name: gatk4_calculatecontamination
description: |
  Calculates the fraction of reads from cross-sample contamination based on summary tables from getpileupsummaries. Output to be used with filtermutectcalls.
keywords:
  - gatk4
  - calculatecontamination
  - cross-samplecontamination
  - getpileupsummaries
  - filtermutectcalls
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' ]
  - pileup:
      type: file
      description: File containing the pileups summary table of a tumor sample to be used to calculate contamination.
      pattern: "*.pileups.table"
  - matched:
      type: file
      description: File containing the pileups summary table of a normal sample that matches with the tumor sample specified in pileup argument. This is an optional input.
      pattern: "*.pileups.table"
  - segmentout:
      type: boolean
      description: specifies whether to output the segmentation table.

output:
  - contamination:
      type: file
      description: File containing the contamination table.
      pattern: "*.contamination.table"
  - segmentation:
      type: file
      description: optional output table containing segmentation of tumor minor allele fractions.
      pattern: "*.segmentation.table"
  - versions:
      type: file
      description: File containing software versions
      pattern: "versions.yml"

authors:
  - "@GCJMackenzie"