--- a/extract_duplicates.xml	Tue Sep 01 07:49:47 2015 -0400
+++ b/extract_duplicates.xml	Tue Sep 01 08:34:27 2015 -0400
@@ -1,11 +1,12 @@
 <tool id="extract_duplicates" name="Extract Duplicates" version="1.1.0">
   <description>to a new dataset</description>
   <command interpreter="bash">
-    extract_duplicates.sh $input $column $header $out_file
+    extract_duplicates.sh $input $column $header "$regex_filter" $out_file
   </command>
   <inputs>
     <param format="tabular" name="input" type="data" label="Input"/>
 		<param name="column" label="on column" type="data_column" data_ref="input" accept_default="true" />
+		<param name="regex_filter" type="text" label="Filter to sanitize the column" value="\\(.*" size='70'/>
 		<param name="header" type="boolean" checked="False" truevalue="yes" falsevalue="no" label="Input file has a header?" help="if checked, the first line of the input will be treated as a header"/>
   </inputs>
   <outputs>