and keep delta mass.
+localize_delta_mass,0,"Include fragment ions mass-shifted by unknown modifications (recommended for open and mass offset searches) (0 for OFF, 1 for ON)."
+delta_mass_exclude_ranges,"(-1.5,3.5)",Exclude mass range for shifted ions searching.
+fragment_ion_series,"b,y","Ion series used in search, specify any of a,b,c,x,y,z,Y,b-18,y-18 (comma separated)."
+ion_series_definitions =,,"User defined ion series. Example: ""b* N -17.026548;b0 N -18.010565""."
+labile_search_mode,off,"type of search (nglycan, labile, or off). Off means non-labile/typical search."
+restrict_deltamass_to,all,"Specify amino acids on which delta masses (mass offsets or search modifications) can occur. Allowed values are single letter codes (e.g. ACD) and '-', must be capitalized. Use 'all' to allow any amino acid."
+diagnostic_intensity_filter,0,[nglycan/labile search_mode only]. Minimum relative intensity for SUM of all detected oxonium ions to achieve for spectrum to contain diagnostic fragment evidence. Calculated relative to spectrum base peak. 0 <= value.
+Y_type_masses =,,[nglycan/labile search_mode only]. Specify fragments of labile mods that are commonly retained on intact peptides (e.g. Y ions for glycans). Only used if 'Y' is included in fragment_ion_series.
+diagnostic_fragments =,,[nglycan/labile search_mode only]. Specify diagnostic fragments of labile mods that appear in the low m/z region. Only used if diagnostic_intensity_filter > 0.
+remainder_fragment_masses =,,[labile search_mode only] List of possible remainder fragment ions to consider. Remainder masses are partial modification masses left on b/y ions after fragmentation.
+search_enzyme_name_1,stricttrypsin,Name of the first enzyme.
+search_enzyme_cut_1,KR,First enzyme's cutting amino acid.
+search_enzyme_nocut_1 =,,First enzyme's protecting amino acid.
+search_enzyme_sense_1,C,First enzyme's cutting terminal.
+allowed_missed_cleavage_1,2,First enzyme's allowed number of missed cleavages per peptide. Maximum value is 5.
+search_enzyme_name_2,null,Name of the second enzyme.
+search_enzyme_cut_2 =,,Second enzyme's cutting amino acid.
+search_enzyme_nocut_2 =,,Second enzyme's protecting amino acid.
+search_enzyme_sense_2,C,Second enzyme's cutting terminal.
+allowed_missed_cleavage_2,2,Second enzyme's allowed number of missed cleavages per peptide. Maximum value is 5.
+num_enzyme_termini,2,"0 for non-enzymatic, 1 for semi-enzymatic, and 2 for fully-enzymatic."
+clip_nTerm_M,1,Specifies the trimming of a protein N-terminal methionine as a variable modification (0 or 1).
+variable_mod_01,15.9949 M 3,
+variable_mod_02,42.0106 [^ 1,
+allow_multiple_variable_mods_on_residue,0,
+max_variable_mods_per_peptide,3,Maximum total number of variable modifications per peptide.
+max_variable_mods_combinations,5000,Maximum number of modified forms allowed for each peptide (up to 65534).
+output_format,tsv_pepXML_pin,"File format of output files (tsv, pin, pepxml, tsv_pin, tsv_pepxml, pepxml_pin, or tsv_pepxml_pin)."
+output_report_topN,1,Reports top N PSMs per input spectrum.
+output_max_expect,50,Suppresses reporting of PSM if top hit has expectation value greater than this threshold.
+report_alternative_proteins,1,"Report alternative proteins for peptides that are found in multiple proteins (0 for no, 1 for yes)."
+precursor_charge,1 4,Assumed range of potential precursor charge states. Only relevant when override_charge is set to 1.
+override_charge,0,Ignores precursor charge and uses charge state specified in precursor_charge range (0 or 1).
+digest_min_length,7,Minimum length of peptides to be generated during in-silico digestion.
+digest_max_length,50,Maximum length of peptides to be generated during in-silico digestion.
+digest_mass_range,500.0 5000.0,Mass range of peptides to be generated during in-silico digestion in Daltons.
+max_fragment_charge,2,Maximum charge state for theoretical fragments to match (1-4).
+track_zero_topN,0,Track top N unmodified peptide results separately from main results internally for boosting features.
+zero_bin_accept_expect,0,Ranks a zero-bin hit above all non-zero-bin hit if it has expectation less than this value.
+zero_bin_mult_expect,1,Multiplies expect value of PSMs in the zero-bin during  results ordering (set to less than 1 for boosting).
