view GFFalign.xml @ 1:afed7e0cf69e draft default tip

"planemo upload for repository https://github.com/abims-sbr/tools-abims/tools/gffalign commit ca7b7864d099e092042f21d86cdc3c4552e54632"
author abims-sbr
date Fri, 08 Jan 2021 15:25:31 +0000
parents 294f5ba28746
children
line wrap: on
line source

<tool id="gffalign" name="GFF align" version="0.1.0+galaxy0" python_template_version="3.5">
    <requirements>
        <requirement type="package" version="1.78">biopython</requirement>
        <requirement type="package" version="0.10.1">gffutils</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        python3 '$__tool_directory__/GFFalign.py'

        '$aln'
        '$queryGFF'
        '$targetGFF'
        
        -m
        -t $t
        -v $v
        #if $extract.extract_fasta == 'true'
            -e $e '$output_extract_fasta'
        #end if

        > '$output_file'
    ]]></command>
    <inputs>
        <param name="aln" type="data" format="tabular" label="Alignement file" help="Alignment file in TAB format. The suggested way to obtain it is to run Last and than convert the file from MAF to TAB with maf-convert" />
        <param name="queryGFF" type="data" format="gff" label="Query organism GFF file" help="Gff file of the query organism. The gene IDs in the GFF must be unique. To solve the problem please extract only the 'gene' lines. Try to format the file with AWK: awk `{if ($3==\'gene\') print $0}` GFFfile" />
        <param name="targetGFF" type="data" format="gff" label="Target organism GFF file" help="Gff file of the 'target' organism. The gene IDs in the GFF must be unique. To solve the problem please extract only the gene lines as explained in queryGff" />

        <!--<param argument="-m" type="boolean" checked="false" truevalue="-memory" falsevalue="" label="Memory" help="Create an in-memory database. This option can't be used with the other DB options. Probably usefull in Galaxy integration" />-->
        <param argument="-t" type="integer" value="30" label="Interval" help="Interval, in nucleotide, within a gene is considered in the same position." />
        <param argument="-v" type="select" multiple="true" label="Verbosity" help="Output options. If not specify the software shows only the genes that are in the exact position of the genes in the target. It's possible to show annotated genes that are in aligned regions but that have different lengths or in slightly different positions. It's possible to select multiple values." >
            <option value="All">All</option>
            <option value="shorter">Shorter</option>
            <option value="longer">Longer</option>
            <option value="offset">Offset</option>
            <option value="new" selected="true">New</option>
            <option value="confirmed">Confirmed</option>
        </param>
        <conditional name="extract">
            <param name="extract_fasta" type="select" label="Extract fasta sequence of the new suggested gene" help="This option needs the fasta file of the genome. This will slow down the process A LOT.">
                <option value="true">Extract fasta sequence</option>
                <option selected="true" value="false">Do not extract fasta sequence</option>
            </param>
            <when value="true">
                <param argument="-e" type="data" format="fasta" label="Fasta file of the genome."/>
            </when>
            <when value="false"/>
        </conditional>
    </inputs>
    <outputs>
        <data name="output_file" format="gff" label="GFF align from ${on_string}"/>
        <data name="output_extract_fasta" format="fasta" label="Extracted fasta sequence from ${on_string}">
            <filter>extract['extract_fasta'] == 'true'</filter>
        </data>
    </outputs>

    <tests>
        <test>
            <param name="aln" value="genome_aln.tab" ftype="tabular"/>
            <param name="queryGFF" value="query.gff" ftype="gff"/>
            <param name="targetGFF" value="target.gff" ftype="gff"/>
            <param name="t" value="30"/>
            <param name="v" value="new"/>
            <output name="output_file" file="output.gff" ftype="gff"/>
        </test>
    </tests>

    <help><![CDATA[
        Tool to extract genes coordinates from a whole genome alignment.
        This script needs an alignement in TAB format and two gff files.
    ]]></help>
    <citations>
        <citation type="bibtex">@manual{title="https://github.com/eosc-life/D4_marine_eukaryote_genomics_portal", url="https://github.com/eosc-life/D4_marine_eukaryote_genomics_portal"}</citation>
    </citations>
</tool>