name: rseqc_readduplication
description: Calculate read duplication rate
keywords:
  - rnaseq
  - duplication
tools:
  - rseqc:
      description: |
        RSeQC package provides a number of useful modules that can comprehensively evaluate
        high throughput sequence data especially RNA-seq data.
      homepage: http://rseqc.sourceforge.net/
      documentation: http://rseqc.sourceforge.net/
      doi: 10.1093/bioinformatics/bts356
      licence: ["GPL-3.0-or-later"]
input:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test', single_end:false ]
  - bam:
      type: file
      description: the alignment in bam format
      pattern: "*.{bam}"
  - bed:
      type: file
      description: a bed file for the reference gene model
      pattern: "*.{bed}"
output:
  - seq_xls:
      type: file
      description: Read duplication rate determined from mapping position of read
      pattern: "*seq.DupRate.xls"
  - pos_xls:
      type: file
      description: Read duplication rate determined from sequence of read
      pattern: "*pos.DupRate.xls"
  - pdf:
      type: file
      description: plot of duplication rate
      pattern: "*.pdf"
  - rscript:
      type: file
      description: script to reproduce the plot
      pattern: "*.R"
  - versions:
      type: file
      description: File containing software versions
      pattern: "versions.yml"
authors:
  - "@drpatelh"
  - "@kevinmenden"