+add_topN_complementary,0,Inserts complementary ions corresponding to the top N most intense fragments in each experimental spectra.
+check_spectral_files,1,Checking spectral files before searching.
+minimum_peaks,15,Minimum number of peaks in experimental spectrum for matching.
+use_topN_peaks,150,Pre-process experimental spectrum to only use top N peaks.
+min_fragments_modelling,2,Minimum number of matched peaks in PSM for inclusion in statistical modeling.
+min_matched_fragments,4,Minimum number of matched peaks for PSM to be reported.
+min_sequence_matches,2,[nglycan/labile search_mode only] Minimum number of sequence-specific (not Y) ions to record a match.
+minimum_ratio,0.01,Filters out all peaks in experimental spectrum less intense than this multiple of the base peak intensity.
+clear_mz_range,0.0 0.0,Removes peaks in this m/z range prior to matching.
+add_Cterm_peptide,0.0,
+add_Nterm_peptide,0.0,
+add_Cterm_protein,0.0,
+add_Nterm_protein,0.0,
+add_G_glycine,0.0,
+add_A_alanine,0.0,
+add_S_serine,0.0,
+add_P_proline,0.0,
+add_V_valine,0.0,
+add_T_threonine,0.0,
+add_C_cysteine,57.02146,
+add_L_leucine,0.0,
+add_I_isoleucine,0.0,
+add_N_asparagine,0.0,
+add_D_aspartic_acid,0.0,
+add_Q_glutamine,0.0,
+add_K_lysine,0.0,
+add_E_glutamic_acid,0.0,
+add_M_methionine,0.0,
+add_H_histidine,0.0,
+add_F_phenylalanine,0.0,
+add_R_arginine,0.0,
+add_Y_tyrosine,0.0,
+add_W_tryptophan,0.0,
+add_B_user_amino_acid,0.0,
+add_J_user_amino_acid,0.0,
+add_O_user_amino_acid,0.0,
+add_U_user_amino_acid,0.0,
+add_X_user_amino_acid,0.0,
+add_Z_user_amino_acid,0.0,

test/params/fragger.params

@@ -0,0 +1,139 @@
+database_name = Q:\MISC_PERSONAL\Bart\Benchmark_experiment_EuBIC\Shared\2023-01-30-decoys-BenchmarkFASTAModule1_DDA.fasta.fas			# Path to the protein database file in FASTA format.
+num_threads = 47			# Number of CPU threads to use.
+
+precursor_mass_lower = -10			# Lower bound of the precursor mass window.
+precursor_mass_upper = 10			# Upper bound of the precursor mass window.
+precursor_mass_units = 1			# Precursor mass tolerance units (0 for Da, 1 for ppm).
+data_type = 0			# Data type (0 for DDA, 1 for DIA, 2 for gas-phase fractionation DIA).
+precursor_true_tolerance = 20			# True precursor mass tolerance (window is +/- this value).
+precursor_true_units = 1			# True precursor mass tolerance units (0 for Da, 1 for ppm).
+fragment_mass_tolerance = 20			# Fragment mass tolerance (window is +/- this value).
+fragment_mass_units = 1			# Fragment mass tolerance units (0 for Da, 1 for ppm).
+calibrate_mass = 2			# Perform mass calibration (0 for OFF, 1 for ON, 2 for ON and find optimal parameters).
+use_all_mods_in_first_search = 0			# Use all variable modifications in first search (0 for No, 1 for Yes).
+decoy_prefix = rev_			# Prefix of the decoy protein entries. Used for parameter optimization only.
+
+deisotope = 1			# Perform deisotoping or not (0=no, 1=yes and assume singleton peaks single charged, 2=yes and assume singleton peaks single or double charged).
+deneutralloss = 1			# Perform deneutrallossing or not (0=no, 1=yes).
+isotope_error = 0/1/2			# Also search for MS/MS events triggered on specified isotopic peaks.
+mass_offsets = 0.0			# Creates multiple precursor tolerance windows with specified mass offsets.
+precursor_mass_mode = selected			# One of isolated/selected/corrected.
+
+remove_precursor_peak = 1			#  Remove precursor peaks from tandem mass spectra. 0 = not remove; 1 = remove the peak with precursor charge; 2 = remove the peaks with all charge states (only for DDA mode).
+remove_precursor_range = -1.500000,1.500000			# m/z range in removing precursor peaks. Only for DDA mode. Unit: Th.
+intensity_transform = 0			# Transform peaks intensities with sqrt root. 0 = not transform; 1 = transform using sqrt root.
