Mercurial > repos > geert-vandeweyer > cuffdiff

changeset 2:17b31ea92891 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Enabled count-based output
author geert-vandeweyer
date Mon, 04 Aug 2014 11:41:19 -0400
parents 82c3d17ecfea
children
files cuffdiff_wrapper.xml
diffstat 1 files changed, 56 insertions(+), 15 deletions(-) [+]
line wrap: on
line diff
--- a/cuffdiff_wrapper.xml	Mon Aug 04 09:53:39 2014 -0400
+++ b/cuffdiff_wrapper.xml	Mon Aug 04 11:41:19 2014 -0400
@@ -37,7 +37,7 @@
                 #end if
             #end if
 
-            #set labels = '\'' + '\',\''.join( [ str( $condition.name ) for $condition in $conditions ] ) + '\''
+            #set labels = '\'' + '\',\''.join( [ str( $condition.name ) for $condition in $in_type.conditions ] ) + '\''
             --labels $labels
 
 	    $length_correction
@@ -62,21 +62,37 @@
 	    #end if
             ## Inputs.
             $gtf_input
-            #for $condition in $conditions:
+
+            #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."/>
-
-        <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>
-
+	<!-- 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>
@@ -127,7 +143,12 @@
             <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>
@@ -197,6 +218,9 @@
         <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 ${on_string}: splicing differential expression testing" from_work_dir="splicing.diff" />
@@ -204,12 +228,29 @@
         <data format="tabular" name="cds_diff" label="${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>
@@ -274,10 +315,10 @@
 
 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
+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