annotate run_de_analysis.xml @ 18:ab87da55fe61 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/trinity commit c468d2b9613f88cc5f96f77ab1e0592d3c9ce707"

<tool id="trinity_run_de_analysis" name="Differential expression analysis" version="@WRAPPER_VERSION@">
    <description>using a Trinity assembly</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="bio_tools"/>
    <expand macro="requirements">
        <requirement type="package" version="3.20.7">bioconductor-edger</requirement>
        <requirement type="package" version="3.34.9">bioconductor-limma</requirement>
        <requirement type="package" version="1.18.1">bioconductor-deseq2</requirement>
    </expand>
    <command detect_errors="aggressive"><![CDATA[

        ln -f -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_reps_min_cpm ${additional_params.min_reps},${additional_params.min_cpm}

        #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" argument="--matrix" type="data" label="Expression matrix" help="output of Build expression matrix - matrix of raw read counts (not normalized!)"/>
        <param format="tabular" name="samples" argument="--samples_file" type="data" label="Sample description" help="file describing samples and replicates"/>

        <conditional name="method_choice">
            <param type="select" name="method" argument="--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" argument="--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" argument="--ROTS_B" type="integer" value="500" label="number of bootstraps and permutation resampling" />
                <param name="rots_k" argument="--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_cpm" type="integer" value="1" label="Minimum count per replicate" help="Only those rows of matrix meeting requirement will be tested"/>
            <param name="min_reps" type="integer" value="2" label="Minimum number of replicates meeting minimum count per replicate" help="Only those rows of matrix meeting requirement will be tested"/>
            <param name="reference_sample" argument="--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" argument="--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" />
        </collection>
        <collection name="count_matrices" type="list" label="Count matrices generated for differential expression on ${on_string}">
            <discover_datasets pattern="(?P&lt;name&gt;.+)\.count_matrix$" ext="tabular" directory="results" />
        </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" />
        </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_GSNO.DESeq2" compare="sim_size" file="count/exp_diff/input.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/input.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/input.matrix.wt_GSNO_vs_wt_ph8.DESeq2.DE_results"/>
            </output_collection>
            <output_collection name="count_matrices">
                <element name="input.matrix.wt_37_vs_wt_GSNO.DESeq2" compare="sim_size" file="count/exp_diff/input.matrix.wt_37_vs_wt_GSNO.DESeq2.count_matrix"/>
                <element name="input.matrix.wt_37_vs_wt_ph8.DESeq2" compare="sim_size" file="count/exp_diff/input.matrix.wt_37_vs_wt_ph8.DESeq2.count_matrix"/>
                <element name="input.matrix.wt_GSNO_vs_wt_ph8.DESeq2" compare="sim_size" file="count/exp_diff/input.matrix.wt_GSNO_vs_wt_ph8.DESeq2.count_matrix"/>
            </output_collection>
            <output_collection name="PDF_results">
                <element name="input.matrix.wt_37_vs_wt_GSNO.DESeq2.DE_results.MA_n_Volcano" compare="sim_size" delta="100" file="count/exp_diff/input.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="200" file="count/exp_diff/input.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/input.matrix.wt_GSNO_vs_wt_ph8.DESeq2.DE_results.MA_n_Volcano.pdf"/>
            </output_collection>
        </test>
        <test>
            <param name="matrix" value="count/qcheck/matrix.counts.matrix"/>
            <param name="samples" value="count/samples.txt"/>
            <param name="method" value="edgeR"/>
