--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/GALAXY_FILES/tools/EMBER/PreProcess_Expression_Data.xml	Wed Feb 29 15:03:33 2012 -0500
@@ -0,0 +1,76 @@
+<tool id="prep_data" name="PreProcess Expression Data" version="1.3">
+  <description>Combines gene expression data</description>
+  <command interpreter="perl">PreProcess_Expression_Data.pl -i $data -c $compslist -a $annot -o $output -p $thresh -l $log -v n</command>
+  <inputs>
+    <param format="txt" name="data" type="data" label="Expression data"/>
+    <param format="txt" name="compslist" type="data" label="Comparison list"/>
+    <param format="txt" name="annot" type="data" label="Annotation file"/>
+    <param name="thresh" type="float" min="0" max="1" label="Percentile threshold" value="0.63" optional="true"/>
+    <param name="log" type="select" label="Log transform data?">
+        <option value="n" selected="true">No</option>
+        <option value="y">Yes</option>
+    </param>
+  </inputs>
+  <outputs>
+    <data format="txt" name="output"/>
+  </outputs>
+
+  <tests>
+    <test>
+      <param name="data" value="EMBER/expression.txt"/>
+      <param name="compslist" value="EMBER/comparisons_list.txt"/>
+      <param name="annot" value="EMBER/annotation.txt"/>
+      <param name="thresh" value="0.63"/>
+      <param name="log" value="n"/>
+      <output name="output" file="EMBER/expression_profiles.txt"/>
+    </test>
+  </tests>
+
+  <help>
+
+This tool discretizes the gene expression data and adds genomic annotations.
+
+More options for the EMBER tools (especially for the main program, EMBER, including searching for multiple expression patterns) are available in the command line version, available at http://dinner-group.uchicago.edu/downloads.html. That package also includes test data and sample outputs.
+
+When using any of the EMBER tools, please cite: M Maienschein-Cline, J Zhou, KP White, R Sciammas, and AR Dinner. Discovering transcription factor regulatory targets using gene expression and binding data. *Bioinformatics*, 28:206-213 (2012).
+
+-----
+
+Description of inputs:
+
+*Expression Data*:
+
+   Microarray data, with data from N experiments (and at least 2 replicates per condition).
+   
+   *Format (N+1 columns)*: [ID] [expt 1 value] [expt 2 value] ... [expt N value]
+
+   IMPORTANT: the first line should be a title line, first field "#ID", and subsequent fields giving the condition/replicate for each column, i.e.,
+
+      #ID [condition]#[replicate]...
+
+   where [condition] matches the values in the Comparison List, and replicate tells which number the file is. [condition] and [replicate] are delimited by a "#" (so don't use that character in the condition name).
+
+*Comparison List*:
+
+   List of behavior dimension definitions. [condition] should match the names in the expression data list.
+
+   *Format (2 columns)*: [condition1] [condition2]
+
+*Annotation File*:
+
+   Gives the genomic coordinates of each probe set.
+
+   *Format (6 columns)*: [probe id] [gene name] [chromosome] [start] [end] [strand]
+
+*Percentile Threshold* (p):
+
+   Used to eliminate genes that are consistently expressed at a very low level. All data are concatenated into one list, and the pth percentile of that list is taken as the thresold. Then a probe set is removed if its value is less than the threshold in ALL conditions.
+
+   p = 1.0 means all probes are retained, p = 0.0 means none are. However, note that this does NOT necessarily imply that 0.63 means 63% of probe sets are retained.
+
+*Log Transform*: whether or not to take the log of the data before discretization.
+
+  </help>
+
+</tool>
+