updated tools docu

imgag · Jul 3, 2023 · 1d9da0c · 1d9da0c
1 parent 2a1d247
commit 1d9da0c
Show file tree

Hide file tree

Showing 8 changed files with 104 additions and 40 deletions.
diff --git a/doc/tools/FastqConcat.md b/doc/tools/FastqConcat.md
@@ -1,5 +1,5 @@
 ### FastqConcat tool help
-	FastqConcat (2020_03-159-g5c8b2e82)
+	FastqConcat (2023_03-107-g2a1d2478)
 
 	Concatinates several FASTQ files into one output FASTQ file.
 
@@ -10,6 +10,8 @@
 	Optional parameters:
 	  -compression_level <int> Output FASTQ compression level from 1 (fastest) to 9 (best compression).
 	                           Default value: '1'
+	  -long_read               Support long reads (> 1kb).
+	                           Default value: 'false'
 
 	Special parameters:
 	  --help                   Shows this help and exits.
@@ -18,8 +20,9 @@
 	  --tdx                    Writes a Tool Definition Xml file. The file name is the application name with the suffix '.tdx'.
 
 ### FastqConcat changelog
-	FastqConcat 2020_03-159-g5c8b2e82
+	FastqConcat 2023_03-107-g2a1d2478
 
+	2023-06-15 Added support for long reads.
 	2020-07-15 Added 'compression_level' parameter.
 	2019-04-08 Initial version of this tool
 [back to ngs-bits](https://github.com/imgag/ngs-bits)
diff --git a/doc/tools/FastqTrim.md b/doc/tools/FastqTrim.md
@@ -1,5 +1,5 @@
 ### FastqTrim tool help
-	FastqTrim (2020_03-159-g5c8b2e82)
+	FastqTrim (2023_03-107-g2a1d2478)
 
 	Trims start/end bases from all reads in a FASTQ file.
 
@@ -16,6 +16,8 @@
 	                           Default value: '0'
 	  -compression_level <int> Output FASTQ compression level from 1 (fastest) to 9 (best compression).
 	                           Default value: '1'
+	  -long_read               Support long reads (> 1kb).
+	                           Default value: 'false'
 
 	Special parameters:
 	  --help                   Shows this help and exits.
@@ -24,8 +26,9 @@
 	  --tdx                    Writes a Tool Definition Xml file. The file name is the application name with the suffix '.tdx'.
 
 ### FastqTrim changelog
-	FastqTrim 2020_03-159-g5c8b2e82
+	FastqTrim 2023_03-107-g2a1d2478
 
+	2023-06-15 Added support for long reads.
 	2020-07-15 Added 'compression_level' parameter.
 	2016-08-26 Added 'len' parameter.
 [back to ngs-bits](https://github.com/imgag/ngs-bits)
diff --git a/doc/tools/NGSDExportAnnotationData.md b/doc/tools/NGSDExportAnnotationData.md
@@ -1,28 +1,30 @@
 ### NGSDExportAnnotationData tool help
-	NGSDExportAnnotationData (2022_12-82-g025eb99e)
+	NGSDExportAnnotationData (2023_03-107-g2a1d2478)
 
-	Generates a VCF file with all variants and annotations from the NGSD and a BED file containing the gene information of the NGSD.
-
-	Mandatory parameters:
-	  -variants <file>      Output variant list as VCF.
+	Export information aboug germline variants, somatic variants and genes form NGSD for use as annotation source, e.g. in megSAP.
 
