Skip to content

Instantly share code, notes, and snippets.

@dleehr

dleehr/exomeseq-preprocessing.cwl

Last active October 5, 2018 13:34
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save dleehr/175a6dfbd63ceac36278e35e97fc89ce to your computer and use it in GitHub Desktop.
Save dleehr/175a6dfbd63ceac36278e35e97fc89ce to your computer and use it in GitHub Desktop.
Download ZIP
Raw
exomeseq-preprocessing.cwl
{
"$graph": [
{
"class": "Workflow",
"inputs": [
{
"type": [
"null",
{
"type": "array",
"items": "File"
}
],
"id": "#exomeseq-00-prepare-reference-data.cwl/bait_intervals"
},
{
"type": "File",
"secondaryFiles": [
".amb",
".ann",
".bwt",
".pac",
".sa",
".fai",
"^.dict"
],
"id": "#exomeseq-00-prepare-reference-data.cwl/reference_genome"
},
{
"type": [
"null",
{
"type": "array",
"items": "File"
}
],
"id": "#exomeseq-00-prepare-reference-data.cwl/target_intervals"
}
],
"outputs": [
{
"type": "File",
"outputSource": "#exomeseq-00-prepare-reference-data.cwl/make_bait_interval_list/output_interval_list_file",
"id": "#exomeseq-00-prepare-reference-data.cwl/bait_interval_list"
},
{
"type": "File",
"outputSource": "#exomeseq-00-prepare-reference-data.cwl/make_target_interval_list/output_interval_list_file",
"id": "#exomeseq-00-prepare-reference-data.cwl/target_interval_list"
}
],
"steps": [
{
"run": "#picard-BedToIntervalList.cwl",
"requirements": [
{
"class": "ResourceRequirement",
"coresMin": 1,
"ramMin": 4000,
"outdirMin": 12000,
"tmpdirMin": 12000
}
],
"in": [
{
"source": "#exomeseq-00-prepare-reference-data.cwl/bait_intervals",
"id": "#exomeseq-00-prepare-reference-data.cwl/make_bait_interval_list/input_file"
},
{
"source": "#exomeseq-00-prepare-reference-data.cwl/reference_genome",
"id": "#exomeseq-00-prepare-reference-data.cwl/make_bait_interval_list/reference_sequence"
}
],
"out": [
"#exomeseq-00-prepare-reference-data.cwl/make_bait_interval_list/output_interval_list_file"
],
"id": "#exomeseq-00-prepare-reference-data.cwl/make_bait_interval_list"
},
{
"run": "#picard-BedToIntervalList.cwl",
"requirements": [
{
"class": "ResourceRequirement",
"coresMin": 1,
"ramMin": 4000,
"outdirMin": 12000,
"tmpdirMin": 12000
}
],
"in": [
{
"source": "#exomeseq-00-prepare-reference-data.cwl/target_intervals",
"id": "#exomeseq-00-prepare-reference-data.cwl/make_target_interval_list/input_file"
},
{
"source": "#exomeseq-00-prepare-reference-data.cwl/reference_genome",
"id": "#exomeseq-00-prepare-reference-data.cwl/make_target_interval_list/reference_sequence"
}
],
"out": [
"#exomeseq-00-prepare-reference-data.cwl/make_target_interval_list/output_interval_list_file"
],
"id": "#exomeseq-00-prepare-reference-data.cwl/make_target_interval_list"
}
],
"id": "#exomeseq-00-prepare-reference-data.cwl"
},
{
"class": "Workflow",
"requirements": [
{
"class": "ScatterFeatureRequirement"
},
{
"class": "SchemaDefRequirement",
"types": [
{
"name": "#bespin-types.yml/FASTQReadPairType",
"type": "record",
"fields": [
{
"name": "#bespin-types.yml/FASTQReadPairType/name",
"type": "string"
},
{
"name": "#bespin-types.yml/FASTQReadPairType/read1_files",
"type": {
"type": "array",
"items": "File"
}
},
{
"name": "#bespin-types.yml/FASTQReadPairType/read2_files",
"type": {
"type": "array",
"items": "File"
}
}
]
},
{
"name": "#bespin-types.yml/ExomeseqStudyType",
"type": "enum",
"label": "The type of study",
"symbols": [
"#bespin-types.yml/ExomeseqStudyType/Small Familial",
"#bespin-types.yml/ExomeseqStudyType/Large Population"
]
}
],
"id": "#bespin-types.yml",
"name": "#bespin-types.yml"
}
],
"inputs": [
{
"type": "File",
"id": "#exomeseq-01-preprocessing.cwl/GATKJar"
},
{
"type": "File",
"id": "#exomeseq-01-preprocessing.cwl/bait_interval_list"
},
{
"type": [
"null",
"int"
],
"id": "#exomeseq-01-preprocessing.cwl/interval_padding"
},
{
"type": [
"null",
{
"type": "array",
"items": "File"
}
],
"id": "#exomeseq-01-preprocessing.cwl/intervals"
},
{
"type": {
"type": "array",
"items": "File"
},
"id": "#exomeseq-01-preprocessing.cwl/knownSites"
},
{
"type": "string",
"id": "#exomeseq-01-preprocessing.cwl/library"
},
{
"type": "string",
"id": "#exomeseq-01-preprocessing.cwl/platform"
},
{
"type": "#bespin-types.yml/FASTQReadPairType",
"id": "#exomeseq-01-preprocessing.cwl/read_pair"
},
{
"type": "File",
"id": "#exomeseq-01-preprocessing.cwl/reference_genome"
},
{
"type": "File",
"id": "#exomeseq-01-preprocessing.cwl/resource_dbsnp"
},
{
"type": "File",
"id": "#exomeseq-01-preprocessing.cwl/target_interval_list"
},
{
"type": "int",
"id": "#exomeseq-01-preprocessing.cwl/threads"
}
],
"outputs": [
{
"type": {
"type": "array",
"items": "File"
},
"outputSource": "#exomeseq-01-preprocessing.cwl/qc/output_qc_report",
"id": "#exomeseq-01-preprocessing.cwl/fastqc_reports"
},
{
"type": "File",
"outputSource": "#exomeseq-01-preprocessing.cwl/variant_calling/output_HaplotypesBam",
"doc": "BAM file containing assembled haplotypes and locally realigned reads",
"id": "#exomeseq-01-preprocessing.cwl/haplotypes_bam"
},
{
"type": "File",
"outputSource": "#exomeseq-01-preprocessing.cwl/collect_hs_metrics/output_hs_metrics_file",
"id": "#exomeseq-01-preprocessing.cwl/hs_metrics"
},
{
"type": "File",
"outputSource": "#exomeseq-01-preprocessing.cwl/mark_duplicates/output_dedup_bam_file",
"id": "#exomeseq-01-preprocessing.cwl/markduplicates_bam"
},
{
"type": "File",
"outputSource": "#exomeseq-01-preprocessing.cwl/variant_calling/output_HaplotypeCaller",
"doc": "VCF file from per sample variant calling",
"id": "#exomeseq-01-preprocessing.cwl/raw_variants"
},
{
"type": "File",
"outputSource": "#exomeseq-01-preprocessing.cwl/recalibrate_02_apply/output_printReads",
"id": "#exomeseq-01-preprocessing.cwl/recalibrated_reads"
},
{
"type": "File",
"outputSource": "#exomeseq-01-preprocessing.cwl/recalibrate_01_analyze/output_baseRecalibrator",
"id": "#exomeseq-01-preprocessing.cwl/recalibration_table"
},
{
"type": {
"type": "array",
"items": "File"
},
"outputSource": "#exomeseq-01-preprocessing.cwl/trim/trim_reports",
"id": "#exomeseq-01-preprocessing.cwl/trim_reports"
}
],
"steps": [
{
"run": "#picard-CollectHsMetrics.cwl",
"requirements": [
{
"class": "ResourceRequirement",
"coresMin": 1,
"ramMin": 4000,
"outdirMin": 12000,
"tmpdirMin": 12000
}
],
"in": [
{
"source": "#exomeseq-01-preprocessing.cwl/bait_interval_list",
"id": "#exomeseq-01-preprocessing.cwl/collect_hs_metrics/bait_intervals"
},
{
"source": "#exomeseq-01-preprocessing.cwl/mark_duplicates/output_dedup_bam_file",
"id": "#exomeseq-01-preprocessing.cwl/collect_hs_metrics/input_file"
},
{
"source": "#exomeseq-01-preprocessing.cwl/generate_sample_filenames/hs_metrics_output_filename",
"id": "#exomeseq-01-preprocessing.cwl/collect_hs_metrics/output_filename"
},
{
"source": "#exomeseq-01-preprocessing.cwl/reference_genome",
"id": "#exomeseq-01-preprocessing.cwl/collect_hs_metrics/reference_sequence"
},
{
"source": "#exomeseq-01-preprocessing.cwl/target_interval_list",
"id": "#exomeseq-01-preprocessing.cwl/collect_hs_metrics/target_intervals"
}
],
"out": [
"#exomeseq-01-preprocessing.cwl/collect_hs_metrics/output_hs_metrics_file"
],
"id": "#exomeseq-01-preprocessing.cwl/collect_hs_metrics"
},
{
"run": "#concat-gz-files.cwl",
"scatter": [
"#exomeseq-01-preprocessing.cwl/combine_reads/files",
"#exomeseq-01-preprocessing.cwl/combine_reads/output_filename"
],
"scatterMethod": "dotproduct",
"in": [
{
"source": "#exomeseq-01-preprocessing.cwl/file_pair_details/reads",
"id": "#exomeseq-01-preprocessing.cwl/combine_reads/files"
},
{
"source": "#exomeseq-01-preprocessing.cwl/generate_sample_filenames/combined_reads_output_filenames",
"id": "#exomeseq-01-preprocessing.cwl/combine_reads/output_filename"
}
],
"out": [
"#exomeseq-01-preprocessing.cwl/combine_reads/output"
],
"id": "#exomeseq-01-preprocessing.cwl/combine_reads"
},
{
"run": "#extract-named-file-pair-details.cwl",
"in": [
{
"source": "#exomeseq-01-preprocessing.cwl/library",
"id": "#exomeseq-01-preprocessing.cwl/file_pair_details/library"
},
{
"source": "#exomeseq-01-preprocessing.cwl/platform",
"id": "#exomeseq-01-preprocessing.cwl/file_pair_details/platform"
},
{
