<tool id="som.py" name="som.py" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.09">
    <description>A tool to perform comparisons only based on chromosome, position, and allele identity for comparison of somatic callsets.</description>

    <macros>
        <token name="@TOOL_VERSION@">0.3.14</token>
        <token name="@VERSION_SUFFIX@">0</token>
    </macros>

    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">hap.py</requirement>
    </requirements>

    <command detect_errors="exit_code"><![CDATA[

#if $reference_genome.source == 'history':
    #set $ref_genome = 'reference.fasta'
    ln -s -f '${reference_genome.history_item}' $ref_genome;
    samtools faidx $ref_genome;
#else:
    #set $ref_genome = $reference_genome.index.fields.path
#end if
    export HGREF='$ref_genome' &&
    som.py
    '$truth'
    '$query'
    -r '$ref_genome'
    -o 'happy' | sed 's/\s\+/\t/g' | tail -n+2> results.tsv
    ]]>
    </command>

    <inputs>
        <conditional name="reference_genome">
            <param name="source" type="select" label="Source for the reference genome" help="Built-in references were created using default options.">
                <option value="indexed" selected="true">Use a built-in genome</option>
                <option value="history">Use a genome from history</option>
            </param>
            <when value="indexed">
                <param name="index" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact the Galaxy team.">
                    <options from_data_table="fasta_indexes">
                        <filter type="sort_by" column="2" />
                        <validator type="no_options" message="No genomes are available for the selected input dataset" />
                    </options>
                </param>
            </when>
            <when value="history">
                <param name="history_item" type="data" format="fasta" label="Reference genome" help="A reference genome in FASTA format" />
            </when>
        </conditional>
        <param name="truth" type="data" format="vcf" label="ground truth variant calls"/>
        <param name="query" type="data" format="vcf" label="query variant calls"/>
    </inputs>

    <outputs>
        <data name="results" label="${tool.name} on ${on_string}" format="tabular" from_work_dir="results.tsv"/>
        <data name="stats" label="${tool.name} on ${on_string}: stats" format="csv" from_work_dir="happy.stats.csv" />
        <data name="metrics" label="${tool.name} on ${on_string}: metrics" format="json" from_work_dir="happy.metrics.json"/>
    </outputs>

    <tests>
        <test expect_num_outputs="3">
            <param name="source" value="history"/>
            <param name="history_item" value="chr21.fa"/>
            <param name="truth" value="small_NA12878-Freebayes-chr21.vcf"/>
            <param name="query" value="small_NA12878-GATK3-chr21.vcf"/>

            <output name="results" file="results.tsv"/>
            <output name="stats" file="happy.stats.csv" compare="sim_size" delta_frac="0.3" />
            <output name="metrics" file="happy.metrics.json" compare="sim_size" delta_frac="0.3" />
        </test>
    </tests>

    <help><![CDATA[
        som.py is a tool to perform comparisons only based on chromosome, position, and allele identity. This comparison will not resolve haplotypes and only verify that the same alleles were observed at the same positions (e.g. for comparison of somatic callsets).
    ]]></help>

</tool>