name: plink2_extract
description: Subset plink pfiles with a text file of variant identifiers
keywords:
  - plink2
  - extract
tools:
  - plink2:
      description: |
        Whole genome association analysis toolset, designed to perform a range
        of basic, large-scale analyses in a computationally efficient manner
      homepage: http://www.cog-genomics.org/plink/2.0/
      documentation: http://www.cog-genomics.org/plink/2.0/general_usage
      tool_dev_url: None
      doi: "10.1186/s13742-015-0047-8"
      licence: ["GPL v3"]

input:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test', single_end:false ]
  - pgen:
      type: file
      description: PLINK 2 binary genotype table
      pattern: "*.{pgen}"
  - psam:
      type: file
      description: PLINK 2 sample information file
      pattern: "*.{psam}"
  - pvar:
      type: file
      description: PLINK 2 variant information file
      pattern: "*.{pvar}"
  - variants:
      type: file
      description: A text file containing variant identifiers to keep (one per line)
      pattern: "*.{keep}"

output:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test', single_end:false ]
  - versions:
      type: file
      description: File containing software versions
      pattern: "versions.yml"
  - extract_pgen:
      type: file
      description: PLINK 2 binary genotype table, containing extracted variants
      pattern: "*.{pgen}"
  - extract_psam:
      type: file
      description: PLINK 2 sample information file associated with the extracted data
      pattern: "*.{psam}"
  - extract_pvar:
      type: file
      description: PLINK 2 variant information file, containing extracted variants
      pattern: "*.{pvar.zst}"

authors:
  - "@nebfield"