name: gatk4_markduplicates_spark
description: This tool locates and tags duplicate reads in a BAM or SAM file, where duplicate reads are defined as originating from a single fragment of DNA.
keywords:
  - markduplicates
  - bam
  - sort
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/articles/360037052812-MarkDuplicates-Picard-
      tool_dev_url: https://github.com/broadinstitute/gatk
      doi: 10.1158/1538-7445.AM2017-3590
      licence: ["MIT"]

input:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test', single_end:false ]
  - bam:
      type: file
      description: Sorted BAM file
      pattern: "*.{bam}"
  - 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:
  - 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"
  - bam:
      type: file
      description: Marked duplicates BAM file
      pattern: "*.{bam}"

authors:
  - "@ajodeh-juma"
  - "@FriederikeHanssen"
  - "@maxulysse"