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   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   fullintervallist:
  30     type: File
  31     label: Full list of intervals to operate over
  32   sample:
  33     type: string
  34     label: Sample Name
  35   knownsites:
  36     type: File
  37     format: edam:format_3016 # VCF
  38     label: VCF of known polymorphic sites for BQSR
  39     secondaryFiles:
  40       - .tbi
  41   scattercount:
  42     type: string
  43     label: Desired split for variant calling
  44   clinvarvcf:
  45     type: File
  46     format: edam:format_3016 # VCF
  47     label: Reference VCF for ClinVar
  48   reportfunc:
  49     type: File
  50     label: Function used to create HTML report
  51   headhtml:
  52     type: File
  53     format: edam:format_2331 # HTML
  54     label: Header for HTML report
  55   tailhtml:
  56     type: File
  57     format: edam:format_2331 # HTML
  58     label: Footer for HTML report
  59
  60 outputs:
  61   qc-html:
  62     type: File[]
  63     label: FASTQ QC reports
  64     format: edam:format_2331 # HTML
  65     outputSource: fastqc/out-html
  66   qc-zip:
  67     type: File[]
  68     label: Zip files of FASTQ QC report and associated data
  69     outputSource: fastqc/out-zip
  70   gvcf:
  71     type: File
  72     outputSource: haplotypecaller/gatheredgvcf
  73     format: edam:format_3016 # GVCF
  74     label: GVCF generated from GATK Haplotype Caller
  75   report:
  76     type: File
  77     outputSource: generate-report/report
  78     format: edam:format_2331 # HTML
  79     label: ClinVar variant report
  80
  81 steps:
  82   fastqc:
  83     run: fastqc.cwl
  84     in:
  85       fastq1: fastq1
  86       fastq2: fastq2
  87     out: [out-html, out-zip]
  88   bwamem-samtools-view:
  89     run: bwamem-samtools-view.cwl
  90     in:
  91       fastq1: fastq1
  92       fastq2: fastq2
  93       reference: reference
  94       sample: sample
  95     out: [bam]
  96   samtools-sort:
  97     run: samtools-sort.cwl
  98     in:
  99       bam: bwamem-samtools-view/bam
 100       sample: sample
 101     out: [sortedbam]
 102   mark-duplicates:
 103     run: mark-duplicates.cwl
 104     in:
 105       bam: samtools-sort/sortedbam
 106     out: [dupbam,dupmetrics]
 107   samtools-index:
 108     run: samtools-index.cwl
 109     in:
 110       bam: mark-duplicates/dupbam
 111     out: [indexedbam]
 112   haplotypecaller:
 113     run: scatter-gatk-wf-with-interval.cwl
 114     in:
 115       reference: reference
 116       fullintervallist: fullintervallist
 117       bam: samtools-index/indexedbam
 118       sample: sample
 119       scattercount: scattercount
 120       knownsites: knownsites
 121     out: [gatheredgvcf]
 122   generate-report:
 123     run: report-wf.cwl
 124     in:
 125       gvcf: haplotypecaller/gatheredgvcf
 126       sample: sample
 127       clinvarvcf: clinvarvcf
 128       reportfunc: reportfunc
 129       headhtml: headhtml
 130       tailhtml: tailhtml
 131     out: [report]
 132
 133 s:codeRepository: https://github.com/arvados/arvados-tutorial
 134 s:license: https://www.gnu.org/licenses/agpl-3.0.en.html
 135
 136 $namespaces:
 137  s: https://schema.org/
 138  edam: http://edamontology.org/
 139
 140 #$schemas:
 141 # - https://schema.org/version/latest/schema.rdf
 142 # - http://edamontology.org/EDAM_1.18.owl