name: picard_markduplicates
description: Locate and tag duplicate reads in a BAM file
keywords:
  - markduplicates
  - pcr
  - duplicates
  - bam
  - sam
  - cram
tools:
  - picard:
      description: |
        A set of command line tools (in Java) for manipulating high-throughput sequencing (HTS)
        data and formats such as SAM/BAM/CRAM and VCF.
      homepage: https://broadinstitute.github.io/picard/
      documentation: https://broadinstitute.github.io/picard/
input:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test', single_end:false ]
  - bam:
      type: file
      description: BAM file
      pattern: "*.{bam}"
output:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test', single_end:false ]
  - bam:
      type: file
      description: BAM file with duplicate reads marked/removed
      pattern: "*.{bam}"
  - bai:
      type: file
      description: An optional BAM index file. If desired, --CREATE_INDEX must be passed as a flag
      pattern: "*.{bai}"
  - metrics:
      type: file
      description: Duplicate metrics file generated by picard
      pattern: "*.{metrics.txt}"
  - versions:
      type: file
      description: File containing software versions
      pattern: "versions.yml"
authors:
  - "@drpatelh"
  - "@projectoriented"