diff tools/fasta_tools/fasta_concatenate_by_species.xml @ 0:9071e359b9a3

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/fasta_tools/fasta_concatenate_by_species.xml	Fri Mar 09 19:37:19 2012 -0500
@@ -0,0 +1,72 @@
+<tool id="fasta_concatenate0" name="Concatenate" version="0.0.0">
+  <description>FASTA alignment by species</description>
+  <command interpreter="python">fasta_concatenate_by_species.py $input1 $out_file1</command>
+  <inputs>
+    <param name="input1" type="data" format="fasta" label="FASTA alignment"/>
+  </inputs>
+  <outputs>
+    <data name="out_file1" format="fasta"/>
+  </outputs>
+  <tests>
+    <test>
+      <param name="input1" value="cf_maf2fasta.dat" />
+      <output name="out_file1" file="fasta_concatenate_out.fasta" />
+    </test>
+  </tests>
+  <help>
+  
+**What it does**
+  
+This tools attempts to parse FASTA headers to determine the species for each sequence in a multiple FASTA alignment.
+It then linearly concatenates the sequences for each species in the file, creating one sequence per determined species.
+
+-------
+
+**Example**
+
+Starting FASTA::
+  
+  >hg18.chr1(+):10016339-10016341|hg18_0
+  GT
+  >panTro2.chr1(+):10195380-10195382|panTro2_0
+  GT
+  >rheMac2.chr1(+):13119747-13119749|rheMac2_0
+  GT
+  >mm8.chr4(-):148269679-148269681|mm8_0
+  GT
+  >canFam2.chr5(+):66213635-66213637|canFam2_0
+  GT
+  
+  >hg18.chr1(-):100323677-100323679|hg18_1
+  GT
+  >panTro2.chr1(-):101678671-101678673|panTro2_1
+  GT
+  >rheMac2.chr1(-):103154011-103154013|rheMac2_1
+  GT
+  >mm8.chr3(+):116620616-116620618|mm8_1
+  GT
+  >canFam2.chr6(+):52954092-52954094|canFam2_1
+  GT
+  
+
+
+becomes::
+  
+  >hg18
+  GTGT
+  >panTro2
+  GTGT
+  >rheMac2
+  GTGT
+  >mm8
+  GTGT
+  >canFam2
+  GTGT
+
+
+.. class:: warningmark 
+
+ This tool will only work properly on files with Galaxy style FASTA headers.
+
+</help>
+</tool>
\ No newline at end of file