name: gatk4_variantrecalibrator
description: |
  Build a recalibration model to score variant quality for filtering purposes.
  It is highly recommended to follow GATK best practices when using this module,
  the gaussian mixture model requires a large number of samples to be used for the
  tool to produce optimal results. For example, 30 samples for exome data. For more details see
  https://gatk.broadinstitute.org/hc/en-us/articles/4402736812443-Which-training-sets-arguments-should-I-use-for-running-VQSR-
keywords:
  - VariantRecalibrator
  - gatk4
  - recalibration_model
tools:
  - gatk4:
      description: |
        Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
        with a primary focus on variant discovery and genotyping. Its powerful processing engine
        and high-performance computing features make it capable of taking on projects of any size.
      homepage: https://gatk.broadinstitute.org/hc/en-us
      documentation: https://gatk.broadinstitute.org/hc/en-us/categories/360002369672s
      doi: 10.1158/1538-7445.AM2017-3590

input:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test' ]
  - vcf:
      type: file
      description: input vcf file containing the variants to be recalibrated
      pattern: "*.vcf.gz"
  - tbi:
      type: file
      description: tbi file matching with -vcf
      pattern: "*.vcf.gz.tbi"
  - resource_vcf:
      type: file
      description: all resource vcf files that are used with the corresponding '--resource' label
      pattern: "*.vcf.gz"
  - resource_tbi:
      type: file
      description: all resource tbi files that are used with the corresponding '--resource' label
      pattern: "*.vcf.gz.tbi"
  - labels:
      type: string
      description: necessary arguments for GATK VariantRecalibrator. Specified to directly match the resources provided. More information can be found at https://gatk.broadinstitute.org/hc/en-us/articles/5358906115227-VariantRecalibrator
  - fasta:
      type: file
      description: The reference fasta file
      pattern: "*.fasta"
  - fai:
      type: file
      description: Index of reference fasta file
      pattern: "fasta.fai"
  - dict:
      type: file
      description: GATK sequence dictionary
      pattern: "*.dict"
output:
  - recal:
      type: file
      description: Output recal file used by ApplyVQSR
      pattern: "*.recal"
  - idx:
      type: file
      description: Index file for the recal output file
      pattern: "*.idx"
  - tranches:
      type: file
      description: Output tranches file used by ApplyVQSR
      pattern: "*.tranches"
  - plots:
      type: file
      description: Optional output rscript file to aid in visualization of the input data and learned model.
      pattern: "*plots.R"
  - version:
      type: file
      description: File containing software versions
      pattern: "*.versions.yml"
authors:
  - "@GCJMackenzie"
  - "@nickhsmith"