annotate omark.xml @ 1:2eebe7f521f3 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/omark/ commit 839a3c8e9b651fbc0f4fefdd79ce1545a257cb0f

<?xml version="1.0"?>
<tool id="omark" name="OMArk" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
    <description>proteome quality assessment</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <requirements>
        <expand macro="requirements" />
    </requirements>

    <command detect_errors="exit_code"><![CDATA[
    omamer search --db '$database.fields.path' --query '$input' --out 'output_omamer'

    &&

    omark
    -f 'output_omamer'
    -d '$database.fields.path'
    $omark_mode
    -i '$input_iso'
    -t '$t'
    -r '$r'
    -o omark_galaxy

    ]]></command>

    <inputs>
        <param name="input" type="data" format="fasta" label="Protein sequences"/>
        <param name="input_iso" type="data" format="txt" optional="true" label="Input isoform file" help="A semi-colon separated file, listing all isoforms of each genes, with one gene per line."/>
        <param argument="-c" name="omark_mode" type="boolean" checked="false" truevalue="-c" falsevalue="" label="Only compute a list of conserved HOGs" help="Can be used to obtain a set of genes on which to train"/>
        <param name="database" label="OMAmer database" type="select">
            <options from_data_table="omamer"/>
        </param>

        <param argument="-t" type="text" optional="true" label="Taxonomic identifier" help="NCBI taxid corresponding to the input proteome">
            <sanitizer invalid_char="">
                <valid initial="string.letters,string.digits">
                    <add value="_" />
                </valid>
            </sanitizer>
            <validator type="regex">[0-9a-zA-Z_]+</validator>
        </param>
        <param argument="-r" type="text" optional="true" label="Taxonomic rank">
            <sanitizer invalid_char="">
                <valid initial="string.letters,string.digits">
                    <add value="_" />
                </valid>
            </sanitizer>
            <validator type="regex">[0-9a-zA-Z_]+</validator>
        </param>

        <param name="outputs" type="select" optional="true" multiple="true" label="Which outputs should be generated">
            <option value="detail_sum" selected="true">Detailed summary</option>
            <option value="hog">HOG identifiers</option>
            <option value="pdf">PDF Graphic representation </option>
            <option value="png">PNG Graphic representation </option>
            <option value="sum">Comparative proteome analysis</option>
            <option value="tax">Taxomony</option>
            <option value="ump">Protein identifiers</option>
        </param>
    </inputs>

    <outputs>
        <data name="omark_detail_sum" format="txt" label="${tool.name} on ${on_string}: Detailed summary" from_work_dir="omark_galaxy/*detailed_summary.txt">
            <filter>outputs and 'detail_sum' in outputs</filter>
        </data>
        <data name="omark_hog" format="omq" label="${tool.name} on ${on_string}: HOG identifiers" from_work_dir="omark_galaxy/*.omq">
            <filter>outputs and 'hog' in outputs</filter>
        </data>
        <data name="omark_pdf" format="pdf" label="${tool.name} on ${on_string}: Graphic representation (pdf)" from_work_dir="omark_galaxy/*.pdf">
            <filter>outputs and 'pdf' in outputs</filter>
        </data>
        <data name="omark_png" format="png" label="${tool.name} on ${on_string}: Graphic representation (png)" from_work_dir="omark_galaxy/*.png">
            <filter>outputs and 'png' in outputs</filter>
        </data>
        <data name="omark_sum" format="sum" label="${tool.name} on ${on_string}: Comparative proteome analysis" from_work_dir="omark_galaxy/*.sum">
            <filter>outputs and 'sum' in outputs</filter>
        </data>
        <data name="omark_tax" format="txt" label="${tool.name} on ${on_string}: Taxomony" from_work_dir="omark_galaxy/*.tax">
            <filter>outputs and 'tax' in outputs</filter>
        </data>
        <data name="omark_ump" format="ump" label="${tool.name} on ${on_string}: Protein identifiers" from_work_dir="omark_galaxy/*.ump">
            <filter>outputs and 'ump' in outputs</filter>
        </data>
    </outputs>

    <tests>
        <test expect_failure="true">
            <param name="input" value="input.fasta"/>
            <param name="outputs" value="sum,detail_sum,png,hog,pdf,ump,tax"/>
            <param name="database" value="test"/>

            <!-- Couldn't create a minimal working hdf5 dataset -->
            <assert_stderr>
                <has_text text="file signature not found"/>
                <has_text text="End of HDF5 error back trace" />
            </assert_stderr>
        </test>
    </tests>


    <help><![CDATA[
        OMark_: is a software for proteome quality assessment.
        It provides measures of proteome completeness, characterizes the consistency
        of all protein coding genes with regard to their homologs, and identifies the
        presence of contamination from other species.

        OMArk relies on the OMA orthology database.
        For more information, please refer to the OMamer_ documentaion.

        .. _OMark: https://github.com/DessimozLab/OMArk
        .. _OMamer: https://github.com/DessimozLab/omamer
    ]]></help>
    <expand macro="citation"/>
</tool>