diff augustus.xml @ 1:3c5116448979 draft

Uploaded

--- a/augustus.xml	Thu Jun 06 09:52:32 2013 -0400
+++ b/augustus.xml	Thu Jun 06 12:20:31 2013 -0400
@@ -3,26 +3,35 @@
     <requirements>
         <requirement type="package" version="2.7">augustus</requirement>
     </requirements>
-    <command>augustus
-        --strand=$strand
-        $noInFrameStop
-        $gff
-        $protein
-        $introns
-        $start
-        $stop
-        $cds
-        $codingseq
-        $singlestrand
-        $input_genome
-        $mea
-        $utr
-        --genemodel=$genemodel
-        --species=$organism
-        --outfile=$output
+    <command>
+        ## 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
 
-        #please set export AUGUSTUS_CONFIG_PATH=/path_to_augustus/augustus/config
-        #or use the --AUGUSTUS_CONFIG_PATH=path switch
+        augustus
+            --strand=$strand
+            $noInFrameStop
+            $gff
+            $protein
+            $introns
+            $start
+            $stop
+            $cds
+            $codingseq
+            $singlestrand
+            $input_genome
+            $mea
+            $utr
+            --genemodel=$genemodel
+            --species=$organism
+            ##--outfile=$output
+        | tee $output 
+        #if $protein or $codingseq:
+            | python extract_features.py 
+                #if $protein:
+                    --protein $protein_output 
+                #if $codingseq:
+                    --codingseq $codingseq_output
 
     </command>
     <inputs>
@@ -109,12 +118,12 @@
             <option value="bacterium">bacterium (beta version)</option>
         </param>
 
-        <param name="protein" type="boolean" label="Output predicted protein sequences (--protein)" truevalue="--protein=on" falsevalue="--protein=off" checked="false" />
+        <param name="protein" type="boolean" label="Output predicted protein sequences (--protein)" truevalue="--protein=on" falsevalue="--protein=off" checked="true" />
+        <param name="codingseq" type="boolean" label="Output coding sequence as comment in the output file (codingseq)" truevalue="--codingseq=on" falsevalue="--codingseq=off" checked="true" />
         <param name="introns" type="boolean" label="Output predicted intron sequences (--introns)" truevalue="--introns=on" falsevalue="--introns=off" checked="false" />
         <param name="start" type="boolean" label="Output predicted start codons (--start)" truevalue="--start=on" falsevalue="--start=off" checked="false" />
         <param name="stop" type="boolean" label="Output predicted stop codons (--stop)" truevalue="--stop=on" falsevalue="--stop=off" checked="false" />
         <param name="cds" type="boolean" label="Output CDS region (--cds)" truevalue="--cds=on" falsevalue="--cds=off" checked="true" />
-        <param name="codingseq" type="boolean" label="Output coding sequence as comment in the output file (codingseq)" truevalue="--codingseq=on" falsevalue="--codingseq=off" checked="false" />
         <param name="gff" type="boolean" label="GFF formated output, standard is GTF (--gff3)" truevalue="--gff3=on" falsevalue="--gff3=off" checked="false" />
 
     </inputs>
@@ -124,6 +133,12 @@
                 <when input="gff" value="--gff3=on" format="gff" />
             </change_format>
         </data>
+        <data format="fasta" name="protein_output">
+            <filter>protein == "--protein=on"</filter>
+        </data>
+        <data format="fasta" name="codingseq_output">
+            <filter>codingseq == "--codingseq=on"</filter>
+        </data>
     </outputs>
     <tests>
         <test>