 	Optional parameters:
-	  -genes <file>         Optional BED file containing the genes and the gene info (only germline).
+	  -germline <file>      Export germline variants (VCF format).
+	                        Default value: ''
+	  -somatic <file>       Export somatic variants (VCF format).
+	                        Default value: ''
+	  -genes <file>         Exports BED file containing genes and gene information.
 	                        Default value: ''
 	  -reference <file>     Reference genome FASTA file. If unset 'reference_genome' from the 'settings.ini' file is used.
 	                        Default value: ''
-	  -test                 Uses the test database instead of on the production database.
-	                        Default value: 'false'
-	  -max_af <float>       Maximum allel frequency of exported variants (default: 0.05).
+	  -max_af <float>       Maximum allel frequency of exported variants (germline).
 	                        Default value: '0.05'
-	  -gene_offset <int>    Defines the number of bases by which the region of each gene is extended.
+	  -gene_offset <int>    Defines the number of bases by which the regions of genes are extended (genes).
 	                        Default value: '5000'
-	  -mode <enum>          Determines the database which is exported.
-	                        Default value: 'germline'
-	                        Valid: 'germline,somatic'
-	  -vicc_config_details  Includes details about VICC interpretation. Works only in somatic mode.
+	  -vicc_config_details  Includes details about VICC interpretation (somatic).
+	                        Default value: 'false'
+	  -threads <int>        Number of threads to use.
+	                        Default value: '5'
+	  -verbose              Enables verbose debug output.
 	                        Default value: 'false'
-	  -debug                Enables debug output (germline only).
+	  -max_vcf_lines <int>  Maximum number of VCF lines to write per chromosome - for debugging.
+	                        Default value: '-1'
+	  -test                 Uses the test database instead of on the production database.
 	                        Default value: 'false'
 
 	Special parameters:
@@ -32,8 +34,10 @@
 	  --tdx                 Writes a Tool Definition Xml file. The file name is the application name with the suffix '.tdx'.
 
 ### NGSDExportAnnotationData changelog
-	NGSDExportAnnotationData 2022_12-82-g025eb99e
+	NGSDExportAnnotationData 2023_03-107-g2a1d2478
 
+	2023-06-18 Refactoring of command line parameters and parallelization of somatic export.
+	2023-06-16 Added support for 'germline_mosaic' column in 'variant' table and added parallelization.
 	2021-07-19 Code and parameter refactoring.
 	2021-07-19 Added support for 'germline_het' and 'germline_hom' columns in 'variant' table.
 	2019-12-06 Comments are now URL encoded.

diff --git a/doc/tools/NGSDExportGff.md b/doc/tools/NGSDExportGff.md
@@ -0,0 +1,22 @@
+### NGSDExportGff tool help
+	NGSDExportGff (2023_03-107-g2a1d2478)
+
+	Writes all transcripts and exons of all genes to a gff3 file.
+
+	Mandatory parameters:
+	  -out <file>  The output file directory.
+
+	Optional parameters:
+	  -test        Uses the test database instead of on the production database.
+	               Default value: 'false'
+
+	Special parameters:
+	  --help       Shows this help and exits.
+	  --version    Prints version and exits.
+	  --changelog  Prints changeloge and exits.
+	  --tdx        Writes a Tool Definition Xml file. The file name is the application name with the suffix '.tdx'.
+
+### NGSDExportGff changelog
+	NGSDExportGff 2023_03-107-g2a1d2478
+
+[back to ngs-bits](https://github.com/imgag/ngs-bits)
diff --git a/doc/tools/NGSDExportSamples.md b/doc/tools/NGSDExportSamples.md
@@ -1,5 +1,5 @@
 ### NGSDExportSamples tool help
-	NGSDExportSamples (2023_02-56-g0fe5818f)
+	NGSDExportSamples (2023_03-107-g2a1d2478)
 
 	Lists processed samples from the NGSD.
 
@@ -12,6 +12,8 @@
 	                           Default value: 'false'
 	  -no_tumor                If set, tumor samples are excluded.
 	                           Default value: 'false'
+	  -no_normal               If set, germline samples are excluded.
+	                           Default value: 'false'
 	  -no_ffpe                 If set, FFPE samples are excluded.
 	                           Default value: 'false'
 	  -match_external_names    If set, also samples for which the external name matches 'sample' are exported.
@@ -50,7 +52,9 @@
 	                           Default value: 'false'
 	  -run_device <string>     Sequencing run device name filter.
 	                           Default value: ''
-	  -run_before <string>     Sequencing run start date before or equal to the given date.
+	  -run_before <string>     Sequencing run before or equal to the given date.
+	                           Default value: ''
+	  -run_after <string>      Sequencing run after or equal to the given date.
 	                           Default value: ''
 	  -no_bad_runs             If set, sequencing runs with 'bad' quality are excluded.
 	                           Default value: 'false'
@@ -79,7 +83,7 @@
 	  --tdx                    Writes a Tool Definition Xml file. The file name is the application name with the suffix '.tdx'.
 
