<?xml version="1.0"?>
<tool id="precheck" name="Du Novo: Check input" version="3.0.2">
  <requirements>
    <requirement type="package" version="3.0.2">dunovo</requirement>
  </requirements>
  <description>for family content</description>
  <command detect_errors="exit_code">
    precheck.py $check_ids --tag-length $tag_len --constant-length $const_len --min-reads $min_reads
      '$fastq1' '$fastq2' &gt; '$output'
  </command>
  <inputs>
    <param name="fastq1" type="data" format="fastq" label="Sequencing reads, mate 1"/>
    <param name="fastq2" type="data" format="fastq" label="Sequencing reads, mate 2"/>
    <param name="min_reads" type="integer" value="3" min="0" label="Minimum reads per family" help="Single-strand families with fewer than this many reads will be skipped."/>
    <param name="tag_len" type="integer" value="12" min="0" label="Tag length" help="Length of each random barcode on the ends of the fragments."/>
    <param name="const_len" type="integer" value="5" min="0" label="Invariant sequence length" help="Length of the sequence between the tag and actual sample sequence (the restriction site, normally)."/>
    <param name="check_ids" type="boolean" truevalue="--validate" falsevalue="--no-check-ids" checked="True" label="Check read names" help="Make sure the ids of the reads in each pair is the same. If checked, this will fail if there is a mismatch."/>
  </inputs>
  <outputs>
    <data name="output" format="tabular"/>
  </outputs>

  <help>

.. class:: infomark

**What it does**

This tool lets you check your input reads before running the Du Novo pipeline. It will tell you about how many unique barcodes are in your dataset, how many families have boths strands present, how many consensus sequences of each type it will be able to form, and more.

.. class:: infomark

**Input**

The input must be in FASTQ format.

  </help>

  <citations>
    <citation type="bibtex">@article{Stoler2016,
      author = {Stoler, Nicholas and Arbeithuber, Barbara and Guiblet, Wilfried and Makova, Kateryna D and Nekrutenko, Anton},
      doi = {10.1186/s13059-016-1039-4},
      issn = {1474-760X},
      journal = {Genome biology},
      number = {1},
      pages = {180},
      pmid = {27566673},
      publisher = {Genome Biology},
      title = {{Streamlined analysis of duplex sequencing data with Du Novo.}},
      url = {http://www.ncbi.nlm.nih.gov/pubmed/27566673},
      volume = {17},
      year = {2016}
    }</citation>
  </citations>

</tool>