comparison abundance_estimation_to_matrix.xml @ 0:e4876b8c81ec draft

Adding Abundance Estimation to Matrix.

0:e4876b8c81ec

<tool id="abundance_estimation_to_matrix" name="abundance_estimation_to_matrix" version="1.0.0">

    <description>Join RSEM estimates from multiple samples into a single matrix</description>
    <requirements>
        <requirement type="package" version="2.7">python</requirement>
        <requirement type="package">trinity</requirement>
    </requirements>
    <command interpreter="python">

        abundance_estimation_to_matrix_wrapper.py 
		#for $q in $RSEM_samples
			${q.file} "${q.column_label}"
		#end for

    </command>
    <inputs>

       <repeat name="RSEM_samples" title="RSEM abundance estimates for samples">
              <param name="file" label="Add file" type="data" format="text"/>
              <param name="column_label" label="column label" type="text" />
       </repeat>

    </inputs>
    <outputs>
        <data format="txt" name="counts_matrix" label="${tool.name} on ${on_string}: Counts Matrix" from_work_dir="matrix.counts.matrix"/>
        <data format="txt" name="tmm_expr_matrix" label="${tool.name} on ${on_string}: TMM EXPR Matrix" from_work_dir="matrix.TMM.EXPR.matrix"/>
	</outputs>
    <tests>
	<test>
                <repeat name="RSEM_samples">
                    <param name="file" value="Sp_ds.RSEM.genes.results" />
                    <param name="column_label" value="Sp_ds" />
                </repeat>
                <repeat name="RSEM_samples">
                    <param name="file" value="Sp_hs.RSEM.genes.results" />
                    <param name="column_label" value="Sp_hs" />
                </repeat>

	        <output name="counts_matrix" >
                    <assert_contents>
                        <has_line_matching expression=".+" />
                        <has_line line="&#009;Sp_ds&#009;Sp_hs" />
                        <has_n_columns n="3" />
                        <has_line_matching expression="TRINITY_DN.+" />
                    </assert_contents>
                </output>
	        <output name="tmm_expr_matrix" >
                    <assert_contents>
                        <has_line_matching expression=".+" />
                        <has_line line="&#009;Sp_ds&#009;Sp_hs" />
                        <has_n_columns n="3" />
                        <has_line_matching expression="TRINITY_DN.+" />
                    </assert_contents>
                </output>
        </test>
        <!-- The following test has not been tested to see if it works.
	<test>
                <repeat name="RSEM_samples">
                    <param name="file" value="Sp_ds.RSEM.isoforms.results" />
                    <param name="column_label" value="Sp_ds" />
                </repeat>
                <repeat name="RSEM_samples">
                    <param name="file" value="Sp_hs.RSEM.isoforms.results" />
                    <param name="column_label" value="Sp_hs" />
                </repeat>

	        <output name="counts_matrix" >
                    <assert_contents>
                        <has_line_matching expression=".+" />
                    </assert_contents>
                </output>
	        <output name="tmm_expr_matrix" >
                    <assert_contents>
                        <has_line_matching expression=".+" />
                    </assert_contents>
                </output>
        </test>
        -->
    </tests>
    <help>
.. class:: infomark 

This step will join the RSEM-computed gene or isoform fragment counts into a matrix file, which will be used to run edgeR and identify differentially expressed transcripts in next few steps. Execution of this will generate a counts matrix file with a name 'abundance_estimation_to_matrix: counts_matrix'.

If you are following the Trinity RNA-seq protocol please go here_ for a galaxy tool walk through or the Nature Protocols paper_.

.. _here: https://github.com/trinityrnaseq/GalaxyTrinityProtocol/wiki
.. _paper: http://www.nature.com/nprot/journal/v8/n8/full/nprot.2013.084.html
    </help>
</tool>