"source": "#exomeseq-01-preprocessing.cwl/read_pair",
"id": "#exomeseq-01-preprocessing.cwl/file_pair_details/read_pair"
}
],
"out": [
"#exomeseq-01-preprocessing.cwl/file_pair_details/reads",
"#exomeseq-01-preprocessing.cwl/file_pair_details/read_pair_name",
"#exomeseq-01-preprocessing.cwl/file_pair_details/read_group_header"
],
"id": "#exomeseq-01-preprocessing.cwl/file_pair_details"
},
{
"run": "#generate-sample-filenames.cwl",
"in": [
{
"source": "#exomeseq-01-preprocessing.cwl/file_pair_details/read_pair_name",
"id": "#exomeseq-01-preprocessing.cwl/generate_sample_filenames/sample_name"
}
],
"out": [
"#exomeseq-01-preprocessing.cwl/generate_sample_filenames/combined_reads_output_filenames",
"#exomeseq-01-preprocessing.cwl/generate_sample_filenames/mapped_reads_output_filename",
"#exomeseq-01-preprocessing.cwl/generate_sample_filenames/sorted_reads_output_filename",
"#exomeseq-01-preprocessing.cwl/generate_sample_filenames/dedup_reads_output_filename",
"#exomeseq-01-preprocessing.cwl/generate_sample_filenames/dedup_metrics_output_filename",
"#exomeseq-01-preprocessing.cwl/generate_sample_filenames/recal_reads_output_filename",
"#exomeseq-01-preprocessing.cwl/generate_sample_filenames/recal_table_output_filename",
"#exomeseq-01-preprocessing.cwl/generate_sample_filenames/raw_variants_output_filename",
"#exomeseq-01-preprocessing.cwl/generate_sample_filenames/haplotypes_bam_output_filename",
"#exomeseq-01-preprocessing.cwl/generate_sample_filenames/hs_metrics_output_filename"
],
"id": "#exomeseq-01-preprocessing.cwl/generate_sample_filenames"
},
{
"run": "#bwa-mem-samtools.cwl",
"requirements": [
{
"class": "ResourceRequirement",
"coresMin": "$(inputs.threads)",
"ramMin": 16000,
"outdirMin": 12000,
"tmpdirMin": 12000
}
],
"in": [
{
"source": "#exomeseq-01-preprocessing.cwl/generate_sample_filenames/mapped_reads_output_filename",
"id": "#exomeseq-01-preprocessing.cwl/map/output_filename"
},
{
"source": "#exomeseq-01-preprocessing.cwl/file_pair_details/read_group_header",
"id": "#exomeseq-01-preprocessing.cwl/map/read_group_header"
},
{
"source": "#exomeseq-01-preprocessing.cwl/trim/trimmed_reads",
"id": "#exomeseq-01-preprocessing.cwl/map/reads"
},
{
"source": "#exomeseq-01-preprocessing.cwl/reference_genome",
"id": "#exomeseq-01-preprocessing.cwl/map/reference"
},
{
"source": "#exomeseq-01-preprocessing.cwl/threads",
"id": "#exomeseq-01-preprocessing.cwl/map/threads"
}
],
"out": [
"#exomeseq-01-preprocessing.cwl/map/output"
],
"id": "#exomeseq-01-preprocessing.cwl/map"
},
{
"run": "#picard-MarkDuplicates.cwl",
"requirements": [
{
"class": "ResourceRequirement",
"coresMin": 1,
"ramMin": 4000,
"outdirMin": 12000,
"tmpdirMin": 12000
}
],
"in": [
{
"source": "#exomeseq-01-preprocessing.cwl/sort/sorted",
"id": "#exomeseq-01-preprocessing.cwl/mark_duplicates/input_file"
},
{
"source": "#exomeseq-01-preprocessing.cwl/generate_sample_filenames/dedup_metrics_output_filename",
"id": "#exomeseq-01-preprocessing.cwl/mark_duplicates/metrics_filename"
},
{
"source": "#exomeseq-01-preprocessing.cwl/generate_sample_filenames/dedup_reads_output_filename",
"id": "#exomeseq-01-preprocessing.cwl/mark_duplicates/output_filename"
}
],
"out": [
"#exomeseq-01-preprocessing.cwl/mark_duplicates/output_dedup_bam_file",
"#exomeseq-01-preprocessing.cwl/mark_duplicates/output_metrics_file"
],
"id": "#exomeseq-01-preprocessing.cwl/mark_duplicates"
},
{
"run": "#fastqc.cwl",
"requirements": [
{
"class": "ResourceRequirement",
"coresMin": 4,
"ramMin": 2500
}
],
"scatter": "#exomeseq-01-preprocessing.cwl/qc/input_fastq_file",
"in": [
{
"source": "#exomeseq-01-preprocessing.cwl/combine_reads/output",
"id": "#exomeseq-01-preprocessing.cwl/qc/input_fastq_file"
},
{
"default": 4,
"id": "#exomeseq-01-preprocessing.cwl/qc/threads"
}
],
"out": [
"#exomeseq-01-preprocessing.cwl/qc/output_qc_report"
],
"id": "#exomeseq-01-preprocessing.cwl/qc"
},
{
"run": "#GATK-BaseRecalibrator.cwl",
"requirements": [
{
"class": "ResourceRequirement",
"coresMin": 8,
"ramMin": 4096
}
],
"in": [
{
"source": "#exomeseq-01-preprocessing.cwl/GATKJar",
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_01_analyze/GATKJar"
},
{
"default": 8,
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_01_analyze/cpu_threads"
},
{
"source": "#exomeseq-01-preprocessing.cwl/mark_duplicates/output_dedup_bam_file",
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_01_analyze/inputBam_BaseRecalibrator"
},
{
"source": "#exomeseq-01-preprocessing.cwl/interval_padding",
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_01_analyze/interval_padding"
},
{
"source": "#exomeseq-01-preprocessing.cwl/intervals",
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_01_analyze/intervals"
},
{
"source": "#exomeseq-01-preprocessing.cwl/knownSites",
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_01_analyze/knownSites"
},
{
"source": "#exomeseq-01-preprocessing.cwl/generate_sample_filenames/recal_table_output_filename",
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_01_analyze/outputfile_BaseRecalibrator"
},
{
"source": "#exomeseq-01-preprocessing.cwl/reference_genome",
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_01_analyze/reference"
}
],
"out": [
"#exomeseq-01-preprocessing.cwl/recalibrate_01_analyze/output_baseRecalibrator"
],
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_01_analyze"
},
{
"run": "#GATK-PrintReads.cwl",
"requirements": [
{
"class": "ResourceRequirement",
"coresMin": 8,
"ramMin": 4096
}
],
"in": [
{
"source": "#exomeseq-01-preprocessing.cwl/GATKJar",
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_02_apply/GATKJar"
},
{
"default": 8,
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_02_apply/cpu_threads"
},
{
"source": "#exomeseq-01-preprocessing.cwl/mark_duplicates/output_dedup_bam_file",
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_02_apply/inputBam_printReads"
},
{
"source": "#exomeseq-01-preprocessing.cwl/recalibrate_01_analyze/output_baseRecalibrator",
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_02_apply/input_baseRecalibrator"
},
{
"source": "#exomeseq-01-preprocessing.cwl/intervals",
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_02_apply/intervals"
},
{
"source": "#exomeseq-01-preprocessing.cwl/generate_sample_filenames/recal_reads_output_filename",
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_02_apply/outputfile_printReads"
},
{
"source": "#exomeseq-01-preprocessing.cwl/reference_genome",
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_02_apply/reference"
}
],
"out": [
"#exomeseq-01-preprocessing.cwl/recalibrate_02_apply/output_printReads"
],
"id": "#exomeseq-01-preprocessing.cwl/recalibrate_02_apply"
},
{
"run": "#picard-SortSam.cwl",
"requirements": [
{
"class": "ResourceRequirement",
"coresMin": 1,
"ramMin": 4000,
"outdirMin": 12000,
"tmpdirMin": 12000
}
],
"in": [
{
"source": "#exomeseq-01-preprocessing.cwl/map/output",
"id": "#exomeseq-01-preprocessing.cwl/sort/input_file"
},
{
"source": "#exomeseq-01-preprocessing.cwl/generate_sample_filenames/sorted_reads_output_filename",
"id": "#exomeseq-01-preprocessing.cwl/sort/output_filename"
}
],
"out": [
"#exomeseq-01-preprocessing.cwl/sort/sorted"
],
"id": "#exomeseq-01-preprocessing.cwl/sort"
},
{
"run": "#trim_galore.cwl",
"requirements": [
{
"class": "ResourceRequirement",
"coresMin": 4,
"ramMin": 8000
}
],
"in": [
{
"default": true,
"id": "#exomeseq-01-preprocessing.cwl/trim/paired"
},
{
"source": "#exomeseq-01-preprocessing.cwl/combine_reads/output",
"id": "#exomeseq-01-preprocessing.cwl/trim/reads"
}
],
"out": [
"#exomeseq-01-preprocessing.cwl/trim/trimmed_reads",
"#exomeseq-01-preprocessing.cwl/trim/trim_reports"
],
"id": "#exomeseq-01-preprocessing.cwl/trim"
},
{
"run": "#GATK-HaplotypeCaller.cwl",
"requirements": [
{
"class": "ResourceRequirement",
"coresMin": 1,
"ramMin": 16384
}
],
"in": [
{
"source": "#exomeseq-01-preprocessing.cwl/GATKJar",
"id": "#exomeseq-01-preprocessing.cwl/variant_calling/GATKJar"
},
{
"source": "#exomeseq-01-preprocessing.cwl/generate_sample_filenames/haplotypes_bam_output_filename",
"id": "#exomeseq-01-preprocessing.cwl/variant_calling/bamOutput"
