diff mytools/dreme.xml @ 0:39217fa39ff2

Uploaded
author xuebing
date Tue, 13 Mar 2012 23:34:52 -0400
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/mytools/dreme.xml	Tue Mar 13 23:34:52 2012 -0400
@@ -0,0 +1,50 @@
+<tool id="dreme" name="DREME">
+  <description>short motif discovery</description>
+  <command interpreter="python">/Users/xuebing/bin/dreme.py -p $input -png     -e $ethresh
+    #if $background_select.bg_select == "fromfile":
+        -n "${bgfile}"
+    #end if
+
+  &amp;&amp; mv dreme_out/dreme.html ${html_outfile}
+  
+  &amp;&amp; mv dreme_out/dreme.txt ${txt_outfile}
+
+  &amp;&amp; mv dreme_out/dreme.xml ${xml_outfile}
+  
+  &amp;&amp; rm -rf dreme_out
+  
+  </command>
+  <inputs>
+      <param name="input" type="data" format="fasta" label="Sequence file (FASTA)"/>      
+     <conditional name="background_select">
+    	<param name="bg_select" type="select" label="Background sequence" >
+		<option value="shuffle" selected="true">shuffle the orignal sequence</option>
+		<option value="fromfile">load from file</option>
+	    </param>
+	    <when value="fromfile">
+		    <param name="bgfile" type="data" format="fasta" label="Background sequence file (FASTA)"/>
+	    </when>
+    </conditional>
+          
+      <param name="ethresh" size="10" type="float" value="0.05" label="E-value threshold"/>
+  </inputs>
+  <outputs>
+
+    <data format="xml" name="xml_outfile" label="${tool.name} on ${on_string} (xml)"/>
+    <data format="txt" name="txt_outfile" label="${tool.name} on ${on_string} (motif)"/>
+    <data format="html" name="html_outfile" label="${tool.name} on ${on_string} (html)"/>    
+  </outputs>
+  <help>
+
+**What it does**
+
+http://meme.sdsc.edu/meme/doc/dreme.html
+
+DREME (Discriminative Regular Expression Motif Elicitation) finds relatively short motifs (up to 8 bases) fast, and can perform discriminative motif discovery if given a negative set, consisting of sequences unlikely to contain a motif of interest that is however likely to be found in the main ("positive") sequence set. If you do not provide a negative set the program shuffles the positive set to provide a background (in the role of the negative set).
+
+The input to DREME is one or two sets of DNA sequences. The program uses a Fisher Exact Test to determine significance of each motif found in the postive set as compared with its representation in the negative set, using a significance threshold that may be set on the command line.
+
+DREME achieves its high speed by restricting its search to regular expressions based on the IUPAC alphabet representing bases and ambiguous characters, and by using a heuristic estimate of generalised motifs' statistical significance. 
+
+  </help>
+</tool>