comparison cuffdiff_wrapper.xml @ 2:17b31ea92891 draft default tip

Enabled count-based output

1:82c3d17ecfea

                    ## Built-in genome.
                    ${__get_data_table_entry__('fasta_indexes', 'value', $gtf_input.dbkey, 'path')}
                #end if
            #end if

            #set labels = '\'' + '\',\''.join( [ str( $condition.name ) for $condition in $conditions ] ) + '\''
            --labels $labels

	    $length_correction

	    ## Set advanced parameters for cufflinks

		--num-frag-assign-draws=$advanced_settings.num_frag_assign_draws
		--min-reps-for-js-test=$advanced_settings.min_reps_for_js_test
	    #end if
            ## Inputs.
            $gtf_input
            #for $condition in $conditions:
                #set samples = ','.join( [ str( $sample.sample ) for $sample in $condition.samples ] )
                $samples
            #end for
    </command>
    <inputs>
        <param format="gtf,gff3" name="gtf_input" type="data" label="Transcripts" help="A transcript GFF3 or GTF file produced by cufflinks, cuffcompare, or other source."/>

        <repeat name="conditions" title="Condition" min="2">
            <param name="name" title="Condition name" type="text" label="Name"/>
            <repeat name="samples" title="Replicate" min="1">
                <param name="sample" label="Add replicate" type="data" format="sam,bam"/>
            </repeat>
        </repeat>

        <param name="library_norm_method" type="select" label="Library normalization method">
            <option value="geometric" selected="True">geometric</option>
            <option value="classic-fpkm">classic-fpkm</option>
            <option value="quartile">quartile</option>
        </param>

        <param name="include_read_group_files" type="select" label="Include Read Group Datasets" help="Read group datasets provide information on replicates.">
            <option value="No" selected="true">No</option>
            <option value="Yes">Yes</option>
        </param>

	<param name="length_correction" type="select" label="apply length correction" help="mode of length normalization to transcript fpkm.">
            <option value="" selected="true">cufflinks effective length correction</option>
            <option value="--no-effective-length-correction">standard length correction</option>
	    <option value="--no-length-correction">no length correction at all (use raw counts)</option>
        </param>

            <filter>(include_read_group_files == 'Yes')</filter>
        </data>
        <data format="tabular" name="tss_groups_read_group" label="${tool.name} on ${on_string}: TSS groups read group tracking" from_work_dir="tss_groups.read_group_tracking" >
            <filter>(include_read_group_files == 'Yes')</filter>
        </data>

        <!-- Standard datasets. -->
        <data format="tabular" name="splicing_diff" label="${tool.name} on ${on_string}: splicing differential expression testing" from_work_dir="splicing.diff" />
        <data format="tabular" name="promoters_diff" label="${tool.name} on ${on_string}: promoters differential expression testing" from_work_dir="promoters.diff" />
        <data format="tabular" name="cds_diff" label="${tool.name} on ${on_string}: CDS overloading diffential expression testing" from_work_dir="cds.diff" />
        <data format="tabular" name="cds_exp_fpkm_tracking" label="${tool.name} on ${on_string}: CDS FPKM differential expression testing" from_work_dir="cds_exp.diff" />
        <data format="tabular" name="cds_fpkm_tracking" label="${tool.name} on ${on_string}: CDS FPKM tracking" from_work_dir="cds.fpkm_tracking" />
        <data format="tabular" name="tss_groups_exp" label="${tool.name} on ${on_string}: TSS groups differential expression testing" from_work_dir="tss_group_exp.diff" />
        <data format="tabular" name="tss_groups_fpkm_tracking" label="${tool.name} on ${on_string}: TSS groups FPKM tracking" from_work_dir="tss_groups.fpkm_tracking" />
        <data format="tabular" name="genes_exp" label="${tool.name} on ${on_string}: gene differential expression testing" from_work_dir="gene_exp.diff" />
        <data format="tabular" name="genes_fpkm_tracking" label="${tool.name} on ${on_string}: gene FPKM tracking" from_work_dir="genes.fpkm_tracking" />
        <data format="tabular" name="isoforms_exp" label="${tool.name} on ${on_string}: transcript differential expression testing" from_work_dir="isoform_exp.diff" />
        <data format="tabular" name="isoforms_fpkm_tracking" label="${tool.name} on ${on_string}: transcript FPKM tracking" from_work_dir="isoforms.fpkm_tracking" />
    </outputs>

