# HG changeset patch
# User fubar
# Date 1315544919 14400
# Node ID ba8c9980350b22ee046b713cc12ff2e38b7fc3aa
# Parent  1959becd059294ed7070f28940553f51bddfb68b
Initial checkin for DGE

diff -r 1959becd0592 -r ba8c9980350b DGE.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/DGE.xml	Fri Sep 09 01:08:39 2011 -0400
@@ -0,0 +1,75 @@
+<tool id="rgDGE" name="Digital differential expression" version="0.01">
+  <description>for RNA counts</description>
+  <command interpreter="python">rgDGE.py --output_html "$html_file.files_path" --input_matrix "$input1" --treatcols "$Treat_cols" 
+       --treatname "$treatment_name" --ctrlcols "$Control_cols" --ctrlname "$control_name" --output_tab "$outtab" --output_html 
+        "$html_file" --output_dir "$html_file.files_path" --method "edgeR"
+  </command>
+  <inputs>
+    <param name="input1"  type="data" format="tabular" label="Select an input matrix - rows are contigs, columns are counts for each sample"
+       help="Use the DGE matrix preparation tool to create these matrices from BAM files and a BED file of contigs"/>
+    <param name="treatment_name" type="text" value="Treatment" size="50" label="Treatment Name"/>
+    <param name="Treat_cols" label="Select columns containing treatment." type="data_column" data_ref="input1" numerical="True" 
+         multiple="true" use_header_names="true" size="120" display="checkboxes">
+        <validator type="no_options" message="Please select at least one column."/>
+    </param>
+
+    <param name="control_name" type="text" value="Control" size="50" label="Control Name"/>
+    <param name="Control_cols" label="Select columns containing control." type="data_column" data_ref="input1" numerical="True" 
+         multiple="true" use_header_names="true" size="120" display="checkboxes">
+        <validator type="no_options" message="Please select at least one column."/>
+    </param>
+
+        <param name="method" type="select" label="Method" >
+            <option value="edgeR" selected="true">edgeR</option>
+            <option value="DESeq">DESeq - coming soonish!</option>
+        </param>
+
+  </inputs>
+  <outputs>
+    <data format="tabular" name="outtab" label="${on_string}_DGE.xls"/>
+    <data format="html" name="html_file" label="${on_string}_DGE.html"/>
+  </outputs>
+<tests>
+<test>
+<param name='input1' value='DGEtest.xls' ftype='tabular' />
+ <param name='treatment_name' value='case' />
+ <param name='control_name' value='control' />
+ <param name='Treat_cols' value='c3,c6,c9' />
+ <param name='Control_cols' value='c2,c5,c8' />
+ <output name='outtab' file='DGEtest1out.xls' ftype='tabular' compare='diff' />
+ <output name='html_file' file='DGEtest1out.html' ftype='html' compare='diff' lines_diff='20' />
+</test>
+</tests>
+<help>
+.. class:: infomark
+    
+**What it does**
+
+Performs digital differential gene expression analysis between two groups (eg a treatment and control) each with biological replicates, from count data arranged in a matrix as a tabular file.
+
+**Input**
+
+A matrix consisting of non-negative integers. The matrix must have a unique header row identifiying the samples, as well as a unique set of row names 
+as  the first column. To create appropriate input files, the "Multiple BAMs to matrix" tool takes multiple bam files containing mapped RNAseq reads mapped to a reference genome, and a BED file containing (eg Refseq) contigs. A count matrix containing contigs as rows and samples as
+columns will be created and can then be used in this tool to estimate differential gene expression using methods appropriate for count data.
+
+**Output**
+
+A tabular file containing relative expression levels, statistical estimates of differential expression probability, the R script, log and sessionInfo, and some helpful diagnostic plots.
+
+.. class:: infomark
+
+**Attribution**
+DGE.R was originally written by: S.Lunke and A.Kaspi.
+Wrapping for Galaxy and general kibbitzing from Ross Lazarus.
+This tool wrapts the edgeR_ Bioconductor package so all calculations and plots are controlled by that code. See edgeR_ for all documentation and appropriate attribution. 
+Recommended reference is Mark D. Robinson, Davis J. McCarthy, Gordon K. Smyth, PMCID: PMC2796818
+
+ .. _LGPL: http://www.gnu.org/copyleft/lesser.html
+ .. _edgeR: http://www.bioconductor.org/packages/2.3/bioc/html/edgeR.html
+
+</help>
+
+</tool>
+
+