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

   1 cwlVersion: v1.1
   2 class: Workflow
   3 label: Scattered variant calling workflow
   4
   5 requirements:
   6   SubworkflowFeatureRequirement: {}
   7   ScatterFeatureRequirement: {}
   8
   9 inputs:
  10   bam:
  11     type: File
  12     format: edam:format_2572 # BAM
  13     label: Indexed sorted BAM with labeled duplicates
  14     secondaryFiles:
  15       - .bai
  16   reference:
  17     type: File
  18     format: edam:format_1929 # FASTA
  19     label: Reference genome
  20     secondaryFiles:
  21       - .amb
  22       - .ann
  23       - .bwt
  24       - .pac
  25       - .sa
  26       - .fai
  27       - ^.dict
  28   fullintervallist:
  29     type: File
  30     label: Full list of intervals to operate over
  31   sample:
  32     type: string
  33     label: Sample Name
  34   knownsites1:
  35     type: File
  36     format: edam:format_3016 # VCF
  37     label: VCF of known polymorphic sites for BQSR
  38     secondaryFiles:
  39       - .idx
  40   knownsites2:
  41     type: File
  42     format: edam:format_3016 # VCF
  43     label: VCF of known polymorphic sites for BQSR
  44     secondaryFiles:
  45       - .tbi
  46   scattercount:
  47     type: string
  48     label: Desired split for variant calling
  49
  50 outputs:
  51   gatheredgvcf:
  52     type: File
  53     format: edam:format_3016 # GVCF
  54     label: Gathered GVCF
  55     secondaryFiles:
  56       - .tbi
  57     outputSource: gather-GVCFs/gatheredgvcf
  58
  59 steps:
  60   splitintervals:
  61     run: gatk-splitintervals.cwl
  62     in:
  63       reference: reference
  64       fullintervallist: fullintervallist
  65       sample: sample
  66       scattercount: scattercount
  67     out: [intervalfiles]
  68
  69   recal-haplotypecaller:
  70     run: gatk-wf-with-interval.cwl
  71     scatter: intervallist
  72     in:
  73       bam: bam
  74       reference: reference
  75       sample: sample
  76       knownsites1: knownsites1
  77       knownsites2: knownsites2
  78       intervallist: splitintervals/intervalfiles
  79     out: [gvcf]
  80
  81   gather-GVCFs:
  82     run: gather-array-vcf.cwl
  83     in:
  84       gvcfarray: recal-haplotypecaller/gvcf
  85       sample: sample
  86       reference: reference
  87     out: [gatheredgvcf]
  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