+activation_types = all			# Filter to only search scans of provided activation type(s). Allowed: All, HCD, CID, ETD, ECD.
+
+write_calibrated_mzml = 0			# Write calibrated MS2 scan to a mzML file (0 for No, 1 for Yes).
+write_uncalibrated_mgf = 0			# Write uncalibrated MS2 scan to a MGF file (0 for No, 1 for Yes). Only for .raw and .d formats.
+mass_diff_to_variable_mod = 0			# Put mass diff as a variable modification. 0 for no; 1 for yes and remove delta mass; 2 for yes and keep delta mass.
+
+localize_delta_mass = 0			# Include fragment ions mass-shifted by unknown modifications (recommended for open and mass offset searches) (0 for OFF, 1 for ON).
+delta_mass_exclude_ranges = (-1.5,3.5)			# Exclude mass range for shifted ions searching.
+fragment_ion_series = b,y			# Ion series used in search, specify any of a,b,c,x,y,z,Y,b-18,y-18 (comma separated).
+ion_series_definitions = 			# User defined ion series. Example: "b* N -17.026548;b0 N -18.010565".
+
+labile_search_mode = off			# type of search (nglycan, labile, or off). Off means non-labile/typical search.
+restrict_deltamass_to = all			# Specify amino acids on which delta masses (mass offsets or search modifications) can occur. Allowed values are single letter codes (e.g. ACD) and '-', must be capitalized. Use 'all' to allow any amino acid.
+diagnostic_intensity_filter = 0			# [nglycan/labile search_mode only]. Minimum relative intensity for SUM of all detected oxonium ions to achieve for spectrum to contain diagnostic fragment evidence. Calculated relative to spectrum base peak. 0 <= value.
+Y_type_masses = 			#  [nglycan/labile search_mode only]. Specify fragments of labile mods that are commonly retained on intact peptides (e.g. Y ions for glycans). Only used if 'Y' is included in fragment_ion_series.
+diagnostic_fragments = 			# [nglycan/labile search_mode only]. Specify diagnostic fragments of labile mods that appear in the low m/z region. Only used if diagnostic_intensity_filter > 0.
+remainder_fragment_masses = 			# [labile search_mode only] List of possible remainder fragment ions to consider. Remainder masses are partial modification masses left on b/y ions after fragmentation.
+
+search_enzyme_name_1 = stricttrypsin			# Name of the first enzyme.
+search_enzyme_cut_1 = KR			# First enzyme's cutting amino acid.
+search_enzyme_nocut_1 = 			# First enzyme's protecting amino acid.
+search_enzyme_sense_1 = C			# First enzyme's cutting terminal.
+allowed_missed_cleavage_1 = 2			# First enzyme's allowed number of missed cleavages per peptide. Maximum value is 5.
+
+search_enzyme_name_2 = null			# Name of the second enzyme.
+search_enzyme_cut_2 = 			# Second enzyme's cutting amino acid.
+search_enzyme_nocut_2 = 			# Second enzyme's protecting amino acid.
+search_enzyme_sense_2 = C			# Second enzyme's cutting terminal.
+allowed_missed_cleavage_2 = 2			# Second enzyme's allowed number of missed cleavages per peptide. Maximum value is 5.
+
+num_enzyme_termini = 2			# 0 for non-enzymatic, 1 for semi-enzymatic, and 2 for fully-enzymatic.
+
+clip_nTerm_M = 1			# Specifies the trimming of a protein N-terminal methionine as a variable modification (0 or 1).
+
+# maximum of 16 mods - amino acid codes, * for any amino acid, [ and ] specifies protein termini, n and c specifies peptide termini
+variable_mod_01 = 15.9949 M 3
+variable_mod_02 = 42.0106 [^ 1
+# variable_mod_03 = 79.96633 STY 3
+# variable_mod_04 = -17.0265 nQnC 1
+# variable_mod_05 = -18.0106 nE 1
+# variable_mod_06 = 4.025107 K 2
+# variable_mod_07 = 6.020129 R 2
+# variable_mod_08 = 8.014199 K 2
+# variable_mod_09 = 10.008269 R 2
+# variable_mod_10 = 0.0 site_10 1
+# variable_mod_11 = 0.0 site_11 1
+# variable_mod_12 = 0.0 site_12 1
+# variable_mod_13 = 0.0 site_13 1
+# variable_mod_14 = 0.0 site_14 1
+# variable_mod_15 = 0.0 site_15 1
+# variable_mod_16 = 0.0 site_16 1
+
+allow_multiple_variable_mods_on_residue = 0
+max_variable_mods_per_peptide = 3			# Maximum total number of variable modifications per peptide.
