<tool id="compare_humann2_output" name="Compare outputs of HUMAnN2 for several samples" version="0.1.0">
    <description>and extract similar and specific information</description>

    <requirements>
    </requirements>

    <stdio>
        <exit_code range="1:" />
        <exit_code range=":-1" />
    </stdio>

    <version_command></version_command>

    <command><![CDATA[
        mkdir specifics 
        &&

        python $__tool_directory__/compare_humann2_output.py
            #for $sample in $samples:
                --sample_name "${sample.sample_name}"
                --charact_input_file "${sample.input}"
                --specific_output_file "specifics/specific_to_${sample.sample_name}.txt"
            #end for

            --most_abundant_characteristics_to_extract $charact_nb
            --more_abundant_output_file $more_abundant_output_file
            --similar_output_file $similar_output_file
            > $log
                
    ]]></command>

    <inputs>
        <repeat name="samples" title="Add sample and input file (HUMAnN2 output after normalization)" >
            <param name="sample_name" type="text" label="Name of the sample" help="(--sample_name)"/>
            <param name="input" format="txt,tabular" type="data" label="Input file corresponding to HUMAnN2 output" help="The HUMAnN2 output file contains relative abundance of gene families or pathways (after normalization, --charact_input_file)"/>
        </repeat>

        <param name="charact_nb" type="integer" value="10" label="Number of most abundant characteristics to extract for each sample" help="(--most_abundant_characteristics_to_extract)"/>
    </inputs>

    <outputs>
        <data name="more_abundant_output_file" format="tabular"
            label="${tool.name} on ${on_string}: More abundant characteristics for each sample" />
        <data name="similar_output_file" format="tabular"
            label="${tool.name} on ${on_string}: Similar characteristics and the relative abundances for all samples" />
        <data name="log" format="txt"
            label="${tool.name} on ${on_string}: Log" />
        <collection name="specific_files" type="list">
            <discover_datasets pattern="__designation_and_ext__" directory="specifics"/>
        </collection>

    </outputs>

    <tests>
        <test>
            <param name="samples_0|sample_name" value="sample1"/>
            <param name="samples_0|input" value="sample_1_pathway_abundances.tabular"/>
            <param name="samples_1|sample_name" value="sample2"/>
            <param name="samples_1|input" value="sample_2_pathway_abundances.tabular"/>
            <param name="charact_nb" value="10"/>
            <output name="more_abundant_output_file" file="more_abundant_pathways.tabular"/>
            <output name="similar_output_file" file="sample_similar_pathways.tabular"/>
            <output name="log" file="sample_comparison_log.txt"/>
            <output_collection name="specific_files" type="list">
                <element name="specific_to_sample1" file="sample_1_specific_pathways.txt" />
                <element name="specific_to_sample2" file="sample_2_specific_pathways.txt" />
            </output_collection>
        </test>
    </tests>

    <help><![CDATA[
**What it does**

This tool compare HUMANnN2 outputs with gene families or pathways and their relative abundances between several samples. Several files are extracted:

  * Similar gene families or pathways between the samples and the relative abundances of these similar characteristics

  * Most abundant gene families or pathways for each sample and the corresponding relative abundance in all samples

  * Specific gene families and pathways for each samples and the relative abundances of these specific characteristics

    ]]></help>

    <citations>
    </citations>
</tool>