diff chemfp_clustering/butina_clustering.xml @ 0:354d3c6bb894 draft

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/chemfp_clustering/butina_clustering.xml	Thu Aug 15 03:27:06 2013 -0400
@@ -0,0 +1,96 @@
+<tool id="ctb_chemfp_butina_clustering" name="Taylor-Butina Clustering" version="0.1">
+    <description>of molecular fingerprints</description>
+    <requirements>
+        <requirement type="package" version="1.1p1">chemfp</requirement>
+        <requirement type="package" version="2.3.2">openbabel</requirement>
+    </requirements>
+    <command interpreter='python'>
+        butina_clustering.py 
+            -i $infile 
+            -t $threshold 
+            -o $outfile 
+            -p 4
+    </command>
+    <inputs>
+        <param name="infile" type="data" format="fps" label="Finperprint dataset" help="Dataset missing? See TIP below"/>
+        <param name='threshold' type='float' value='0.8'/>
+    </inputs>
+    <outputs>
+        <data format="tabular" name="outfile" label="${tool.name} on ${on_string}"/>
+    </outputs>
+    <tests>
+        <test>
+            <param name="infile" ftype="fps" value="q.fps"/>
+            <param name='threshold' value='0.8' ></param>
+            <output name="outfile" ftype="tabular"  file='Taylor-Butina_Clustering_on_data_q.txt'/>
+        </test>
+    </tests>
+<help>
+
+
+.. class:: infomark
+
+**What this tool does**
+
+Unsupervised non-hierarchical clustering method based on the Taylor-Butina algorithm, which guarantees that every cluster contains molecules which are within a distance cutoff of the central molecule. This tool is based on the chemfp_ project.
+
+.. _chemfp: http://chemfp.com/
+
+-----
+
+.. class:: infomark
+
+**Input**
+
+| Molecular fingerprints in FPS format.
+| Open Babel Fastsearch index is not supported.
+
+* Example::
+
+	-  fingerprints in FPS format
+
+		#FPS1
+		#num_bits=881
+		#type=CACTVS-E_SCREEN/1.0 extended=2
+		#software=CACTVS/unknown
+		#source=/home/mohammed/galaxy-central/database/files/000/dataset_423.dat
+		#date=2012-02-09T13:20:37
+		07ce04000000000000000000000000000080060000000c000000000000001a800f0000780008100000701487e960cc0bed3248000580644626004101b4844805901b041c2e
+		19511e45039b8b2926101609401b13e40800000000000100200000040080000010000002000000000000	55169009
+		07ce04000000000000000000000000000080060000000c000000000000001a800f0000780008100000701087e960cc0bed3248000580644626004101b4844805901b041c2e
+		19111e45039b8b2926105609401313e40800000000000100200000040080000010000002000000000000	55079807
+		........
+
+	- Tanimoto threshold : 0.8 (between 0 and 1)
+
+-----
+
+.. class:: infomark
+
+**Output**
+
+* Example::
+
+	0 true singletons
+	=> 
+
+	0 false singletons
+	=> 
+
+	1 clusters
+	55091849 has 12 other members
+	=> 6499094 6485578 55079807 3153534 55102353 55091466 55091416 6485577 55169009 55091752 55091467 55168823
+
+-----
+
+.. class:: infomark
+
+**Cite**
+
+The chemfp_ project from Andrew Dalke!
+
+.. _chemfp: http://chemfp.com/
+
+ </help>
+
+</tool>