annotate contamination.xml @ 0:3f73568fafdc draft default tip

planemo upload for repository https://github.com/Helmholtz-UFZ/ufz-galaxy-tools/blob/main/tools/phabox commit 3c8e23e1dea22f625fb6f77ae61e1f4b605aaae2

<tool id="phabox_contamination" name="PhaBOX contamination" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.1" license="MIT">
    <description>Contamination/provirus detection</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <xrefs>
        <xref type="bio.tools">phabox</xref>
    </xrefs>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">phabox</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        phabox2 --task contamination
            @GENERAL@
            @CONTAMINATION@
    ]]></command>
    <inputs>
        <expand macro="general"/>
        <expand macro="contamination"/>
    </inputs>
    <outputs>
        <data name="out" format="tabular" from_work_dir="output/final_prediction/contamination_prediction.tsv"/>
    </outputs>
    <tests>
        <test>
            <param name="dbdir" value="phaboxdb"/>
            <param name="contigs" value="example_contigs.fa"/>
            <output name="out">
                <assert_contents>
                    <has_line line="Accession&#9;Length&#9;Total_genes&#9;Viral_genes&#9;Prokaryotic_genes&#9;Kmer_freq&#9;Contamination&#9;Provirus&#9;Pure_viral"/>
                    <has_n_lines n="11"/>
                    <has_n_columns n="9"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[

Check for contaminations / proviruses.


@COMMON_INPUT_DOC@

**Output**:

@COMMON_OUTPUT_DOC@
- Total_genes: number of genes in the contigs (predicted by prodigal-gv)
- Viral_genes: number of viral marker genes
- Prokaryotic_genes: number of prokaryotic marker genes
- Kmer_freq: average frequency of 20-mer. This is a value to estimate the copy number of the genes; usually, the Kmer_freq of 99.9% virus is less than 1.25.
- Contamination:
- Provirus: Whether the sequence is a provirus
- Pure_viral: High quality or Medium quality or Low quality


    ]]></help>
    <expand macro="citations"/>
</tool>