name: umitools_dedup
description: Deduplicate reads based on the mapping co-ordinate and the UMI attached to the read.
keywords:
  - umitools
  - deduplication
tools:
  - umi_tools:
    description: >
      UMI-tools contains tools for dealing with Unique Molecular Identifiers (UMIs)/Random Molecular Tags (RMTs)
      and single cell RNA-Seq cell barcodes
    documentation: https://umi-tools.readthedocs.io/en/latest/
    license: ["MIT"]
input:
  - meta:
    type: map
    description: |
      Groovy Map containing sample information
        e.g. [ id:'test', single_end:false ]
  - bam:
    type: file
    description: |
      BAM file containing reads to be deduplicated via UMIs.
    pattern: "*.{bam}"
  - bai:
    type: file
    description: |
      BAM index files corresponding to the input BAM file.
    pattern: "*.{bai}"
output:
  - meta:
    type: map
    description: |
      Groovy Map containing sample information
        e.g. [ id:'test', single_end:false ]
  - bam:
    type: file
    description: BAM file with deduplicated UMIs.
    pattern: "*.{bam}"
  - tsv_edit_distance:
    type: file
    description: Reports the (binned) average edit distance between the UMIs at each position.
    pattern: "*edit_distance.tsv"
  - tsv_per_umi:
    type: file
    description: UMI-level summary statistics.
    pattern: "*per_umi.tsv"
  - tsv_umi_per_position:
    type: file
    description: Tabulates the counts for unique combinations of UMI and position.
    pattern: "*per_position.tsv"
  - versions:
    type: file
    description: File containing software versions
    pattern: "versions.yml"

authors:
  - "@drpatelh"
  - "@grst"
  - "@klkeys"