view seqtk_sample.xml @ 1:61718851f199 draft

Uploaded
author iuc
date Thu, 05 Feb 2015 12:00:43 -0500
parents e0a0fd938de4
children f73729b62b51
line wrap: on
line source

<?xml version="1.0"?>
<tool id="seqtk_sample" name="seqtk_sample" version="@WRAPPER_VERSION@.0">
    <description>random subsample of fasta or fastq sequences</description>
  <macros>
    <import>macros.xml</import>
  </macros>
  <expand macro="requirements"/>
  <expand macro="stdio"/>
  <command><![CDATA[seqtk sample -s $s
      $in_file
      $subsample_size
> $default]]></command>
  <inputs>
    <expand macro="in_faq" />
    <param label="RNG seed" help="(-s)" name="s" type="integer" value="4"/>
    <param label="Subsample (decimal fraction or number)" name="subsample_size" type="integer" value="100"/>
  </inputs>
  <outputs>
    <data format_source="in_file" hidden="false" name="default" label="Subsample of reads from $in_file.name"/>
  </outputs>
  <tests>
    <test>
      <param name="in_file" value="seqtk_sample.fa"/>
      <param name="subsample_size" value="4"/>
      <param name="s" value="4"/>
      <output name="default" file="seqtk_sample.out" ftype="fasta"/>
    </test>
  </tests>
  <help><![CDATA[
**What it does**

Takes a random subsample of fasta or fastq sequences. The RNG is seedable to allow for reproducible results, and defaults to `4 <http://xkcd.com/221/>`__.

The subsample size can be a decimal fraction <=1, where 1 implies 100% of the reads should be used. If a number >1 is provided, that many reads will be taken from the dataset.

@ATTRIBUTION@
]]></help>
</tool>