<tool id="run_DE_analysis" name="Differential expression analysis" version="2.1.1.1">
    <description>using a Trinity assembly</description>
    <requirements>
        <requirement type="package" version="2.1.1">trinity</requirement>
        <!-- odering is crucial, otherwise R will override the ENV variables from deseq2 -->
        <requirement type="package" version="1.10.0">deseq2</requirement>
        <requirement type="package" version="1.10.0">bioconductor-deseq2</requirement>
        <requirement type="package" version="3.14.0">bioconductor-edger</requirement>
        <requirement type="package" version="3.28.10">bioconductor-limma</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:"/>
    </stdio>
    <command><![CDATA[

        ln -s "${matrix}" "input.matrix"

        &&

        run_DE_analysis.pl

        --matrix "input.matrix"

        --samples_file "${samples}"

        --method ${method_choice.method}

        #if $method_choice.method == "edgeR":
            --dispersion ${method_choice.edger_dispersion}
        #end if

        #if $method_choice.method == "ROTS":
            --ROTS_B ${method_choice.rots_b}
            --ROTS_K ${method_choice.rots_k}
        #end if

        --min_rowSum_counts ${additional_params.min_rowSum_counts}

        #if $additional_params.reference_sample:
            --reference_sample ${additional_params.reference_sample}
        #end if

        #if $additional_params.contrasts:
            --contrasts ${additional_params.contrasts}
        #end if

        --output results

    ]]></command>
    <inputs>
        <param format="tabular" name="matrix" type="data" label="Expression matrix" help="output of abundance_estimates_to_matrix tool"/>
        <param format="tabular" name="samples" type="data" label="Sample description" help="file describing samples and replicates"/>

        <conditional name="method_choice">
            <param type="select" name="method" label="Differential analysis method">
                <option value="edgeR">edgeR</option>
                <option value="DESeq2">DESeq2</option>
                <option value="voom">voom</option>
                <option value="ROTS">ROTS</option>
            </param>
            <when value="edgeR">
                <param name="edger_dispersion" type="float" value="0.1" label="edgeR dispersion value" help="Read edgeR manual to guide your value choice" />
            </when>
            <when value="ROTS">
                <param name="rots_b" type="integer" value="500" label="number of bootstraps and permutation resampling" />
                <param name="rots_k" type="integer" value="5000" label="largest top genes size" />
            </when>
            <when value="voom">
            </when>
            <when value="DESeq2">
            </when>
        </conditional>

        <section name="additional_params" title="Additional Options" expanded="False">
            <param name="min_rowSum_counts" type="integer" value="2" label="Minimum count" help="Only those rows of matrix meeting requirement will be tested"/>
            <param name="reference_sample" type="text" optional="true" value="" label="Name of a sample to which all other samples should be compared" help="default is doing all pairwise-comparisons among samples"/>
            <param format="tabular" name="contrasts" optional="true" type="data" label="Pairs of sample comparisons to perform" help="A 2-column tabular with lists of pairs of samples to compare"/>
        </section>
    </inputs>
    <outputs>
        <collection name="DE_results" type="list" label="Differential expression results on ${on_string}">
            <discover_datasets pattern="(?P&lt;name&gt;.+)\.DE_results" ext="tabular" directory="results" visible="true" />
        </collection>
        <collection name="PDF_results" type="list" label="Differential expression plots on ${on_string}">
            <discover_datasets pattern="(?P&lt;name&gt;.+)\.pdf" ext="pdf" directory="results" visible="true" />
        </collection>
    </outputs>
    <tests>
        <test>
            <param name="matrix" value="count/qcheck/matrix.counts.matrix"/>
            <param name="samples" value="count/samples.txt"/>
            <param name="method" value="DESeq2"/>
            <output_collection name="DE_results">
                <element name="input.matrix.wt_37_vs_wt_ph8.DESeq2" compare="sim_size" file="count/exp_diff/matrix.counts.matrix.wt_37_vs_wt_GSNO.DESeq2.DE_results"/>
                <element name="input.matrix.wt_37_vs_wt_ph8.DESeq2" compare="sim_size" file="count/exp_diff/matrix.counts.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results"/>
                <element name="input.matrix.wt_GSNO_vs_wt_ph8.DESeq2" compare="sim_size" file="count/exp_diff/matrix.counts.matrix.wt_GSNO_vs_wt_ph8.DESeq2.DE_results"/>
            </output_collection>
            <output_collection name="PDF_results">
                <element name="input.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results.MA_n_Volcano" compare="sim_size" delta="100" file="count/exp_diff/matrix.counts.matrix.wt_37_vs_wt_GSNO.DESeq2.DE_results.MA_n_Volcano.pdf"/>
                <element name="input.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results.MA_n_Volcano" compare="sim_size" delta="100" file="count/exp_diff/matrix.counts.matrix.wt_37_vs_wt_ph8.DESeq2.DE_results.MA_n_Volcano.pdf"/>
                <element name="input.matrix.wt_GSNO_vs_wt_ph8.DESeq2.DE_results.MA_n_Volcano" compare="sim_size" delta="100" file="count/exp_diff/matrix.counts.matrix.wt_GSNO_vs_wt_ph8.DESeq2.DE_results.MA_n_Volcano.pdf"/>
            </output_collection>
        </test>
    </tests>
    <help>
<![CDATA[
Trinity_ assembles transcript sequences from Illumina RNA-Seq data.
This tool performs differential expression analyses on a transcriptome assembled with Trinity.

**Inputs**

This tool uses the matrix produced by 'Build expression matrix for a de novo assembly of RNA-Seq data by Trinity' tool.

You must describe your samples and replicates with a tabular file looking like this:

=========== ================
ConditionA  CondA_replicate1
----------- ----------------
ConditionA  CondA_replicate2
----------- ----------------
ConditionB  CondB_replicate1
----------- ----------------
ConditionB  CondB_replicate2
----------- ----------------
ConditionC  CondC_replicate1
----------- ----------------
ConditionC  CondC_replicate2
----------- ----------------
ConditionC  CondC_replicate3
=========== ================

It will probably be the same file as used in the tool 'RNASeq samples quality check for transcript quantification'.
The names in column 2 must match the names given in the tool 'Build expression matrix for a de novo assembly of RNA-Seq data by Trinity'.


.. _Trinity: http://trinityrnaseq.github.io
]]>
    </help>

     <citations>
        <citation type="doi">10.1038/nbt.1883</citation>
    </citations>
</tool>