annotate cuffmerge_wrapper.xml @ 15:86285ddd4512 draft default tip

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/cufflinks/cuffmerge commit 92be38a0f40ef6d6ccb55999f3eb8bf960e376c8"

<tool id="cuffmerge" name="Cuffmerge" version="@VERSION@.3">
    <description>merge together several Cufflinks assemblies</description>
    <macros>
      <import>cuff_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <version_command>cuffmerge -v</version_command>
    <command detect_errors="aggressive"><![CDATA[
        @CUFFLINKS_LINK_GTF_INPUTS@
        echo @CUFFLINKS_GTF_INPUTS@ | sed 's/\s\+/\n/' > assembly_GTF_list.txt &&
        cuffmerge 
            -o output
            --num-threads="\${GALAXY_SLOTS:-4}"
            ## Use annotation reference?
            #if $annotation.use_ref_annotation == "Yes":
                -g '${annotation.reference_annotation}'
            #end if
            
            ## Use sequence data?
            #if $seq_data.use_seq_data == "Yes":
                -s
                #if $seq_data.seq_source.index_source == "history":
                    '${seq_data.seq_source.ref_file}'
                #else:
                    '${seq_data.seq_source.index.fields.path}'
                #end if
            #end if

            --min-isoform-fraction="${min_isoform_fraction}"
            assembly_GTF_list.txt
    ]]></command>
    <inputs>
        <expand macro="cufflinks_gtf_inputs" />
        <conditional name="annotation">
            <param name="use_ref_annotation" type="select" label="Use Reference Annotation">
                <option value="No">No</option>
                <option value="Yes">Yes</option>
            </param>
            <when value="Yes">
                <param format="gff3,gtf" name="reference_annotation" type="data" label="Reference Annotation" help="Requires an annotation file in GFF3 or GTF format."/>    
            </when>
            <when value="No">
            </when>
        </conditional>
        <conditional name="seq_data">
            <param name="use_seq_data" type="select" label="Use Sequence Data" help="Use sequence data for some optional classification functions, including the addition of the p_id attribute required by Cuffdiff.">
                <option value="No">No</option>
                <option value="Yes">Yes</option>
            </param>
            <when value="No"></when>
            <when value="Yes">
                <conditional name="seq_source">
                  <param name="index_source" type="select" label="Choose the source for the reference list">
                    <option value="cached">Locally cached</option>
                    <option value="history">History</option>
                  </param>
                  <when value="cached">
                    <param name="index" type="select" label="Using reference genome">
                      <options from_data_table="fasta_indexes">
                        <filter type="data_meta" ref="inputs" key="dbkey" column="1" />
                        <validator type="no_options" message="No reference genome is available for the build associated with the selected input dataset" />
                      </options>
                    </param>
                  </when>
                  <when value="history">
                      <param name="ref_file" type="data" format="fasta" label="Using reference file" />
                  </when>
                </conditional>
            </when>
        </conditional>
        <param name="min_isoform_fraction" type="float" min="0" max="1" value="0.05" label="Minimum isoform fraction" help="Discard isoforms with abundance below this value" />
    </inputs>

    <outputs>
        <data format="gtf" name="merged_transcripts" label="${tool.name} on ${on_string}: merged transcripts" from_work_dir="output/merged.gtf"/>
    </outputs>

    <tests>
        <!-- 
            cuffmerge -g cuffcompare_in3.gtf cuffcompare_in1.gtf cuffcompare_in2.gtf
        -->
        <test>
            <param name="inputs" value="cuffcompare_in1.gtf,cuffcompare_in2.gtf" ftype="gtf"/>
            <param name="use_ref_annotation" value="Yes"/>
            <param name="reference_annotation" value="cuffcompare_in3.gtf" ftype="gtf"/>
            <param name="min_isoform_fraction" value="0.08" />
            <param name="use_seq_data" value="No"/>
            <!-- oId assignment differ/are non-deterministic -->
            <output name="merged_transcripts" file="cuffmerge_out1.gtf" lines_diff="50"/>
        </test>
    </tests>

    <help>
**Cuffmerge Overview**

Cuffmerge is part of Cufflinks_. Please cite: Trapnell C, Williams BA, Pertea G, Mortazavi AM, Kwan G, van Baren MJ, Salzberg SL, Wold B, Pachter L. Transcript assembly and abundance estimation from RNA-Seq reveals thousands of new transcripts and switching among isoforms. Nature Biotechnology doi:10.1038/nbt.1621

.. _Cufflinks: http://cole-trapnell-lab.github.io/cufflinks/

------

**Know what you are doing**

.. class:: warningmark

There is no such thing (yet) as an automated gearshift in expression analysis. It is all like stick-shift driving in San Francisco. In other words, running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy.

.. __: http://cole-trapnell-lab.github.io/cufflinks/cuffmerge/

------

**Input format**

Cuffmerge takes Cufflinks' GTF output as input, and optionally can take a "reference" annotation (such as from Ensembl_)

.. _Ensembl: http://www.ensembl.org 

------

**Outputs**

Cuffmerge produces the following output files:

Merged transcripts file:

Cuffmerge produces a GTF file that contains an assembly that merges together the input assemblies.
    </help>
    <expand macro="citations"/>
</tool>