view extract_re_contigs.xml @ 4:d7bb42f254a2 draft

"planemo upload commit fa6d4eb0c804e873b60bb2ba3d0e85646c9cd764"
author petr-novak
date Mon, 14 Mar 2022 10:16:07 +0000
parents ea6a3059a6af
children eca9213923b1
line wrap: on
line source

<tool id="extract_re_contigs" name="Extract Repeat Library from RepeatExplorer Archive" version="0.1.0" python_template_version="3.5">
    <requirements>
        <requirement type="package" version="3">python</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        $__tool_directory__/get_contigs_from_re_archive.py -re '$re_archive' -m 5 -L 50 -f '$contigs'
    ]]></command>
    <inputs>
        <param type="data" name="re_archive" format="zip" label="RepeatExplorer archive"/>
        <param type="integer" name="min_coverage" value="5" min="1" max="100" label="minimal read depth coverage of contigs" help="region with lower coverage are trimmed off or hardmasked"/>
        <param type="integer" name="min_length" value="20" min="10" lebel="Minimum length of extracted contigs" />
    </inputs>
    <outputs>
        <data name="contigs" format="fasta" label="Contigs(Repeat library) extracted from RepeatExplorer archive ${re_archive.hid}"/>
    </outputs>
    <help><![CDATA[
        This tool extracts contigs and TAREAN concesus from RepeatExplorer archive in fasta format. Sequences with reads depth smaller that threshold are removed. Contigs shorter that specied threshold ere also filtered  out. Filtering does not affect TAREAN consensus. Extracted sequences have Id in format CLXContigY where X is cluster ID and Y is number of contig. 
    ]]></help>
</tool>