<tool id="arriba_get_filters" name="Arriba Get Filters" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" python_template_version="3.5">
    <description>to history</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version_command" />
    <command detect_errors="exit_code"><![CDATA[
    BASE_DIR=\$(dirname \$(dirname `which arriba`)) &&
    REF_SCRIPT=`find \$BASE_DIR -name 'download_references.sh'` &&
    REF_DIR=\$(dirname \$REF_SCRIPT) &&
    REF_NAME=${arriba_reference_name.split('+')[0].replace('viral','')} &&
    echo \$REF_NAME &&
    cp `find \$REF_DIR -name 'blacklist_*' | grep -i \$REF_NAME` '$blacklist' && 
    cp `find \$REF_DIR -name 'known_fusions_*' | grep -i \$REF_NAME` '$known_fusions' &&
    cp `find \$REF_DIR -name 'protein_domains_*' | grep -i \$REF_NAME` '$protein_domains' &&
    cp `find \$REF_DIR -name 'cytobands_*' | grep -i \$REF_NAME` '$cytobands'
    #*
    cp "\$REF_DIR/blacklist_*${arriba_reference_name}*" '$blacklist' &&
    cp "\$REF_DIR/known_fusions_*${arriba_reference_name}*" '$known_fusions' &&
    cp "\$REF_DIR/protein_domains_*${arriba_reference_name}*" '$protein_domains' &&
    cp "\$REF_DIR/cytobands_*${arriba_reference_name}*" '$cytobands'
    *#
    ]]></command>
    <inputs>
        <param name="arriba_reference_name" type="text" label="Select reference">
            <help>GRCh38 GRCh37 hg38 hg19 GRCm38 mm10</help>
            <option value="GRCh38">GRCh38</option>
            <option value="GRCh37">GRCh37</option>
            <option value="hg38">hg38</option>
            <option value="hg19">hg19</option>
            <option value="GRCm38">GRCm38</option>
            <option value="mm10">mm10</option>
        </param>
    </inputs>
    <outputs>
        <data name="blacklist" format="tabular.gz" label="${tool.name} ${arriba_reference_name} blacklist.tsv.gz"/>
        <data name="known_fusions" format="tabular.gz" label="${tool.name} ${arriba_reference_name} known_fusions.tsv.gz"/>
        <data name="protein_domains" format="gff3" label="${tool.name} ${arriba_reference_name} protein_domains.gff3"/>
        <data name="cytobands" format="tabular" label="${tool.name} ${arriba_reference_name} cytobands.tsv"/>
    </outputs>
    <tests>
        <test>
            <param name="arriba_reference_name" value="GRCh38"/>
            <output name="cytobands">
                <assert_contents>
                    <has_text_matching expression="1\t1\t\d+\tp36.33\tgneg"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
**Arriba Get Filters**

Arriba_ is a fast tool to search for aberrant transcripts such as gene fusions.
It is based on chimeric alignments found by the STAR RNA-Seq aligner.

The **Arriba Get Filters** tool adds the following Arriba distribution input_files_ to your galaxy history:

  - blacklist
  - known_fusions
  - protein_domains
  - cytobands


.. _Arriba: https://arriba.readthedocs.io/en/latest/
.. _input_files: https://arriba.readthedocs.io/en/latest/input-files/

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