diff tools/blast_rbh/blast_rbh.xml @ 12:661276ad882e draft

Uploaded v0.1.3, uses Biopython for making NR

--- a/tools/blast_rbh/blast_rbh.xml	Thu Aug 14 07:11:59 2014 -0400
+++ b/tools/blast_rbh/blast_rbh.xml	Tue Oct 14 06:53:40 2014 -0400
@@ -1,10 +1,12 @@
-<tool id="blast_reciprocal_best_hits" name="BLAST Reciprocal Best Hits (RBH)" version="0.1.2">
+<tool id="blast_reciprocal_best_hits" name="BLAST Reciprocal Best Hits (RBH)" version="0.1.3">
     <description>from two FASTA files</description>
     <requirements>
-            <requirement type="binary">makeblastdb</requirement>
-            <requirement type="binary">blastp</requirement>
-            <requirement type="binary">blastn</requirement>
-            <requirement type="package" version="2.2.29">blast+</requirement>
+        <requirement type="package" version="1.64">biopython</requirement>
+        <requirement type="python-module">Bio</requirement>
+        <requirement type="binary">makeblastdb</requirement>
+        <requirement type="binary">blastp</requirement>
+        <requirement type="binary">blastn</requirement>
+        <requirement type="package" version="2.2.29">blast+</requirement>
     </requirements>
     <version_command interpreter="python">
 blast_rbh.py --version
@@ -17,6 +19,7 @@
 #else
 -t $seq.prot_type
 #end if
+$make_nr
 -i $identity
 -c $q_cover
 -o "$output"
@@ -61,6 +64,9 @@
         <param name="q_cover" type="float" value="50" min="0" max="100"
 	       label="Minimum percentage query coverage for BLAST matches"
 	       help="Default is 50%, use 0 for no filtering." />
+        <param name="make_nr" type="boolean" checked="false" truevalue="--nr" falsevalue=""
+	       label="Process input FASTA files to collapse identical sequences"
+               help="i.e. First make the input non-redundant" />
     </inputs>
     <outputs>
         <data name="output" format="tabular" label="BLAST RBH: $fasta_a.name vs $fasta_b.name" />
@@ -201,6 +207,13 @@
 can happen following gene duplication, or for (near) identical gene
 duplicates.
 
+The tool can optionally make the FASTA files non-redundant by replacing
+repeated identical sequences with a single representative before building
+the databases and running BLAST.
+
+Finally, the tool can be run using the same FASTA input file to look for
+RBH within the dataset. In this case, self matches are discarded.
+
 .. class:: warningmark
 
 **Note**