},
{
"source": "#exomeseq-01-preprocessing.cwl/resource_dbsnp",
"id": "#exomeseq-01-preprocessing.cwl/variant_calling/dbsnp"
},
{
"default": "GVCF",
"id": "#exomeseq-01-preprocessing.cwl/variant_calling/emitRefConfidence"
},
{
"default": [
"StandardAnnotation",
"AS_StandardAnnotation"
],
"id": "#exomeseq-01-preprocessing.cwl/variant_calling/group"
},
{
"source": "#exomeseq-01-preprocessing.cwl/recalibrate_02_apply/output_printReads",
"id": "#exomeseq-01-preprocessing.cwl/variant_calling/inputBam_HaplotypeCaller"
},
{
"source": "#exomeseq-01-preprocessing.cwl/interval_padding",
"id": "#exomeseq-01-preprocessing.cwl/variant_calling/interval_padding"
},
{
"source": "#exomeseq-01-preprocessing.cwl/intervals",
"id": "#exomeseq-01-preprocessing.cwl/variant_calling/intervals"
},
{
"source": "#exomeseq-01-preprocessing.cwl/generate_sample_filenames/raw_variants_output_filename",
"id": "#exomeseq-01-preprocessing.cwl/variant_calling/outputfile_HaplotypeCaller"
},
{
"source": "#exomeseq-01-preprocessing.cwl/reference_genome",
"id": "#exomeseq-01-preprocessing.cwl/variant_calling/reference"
}
],
"out": [
"#exomeseq-01-preprocessing.cwl/variant_calling/output_HaplotypeCaller",
"#exomeseq-01-preprocessing.cwl/variant_calling/output_HaplotypesBam"
],
"id": "#exomeseq-01-preprocessing.cwl/variant_calling"
}
],
"id": "#exomeseq-01-preprocessing.cwl"
},
{
"class": "CommandLineTool",
"requirements": [
{
"class": "EnvVarRequirement",
"envDef": [
{
"envName": "PATH",
"envValue": "/usr/local/bin/:/usr/bin:/bin"
}
],
"id": "#envvar-global.yml",
"name": "#envvar-global.yml"
},
{
"class": "DockerRequirement",
"dockerPull": "dukegcb/gatk-base:3"
}
],
"hints": [
{
"class": "SoftwareRequirement",
"packages": [
{
"version": [
"3.8"
],
"package": "gatk",
"https://schema.org/citation": "https://dx.doi.org/10.1038/ng.806"
}
]
}
],
"inputs": [
{
"type": "File",
"inputBinding": {
"position": 1,
"prefix": "-jar"
},
"id": "#GATK-BaseRecalibrator.cwl/GATKJar"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "--binary_tag_name"
},
"doc": "the binary tag covariate name if using it",
"id": "#GATK-BaseRecalibrator.cwl/binary_tag_name"
},
{
"type": [
"null",
"File"
],
"inputBinding": {
"position": 2,
"prefix": "--BQSR"
},
"doc": "Input covariates table file for on-the-fly base quality score recalibration",
"id": "#GATK-BaseRecalibrator.cwl/bqsr"
},
{
"type": [
"null",
"double"
],
"inputBinding": {
"position": 2,
"prefix": "--bqsrBAQGapOpenPenalty"
},
"doc": "BQSR BAQ gap open penalty (Phred Scaled). Default value is 40. 30 is perhaps better for whole genome call sets",
"id": "#GATK-BaseRecalibrator.cwl/bqsrBAQGapOpenPenalty"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "--covariate"
},
"doc": "One or more covariates to be used in the recalibration. Can be specified multiple times",
"id": "#GATK-BaseRecalibrator.cwl/covariate"
},
{
"type": [
"null",
"int"
],
"doc": "controls the number of CPU threads allocated to each data thread",
"default": 8,
"inputBinding": {
"position": 2,
"prefix": "-nct"
},
"id": "#GATK-BaseRecalibrator.cwl/cpu_threads"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--deletions_default_quality"
},
"doc": "default quality for the base deletions covariate",
"id": "#GATK-BaseRecalibrator.cwl/deletions_default_quality"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--indels_context_size"
},
"doc": "Size of the k-mer context to be used for base insertions and deletions",
"id": "#GATK-BaseRecalibrator.cwl/indels_context_size"
},
{
"type": "File",
"inputBinding": {
"position": 2,
"prefix": "-I"
},
"secondaryFiles": [
"^.bai"
],
"doc": "bam file produced after indelRealigner",
"id": "#GATK-BaseRecalibrator.cwl/inputBam_BaseRecalibrator"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--insertions_default_quality"
},
"doc": "default quality for the base insertions covariate",
"id": "#GATK-BaseRecalibrator.cwl/insertions_default_quality"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--interval_padding"
},
"doc": "Amount of padding (in bp) to add to each interval",
"id": "#GATK-BaseRecalibrator.cwl/interval_padding"
},
{
"type": [
"null",
{
"type": "array",
"items": "File",
"inputBinding": {
"prefix": "--intervals"
}
}
],
"inputBinding": {
"position": 2
},
"doc": "One or more genomic intervals over which to operate",
"id": "#GATK-BaseRecalibrator.cwl/intervals"
},
{
"type": "string",
"default": "-Xmx4g",
"inputBinding": {
"position": 0
},
"id": "#GATK-BaseRecalibrator.cwl/java_arg"
},
{
"type": [
"null",
{
"type": "array",
"items": "File",
"inputBinding": {
"prefix": "--knownSites"
}
}
],
"secondaryFiles": [
".idx"
],
"inputBinding": {
"position": 2
},
"doc": "Any number of VCF files representing known SNPs and/or indels. Could be e.g. dbSNP and/or official 1000 Genomes indel calls. SNPs in these files will be ignored unless the --mismatchFraction argument is used. optional parameter.",
"id": "#GATK-BaseRecalibrator.cwl/knownSites"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--list"
},
"doc": "List the available covariates and exit",
"id": "#GATK-BaseRecalibrator.cwl/list"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--lowMemoryMode"
},
"doc": "Reduce memory usage in multi-threaded code at the expense of threading efficiency",
"id": "#GATK-BaseRecalibrator.cwl/lowMemoryMode"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--low_quality_tail"
},
"doc": "minimum quality for the bases in the tail of the reads to be considered",
"id": "#GATK-BaseRecalibrator.cwl/low_quality_tail"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--maximum_cycle_value"
},
"doc": "The maximum cycle value permitted for the Cycle covariate",
"id": "#GATK-BaseRecalibrator.cwl/maximum_cycle_value"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--mismatches_context_size"
},
"doc": "Size of the k-mer context to be used for base mismatches",
"id": "#GATK-BaseRecalibrator.cwl/mismatches_context_size"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--mismatches_default_quality"
},
"doc": "default quality for the base mismatches covariate",
"id": "#GATK-BaseRecalibrator.cwl/mismatches_default_quality"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--no_standard_covs"
},
"doc": "Do not use the standard set of covariates, but rather just the ones listed using the -cov argument",
"id": "#GATK-BaseRecalibrator.cwl/no_standard_covs"
},
{
"type": [
"null",
"File"
],
"inputBinding": {
"position": 2,
"prefix": "--out"
},
"doc": "The output recalibration table file to create",
"id": "#GATK-BaseRecalibrator.cwl/out"
},
{
"type": "string",
"inputBinding": {
"position": 2,
"prefix": "-o"
},
"doc": "name of the output file from baseRecalibrator",
"id": "#GATK-BaseRecalibrator.cwl/outputfile_BaseRecalibrator"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--quantizing_levels"
},
"doc": "Sort the rows in the tables of reports. Whether GATK report tables should have rows in sorted order, starting from leftmost column",
"id": "#GATK-BaseRecalibrator.cwl/quantizing_levels"
},
{
"type": "File",
"inputBinding": {
"position": 2,
"prefix": "-R"
},
"secondaryFiles": [
".amb",
".ann",
".bwt",
".pac",
".sa",
".fai",
"^.dict"
],
"id": "#GATK-BaseRecalibrator.cwl/reference"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--run_without_dbsnp_potentially_ruining_quality"
},
"doc": "If specified, allows the recalibrator to be used without a dbsnp rod. Very unsafe and for expert users only.",
"id": "#GATK-BaseRecalibrator.cwl/run_without_dbsnp_potentially_ruining_quality"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "--solid_nocall_strategy"
},
"doc": "Defines the behavior of the recalibrator when it encounters no calls in the color space. Options = THROW_EXCEPTION, LEAVE_READ_UNRECALIBRATED, or PURGE_READ",
"id": "#GATK-BaseRecalibrator.cwl/solid_nocall_strategy"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "--solid_recal_mode"
},
"doc": "How should we recalibrate solid bases in which the reference was inserted? Options = DO_NOTHING, SET_Q_ZERO, SET_Q_ZERO_BASE_N, or REMOVE_REF_BIAS",