+max_variable_mods_combinations = 5000			# Maximum number of modified forms allowed for each peptide (up to 65534).
+
+output_format = tsv_pepXML_pin			# File format of output files (tsv, pin, pepxml, tsv_pin, tsv_pepxml, pepxml_pin, or tsv_pepxml_pin).
+output_report_topN = 1			# Reports top N PSMs per input spectrum.
+output_max_expect = 50			# Suppresses reporting of PSM if top hit has expectation value greater than this threshold.
+report_alternative_proteins = 1			# Report alternative proteins for peptides that are found in multiple proteins (0 for no, 1 for yes).
+
+precursor_charge = 1 4			# Assumed range of potential precursor charge states. Only relevant when override_charge is set to 1.
+override_charge = 0			# Ignores precursor charge and uses charge state specified in precursor_charge range (0 or 1).
+
+digest_min_length = 7			# Minimum length of peptides to be generated during in-silico digestion.
+digest_max_length = 50			# Maximum length of peptides to be generated during in-silico digestion.
+digest_mass_range = 500.0 5000.0			# Mass range of peptides to be generated during in-silico digestion in Daltons.
+max_fragment_charge = 2			# Maximum charge state for theoretical fragments to match (1-4).
+
+track_zero_topN = 0			# Track top N unmodified peptide results separately from main results internally for boosting features.
+zero_bin_accept_expect = 0			# Ranks a zero-bin hit above all non-zero-bin hit if it has expectation less than this value.
+zero_bin_mult_expect = 1			# Multiplies expect value of PSMs in the zero-bin during  results ordering (set to less than 1 for boosting).
+add_topN_complementary = 0			# Inserts complementary ions corresponding to the top N most intense fragments in each experimental spectra.
+
+check_spectral_files = 1			# Checking spectral files before searching.
+minimum_peaks = 15			# Minimum number of peaks in experimental spectrum for matching.
+use_topN_peaks = 150			# Pre-process experimental spectrum to only use top N peaks.
+min_fragments_modelling = 2			# Minimum number of matched peaks in PSM for inclusion in statistical modeling.
+min_matched_fragments = 4			# Minimum number of matched peaks for PSM to be reported.
+min_sequence_matches = 2			# [nglycan/labile search_mode only] Minimum number of sequence-specific (not Y) ions to record a match.
+minimum_ratio = 0.01			# Filters out all peaks in experimental spectrum less intense than this multiple of the base peak intensity.
+clear_mz_range = 0.0 0.0			# Removes peaks in this m/z range prior to matching.
+
+add_Cterm_peptide = 0.0
+add_Nterm_peptide = 0.0
+add_Cterm_protein = 0.0
+add_Nterm_protein = 0.0
+
+add_G_glycine = 0.0
+add_A_alanine = 0.0
+add_S_serine = 0.0
+add_P_proline = 0.0
+add_V_valine = 0.0
+add_T_threonine = 0.0
+add_C_cysteine = 57.02146
+add_L_leucine = 0.0
+add_I_isoleucine = 0.0
+add_N_asparagine = 0.0
+add_D_aspartic_acid = 0.0
+add_Q_glutamine = 0.0
+add_K_lysine = 0.0
+add_E_glutamic_acid = 0.0
+add_M_methionine = 0.0
+add_H_histidine = 0.0
+add_F_phenylalanine = 0.0
+add_R_arginine = 0.0
+add_Y_tyrosine = 0.0
+add_W_tryptophan = 0.0
+add_B_user_amino_acid = 0.0
+add_J_user_amino_acid = 0.0
+add_O_user_amino_acid = 0.0
+add_U_user_amino_acid = 0.0
+add_X_user_amino_acid = 0.0
+add_Z_user_amino_acid = 0.0
+

test/test_parse_params_fragger.py

@@ -0,0 +1,18 @@
+from pathlib import Path
+
+import pandas as pd
+
+import proteobench.io.params.fragger as fragger_params
+
+TESTDATA_DIR = Path(__file__).parent / "params"
+
+
+def test_read_file():
+    file = TESTDATA_DIR / "fragger.params"
+    csv_expected = TESTDATA_DIR / "fragger.csv"
+    expected = pd.read_csv(csv_expected)
+    data = fragger_params.read_file(file)
+    actual = pd.DataFrame.from_records(
+        data, columns=(fragger_params.Parameter._fields)
+    ).set_index(fragger_params.Parameter._fields[0])
+    actual.equals(expected)