annotate cuffmerge_wrapper.xml @ 7:25b0f2f2c506

Replace sam_fa_indices.loc with fasta_indexes.loc in fasta_indexes.loc.sample.

<tool id="cuffmerge" name="Cuffmerge" version="0.0.6">
    <!-- Wrapper supports Cuffmerge versions 1.3 and newer -->
    <description>merge together several Cufflinks assemblies</description>
    <requirements>
        <requirement type="package" version="2.1.1">cufflinks</requirement>
    </requirements>
    <command interpreter="python">
        cuffmerge_wrapper.py
        
            --num-threads="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 $seq_data.seq_source.index_source == "history":
                    --ref_file=$seq_data.seq_source.ref_file
                #else:
                    --index=${bias_correction.seq_source.index.fields.path}
                #end if
            #end if
            
            ## Outputs.
            --merged-transcripts=${merged_transcripts}
                        
            ## Inputs.
            ${first_input}
            #for $input_file in $input_files:
              ${input_file.additional_input}
            #end for
            
    </command>
    <inputs>
        <param format="gtf" name="first_input" type="data" label="GTF file produced by Cufflinks" help=""/>
        <repeat name="input_files" title="Additional GTF Input Files">
            <param format="gtf" name="additional_input" type="data" label="GTF file produced by Cufflinks" help=""/>
        </repeat>
        <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="first_input" 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>
    </inputs>

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

    <tests>
        <!-- 
            cuffmerge -g cuffcompare_in3.gtf cuffcompare_in1.gtf cuffcompare_in2.gtf
        -->
        <test>
            <param name="first_input" value="cuffcompare_in1.gtf" ftype="gtf"/>
            <param name="additional_input" value="cuffcompare_in2.gtf" ftype="gtf"/>
            <param name="use_ref_annotation" value="Yes"/>
            <param name="reference_annotation" value="cuffcompare_in3.gtf" ftype="gtf"/>
            <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://cufflinks.cbcb.umd.edu/
        
------

**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://cufflinks.cbcb.umd.edu/manual.html#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>
</tool>