"id": "#GATK-BaseRecalibrator.cwl/solid_recal_mode"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--sort_by_all_columns"
},
"doc": "Sort the rows in the tables of reports. Whether GATK report tables should have rows in sorted order, starting from leftmost column",
"id": "#GATK-BaseRecalibrator.cwl/sort_by_all_columns"
}
],
"outputs": [
{
"type": "File",
"outputBinding": {
"glob": "$(inputs.outputfile_BaseRecalibrator)"
},
"id": "#GATK-BaseRecalibrator.cwl/output_baseRecalibrator"
}
],
"arguments": [
{
"valueFrom": "$(runtime.tmpdir)",
"position": 0,
"separate": false,
"prefix": "-Djava.io.tmpdir="
},
{
"valueFrom": "BaseRecalibrator",
"position": 2,
"prefix": "-T"
}
],
"baseCommand": [
"java"
],
"doc": "GATK-BaseRecalibrator.cwl is developed for CWL consortium\nIt generate base recalibration table to compensate for systematic errors in basecalling confidences\n Usage: java -jar GenomeAnalysisTK.jar -T BaseRecalibrator -R reference.fasta -I my_reads.bam -knownSites latest_dbsnp.vcf -o recal_data.table.\n",
"id": "#GATK-BaseRecalibrator.cwl"
},
{
"class": "CommandLineTool",
"requirements": [
{
"$import": "#envvar-global.yml"
},
{
"class": "DockerRequirement",
"dockerPull": "dukegcb/gatk-base:3"
}
],
"hints": [
{
"class": "SoftwareRequirement",
"packages": [
{
"version": [
"3.8"
],
"package": "gatk",
"https://schema.org/citation": "https://dx.doi.org/10.1038/ng.806"
}
]
}
],
"inputs": [
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--indelSizeToEliminateInRefModel"
},
"doc": "The size of an indel to check for in the reference model",
"id": "#GATK-HaplotypeCaller.cwl/ERCIS"
},
{
"type": "File",
"inputBinding": {
"position": 1,
"prefix": "-jar"
},
"id": "#GATK-HaplotypeCaller.cwl/GATKJar"
},
{
"type": [
"null",
{
"type": "array",
"items": "int"
}
],
"inputBinding": {
"position": 2
},
"doc": "Input prior for calls",
"id": "#GATK-HaplotypeCaller.cwl/GVCFGQBands"
},
{
"type": [
"null",
"double"
],
"inputBinding": {
"position": 2,
"prefix": "--activeProbabilityThreshold"
},
"doc": "Threshold for the probability of a profile state being active.",
"id": "#GATK-HaplotypeCaller.cwl/activeProbabilityThreshold"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--activeRegionExtension"
},
"doc": "The active region extension; if not provided defaults to Walker annotated default",
"id": "#GATK-HaplotypeCaller.cwl/activeRegionExtension"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--activeRegionMaxSize"
},
"doc": "The active region maximum size; if not provided defaults to Walker annotated default",
"id": "#GATK-HaplotypeCaller.cwl/activeRegionMaxSize"
},
{
"type": [
"null",
"File"
],
"inputBinding": {
"position": 2,
"prefix": "--activeRegionOut"
},
"doc": "Output the active region to this IGV formatted file",
"id": "#GATK-HaplotypeCaller.cwl/activeRegionOut"
},
{
"type": [
"null",
"File"
],
"inputBinding": {
"position": 2,
"prefix": "--activityProfileOut"
},
"doc": "Output the raw activity profile results in IGV format",
"id": "#GATK-HaplotypeCaller.cwl/activityProfileOut"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--allSitePLs"
},
"doc": "Annotate all sites with PLs",
"id": "#GATK-HaplotypeCaller.cwl/allSitePLs"
},
{
"type": [
"null",
{
"type": "array",
"items": "string"
}
],
"inputBinding": {
"position": 2
},
"doc": "The set of alleles at which to genotype when --genotyping_mode is GENOTYPE_GIVEN_ALLELES",
"id": "#GATK-HaplotypeCaller.cwl/alleles"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--allowNonUniqueKmersInRef"
},
"doc": "Allow graphs that have non-unique kmers in the reference",
"id": "#GATK-HaplotypeCaller.cwl/allowNonUniqueKmersInRef"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--annotateNDA"
},
"doc": "If provided, we will annotate records with the number of alternate alleles that were discovered (but not necessarily genotyped) at a given site",
"id": "#GATK-HaplotypeCaller.cwl/annotateNDA"
},
{
"type": [
"null",
{
"type": "array",
"items": "string"
}
],
"inputBinding": {
"position": 2
},
"doc": "One or more specific annotations to apply to variant calls",
"id": "#GATK-HaplotypeCaller.cwl/annotation"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "--bamOutput"
},
"doc": "File to which assembled haplotypes should be written",
"id": "#GATK-HaplotypeCaller.cwl/bamOutput"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "--bamWriterType"
},
"doc": "Which haplotypes should be written to the BAM.",
"id": "#GATK-HaplotypeCaller.cwl/bamWriterType"
},
{
"type": [
"null",
"double"
],
"inputBinding": {
"position": 2,
"prefix": "--consensus"
},
"doc": "The sigma of the band pass filter Gaussian kernel; if not provided defaults to Walker annotated default",
"id": "#GATK-HaplotypeCaller.cwl/bandPassSigma"
},
{
"type": [
"null",
{
"type": "array",
"items": "string"
}
],
"inputBinding": {
"position": 2
},
"doc": "comp binds reference ordered data. This argument supports ROD files of the following types BCF2, VCF, VCF3",
"id": "#GATK-HaplotypeCaller.cwl/comp"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--consensus"
},
"doc": "Print out very verbose debug information about each triggering active region",
"id": "#GATK-HaplotypeCaller.cwl/consensus"
},
{
"type": [
"null",
"File"
],
"inputBinding": {
"position": 2,
"prefix": "--contamination_fraction_to_filter"
},
"doc": "Tab-separated File containing fraction of contamination in sequencing data (per sample) to aggressively remove. Format should be \"\" (Contamination is double) per line; No header.",
"id": "#GATK-HaplotypeCaller.cwl/contamination"
},
{
"type": [
"null",
"int"
],
"doc": "controls the number of CPU threads allocated to each data thread",
"inputBinding": {
"position": 2,
"prefix": "-nct"
},
"id": "#GATK-HaplotypeCaller.cwl/cpu_threads"
},
{
"type": [
"null",
"File"
],
"inputBinding": {
"position": 2,
"prefix": "--dbsnp"
},
"doc": "latest_dbsnp.vcf set of known indels",
"id": "#GATK-HaplotypeCaller.cwl/dbsnp"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--debug"
},
"doc": "Print out very verbose debug information about each triggering active region",
"id": "#GATK-HaplotypeCaller.cwl/debug"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--disableOptimizations"
},
"doc": "Dont skip calculations in ActiveRegions with no variants",
"id": "#GATK-HaplotypeCaller.cwl/disableOptimizations"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--doNotRunPhysicalPhasing"
},
"doc": "As of GATK 3.3, HaplotypeCaller outputs physical (read-based) information (see version 3.3 release notes and documentation for details). This argument disables that behavior.",
"id": "#GATK-HaplotypeCaller.cwl/doNotRunPhysicalPhasing"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--dontIncreaseKmerSizesForCycles"
},
"doc": "Disable iterating over kmer sizes when graph cycles are detected",
"id": "#GATK-HaplotypeCaller.cwl/dontIncreaseKmerSizesForCycles"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--dontTrimActiveRegions"
},
"doc": "If specified, we will not trim down the active region from the full region (active + extension) to just the active interval for genotyping",
"id": "#GATK-HaplotypeCaller.cwl/dontTrimActiveRegions"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "--emitRefConfidence"
},
"doc": "Mode for emitting reference confidence scores",
"id": "#GATK-HaplotypeCaller.cwl/emitRefConfidence"
},
{
"type": [
"null",
{
"type": "array",
"items": "string"
}
],
"inputBinding": {
"position": 2
},
"doc": "One or more specific annotations to exclude",
"id": "#GATK-HaplotypeCaller.cwl/excludeAnnotation"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--forceActive"
},
"doc": "If provided, all bases will be tagged as active",
"id": "#GATK-HaplotypeCaller.cwl/forceActive"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--gcpHMM"
},
"doc": "Flat gap continuation penalty for use in the Pair HMM",
"id": "#GATK-HaplotypeCaller.cwl/gcpHMM"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "--genotyping_mode"
},
"doc": "The --genotyping_mode argument is an enumerated type (GenotypingOutputMode), which can have one of the following values",