            <output_collection name="DE_results">
                <element name="input.matrix.wt_37_vs_wt_GSNO.edgeR" compare="sim_size" file="count/exp_diff/input.matrix.wt_37_vs_wt_GSNO.edgeR.DE_results"/>
                <element name="input.matrix.wt_37_vs_wt_ph8.edgeR" compare="sim_size" file="count/exp_diff/input.matrix.wt_37_vs_wt_ph8.edgeR.DE_results"/>
                <element name="input.matrix.wt_GSNO_vs_wt_ph8.edgeR" compare="sim_size" file="count/exp_diff/input.matrix.wt_GSNO_vs_wt_ph8.edgeR.DE_results"/>
            </output_collection>
            <output_collection name="count_matrices">
                <element name="input.matrix.wt_37_vs_wt_GSNO.edgeR" compare="sim_size" file="count/exp_diff/input.matrix.wt_37_vs_wt_GSNO.edgeR.count_matrix"/>
                <element name="input.matrix.wt_37_vs_wt_ph8.edgeR" compare="sim_size" file="count/exp_diff/input.matrix.wt_37_vs_wt_ph8.edgeR.count_matrix"/>
                <element name="input.matrix.wt_GSNO_vs_wt_ph8.edgeR" compare="sim_size" file="count/exp_diff/input.matrix.wt_GSNO_vs_wt_ph8.edgeR.count_matrix"/>
            </output_collection>
            <output_collection name="PDF_results">
                <element name="input.matrix.wt_37_vs_wt_GSNO.edgeR.DE_results.MA_n_Volcano" compare="sim_size" delta="100" file="count/exp_diff/input.matrix.wt_37_vs_wt_GSNO.edgeR.DE_results.MA_n_Volcano.pdf"/>
                <element name="input.matrix.wt_37_vs_wt_ph8.edgeR.DE_results.MA_n_Volcano" compare="sim_size" delta="100" file="count/exp_diff/input.matrix.wt_37_vs_wt_ph8.edgeR.DE_results.MA_n_Volcano.pdf"/>
                <element name="input.matrix.wt_GSNO_vs_wt_ph8.edgeR.DE_results.MA_n_Volcano" compare="sim_size" delta="100" file="count/exp_diff/input.matrix.wt_GSNO_vs_wt_ph8.edgeR.DE_results.MA_n_Volcano.pdf"/>
            </output_collection>
        </test>
        <test>
            <param name="matrix" value="count/qcheck/matrix.counts.matrix"/>
            <param name="samples" value="count/samples.txt"/>
            <param name="method" value="voom"/>
            <output_collection name="DE_results">
                <element name="input.matrix.wt_37_vs_wt_GSNO.voom" compare="sim_size" file="count/exp_diff/input.matrix.wt_37_vs_wt_GSNO.voom.DE_results"/>
                <element name="input.matrix.wt_37_vs_wt_ph8.voom" compare="sim_size" file="count/exp_diff/input.matrix.wt_37_vs_wt_ph8.voom.DE_results"/>
                <element name="input.matrix.wt_GSNO_vs_wt_ph8.voom" compare="sim_size" file="count/exp_diff/input.matrix.wt_GSNO_vs_wt_ph8.voom.DE_results"/>
            </output_collection>
            <output_collection name="count_matrices">
                <element name="input.matrix.wt_37_vs_wt_GSNO.voom" compare="sim_size" file="count/exp_diff/input.matrix.wt_37_vs_wt_GSNO.voom.count_matrix"/>
                <element name="input.matrix.wt_37_vs_wt_ph8.voom" compare="sim_size" file="count/exp_diff/input.matrix.wt_37_vs_wt_ph8.voom.count_matrix"/>
                <element name="input.matrix.wt_GSNO_vs_wt_ph8.voom" compare="sim_size" file="count/exp_diff/input.matrix.wt_GSNO_vs_wt_ph8.voom.count_matrix"/>
            </output_collection>
            <output_collection name="PDF_results">
                <element name="input.matrix.wt_37_vs_wt_GSNO.voom.DE_results.MA_n_Volcano" compare="sim_size" delta="100" file="count/exp_diff/input.matrix.wt_37_vs_wt_GSNO.voom.DE_results.MA_n_Volcano.pdf"/>
                <element name="input.matrix.wt_37_vs_wt_ph8.voom.DE_results.MA_n_Volcano" compare="sim_size" delta="100" file="count/exp_diff/input.matrix.wt_37_vs_wt_ph8.voom.DE_results.MA_n_Volcano.pdf"/>
                <element name="input.matrix.wt_GSNO_vs_wt_ph8.voom.DE_results.MA_n_Volcano" compare="sim_size" delta="100" file="count/exp_diff/input.matrix.wt_GSNO_vs_wt_ph8.voom.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
=========== ================


This file can be generated with the 'Describe samples and replicates' tool.
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>

    <expand macro="citation" />
</tool>