view ctat_edger_differential_expression.xml @ 0:f36264827fb4 draft default tip

Upload ctat tools.

<tool id="ctat_edger_differential_expression" name="ctat_edger_differential_expression" version="1.0.0" profile="17.05">

    <description>Identify Differentially Expressed Transcripts Using EdgeR</description>
    <requirements>
        <requirement type="package" version="2.7">python</requirement>
        <requirement type="package">subprocess32</requirement>
        <requirement type="package">bzip2</requirement>
        <requirement type="package" version="1.3.0">rsem</requirement>
        <requirement type="package" version="3">bioconductor-edger</requirement>
        <requirement type="package" version="2">bioconductor-qvalue</requirement>
        <requirement type="package" version="2.6.6">trinity</requirement>
    </requirements>
    <command detect_errors="exit_code">
        <![CDATA[
 		python $__tool_directory__/ctat_edger_differential_expression.py 
			$counts_matrix 
			$dispersion
        ]]>
    </command>
    <inputs>
		
		<param type="data" format="txt" name="counts_matrix" label="Matrix of RNA-Seq fragment counts for transcripts per condition" />
		<param type="data" format="fasta" name="transcripts_fasta_file" label="Transcripts fasta file corresponding to matrix" />
		<param type="float" name="dispersion" value="0.1" min="0" label="dispersion value" help="Dispersion value to be used in the negative binomial" />
	
    </inputs>
    <outputs>
        <!--
        <data format="tar.gz" name="EdgeR_Archive" label="${tool.name} on ${on_string}: EdgeR_Results.tar.gz" from_work_dir="edgeR_results.tar.gz" />
       -->
        <data format="txt" name="EdgeR_Archive" label="${tool.name} on ${on_string}: EdgeR_Results.tar.gz" from_work_dir="edgeR_results.tar.gz" />
			
    </outputs>
    <tests>
	<test>
	    <param name="counts_matrix" value="Sp.counts.matrix" />
            <!-- The transcripts_fasta_file does not seem to be used for anything. -->
	    <param name="transcripts_fasta_file" value="Sp.Trinity.fasta" />
	    <param name="dispersion" value="0.1" />

            <!-- One could create more detailed tests if the output files were explicitly
                 saved rather than placed into an archive. We had a case where the archive
                 was being created, but it was missing one of the files, or one of the
                 files was empty. There is no easy way to look into the archive file to
                 test this.
            -->
	    <output name="EdgeR_Archive" >
                <assert_contents>
                    <has_line_matching expression=".+" />
                    <!-- The following is the magic number for all gzip files. -->
                    <has_text_matching expression="\x1F\x8B" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>
.. class:: infomark

edgeR is a Bioconductor package focusing on the analysis of digital gene expression data derived from RNA-Seq sequencing technologies.

To learn more about edgeR read their paper_, visit their website_ , or read this user_ guide_ .
If you are following the Trinity RNA-seq protocol please go here_ for a galaxy tool walk through or the Nature Protocols publication_ .

.. _paper: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2796818/
.. _publication: http://www.nature.com/nprot/journal/v8/n8/full/nprot.2013.084.html
.. _user: https://bioconductor.org/packages/devel/bioc/vignettes/edgeR/inst/doc/edgeRUsersGuide.pdf
.. _guide: https://bioconductor.org/packages/devel/bioc/vignettes/edgeR/inst/doc/edgeRUsersGuide.pdf
.. _website: http://bioinf.wehi.edu.au/edgeR/
.. _here: https://github.com/trinityrnaseq/GalaxyTrinityProtocol/wiki
    </help>

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

</tool>