WGS-processing/cwl/helper/gatk-wf-with-interval.cwl

   1 cwlVersion: v1.1
   2 class: Workflow
   3 label: Variant calling workflow for given interval
   4
   5 requirements:
   6   SubworkflowFeatureRequirement: {}
   7
   8 inputs:
   9   bam:
  10     type: File
  11     format: edam:format_2572 # BAM
  12     label: Indexed sorted BAM with labeled duplicates
  13     secondaryFiles:
  14       - .bai
  15   reference:
  16     type: File
  17     format: edam:format_1929 # FASTA
  18     label: Reference genome
  19     secondaryFiles:
  20       - .amb
  21       - .ann
  22       - .bwt
  23       - .pac
  24       - .sa
  25       - .fai
  26       - ^.dict
  27   sample:
  28     type: string
  29     label: Sample Name
  30   knownsites1:
  31     type: File
  32     format: edam:format_3016 # VCF
  33     label: VCF of known SNPS sites for BQSR
  34     secondaryFiles:
  35       - .idx
  36   knownsites2:
  37     type: File
  38     format: edam:format_3016 # VCF
  39     label: VCF of known indel sites for BQSR
  40     secondaryFiles:
  41       - .tbi
  42   intervallist:
  43     type: File
  44     label: Scatter intervals file
  45
  46 outputs:
  47   gvcf:
  48     type: File
  49     format: edam:format_3016 # GVCF
  50     label: Given interval filtered GVCF
  51     outputSource: selectvariants/filteredgvcf
  52
  53 steps:
  54   basecalibrator:
  55     run: gatk-baserecalibrator-with-interval.cwl
  56     in:
  57       bam: bam
  58       reference: reference
  59       sample: sample
  60       knownsites1: knownsites1
  61       knownsites2: knownsites2
  62       intervallist: intervallist
  63     out: [recaltable]
  64   applyBQSR:
  65     run: gatk-applyBSQR-with-interval.cwl
  66     in:
  67       reference: reference
  68       bam: bam
  69       sample: sample
  70       intervallist: intervallist
  71       recaltable: basecalibrator/recaltable
  72     out: [recalbam]
  73   haplotypecaller:
  74     run: gatk-haplotypecaller-with-interval.cwl
  75     in:
  76       reference: reference
  77       bam: applyBQSR/recalbam
  78       sample: sample
  79       intervallist: intervallist
  80     out: [gvcf]
  81   selectvariants:
  82     run: gatk-selectvariants.cwl
  83     in:
  84       gvcf: haplotypecaller/gvcf
  85       reference: reference
  86       sample: sample
  87     out: [filteredgvcf]
  88
  89 s:codeRepository: https://github.com/arvados/arvados-tutorial
  90 s:license: https://www.gnu.org/licenses/agpl-3.0.en.html
  91
  92 $namespaces:
  93  s: https://schema.org/
  94  edam: http://edamontology.org/
  95
  96 #$schemas:
  97 # - https://schema.org/version/latest/schema.rdf
  98 # - http://edamontology.org/EDAM_1.18.owl