# HG changeset patch
# User jjohnson
# Date 1315838588 14400
# Node ID 23f5701549b1a03a52bf0701d1ca1cf88036f104

Uploaded

diff -r 000000000000 -r 23f5701549b1 cd_hit_est.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cd_hit_est.xml	Mon Sep 12 10:43:08 2011 -0400
@@ -0,0 +1,69 @@
+<tool id="cd_hit_est" name="CD-HIT-EST" version="1.0">
+ <description>Cluster a nucleotide dataset into representative sequences</description>
+ <command>
+  cd-hit-est -i $fasta_in -o rep_seq -c $similarity -n $wordsize $strand
+ </command>
+ <inputs>
+  <param name="fasta_in" type="data" format="fasta" label="EST Sequences to cluster"/>
+  <param name="similarity" type="float" value="0.9"  label="similarity threshold: .75 - 1.0, default is .9">
+    <validator type="in_range" message="sequence similarity threshold should be .75 - 1.0" min=".75" max="1.0"/>
+  </param>
+  <param name="wordsize" type="integer" value="8"  label="word size">
+    <help> Suggested word size:
+          8,9,10 for thresholds 0.90 ~ 1.0
+          7      for thresholds 0.88 ~ 0.9
+          6      for thresholds 0.85 ~ 0.88
+          5      for thresholds 0.80 ~ 0.85
+          4      for thresholds 0.75 ~ 0.8 
+    </help>
+    <validator type="in_range" message="word size should be between 4 and 10" min="4" max="10"/>
+  </param>
+  <param name="strand" type="boolean" truevalue="-r 1" falsevalue="" checked="false" label="Compare both strands"/>
+ </inputs>
+ <outputs>
+  <data format="txt" name="clusters_out" label="${tool.name} on ${on_string}: clusters" from_work_dir="rep_seq.clstr"/>
+  <data format="fasta" name="fasta_out" label="${tool.name} on ${on_string}: representatives.fasta" from_work_dir="rep_seq"/>
+ </outputs>
+ <requirements>
+  <requirement type="binary">cd-hit-est</requirement>
+ </requirements>
+ <tests>
+ </tests>
+ <help>
+**CD-HIT-EST**
+
+CD-HIT_ stands for Cluster Database at High Identity with Tolerance. The program (cd-hit) takes a fasta format sequence database as input and produces a set of 'non-redundant' (nr) representative sequences as output. In addition cd-hit outputs a cluster file, documenting the sequence 'groupies' for each nr sequence representative. The idea is to reduce the overall size of the database without removing any sequence information by only removing 'redundant' (or highly similar) sequences. This is why the resulting database is called non-redundant (nr). Essentially, cd-hit produces a set of closely related protein families from a given fasta sequence database.
+
+.. _CD-HIT: http://www.bioinformatics.org/cd-hit/
+
+------
+
+**Inputs**
+
+cd-hit-est requires a fasta dataset as input.
+ 
+------
+
+**Outputs**
+
+A fasta datasets containing representative sequences.
+
+A text file listing the mapping of sequences to the representative sequences::
+
+	>Cluster 0
+	0 2799aa, >PF04998.6|RPOC2_CHLRE/275-3073... *
+	>Cluster 1
+	0 2214aa, >PF06317.1|Q6Y625_9VIRU/1-2214... at 80%
+	1 2215aa, >PF06317.1|O09705_9VIRU/1-2215... at 84%
+	2 2217aa, >PF06317.1|Q6Y630_9VIRU/1-2217... *
+	3 2216aa, >PF06317.1|Q6GWS6_9VIRU/1-2216... at 84%
+	4 527aa, >PF06317.1|Q67E14_9VIRU/6-532... at 63%
+	>Cluster 2
+	0 2202aa, >PF06317.1|Q6UY61_9VIRU/8-2209... at 60%
+	1 2208aa, >PF06317.1|Q6IVU4_JUNIN/1-2208... *
+	2 2207aa, >PF06317.1|Q6IVU0_MACHU/1-2207... at 73%
+	3 2208aa, >PF06317.1|RRPO_TACV/1-2208... at 69%
+
+
+ </help>
+</tool>