"id": "#GATK-HaplotypeCaller.cwl/genotyping_mode"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--phredScaledGlobalReadMismappingRate"
},
"doc": "The global assumed mismapping rate for reads",
"id": "#GATK-HaplotypeCaller.cwl/globalMAPQ"
},
{
"type": [
"null",
"File"
],
"inputBinding": {
"position": 2,
"prefix": "--graphOutput"
},
"doc": "Write debug assembly graph information to this file",
"id": "#GATK-HaplotypeCaller.cwl/graphOutput"
},
{
"type": {
"type": "array",
"items": "string",
"inputBinding": {
"prefix": "--group"
}
},
"inputBinding": {
"position": 2
},
"doc": "One or more classes/groups of annotations to apply to variant calls",
"id": "#GATK-HaplotypeCaller.cwl/group"
},
{
"type": [
"null",
"double"
],
"inputBinding": {
"position": 2,
"prefix": "--heterozygosity"
},
"doc": "Heterozygosity for indel calling",
"id": "#GATK-HaplotypeCaller.cwl/heterozygosity"
},
{
"type": [
"null",
"double"
],
"inputBinding": {
"position": 2,
"prefix": "--indel_heterozygosity"
},
"doc": "Heterozygosity for indel calling",
"id": "#GATK-HaplotypeCaller.cwl/indel_heterozygosity"
},
{
"type": "File",
"inputBinding": {
"position": 2,
"prefix": "-I"
},
"secondaryFiles": [
"^.bai"
],
"doc": "bam file produced after printReads",
"id": "#GATK-HaplotypeCaller.cwl/inputBam_HaplotypeCaller"
},
{
"type": [
"null",
{
"type": "array",
"items": "double"
}
],
"inputBinding": {
"position": 2
},
"doc": "Input prior for calls",
"id": "#GATK-HaplotypeCaller.cwl/input_prior"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--interval_padding"
},
"doc": "Amount of padding (in bp) to add to each interval",
"id": "#GATK-HaplotypeCaller.cwl/interval_padding"
},
{
"type": [
"null",
{
"type": "array",
"items": "File"
}
],
"inputBinding": {
"position": 2,
"prefix": "--intervals"
},
"doc": "One or more genomic intervals over which to operate",
"id": "#GATK-HaplotypeCaller.cwl/intervals"
},
{
"type": "string",
"default": "-Xmx4g",
"inputBinding": {
"position": 0
},
"id": "#GATK-HaplotypeCaller.cwl/java_arg"
},
{
"type": [
"null",
{
"type": "array",
"items": "int"
}
],
"inputBinding": {
"position": 2
},
"doc": "Kmer size to use in the read threading assembler",
"id": "#GATK-HaplotypeCaller.cwl/kmerSize"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--maxNumHaplotypesInPopulation"
},
"doc": "Maximum number of haplotypes to consider for your population",
"id": "#GATK-HaplotypeCaller.cwl/maxNumHaplotypesInPopulation"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--maxReadsInRegionPerSample"
},
"doc": "Maximum reads in an active region",
"id": "#GATK-HaplotypeCaller.cwl/maxReadsInRegionPerSample"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--max_alternate_alleles"
},
"doc": "Maximum number of alternate alleles to genotype",
"id": "#GATK-HaplotypeCaller.cwl/max_alternate_alleles"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--minDanglingBranchLength"
},
"doc": "Minimum length of a dangling branch to attempt recovery",
"id": "#GATK-HaplotypeCaller.cwl/minDanglingBranchLength"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--minPruning"
},
"doc": "Minimum support to not prune paths in the graph",
"id": "#GATK-HaplotypeCaller.cwl/minPruning"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--minReadsPerAlignmentStart"
},
"doc": "Minimum number of reads sharing the same alignment start for each genomic location in an active region",
"id": "#GATK-HaplotypeCaller.cwl/minReadsPerAlignmentStart"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--min_base_quality_score"
},
"doc": "Minimum base quality required to consider a base for calling",
"id": "#GATK-HaplotypeCaller.cwl/min_base_quality_score"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--numPruningSamples"
},
"doc": "Number of samples that must pass the minPruning threshold",
"id": "#GATK-HaplotypeCaller.cwl/numPruningSamples"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "--output_mode"
},
"doc": "The PCR indel model to use",
"id": "#GATK-HaplotypeCaller.cwl/output_mode"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "-o"
},
"doc": "name of the output file from HaplotypeCaller",
"id": "#GATK-HaplotypeCaller.cwl/outputfile_HaplotypeCaller"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "--pcr_indel_model"
},
"doc": "The PCR indel model to use",
"id": "#GATK-HaplotypeCaller.cwl/pcr_indel_model"
},
{
"type": "File",
"inputBinding": {
"position": 2,
"prefix": "-R"
},
"secondaryFiles": [
".amb",
".ann",
".bwt",
".pac",
".sa",
".fai",
"^.dict"
],
"id": "#GATK-HaplotypeCaller.cwl/reference"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "--sample_name"
},
"doc": "Use additional trigger on variants found in an external alleles file",
"id": "#GATK-HaplotypeCaller.cwl/sample_name"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--sample_ploidy"
},
"doc": "Use additional trigger on variants found in an external alleles file",
"id": "#GATK-HaplotypeCaller.cwl/sample_ploidy"
},
{
"type": [
"null",
"double"
],
"inputBinding": {
"position": 2,
"prefix": "--standard_min_confidence_threshold_for_calling"
},
"doc": "The minimum phred-scaled confidence threshold at which variants should be called",
"id": "#GATK-HaplotypeCaller.cwl/stand_call_conf"
},
{
"type": [
"null",
"double"
],
"inputBinding": {
"position": 2,
"prefix": "--standard_min_confidence_threshold_for_emitting"
},
"doc": "The minimum phred-scaled confidence threshold at which variants should be emitted (and filtered with LowQual if less than the calling threshold)",
"id": "#GATK-HaplotypeCaller.cwl/stand_emit_conf"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--useAllelesTrigger"
},
"doc": "Use additional trigger on variants found in an external alleles file",
"id": "#GATK-HaplotypeCaller.cwl/useAllelesTrigger"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--useFilteredReadsForAnnotations"
},
"doc": "Use the contamination-filtered read maps for the purposes of annotating variants",
"id": "#GATK-HaplotypeCaller.cwl/useFilteredReadsForAnnotations"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--variant_index_parameter"
},
"doc": "Index parameter, needed by emitRefConfidence GVCF if output extension not .g.vcf",
"id": "#GATK-HaplotypeCaller.cwl/variant_index_parameter"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "--variant_index_type"
},
"doc": "Index type, needed by emitRefConfidence GVCF if output extension not .g.vcf",
"id": "#GATK-HaplotypeCaller.cwl/variant_index_type"
}
],
"outputs": [
{
"type": "File",
"outputBinding": {
"glob": "$(inputs.outputfile_HaplotypeCaller)"
},
"secondaryFiles": [
".idx"
],
"id": "#GATK-HaplotypeCaller.cwl/output_HaplotypeCaller"
},
{
"type": [
"null",
"File"
],
"outputBinding": {
"glob": "$(inputs.bamOutput)"
},
"id": "#GATK-HaplotypeCaller.cwl/output_HaplotypesBam"
}
],
"arguments": [
{
"valueFrom": "$(runtime.tmpdir)",
"position": 0,
"separate": false,
"prefix": "-Djava.io.tmpdir="
},
{
"valueFrom": "HaplotypeCaller",
"position": 2,
"prefix": "-T"
}
],
"baseCommand": [
"java"
],
"doc": "GATK-RealignTargetCreator.cwl is developed for CWL consortium\nCall germline SNPs and indels via local re-assembly of haplotypes\n",
"id": "#GATK-HaplotypeCaller.cwl"
},
{
"class": "CommandLineTool",
"requirements": [
{
"$import": "#envvar-global.yml"
},
{
"class": "DockerRequirement",
"dockerPull": "dukegcb/gatk-base:3"
}
],
"hints": [
{
"class": "SoftwareRequirement",
"packages": [
{
"version": [
"3.8"
],
"package": "gatk",
"https://schema.org/citation": "https://dx.doi.org/10.1038/ng.806"
}
]
}
],
"inputs": [
{
"type": "File",
"inputBinding": {
"position": 1,
"prefix": "-jar"
},
"id": "#GATK-PrintReads.cwl/GATKJar"
},
{
"type": [
"null",
"int"
],
"doc": "controls the number of CPU threads allocated to each data thread",
"default": 8,
"inputBinding": {
"position": 2,
"prefix": "-nct"
},
"id": "#GATK-PrintReads.cwl/cpu_threads"
},
{
"type": "File",
"inputBinding": {
"position": 2,
"prefix": "-I"
},
"secondaryFiles": [
"^.bai"
],
"doc": "bam file produced after indelRealigner",
"id": "#GATK-PrintReads.cwl/inputBam_printReads"
},
{
"type": "File",
"inputBinding": {
"position": 2,
"prefix": "-BQSR"
