diff augustus.xml @ 2:a77a4e9921e0 draft

Uploaded
author bgruening
date Wed, 06 May 2015 14:31:02 -0400
parents e2b822d7408f
children f5075dee9d6b
line wrap: on
line diff
--- a/augustus.xml	Thu Dec 05 09:44:17 2013 -0500
+++ b/augustus.xml	Wed May 06 14:31:02 2015 -0400
@@ -3,9 +3,15 @@
     <parallelism method="multi" split_inputs="input_genome" split_mode="to_size" split_size="10" merge_outputs="output,protein_output,codingseq_output"></parallelism>
     <requirements>
         <requirement type="package" version="2.7">augustus</requirement>
-        <requirement type="set_environment">AUGUSTUS_SCRIPT_PATH</requirement>
     </requirements>
+    <stdio>
+        <exit_code range="1:" />
+        <exit_code range=":-1" />
+        <regex match="Error:" />
+        <regex match="Exception:" />
+    </stdio>
     <command>
+<![CDATA[
         ## please set export AUGUSTUS_CONFIG_PATH=/path_to_augustus/augustus/config
         ## or use the --AUGUSTUS_CONFIG_PATH=path if you are not installing through the toolshed
         ## Augustus writes the protein and coding sequences as comment into the gff/gtf file an external script is used to extract the sequences into additional files
@@ -14,7 +20,7 @@
             --strand=$strand
             $noInFrameStop
             $gff
-            
+
             #if 'protein' in str($outputs).split(','):
                 --protein=on
             #else:
@@ -26,7 +32,7 @@
             #else:
                 --codingseq=off
             #end if
-            
+
             #if 'introns' in str($outputs).split(','):
                 --introns=on
             #else:
@@ -58,9 +64,9 @@
             --genemodel=$genemodel
             --species=$organism
             ##--outfile=$output
-        | tee $output 
+        | tee $output
         #if 'protein' in str($outputs).split(',') or 'codingseq' in str($outputs).split(','):
-            | python \$AUGUSTUS_SCRIPT_PATH/extract_features.py
+            | python $__tool_directory__/extract_features.py
                 #if 'protein' in str($outputs).split(','):
                     --protein $protein_output
                 #end if
@@ -68,6 +74,7 @@
                     --codingseq $codingseq_output
                 #end if
         #end if
+]]>
     </command>
     <inputs>
         <param name="input_genome" type="data" format="fasta" label="Genome Sequence"/>
@@ -136,13 +143,13 @@
             <option value="cacao">Theobroma cacao (cacao)</option>
             <option value="heliconius_melpomene1">Heliconius melpomene</option>
             <option value="xenoturbella">Xenoturbella</option>
-        </param> 
+        </param>
 
         <param name="strand" type="select" multiple="false" format="text" help="Report predicted genes on both strands, just the forward or just the backward strand.">
             <option value="both">both</option>
             <option value="forward">forward</option>
             <option value="backward">backward</option>
-        </param> 
+        </param>
 
         <param name="genemodel" label="Gene Model" type="select" multiple="false" format="text" help="Gene Model to predict, for more information please refere to the help.">
             <option value="complete">complete</option>
@@ -213,6 +220,7 @@
         </test>
     </tests>
     <help>
+<![CDATA[
 
 **What it does**
 
@@ -271,12 +279,9 @@
     scaffold1|size1992969	AUGUSTUS	stop_codon	19380	19382	.	+	0	transcript_id "g6.t1"; gene_id "g6";
 
 
-**References**
-
-Mario Stanke and Stephan Waack (2003) 
-Gene Prediction with a Hidden-Markov Model and a new Intron Submodel. 
-Bioinformatics, Vol. 19, Suppl. 2, pages ii215-ii225
-
-
+]]>
     </help>
+    <citations>
+        <citation type="doi">10.1093/bioinformatics/btg1080</citation>
+    </citations>
 </tool>