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"
  - 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"
  - allelespecific:
      type: boolean
      description: specify whether to use allele specific annotations
      pattern: "{true,false}"
  - resvcfs:
      type: list
      description: resource files to be used as truth, training and known sites resources, this imports the files into the module, file names are specified again in the resource_labels to be called via the command.
      pattern: "*/hapmap_3.3.hg38_chr21.vcf.gz"
  - restbis:
      type: list
      description: tbis for the corresponding vcfs files to be used as truth, training and known resources.
      pattern: "*/hapmap_3.3.hg38_chr21.vcf.gz.tbi"
  - reslabels:
      type: list
      description: labels for the resource files to be used as truth, training and known sites resources, label should include an identifier,which kind of resource(s) it is, prior value and name of the file.
      pattern: "hapmap,known=false,training=true,truth=true,prior=15.0 hapmap_3.3.hg38_chr21.vcf.gz"
  - annotation:
      type: list
      description: specify which annotations should be used for calculations.
      pattern: "['QD', 'MQ', 'FS', 'SOR']"
  - mode:
      type: string
      description: specifies which recalibration mode to employ (SNP is default, BOTH is intended for testing only)
      pattern: "{SNP,INDEL,BOTH}"
  - rscript:
      type: boolean
      description: specify whether to generate rscript.plot output file
      pattern: "{true,false}"
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"