},
"doc": "the recalibration table produced by BaseRecalibration",
"id": "#GATK-PrintReads.cwl/input_baseRecalibrator"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 2,
"prefix": "--interval_padding"
},
"doc": "Amount of padding (in bp) to add to each interval",
"id": "#GATK-PrintReads.cwl/interval_padding"
},
{
"type": [
"null",
{
"type": "array",
"items": "File",
"inputBinding": {
"prefix": "--intervals"
}
}
],
"inputBinding": {
"position": 2
},
"doc": "One or more genomic intervals over which to operate",
"id": "#GATK-PrintReads.cwl/intervals"
},
{
"type": "string",
"default": "-Xmx4g",
"inputBinding": {
"position": 0
},
"id": "#GATK-PrintReads.cwl/java_arg"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "--number"
},
"doc": "Exclude all reads with this platform from the output",
"id": "#GATK-PrintReads.cwl/number"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "-o"
},
"doc": "name of the output file from indelRealigner",
"id": "#GATK-PrintReads.cwl/outputfile_printReads"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "--platform"
},
"doc": "Exclude all reads with this platform from the output",
"id": "#GATK-PrintReads.cwl/platform"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 2,
"prefix": "--readGroup"
},
"doc": "Exclude all reads with this read group from the output",
"id": "#GATK-PrintReads.cwl/readGroup"
},
{
"type": "File",
"inputBinding": {
"position": 2,
"prefix": "-R"
},
"secondaryFiles": [
".amb",
".ann",
".bwt",
".pac",
".sa",
".fai",
"^.dict"
],
"id": "#GATK-PrintReads.cwl/reference"
},
{
"type": [
"null",
{
"type": "array",
"items": "File"
}
],
"inputBinding": {
"position": 2
},
"id": "#GATK-PrintReads.cwl/sample_file"
},
{
"type": [
"null",
{
"type": "array",
"items": "string"
}
],
"inputBinding": {
"position": 2
},
"doc": "Sample name to be included in the analysis. Can be specified multiple times.",
"id": "#GATK-PrintReads.cwl/sample_name"
},
{
"type": [
"null",
"boolean"
],
"inputBinding": {
"position": 2,
"prefix": "--simplify"
},
"doc": "Erase all extra attributes in the read but keep the read group information",
"id": "#GATK-PrintReads.cwl/simplify"
}
],
"outputs": [
{
"type": "File",
"outputBinding": {
"glob": "$(inputs.outputfile_printReads)"
},
"secondaryFiles": [
"^.bai"
],
"id": "#GATK-PrintReads.cwl/output_printReads"
}
],
"arguments": [
{
"valueFrom": "$(runtime.tmpdir)",
"position": 0,
"separate": false,
"prefix": "-Djava.io.tmpdir="
},
{
"valueFrom": "PrintReads",
"position": 2,
"prefix": "-T"
}
],
"baseCommand": [
"java"
],
"doc": "GATK-RealignTargetCreator.cwl is developed for CWL consortium\nPrints all reads that have a mapping quality above zero\n Usage: java -Xmx4g -jar GenomeAnalysisTK.jar -T PrintReads -R reference.fasta -I input1.bam -I input2.bam -o output.bam --read_filter MappingQualityZero\n",
"id": "#GATK-PrintReads.cwl"
},
{
"class": "CommandLineTool",
"requirements": [
{
"$import": "#envvar-global.yml"
},
{
"class": "DockerRequirement",
"dockerPull": "dukegcb/bwa-samtools:0.7.12_1.2.1-254-6462e34"
},
{
"class": "InlineJavascriptRequirement"
}
],
"hints": [
{
"class": "SoftwareRequirement",
"packages": [
{
"version": [
"0.7.12"
],
"package": "bwa",
"https://schema.org/citation": "https://dx.doi.org/10.1093/bioinformatics/btp324"
},
{
"version": [
"1.2-242-g4d56437"
],
"package": "samtools",
"https://schema.org/citation": "https://doi.org/10.1093/bioinformatics/btp352"
}
]
}
],
"inputs": [
{
"type": [
"null",
{
"type": "array",
"items": "int"
}
],
"inputBinding": {
"position": 1,
"prefix": "-I",
"itemSeparator": ","
},
"id": "#bwa-mem-samtools.cwl/min_std_max_min"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 1,
"prefix": "-k"
},
"doc": "-k INT minimum seed length [19]",
"id": "#bwa-mem-samtools.cwl/minimum_seed_length"
},
{
"type": "string",
"id": "#bwa-mem-samtools.cwl/output_filename"
},
{
"type": [
"null",
"string"
],
"inputBinding": {
"position": 1,
"prefix": "-R"
},
"doc": "-R STR read group header line such as '@RG\\tID:foo\\tSM:bar' [null]",
"id": "#bwa-mem-samtools.cwl/read_group_header"
},
{
"type": {
"type": "array",
"items": "File"
},
"inputBinding": {
"position": 3
},
"id": "#bwa-mem-samtools.cwl/reads"
},
{
"type": "File",
"inputBinding": {
"position": 2
},
"secondaryFiles": [
".amb",
".ann",
".bwt",
".pac",
".sa"
],
"id": "#bwa-mem-samtools.cwl/reference"
},
{
"type": [
"null",
"int"
],
"inputBinding": {
"position": 1,
"prefix": "-t"
},
"doc": "-t INT number of threads [1]",
"id": "#bwa-mem-samtools.cwl/threads"
}
],
"stdout": "$(inputs.output_filename)",
"outputs": [
{
"type": "File",
"outputBinding": {
"glob": "$(inputs.output_filename)"
},
"id": "#bwa-mem-samtools.cwl/output"
}
],
"baseCommand": [
"bwamem-to-samtools.sh"
],
"doc": "Usage: bwa mem [options] <idxbase> <in1.fq> [in2.fq]\n\nAlgorithm options:\n -w INT band width for banded alignment [100]\n -d INT off-diagonal X-dropoff [100]\n -r FLOAT look for internal seeds inside a seed longer than {-k} * FLOAT [1.5]\n -y INT seed occurrence for the 3rd round seeding [20]\n -c INT skip seeds with more than INT occurrences [500]\n -D FLOAT drop chains shorter than FLOAT fraction of the longest overlapping chain [0.50]\n -W INT discard a chain if seeded bases shorter than INT [0]\n -m INT perform at most INT rounds of mate rescues for each read [50]\n -S skip mate rescue\n -P skip pairing; mate rescue performed unless -S also in use\n -e discard full-length exact matches\n\nScoring options:\n\n -A INT score for a sequence match, which scales options -TdBOELU unless overridden [1]\n -B INT penalty for a mismatch [4]\n -O INT[,INT] gap open penalties for deletions and insertions [6,6]\n -E INT[,INT] gap extension penalty; a gap of size k cost '{-O} + {-E}*k' [1,1]\n -L INT[,INT] penalty for 5'- and 3'-end clipping [5,5]\n -U INT penalty for an unpaired read pair [17]\n\n -x STR read type. Setting -x changes multiple parameters unless overriden [null]\n pacbio: -k17 -W40 -r10 -A1 -B1 -O1 -E1 -L0 (PacBio reads to ref)\n ont2d: -k14 -W20 -r10 -A1 -B1 -O1 -E1 -L0 (Oxford Nanopore 2D-reads to ref)\n intractg: -B9 -O16 -L5 (intra-species contigs to ref)\n\nInput/output options:\n\n -p smart pairing (ignoring in2.fq)\n -R STR read group header line such as '@RG\\tID:foo\\tSM:bar' [null]\n -H STR/FILE insert STR to header if it starts with @; or insert lines in FILE [null]\n -j treat ALT contigs as part of the primary assembly (i.e. ignore <idxbase>.alt file)\n\n -v INT verbose level: 1=error, 2=warning, 3=message, 4+=debugging [3]\n -T INT minimum score to output [30]\n -h INT[,INT] if there are <INT hits with score >80% of the max score, output all in XA [5,200]\n -a output all alignments for SE or unpaired PE\n -C append FASTA/FASTQ comment to SAM output\n -V output the reference FASTA header in the XR tag\n -Y use soft clipping for supplementary alignments\n -M mark shorter split hits as secondary\n\n -I FLOAT[,FLOAT[,INT[,INT]]]\n specify the mean, standard deviation (10% of the mean if absent), max\n (4 sigma from the mean if absent) and min of the insert size distribution.\n FR orientation only. [inferred]\n\nNote: Please read the man page for detailed description of the command line and options.\n",
"id": "#bwa-mem-samtools.cwl"
},
{
"class": "CommandLineTool",
"requirements": [
{
"class": "InitialWorkDirRequirement",
"listing": [
{
"entryname": "combinefiles.sh",
"entry": "zcat \"$@\" | gzip\n"
}
]
}
],
"baseCommand": "bash",
"arguments": [
"combinefiles.sh"
],
"inputs": [
{
"type": {
"type": "array",
"items": "File"
},
"inputBinding": {
"position": 2,
"shellQuote": false
},
"id": "#concat-gz-files.cwl/files"
},
{
"type": "string",
"id": "#concat-gz-files.cwl/output_filename"
}
],
"stdout": "$(inputs.output_filename)",
"outputs": [
{
"type": "File",
"outputBinding": {
"glob": "$(inputs.output_filename)"
},
"id": "#concat-gz-files.cwl/output"
}
],
"id": "#concat-gz-files.cwl"
},
{
"class": "ExpressionTool",
"label": "Given a FASTQReadPairType returns a 2D array of the files contained within",
"requirements": [
{
"class": "InlineJavascriptRequirement"
},
{
"$import": "#bespin-types.yml"