    <tests>
        <test>
                <!--

**Outputs**

Cuffdiff produces many output files:

1. Transcript FPKM expression tracking.
2. Gene FPKM expression tracking; tracks the summed FPKM of transcripts sharing each gene_id
3. Primary transcript FPKM tracking; tracks the summed FPKM of transcripts sharing each tss_id
4. Coding sequence FPKM tracking; tracks the summed FPKM of transcripts sharing each p_id, independent of tss_id
5. Transcript differential FPKM.
6. Gene differential FPKM. Tests difference sin the summed FPKM of transcripts sharing each gene_id
7. Primary transcript differential FPKM. Tests difference sin the summed FPKM of transcripts sharing each tss_id
8. Coding sequence differential FPKM. Tests difference sin the summed FPKM of transcripts sharing each p_id independent of tss_id
9. Differential splicing tests: this tab delimited file lists, for each primary transcript, the amount of overloading detected among its isoforms, i.e. how much differential splicing exists between isoforms processed from a single primary transcript. Only primary transcripts from which two or more isoforms are spliced are listed in this file.

2:17b31ea92891

                    ## Built-in genome.
                    ${__get_data_table_entry__('fasta_indexes', 'value', $gtf_input.dbkey, 'path')}
                #end if
            #end if

            #set labels = '\'' + '\',\''.join( [ str( $condition.name ) for $condition in $in_type.conditions ] ) + '\''
            --labels $labels

	    $length_correction

	    ## Set advanced parameters for cufflinks

		--num-frag-assign-draws=$advanced_settings.num_frag_assign_draws
		--min-reps-for-js-test=$advanced_settings.min_reps_for_js_test
	    #end if
            ## Inputs.
            $gtf_input

            #for $condition in $in_type.conditions:
                #set samples = ','.join( [ str( $sample.sample ) for $sample in $condition.samples ] )
                $samples
            #end for
    </command>
    <inputs>
        <param format="gtf,gff3" name="gtf_input" type="data" label="Transcripts" help="A transcript GFF3 or GTF file produced by cufflinks, cuffcompare, or other source."/>
	<!-- DEFAULT : use BAM/SAM files -->
        <conditional name="in_type">
	    <param name="set_in_type" type="select" label="Input data type" help="CuffDiff supports either CXB (from cuffquant) or SAM/BAM input files. Mixing is not supported. Default: SAM/BAM">
		<option value="BAM">SAM/BAM</option>
		<option value="CXB">Cuffquant .cxb</option>
	    </param>
	    <when value="BAM">
	        <repeat name="conditions" title="Condition" min="2">
	            <param name="name" title="Condition name" type="text" label="Name"/>
	            <repeat name="samples" title="Replicate" min="1">
	                <param name="sample" label="Add replicate" type="data" format="sam,bam"/>
	            </repeat>
	        </repeat>
	    </when>
	    <when value="CXB">
		<repeat name="conditions" title="Condition" min="2">
	            <param name="name" title="Condition name" type="text" label="Name"/>
	            <repeat name="samples" title="Replicate" min="1">
	                <param name="sample" label="Add replicate" type="data" format="cxb"/>
	            </repeat>
	        </repeat>
	    </when>
     	</conditional>
        <param name="library_norm_method" type="select" label="Library normalization method">
            <option value="geometric" selected="True">geometric</option>
            <option value="classic-fpkm">classic-fpkm</option>
            <option value="quartile">quartile</option>
        </param>

        <param name="include_read_group_files" type="select" label="Include Read Group Datasets" help="Read group datasets provide information on replicates.">
            <option value="No" selected="true">No</option>
            <option value="Yes">Yes</option>
        </param>
	
	<param name="include_count_files" type="select" label="Include Count Based output files" help="Cuffdiff estimates the number of fragments that originated from each transcript, primary transcript, and gene in each sample. Primary transcript and gene counts are computed by summing the counts of transcripts in each primary transcript group or gene group.">
            <option value="No" selected="true">No</option>
            <option value="Yes">Yes</option>
        </param>
	
	<param name="length_correction" type="select" label="apply length correction" help="mode of length normalization to transcript fpkm.">
            <option value="" selected="true">cufflinks effective length correction</option>
            <option value="--no-effective-length-correction">standard length correction</option>
	    <option value="--no-length-correction">no length correction at all (use raw counts)</option>
        </param>

