WGS-processing/cwl/helper/bwamem-gatk-report-wf.cwl

   1 cwlVersion: v1.1
   2 class: Workflow
   3 label: WGS processing workflow for single sample
   4
   5 requirements:
   6   - class: SubworkflowFeatureRequirement
   7
   8 inputs:
   9   fastq1:
  10     type: File
  11     format: edam:format_1930 # FASTQ
  12     label: One of set of pair-end FASTQs (R1)
  13   fastq2:
  14     type: File
  15     format: edam:format_1930 # FASTQ
  16     label: One of set of pair-end FASTQs (R2)
  17   reference:
  18     type: File
  19     format: edam:format_1929 # FASTA
  20     label: Reference genome
  21     secondaryFiles:
  22       - .amb
  23       - .ann
  24       - .bwt
  25       - .pac
  26       - .sa
  27       - .fai
  28       - ^.dict
  29   sample:
  30     type: string
  31     label: Sample Name
  32   knownsites:
  33     type: File
  34     format: edam:format_3016 # VCF
  35     label: VCF of known polymorphic sites for BQSR
  36     secondaryFiles:
  37       - .tbi
  38   scattercount:
  39     type: string
  40     label: Desired split for variant calling
  41   clinvarvcf:
  42     type: File
  43     format: edam:format_3016 # VCF
  44     label: Reference VCF for ClinVar
  45   reportfunc:
  46     type: File
  47     label: Function used to create HTML report
  48   headhtml:
  49     type: File
  50     format: edam:format_1964 # HTML
  51     label: Header for HTML report
  52   tailhtml:
  53     type: File
  54     format: edam:format_1964 # HTML
  55     label: Footer for HTML report
  56
  57 outputs:
  58   qc-html:
  59     type: File[]
  60     label: FASTQ QC reports
  61     format: edam:format_1964 # HTML
  62     outputSource: fastqc/out-html
  63   qc-zip:
  64     type: File[]
  65     label: Zip files of FASTQ QC report and associated data
  66     outputSource: fastqc/out-zip
  67   gvcf:
  68     type: File
  69     outputSource: haplotypecaller/gatheredgvcf
  70     format: edam:format_3016 # GVCF
  71     label: GVCF generated from GATK Haplotype Caller
  72   report:
  73     type: File
  74     outputSource: generate-report/report
  75     format: edam:format_1964 # HTML
  76     label: ClinVar variant report
  77
  78 steps:
  79   fastqc:
  80     run: fastqc.cwl
  81     in:
  82       fastq1: fastq1
  83       fastq2: fastq2
  84     out: [out-html, out-zip]
  85   bwamem-samtools-view:
  86     run: bwamem-samtools-view.cwl
  87     in:
  88       fastq1: fastq1
  89       fastq2: fastq2
  90       reference: reference
  91       sample: sample
  92     out: [bam]
  93   samtools-sort:
  94     run: samtools-sort.cwl
  95     in:
  96       bam: bwamem-samtools-view/bam
  97       sample: sample
  98     out: [sortedbam]
  99   mark-duplicates:
 100     run: mark-duplicates.cwl
 101     in:
 102       bam: samtools-sort/sortedbam
 103     out: [dupbam,dupmetrics]
 104   samtools-index:
 105     run: samtools-index.cwl
 106     in:
 107       bam: mark-duplicates/dupbam
 108     out: [indexedbam]
 109   haplotypecaller:
 110     run: scatter-gatk-wf-with-interval.cwl
 111     in:
 112       reference: reference
 113       bam: samtools-index/indexedbam
 114       sample: sample
 115       scattercount: scattercount
 116       knownsites: knownsites
 117     out: [gatheredgvcf]
 118   generate-report:
 119     run: report-wf.cwl
 120     in:
 121       gvcf: haplotypecaller/gatheredgvcf
 122       samplename: sample
 123       clinvarvcf: clinvarvcf
 124       reportfunc: reportfunc
 125       headhtml: headhtml
 126       tailhtml: tailhtml
 127     out: [report]
 128
 129 s:codeRepository: https://github.com/arvados/arvados-tutorial
 130 s:license: https://www.gnu.org/licenses/agpl-3.0.en.html
 131
 132 $namespaces:
 133  s: https://schema.org/
 134  edam: http://edamontology.org/
 135
 136 $schemas:
 137  - https://schema.org/version/latest/schema.rdf
 138  - http://edamontology.org/EDAM_1.18.owl