 ### NGSDExportSamples changelog
-	NGSDExportSamples 2023_02-56-g0fe5818f
+	NGSDExportSamples 2023_03-107-g2a1d2478
 
 	2022-11-11 Added 'ancestry' and 'phenotypes' filter options.
 	2022-03-03 Added 'disease_group', 'disease_status', 'project_type' and 'tissue' filter options.

diff --git a/doc/tools/NGSDExportStudyGHGA.md b/doc/tools/NGSDExportStudyGHGA.md
@@ -1,24 +1,25 @@
 ### NGSDExportStudyGHGA tool help
-	NGSDExportStudyGHGA (2022_12-82-g025eb99e)
+	NGSDExportStudyGHGA (2023_03-107-g2a1d2478)
 
 	Exports meta data of a study from NGSD to a JSON format for import into GHGA.
 
 	Mandatory parameters:
-	  -data <file> JSON file with data that is not contained in NGSD.
-	  -out <file>  Output JSON file.
+	  -samples <file> TSV file with pseudonym, SAP ID and processed sample ID
+	  -data <file>    JSON file with data that is not contained in NGSD.
+	  -out <file>     Output JSON file.
 
 	Optional parameters:
-	  -test        Test mode: uses the test NGSD, does not calcualte size/checksum of BAMs, ...
-	               Default value: 'false'
+	  -test           Test mode: uses the test NGSD, does not calcualte size/checksum of BAMs, ...
+	                  Default value: 'false'
 
 	Special parameters:
-	  --help       Shows this help and exits.
-	  --version    Prints version and exits.
-	  --changelog  Prints changeloge and exits.
-	  --tdx        Writes a Tool Definition Xml file. The file name is the application name with the suffix '.tdx'.
+	  --help          Shows this help and exits.
+	  --version       Prints version and exits.
+	  --changelog     Prints changeloge and exits.
+	  --tdx           Writes a Tool Definition Xml file. The file name is the application name with the suffix '.tdx'.
 
 ### NGSDExportStudyGHGA changelog
-	NGSDExportStudyGHGA 2022_12-82-g025eb99e
+	NGSDExportStudyGHGA 2023_03-107-g2a1d2478
 
 	2023-01-31 Initial implementation (version 0.9.0 of schema).
 [back to ngs-bits](https://github.com/imgag/ngs-bits)
diff --git a/doc/tools/NGSDImportSampleQC.md b/doc/tools/NGSDImportSampleQC.md
@@ -0,0 +1,25 @@
+### NGSDImportSampleQC tool help
+	NGSDImportSampleQC (2023_03-107-g2a1d2478)
+
+	Imports QC metrics of a sample into NGSD.
+
+	Mandatory parameters:
+	  -ps <string>      Processed sample name.
+	  -files <filelist> qcML files to import.
+
+	Optional parameters:
+	  -force            Overwrites already existing QC metrics instead of throwing an error.
+	                    Default value: 'false'
+	  -test             Uses the test database instead of on the production database.
+	                    Default value: 'false'
+
+	Special parameters:
+	  --help            Shows this help and exits.
+	  --version         Prints version and exits.
+	  --changelog       Prints changeloge and exits.
+	  --tdx             Writes a Tool Definition Xml file. The file name is the application name with the suffix '.tdx'.
+
+### NGSDImportSampleQC changelog
+	NGSDImportSampleQC 2023_03-107-g2a1d2478
+
+[back to ngs-bits](https://github.com/imgag/ngs-bits)
diff --git a/doc/tools/VariantFilterAnnotations.md b/doc/tools/VariantFilterAnnotations.md
@@ -1,5 +1,5 @@
 ### VariantFilterAnnotations tool help
-	VariantFilterAnnotations (2023_03-63-gec44de43)
+	VariantFilterAnnotations (2023_03-107-g2a1d2478)
 
 	Filter a variant list in GSvar format based on variant annotations.
 
@@ -41,7 +41,8 @@
 	Count NGSD                         Filter based on the hom/het occurances of a variant in the NGSD.
 	                                   Parameters:
 	                                     max_count - Maximum NGSD count [default=20] [min=0]
-	                                     ignore_genotype - If set, all NGSD entries are counted independent of the variant genotype. Otherwise, for homozygous variants only homozygous NGSD entries are counted and for heterozygous variants all NGSD entries are counted. [default=false]
+	                                     ignore_genotype - If set, all variants in NGSD are counted independent of the genotype. Otherwise, for homozygous variants only homozygous NGSD variants are counted and for heterozygous variants homozygous and heterozygous NGSD variants are counted. [default=false]
+	                                     mosaic_as_het - If set, mosaic variants are counted as heterozygous. Otherwise, they are not counted. [default=false]
 	Filter column empty                Filter that perserves variants which have no entry in the 'filter' column.
 	Filter columns                     Filter based on the entries of the 'filter' column.
 	                                   Parameters:
@@ -126,8 +127,9 @@
 	                                     max_af_nor - Maximum allele frequency in normal sample [%] [default=1] [min=0.0] [max=100.0]
 	Splice effect                      Filter based on the predicted change in splice effect
 	                                   Parameters:
-	                                     MaxEntScan - Minimum percentage change in the value of MaxEntScan. Positive min. increase, negative min. decrease. Disabled if set to zero. [default=-15]
-	                                     SpliceAi - Minimum SpliceAi value. Disabled if set to zero. [default=0.5] [min=0] [max=1]
+	                                     SpliceAi - Minimum SpliceAi score. Disabled if set to zero. [default=0.5] [min=0] [max=1]
+	                                     MaxEntScan - Minimum predicted splice effect. Disabled if set to LOW. [default=HIGH] [valid=HIGH,MODERATE,LOW]
+	                                     splice_site_only - Use native splice site predictions only. Skip de-novo acceptor/donor predictions (MaxEntScan). [default=true]
 	                                     action - Action to perform [default=FILTER] [valid=KEEP,FILTER]
 	Text search                        Filter for text match in variant annotations.
 	                                   The text comparison ignores the case.
@@ -141,8 +143,8 @@
 	                                     build - Genome build used for pseudoautosomal region coordinates [default=hg38] [valid=hg19,hg38]
 	Tumor zygosity                     Filter based on the zygosity of tumor-only samples. Filters out germline het/hom calls.
 	                                   Parameters:
-	                                     het_af_range - Consider allele frequencies of 50% ± het_af_range as heterozygous and thus as germline. [default=0] [min=0] [max=49.9]
-	                                     hom_af_range - Consider allele frequencies of 100% ± hom_af_range as homozygous and thus as germline. [default=0] [min=0] [max=99.9]
+	                                     het_af_range - Consider allele frequencies of 50% ± het_af_range as heterozygous and thus as germline. [default=0] [min=0] [max=49.9]
+	                                     hom_af_range - Consider allele frequencies of 100% ± hom_af_range as homozygous and thus as germline. [default=0] [min=0] [max=99.9]
 	Variant quality                    Filter for variant quality
 	                                   Parameters:
 	                                     qual - Minimum variant quality score (Phred) [default=250] [min=0]
@@ -173,7 +175,7 @@
 	  --tdx           Writes a Tool Definition Xml file. The file name is the application name with the suffix '.tdx'.
 
 ### VariantFilterAnnotations changelog
-	VariantFilterAnnotations 2023_03-63-gec44de43
+	VariantFilterAnnotations 2023_03-107-g2a1d2478
 
 	2018-07-30 Replaced command-line parameters by INI file and added many new filters.
 	2017-06-14 Refactoring of genotype-based filters: now also supports multi-sample filtering of affected and control samples.