diff filter/ob_remDuplicates.xml @ 0:527ecd2fc500 draft

Uploaded
author bgruening
date Thu, 15 Aug 2013 03:25:06 -0400
parents
children 125da3a296ca
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/filter/ob_remDuplicates.xml	Thu Aug 15 03:25:06 2013 -0400
@@ -0,0 +1,86 @@
+<tool id="ctb_remDuplicates" name="Remove duplicated molecules" version="1.0">
+    <description></description>
+    <parallelism method="multi" split_inputs="infile" split_mode="to_size" split_size="10000" shared_inputs="" merge_outputs="outfile"></parallelism>
+    <requirements>
+        <requirement type="package" version="2.3.2">openbabel</requirement>
+    </requirements>
+  <command>
+    obabel
+      -i"${infile.ext}"
+       "${infile}"
+      -ocopy
+      --unique "${descriptor}"
+      -O "${outfile}"
+      -e
+      2>&#38;1
+  </command>
+  <inputs>
+    <param name="infile" type="data" format="sdf,mol,mol2,cml,inchi,smi" label="Molecular input file"/>
+    <param name="descriptor" type="select" label="Select descriptor for molecule comparison">
+      <option value="inchi" checked="True">InChI (default)</option>
+      <option value="cansmi">Canonical SMILES</option>
+      <option value="cansmiNS">Canonical SMILES (without stereo)</option>
+    </param>
+  </inputs>
+  <outputs>
+    <data format_source="infile" name="outfile"/>
+  </outputs>
+  <tests>
+    <test>
+        <param name="infile" ftype="smi" value="2_mol.smi"/>
+            <param name="descriptor" value="inchi" />
+        <output name="outfile" ftype="smi" file="ob_remDuplicates_on_2_mol.smi" />
+    </test>
+  </tests>
+  <help>
+
+.. class:: infomark
+
+**What this tool does**
+
+Filters a library of compounds and removes duplicated molecules.
+
+-----
+
+.. class:: warningmark
+
+**Hint**
+
+Comparison based on Canonical SMILES without stereochemistry may be useful in cases where this information is not crucial for library preparation. Several VS tools will automatically generate stereoisomeric forms.
+
+-----
+
+.. class:: infomark
+
+**Input**
+
+| - `InChI`_
+| - `SMILES Format`_
+
+.. _InChI: http://www.iupac.org/home/publications/e-resources/inchi.html
+.. _SMILES Format: http://en.wikipedia.org/wiki/Simplified_molecular_input_line_entry_specification
+
+-----
+
+.. class:: infomark
+
+**Output** 
+
+Same as input format.
+
+-----
+
+.. class:: infomark
+
+**Cite**
+
+N M O'Boyle, M Banck, C A James, C Morley, T Vandermeersch, and G R Hutchison - `Open Babel: An open chemical toolbox.`_
+
+.. _`Open Babel: An open chemical toolbox.`: http://www.jcheminf.com/content/3/1/33
+
+`Open Babel`_
+
+.. _`Open Babel`: http://openbabel.org/wiki/Main_Page
+
+  </help>
+</tool>