X-Git-Url: https://git.arvados.org/arvados-tutorial.git/blobdiff_plain/92172b0bceb7af669a8dd09cea04c93e041dfe2e..ec300c76b5a3f927c3cd5035669b70847ade3854:/WGS-processing/cwl/helper/bwamem-gatk-report-wf.cwl diff --git a/WGS-processing/cwl/helper/bwamem-gatk-report-wf.cwl b/WGS-processing/cwl/helper/bwamem-gatk-report-wf.cwl index f601e95..dbb1d50 100644 --- a/WGS-processing/cwl/helper/bwamem-gatk-report-wf.cwl +++ b/WGS-processing/cwl/helper/bwamem-gatk-report-wf.cwl @@ -1,14 +1,23 @@ cwlVersion: v1.1 class: Workflow +label: WGS processing workflow for single sample requirements: - - class: SubworkflowFeatureRequirement + SubworkflowFeatureRequirement: {} inputs: - fastq1: File - fastq2: File + fastq1: + type: File + format: edam:format_1930 # FASTQ + label: One of set of pair-end FASTQs (R1) + fastq2: + type: File + format: edam:format_1930 # FASTQ + label: One of set of pair-end FASTQs (R2) reference: type: File + format: edam:format_1929 # FASTA + label: Reference genome secondaryFiles: - .amb - .ann @@ -17,33 +26,61 @@ inputs: - .sa - .fai - ^.dict - sample: string + fullintervallist: + type: File + label: Full list of intervals to operate over + sample: + type: string + label: Sample Name knownsites: type: File + format: edam:format_3016 # VCF + label: VCF of known polymorphic sites for BQSR secondaryFiles: - .tbi - scattercount: string - clinvarvcf: File - reportfunc: File - headhtml: File - tailhtml: File + scattercount: + type: string + label: Desired split for variant calling + clinvarvcf: + type: File + format: edam:format_3016 # VCF + label: Reference VCF for ClinVar + reportfunc: + type: File + label: Function used to create HTML report + headhtml: + type: File + format: edam:format_2331 # HTML + label: Header for HTML report + tailhtml: + type: File + format: edam:format_2331 # HTML + label: Footer for HTML report outputs: qc-html: type: File[] + label: FASTQ QC reports + format: edam:format_2331 # HTML outputSource: fastqc/out-html qc-zip: type: File[] + label: Zip files of FASTQ QC report and associated data outputSource: fastqc/out-zip gvcf: type: File outputSource: haplotypecaller/gatheredgvcf + format: edam:format_3016 # GVCF + label: GVCF generated from GATK Haplotype Caller report: type: File outputSource: generate-report/report + format: edam:format_2331 # HTML + label: ClinVar variant report + steps: fastqc: - run: ./helper/fastqc.cwl + run: fastqc.cwl in: fastq1: fastq1 fastq2: fastq2 @@ -57,13 +94,13 @@ steps: sample: sample out: [bam] samtools-sort: - run: ./helper/samtools-sort.cwl + run: samtools-sort.cwl in: bam: bwamem-samtools-view/bam sample: sample out: [sortedbam] mark-duplicates: - run: ./helper/mark-duplicates.cwl + run: mark-duplicates.cwl in: bam: samtools-sort/sortedbam out: [dupbam,dupmetrics] @@ -73,21 +110,33 @@ steps: bam: mark-duplicates/dupbam out: [indexedbam] haplotypecaller: - run: ./helper/scatter-gatk-wf-with-interval.cwl + run: scatter-gatk-wf-with-interval.cwl in: reference: reference + fullintervallist: fullintervallist bam: samtools-index/indexedbam sample: sample scattercount: scattercount - knownsites1: knownsites + knownsites: knownsites out: [gatheredgvcf] generate-report: - run: ./helper/report-wf.cwl + run: report-wf.cwl in: gvcf: haplotypecaller/gatheredgvcf - samplename: sample + sample: sample clinvarvcf: clinvarvcf reportfunc: reportfunc headhtml: headhtml tailhtml: tailhtml - out: [report] + out: [report] + +s:codeRepository: https://github.com/arvados/arvados-tutorial +s:license: https://www.gnu.org/licenses/agpl-3.0.en.html + +$namespaces: + s: https://schema.org/ + edam: http://edamontology.org/ + +#$schemas: +# - https://schema.org/version/latest/schema.rdf +# - http://edamontology.org/EDAM_1.18.owl