            <filter>(include_read_group_files == 'Yes')</filter>
        </data>
        <data format="tabular" name="tss_groups_read_group" label="${tool.name} on ${on_string}: TSS groups read group tracking" from_work_dir="tss_groups.read_group_tracking" >
            <filter>(include_read_group_files == 'Yes')</filter>
        </data>
 	<data format="text" name="read_group_info" label="${tool.name} on ${on_string}: read group info" from_work_dir="read_groups.info" >
            <filter>(include_read_group_files == 'Yes')</filter>
        </data>

        <!-- Standard datasets. -->
        <data format="tabular" name="splicing_diff" label="${tool.name} on ${on_string}: splicing differential expression testing" from_work_dir="splicing.diff" />
        <data format="tabular" name="promoters_diff" label="${tool.name} on ${on_string}: promoters differential expression testing" from_work_dir="promoters.diff" />
        <data format="tabular" name="cds_diff" label="${tool.name} on ${on_string}: CDS overloading diffential expression testing" from_work_dir="cds.diff" />
        <data format="tabular" name="cds_exp_fpkm_tracking" label="${tool.name} on ${on_string}: CDS FPKM differential expression testing" from_work_dir="cds_exp.diff" />
        <data format="tabular" name="cds_fpkm_tracking" label="${tool.name} on ${on_string}: CDS FPKM tracking" from_work_dir="cds.fpkm_tracking" />
        <data format="tabular" name="cds_count_tracking" label="${tool.name} on ${on_string}: CDS count tracking" from_work_dir="cds.count_tracking" >
		<filter>(include_count_files == 'Yes')</filter>
        </data>

        <data format="tabular" name="tss_groups_exp" label="${tool.name} on ${on_string}: TSS groups differential expression testing" from_work_dir="tss_group_exp.diff" />
        <data format="tabular" name="tss_groups_fpkm_tracking" label="${tool.name} on ${on_string}: TSS groups FPKM tracking" from_work_dir="tss_groups.fpkm_tracking" />
        <data format="tabular" name="tss_groups_count_tracking" label="${tool.name} on ${on_string}: TSS count FPKM tracking" from_work_dir="tss_groups.count_tracking" >
		<filter>(include_count_files == 'Yes')</filter>
        </data>

        <data format="tabular" name="genes_exp" label="${tool.name} on ${on_string}: gene differential expression testing" from_work_dir="gene_exp.diff" />
        <data format="tabular" name="genes_fpkm_tracking" label="${tool.name} on ${on_string}: gene FPKM tracking" from_work_dir="genes.fpkm_tracking" />
        <data format="tabular" name="genes_count_tracking" label="${tool.name} on ${on_string}: gene count tracking" from_work_dir="genes.count_tracking" >
		<filter>(include_count_files == 'Yes')</filter>
        </data>

        <data format="tabular" name="isoforms_exp" label="${tool.name} on ${on_string}: transcript differential expression testing" from_work_dir="isoform_exp.diff" />
        <data format="tabular" name="isoforms_fpkm_tracking" label="${tool.name} on ${on_string}: transcript FPKM tracking" from_work_dir="isoforms.fpkm_tracking" />
        <data format="tabular" name="isoforms_count_tracking" label="${tool.name} on ${on_string}: transcript count tracking" from_work_dir="isoforms.count_tracking" >
		<filter>(include_count_files == 'Yes')</filter>
        </data>
	

    </outputs>

    <tests>
        <test>
                <!--

**Outputs**

Cuffdiff produces many output files:

1. Transcript FPKM (+count) expression tracking.
2. Gene FPKM (+count) expression tracking; tracks the summed FPKM of transcripts sharing each gene_id
3. Primary transcript FPKM (+count) tracking; tracks the summed FPKM of transcripts sharing each tss_id
4. Coding sequence FPKM (+count) tracking; tracks the summed FPKM of transcripts sharing each p_id, independent of tss_id
5. Transcript differential FPKM.
6. Gene differential FPKM. Tests difference sin the summed FPKM of transcripts sharing each gene_id
7. Primary transcript differential FPKM. Tests difference sin the summed FPKM of transcripts sharing each tss_id
8. Coding sequence differential FPKM. Tests difference sin the summed FPKM of transcripts sharing each p_id independent of tss_id
9. Differential splicing tests: this tab delimited file lists, for each primary transcript, the amount of overloading detected among its isoforms, i.e. how much differential splicing exists between isoforms processed from a single primary transcript. Only primary transcripts from which two or more isoforms are spliced are listed in this file.