annotate funannotate_clean.xml @ 0:b5ec3983deda draft

"planemo upload commit 9613152729099079c7465c3d5d42005ef22ca91e"

<tool id="funannotate_clean" name="Funannotate assembly clean" profile="20.01" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
    <description></description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <requirements>
        <expand macro="requirements" />
    </requirements>
    <version_command>funannotate check --show-versions</version_command>
    <command><![CDATA[
funannotate clean
--input '${input}'
--out '${output}'
--pident ${pident}
--cov ${cov}
--minlen ${minlen}
${exhaustive}
    ]]></command>
    <inputs>
        <param argument="--input" type="data" format="fasta" label="Assembly to clean" />

        <param argument="--pident" type="integer" value="95" label="Percent identity of overlap" />
        <param argument="--cov" type="integer" value="95" label="Percent coverage of overlap" />
        <param argument="--minlen" type="integer" value="500" label="Minimum length of contig to keep" />

        <param argument="--exhaustive" type="boolean" checked="false" truevalue="--exhaustive" falsevalue="" label="Test every contig" help="Default is to stop at N50 value" />
    </inputs>
    <outputs>
        <data name='output' format='fasta' label="${tool.name} on ${on_string}: cleaned assembly" />
    </outputs>
    <tests>
        <test>
            <param name="input" value="genome.fa" />
            <output name="output" file="cleaned.fa" compare="diff" />
        </test>
        <test>
            <param name="input" value="genome.fa" />
            <param name="pident" value="100" />
            <param name="cov" value="100" />
            <output name="output" file="cleaned_ident.fa" compare="diff" />
        </test>
    </tests>
    <help><![CDATA[
Funannotate_ clean
------------------

Funannotate_ is a pipeline for genome annotation (built specifically for fungi, but will also work with higher eukaryotes).

When working with haploid assemblies, sometimes you want to remove some repetitive contigs that are contained in other scaffolds of the assembly. If the repeats are indeed unique, then we want to keep them in the assembly. Funannotate can help “clean” up repetitive contigs in your assembly. This is done using a “leave one out” methodology using minimap2 or mummer (nucmer), where the the shortest contigs/scaffolds are aligned to the rest of the assembly to determine if it is repetitive. The script loops through the contigs starting with the shortest and workings its way to the N50 of the assembly, dropping contigs/scaffolds that are greater than the percent coverage of overlap (--cov) and the percent identity of overlap (--pident).

.. _Funannotate: http://funannotate.readthedocs.io
    ]]></help>
    <expand macro="citations" />
</tool>