}
],
"inputs": [
{
"type": "string",
"id": "#extract-named-file-pair-details.cwl/library"
},
{
"type": "string",
"id": "#extract-named-file-pair-details.cwl/platform"
},
{
"type": "#bespin-types.yml/FASTQReadPairType",
"id": "#extract-named-file-pair-details.cwl/read_pair"
}
],
"outputs": [
{
"type": "string",
"id": "#extract-named-file-pair-details.cwl/read_group_header"
},
{
"type": "string",
"id": "#extract-named-file-pair-details.cwl/read_pair_name"
},
{
"type": {
"type": "array",
"items": {
"type": "array",
"items": "File"
}
},
"id": "#extract-named-file-pair-details.cwl/reads"
}
],
"expression": "${\n var readPairName = inputs.read_pair.name;\n var readGroupHeader = \"@RG\" +\n \"\\\\tID:\" + readPairName +\n \"\\\\tLB:\" + inputs.library +\n \"\\\\tPL:\" + inputs.platform +\n \"\\\\tPU:\" + readPairName +\n \"\\\\tSM:\" + readPairName;\n return {\n reads: [\n inputs.read_pair.read1_files,\n inputs.read_pair.read2_files,\n ],\n read_pair_name: readPairName,\n read_group_header: readGroupHeader\n };\n\n}\n",
"id": "#extract-named-file-pair-details.cwl"
},
{
"class": "CommandLineTool",
"hints": [
{
"class": "DockerRequirement",
"dockerPull": "dukegcb/fastqc:0.11.4"
},
{
"class": "SoftwareRequirement",
"packages": [
{
"version": [
"0.11.4"
],
"package": "fastqc",
"https://schema.org/citation": "https://www.bioinformatics.babraham.ac.uk/projects/fastqc/"
}
]
}
],
"requirements": [
{
"class": "InlineJavascriptRequirement"
}
],
"inputs": [
{
"type": "string",
"default": "fastq",
"inputBinding": {
"position": 3,
"prefix": "--format"
},
"id": "#fastqc.cwl/format"
},
{
"type": "File",
"inputBinding": {
"position": 4
},
"id": "#fastqc.cwl/input_fastq_file"
},
{
"type": "boolean",
"default": true,
"inputBinding": {
"prefix": "--noextract",
"position": 2
},
"id": "#fastqc.cwl/noextract"
},
{
"type": "int",
"default": 1,
"doc": "The number of threads to use. The fastqc wrapper script requests 250MB of memory per thread, so keep this in line with any CWL ResourceRequirement",
"inputBinding": {
"position": 5,
"prefix": "--threads"
},
"id": "#fastqc.cwl/threads"
}
],
"outputs": [
{
"type": "File",
"outputBinding": {
"glob": "*_fastqc.zip"
},
"id": "#fastqc.cwl/output_qc_report"
}
],
"baseCommand": "fastqc",
"arguments": [
{
"valueFrom": "$('/tmp')",
"prefix": "--dir",
"position": 5
},
{
"valueFrom": "$(runtime.outdir)",
"prefix": "-o",
"position": 5
}
],
"id": "#fastqc.cwl"
},
{
"class": "ExpressionTool",
"label": "Generates a set of file names for preprocessing steps based on an input sample name",
"requirements": [
{
"class": "InlineJavascriptRequirement"
}
],
"inputs": [
{
"type": "string",
"id": "#generate-sample-filenames.cwl/sample_name"
}
],
"outputs": [
{
"type": {
"type": "array",
"items": "string"
},
"id": "#generate-sample-filenames.cwl/combined_reads_output_filenames"
},
{
"type": "string",
"id": "#generate-sample-filenames.cwl/dedup_metrics_output_filename"
},
{
"type": "string",
"id": "#generate-sample-filenames.cwl/dedup_reads_output_filename"
},
{
"type": "string",
"id": "#generate-sample-filenames.cwl/haplotypes_bam_output_filename"
},
{
"type": "string",
"id": "#generate-sample-filenames.cwl/hs_metrics_output_filename"
},
{
"type": "string",
"id": "#generate-sample-filenames.cwl/mapped_reads_output_filename"
},
{
"type": "string",
"id": "#generate-sample-filenames.cwl/raw_variants_output_filename"
},
{
"type": "string",
"id": "#generate-sample-filenames.cwl/recal_reads_output_filename"
},
{
"type": "string",
"id": "#generate-sample-filenames.cwl/recal_table_output_filename"
},
{
"type": "string",
"id": "#generate-sample-filenames.cwl/sorted_reads_output_filename"
}
],
"expression": "${\n function makeFilename(base, suffix, extension) {\n return base + '-' + suffix + '.' + extension;\n }\n var base = inputs.sample_name\n\n return {\n combined_reads_output_filenames: [\n makeFilename(base, 'R1', 'fastq.gz'),\n makeFilename(base, 'R2', 'fastq.gz'),\n ],\n mapped_reads_output_filename: makeFilename(base, 'mapped', 'bam'),\n sorted_reads_output_filename: makeFilename(base, 'sorted', 'bam'),\n dedup_reads_output_filename: makeFilename(base, 'dedup', 'bam'),\n dedup_metrics_output_filename: makeFilename(base, 'dedup-metrics', 'out'),\n recal_reads_output_filename: makeFilename(base, 'recal', 'bam'),\n recal_table_output_filename: makeFilename(base, 'recal', 'table'),\n raw_variants_output_filename: makeFilename(base, 'raw_variants', 'g.vcf'),\n haplotypes_bam_output_filename: makeFilename(base, 'haplotypes', 'bam'),\n hs_metrics_output_filename: makeFilename(base, 'hs', 'txt')\n };\n}\n",
"id": "#generate-sample-filenames.cwl"
},
{
"class": "CommandLineTool",
"requirements": [
{
"class": "DockerRequirement",
"dockerPull": "dukegcb/picard:2.10.7"
},
{
"class": "InlineJavascriptRequirement"
}
],
"hints": [
{
"class": "SoftwareRequirement",
"packages": [
{
"version": [
"2.10.7"
],
"package": "picard",
"https://schema.org/citation": "http://broadinstitute.github.io/picard"
}
]
}
],
"inputs": [
{
"type": [
"null",
{
"type": "array",
"items": "File"
}
],
"doc": "The bed file to be converted to interval_list format. Required.",
"inputBinding": {
"prefix": "I=",
"shellQuote": false
},
"id": "#picard-BedToIntervalList.cwl/input_file"
},
{
"type": [
"null",
"string"
],
"doc": "Interval list output filename.",
"default": "list.interval_list",
"inputBinding": {
"prefix": "O=",
"shellQuote": false
},
"id": "#picard-BedToIntervalList.cwl/output_filename"
},
{
"type": "File",
"doc": "The reference sequences in fasta format.",
"inputBinding": {
"prefix": "SD=",
"shellQuote": false
},
"id": "#picard-BedToIntervalList.cwl/reference_sequence"
}
],
"outputs": [
{
"type": "File",
"outputBinding": {
"glob": "$(inputs.output_filename)"
},
"id": "#picard-BedToIntervalList.cwl/output_interval_list_file"
}
],
"baseCommand": [
"java",
"-Xmx4g"
],
"arguments": [
{
"valueFrom": "/opt/picard/picard.jar",
"position": -1,
"prefix": "-jar"
},
{
"valueFrom": "BedToIntervalList",
"position": 0
}
],
"id": "#picard-BedToIntervalList.cwl"
},
{
"class": "CommandLineTool",
"requirements": [
{
"class": "DockerRequirement",
"dockerPull": "dukegcb/picard:2.10.7"
},
{
"class": "InlineJavascriptRequirement"
}
],
"hints": [
{
"class": "SoftwareRequirement",
"packages": [
{
"version": [
"2.10.7"
],
"package": "picard",
"https://schema.org/citation": "http://broadinstitute.github.io/picard"
}
]
}
],
"inputs": [
{
"type": "File",
"doc": "The bait interval file in picard interval_list format (from capture kit).",
"inputBinding": {
"prefix": "BAIT_INTERVALS=",
"shellQuote": false
},
"id": "#picard-CollectHsMetrics.cwl/bait_intervals"
},
{
"type": "File",
"doc": "The BAM or SAM file to collect metrics from. Required.",
"inputBinding": {
"prefix": "I=",
"shellQuote": false
},
"id": "#picard-CollectHsMetrics.cwl/input_file"
},
{
"type": [
"null",
"string"
],
"doc": "The metrics output filename.",
"default": "hs_metrics.txt",
"inputBinding": {
"prefix": "O=",
"shellQuote": false
},
"id": "#picard-CollectHsMetrics.cwl/output_filename"
},
{
"type": "File",
"doc": "The reference sequences in fasta format.",
"inputBinding": {
"prefix": "R=",
"shellQuote": false
},
"id": "#picard-CollectHsMetrics.cwl/reference_sequence"
},
{
"type": "File",
"doc": "The target interval file in picard interval_list format (from capture kit).",
"inputBinding": {
"prefix": "TARGET_INTERVALS=",
"shellQuote": false
},
"id": "#picard-CollectHsMetrics.cwl/target_intervals"
}
],
"outputs": [
{
"type": "File",
"outputBinding": {
"glob": "$(inputs.output_filename)"
},
"id": "#picard-CollectHsMetrics.cwl/output_hs_metrics_file"
}
],
"baseCommand": [
"java",
"-Xmx4g"
],
"arguments": [
{
"valueFrom": "/opt/picard/picard.jar",
"position": -1,
"prefix": "-jar"
},
{
"valueFrom": "CollectHsMetrics",
"position": 0
}
],
"id": "#picard-CollectHsMetrics.cwl"
},
{
"class": "CommandLineTool",
"requirements": [
{
"class": "DockerRequirement",
"dockerPull": "dukegcb/picard:2.10.7"
},
{
"class": "InlineJavascriptRequirement"
}
],
"hints": [
{
"class": "SoftwareRequirement",
"packages": [
{
"version": [
"2.10.7"
],
"package": "picard",
"https://schema.org/citation": "http://broadinstitute.github.io/picard"
}
]
}
],
"inputs": [
{
"type": "File",
"doc": "One or more input SAM or BAM files to analyze. Must be coordinate sorted.",
"inputBinding": {
"prefix": "INPUT=",
"shellQuote": false
},
"id": "#picard-MarkDuplicates.cwl/input_file"
},
{
"type": [
"null",
"string"
],
"doc": "Output metrics filename",
"default": "marked_dup_metrics.txt",
"inputBinding": {
"prefix": "METRICS_FILE=",
"shellQuote": false
},
"id": "#picard-MarkDuplicates.cwl/metrics_filename"
},
{
"type": [
"null",
"string"
],
"doc": "Output filename",
"default": "marked_duplicates.bam",
"inputBinding": {
"prefix": "OUTPUT=",
"shellQuote": false
},
"id": "#picard-MarkDuplicates.cwl/output_filename"
},
{
"type": "boolean",
"doc": "If true do not write duplicates to the output file instead of writing them with appropriate flags set. (Default true).",
"default": true,
"inputBinding": {
"prefix": "REMOVE_DUPLICATES=",
"shellQuote": false
},
"id": "#picard-MarkDuplicates.cwl/remove_duplicates"
}
],
"outputs": [
{
"type": "File",
"outputBinding": {
"glob": "$(inputs.output_filename)"
},
"secondaryFiles": [
"^.bai"
],
"id": "#picard-MarkDuplicates.cwl/output_dedup_bam_file"
},
{
"type": "File",
"outputBinding": {
"glob": "$(inputs.metrics_filename)"
},
"id": "#picard-MarkDuplicates.cwl/output_metrics_file"
}
],
"baseCommand": [
"java"
],
"arguments": [
{
"valueFrom": "-Xmx4g",
"position": -2
},
{
"valueFrom": "/opt/picard/picard.jar",
"position": -1,
"prefix": "-jar"
},
{
"valueFrom": "MarkDuplicates",
"position": 0
},
{
"valueFrom": "CREATE_INDEX=True",
"position": 0
}
],
"id": "#picard-MarkDuplicates.cwl"
},
{
"class": "CommandLineTool",
"requirements": [
{
"class": "DockerRequirement",
"dockerPull": "dukegcb/picard:2.10.7"
},
{
"class": "InlineJavascriptRequirement"
}
],
"hints": [
{
"class": "SoftwareRequirement",
"packages": [
{
"version": [
"2.10.7"
],
"package": "picard",
"https://schema.org/citation": "http://broadinstitute.github.io/picard"
}
]
}
],
"inputs": [
{
"type": "File",
"doc": "The BAM or SAM file to sort. Required.",
"inputBinding": {
"prefix": "INPUT=",
"shellQuote": false
},
"id": "#picard-SortSam.cwl/input_file"
},
{
"type": [
"null",
"string"
],
"doc": "The sorted BAM or SAM output file.",
"default": "sorted.bam",
"inputBinding": {
"prefix": "OUTPUT=",
"shellQuote": false
},
"id": "#picard-SortSam.cwl/output_filename"
},
{
"type": "string",
"doc": "Sort order of output file Required. Possible values: {unsorted, queryname, coordinate, duplicate}",
"default": "coordinate",
"inputBinding": {
"prefix": "SORT_ORDER=",
"shellQuote": false
},
"id": "#picard-SortSam.cwl/sort_order"
}
],
"outputs": [
{
"type": "File",
"outputBinding": {
"glob": "$(inputs.output_filename)"
},
"secondaryFiles": [
"^.bai"
],
"id": "#picard-SortSam.cwl/sorted"
}
],
"baseCommand": [
"java",
"-Xmx4g"
],
"arguments": [
{
"valueFrom": "/opt/picard/picard.jar",
"position": -1,
"prefix": "-jar"
},
{
"valueFrom": "SortSam",
"position": 0
}
],
"id": "#picard-SortSam.cwl"
},
{
"class": "CommandLineTool",
"hints": [
{
"class": "DockerRequirement",
"dockerPull": "dukegcb/trim-galore:0.4.4"
},
{
"class": "SoftwareRequirement",
"packages": [
{
"version": [
"1.14"
],
"package": "cutadapt",
"https://schema.org/citation": "https://dx.doi.org/10.14806/ej.17.1.200"
},
{
"version": [
"0.4.4"
],
"package": "trimgalore",
"https://schema.org/citation": "https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/"
}
]
}
],
"inputs": [
{
"type": "boolean",
"inputBinding": {
"position": 1,
"prefix": "--paired"
},
"id": "#trim_galore.cwl/paired"
},
{
"type": {
"type": "array",
"items": "File"
},
"inputBinding": {
"position": 3
},
"id": "#trim_galore.cwl/reads"
}
],
"outputs": [
{
"type": {
"type": "array",
"items": "File"
},
"outputBinding": {
"glob": "*_trimming_report.txt"
},
"id": "#trim_galore.cwl/trim_reports"
},
{
"type": {
"type": "array",
"items": "File"
},
"outputBinding": {
"glob": "*_val_*.fq*"
},
"id": "#trim_galore.cwl/trimmed_reads"
}
],
"baseCommand": "trim_galore",
"arguments": [
{
"valueFrom": "$(runtime.outdir)",
"prefix": "-o",
"position": 2
}
],
"id": "#trim_galore.cwl"
},
{
"class": "Workflow",
"label": "WES Preprocessing",
"doc": "Whole Exome Sequence analysis Preprocessing\n",
"requirements": [
{
"class": "ScatterFeatureRequirement"
},
{
"class": "SubworkflowFeatureRequirement"
},
{
"$import": "#bespin-types.yml"
}
],
"inputs": [
{
"type": "File",
"id": "#main/GATKJar"
},
{
"type": [
"null",
{
"type": "array",
"items": "File"
}
],
"id": "#main/bait_intervals"
},
{
"type": [
"null",
"int"
],
"id": "#main/interval_padding"
},
{
"type": {
"type": "array",
"items": "File"
},
"secondaryFiles": [
".idx"
],
"id": "#main/knownSites"
},
{
"type": "string",
"id": "#main/library"
},
{
"type": "string",
"id": "#main/platform"
},
{
"type": "#bespin-types.yml/FASTQReadPairType",
"id": "#main/read_pair"
},
{
"type": "File",
"secondaryFiles": [
".amb",
".ann",
".bwt",
".pac",
".sa",
".fai",
"^.dict"
],
"id": "#main/reference_genome"
},
{
"type": "File",
"secondaryFiles": [
".idx"
],
"id": "#main/resource_dbsnp"
},
{
"type": [
"null",
{
"type": "array",
"items": "File"
}
],
"id": "#main/target_intervals"
},
{
"type": [
"null",
"int"
],
"id": "#main/threads"
}
],
"outputs": [
{
"type": {
"type": "array",
"items": "File"
},
"outputSource": "#main/preprocessing/fastqc_reports",
"id": "#main/fastqc_reports"
},
{
"type": "File",
"outputSource": "#main/preprocessing/hs_metrics",
"id": "#main/hs_metrics"
},
{
"type": "File",
"outputSource": "#main/preprocessing/markduplicates_bam",
"doc": "BAM and bai files from markduplicates",
"id": "#main/markduplicates_bam"
},
{
"type": "File",
"outputSource": "#main/preprocessing/raw_variants",
"id": "#main/raw_variants"
},
{
"type": "File",
"outputSource": "#main/preprocessing/recalibrated_reads",
"doc": "BAM files containing recalibrated reads",
"id": "#main/recalibrated_reads"
},
{
"type": {
"type": "array",
"items": "File"
},
"outputSource": "#main/preprocessing/trim_reports",
"id": "#main/trim_reports"
}
],
"steps": [
{
"run": "#exomeseq-00-prepare-reference-data.cwl",
"in": [
{
"source": "#main/bait_intervals",
"id": "#main/prepare_reference_data/bait_intervals"
},
{
"source": "#main/reference_genome",
"id": "#main/prepare_reference_data/reference_genome"
},
{
"source": "#main/target_intervals",
"id": "#main/prepare_reference_data/target_intervals"
}
],
"out": [
"#main/prepare_reference_data/target_interval_list",
"#main/prepare_reference_data/bait_interval_list"
],
"id": "#main/prepare_reference_data"
},
{
"run": "#exomeseq-01-preprocessing.cwl",
"in": [
{
"source": "#main/GATKJar",
"id": "#main/preprocessing/GATKJar"
},
{
"source": "#main/prepare_reference_data/bait_interval_list",
"id": "#main/preprocessing/bait_interval_list"
},
{
"source": "#main/interval_padding",
"id": "#main/preprocessing/interval_padding"
},
{
"source": "#main/target_intervals",
"id": "#main/preprocessing/intervals"
},
{
"source": "#main/knownSites",
"id": "#main/preprocessing/knownSites"
},
{
"source": "#main/library",
"id": "#main/preprocessing/library"
},
{
"source": "#main/platform",
"id": "#main/preprocessing/platform"
},
{
"source": "#main/read_pair",
"id": "#main/preprocessing/read_pair"
},
{
"source": "#main/reference_genome",
"id": "#main/preprocessing/reference_genome"
},
{
"source": "#main/resource_dbsnp",
"id": "#main/preprocessing/resource_dbsnp"
},
{
"source": "#main/prepare_reference_data/target_interval_list",
"id": "#main/preprocessing/target_interval_list"
},
{
"source": "#main/threads",
"id": "#main/preprocessing/threads"
}
],
"out": [
"#main/preprocessing/fastqc_reports",
"#main/preprocessing/trim_reports",
"#main/preprocessing/markduplicates_bam",
"#main/preprocessing/recalibration_table",
"#main/preprocessing/recalibrated_reads",
"#main/preprocessing/raw_variants",
"#main/preprocessing/hs_metrics"
],
"id": "#main/preprocessing"
}
],
"id": "#main"
}
],
"cwlVersion": "v1.0",
"$schemas": [
"https://schema.org/docs/schema_org_rdfa.html"
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment