Mercurial > repos > bjoern-gruening > augustus

diff augustus.xml @ 5:a4fab0c1ae1a

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author bjoern-gruening
date Sun, 09 Jun 2013 07:54:25 -0400
parents 796814f16b12
children
line wrap: on
line diff
--- a/augustus.xml	Tue Oct 30 06:29:50 2012 -0400
+++ b/augustus.xml	Sun Jun 09 07:54:25 2013 -0400
@@ -1,40 +1,48 @@
-<tool id="augustus" name="Augustus" version="0.2">
-	<description>gene prediction for eukaryotic genomes</description>
+<tool id="augustus" name="Augustus" version="0.3">
+    <description>gene prediction for eukaryotic genomes</description>
     <requirements>
-        <requirement type="package" version="2.6.1">augustus</requirement>
+        <requirement type="package" version="2.7">augustus</requirement>
+        <requirement type="set_environment">AUGUSTUS_SCRIPT_PATH</requirement>
     </requirements>
-    <command>augustus
-        --strand=$strand
-        $noInFrameStop
-        $gff
-        $protein
-        $introns
-        $start
-        $stop
-        $cds
-        $codingseq
-        $singlestrand
-        $input_genome 
-        --genemodel=$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 \$AUGUSTUS_SCRIPT_PATH/extract_features.py
+                #if $protein:
+                    --protein $protein_output
+                #end if
+                #if $codingseq:
+                    --codingseq $codingseq_output
+                #end if
+        #end if
     </command>
-	<inputs>
-		<param name="input_genome" type="data" format="fasta" label="Genome Sequence"/>
-		<param name="noInFrameStop" type="boolean" label="Don't report transcripts with in-frame stop codons. Otherwise, intron-spanning stop codons could occur" truevalue="--noInFrameStop=true" falsevalue="--noInFrameStop=false" checked="false" />
-		<param name="gff" type="boolean" label="GFF formated output, standard is GTF" truevalue="--gff3=on" falsevalue="--gff3=off" checked="false" />
-		<param name="protein" type="boolean" label="Output predicted protein sequences" truevalue="--protein=on" falsevalue="--protein=off" checked="false" />
-		<param name="introns" type="boolean" label="Output predicted intron sequences" truevalue="--introns=on" falsevalue="--introns=off" checked="false" />
-		<param name="start" type="boolean" label="Output predicted start codons" truevalue="--start=on" falsevalue="--start=off" checked="false" />
-		<param name="stop" type="boolean" label="Output predicted stop codons" truevalue="--stop=on" falsevalue="--stop=off" checked="false" />
-		<param name="cds" type="boolean" label="Output CDS region" truevalue="--cds=on" falsevalue="--cds=off" checked="true" />
-		<param name="codingseq" type="boolean" label="Output coding sequence as comment in the output file" truevalue="--codingseq=on" falsevalue="--codingseq=off" checked="false" />
-
-		<param name="singlestrand" type="boolean" label="Predict genes independently on each strand, allow overlapping genes on opposite strands" truevalue="--singlestrand=true" falsevalue="--singlestrand=false" checked="false" />
+    <inputs>
+        <param name="input_genome" type="data" format="fasta" label="Genome Sequence"/>
+        <param name="noInFrameStop" type="boolean" label="Don't report transcripts with in-frame stop codons (--noInFrameStop)" truevalue="--noInFrameStop=true" falsevalue="--noInFrameStop=false" checked="false" help="Otherwise, intron-spanning stop codons could occur" />
+        <param name="singlestrand" type="boolean" label="Predict genes independently on each strand, allow overlapping genes on opposite strands (--singlestrand)" truevalue="--singlestrand=true" falsevalue="--singlestrand=false" checked="false" />
+        <param name="mea" type="boolean" label="Using the maximum expected accuracy approach (--mea)" truevalue="--mea=1" falsevalue="" checked="false" help="MEA is an alternative decoding approach." />
+        <param name="utr" type="boolean" label="Predict the untranslated regions in addition to the coding sequence (--UTR)" truevalue="--UTR=on" falsevalue="--UTR=off" checked="false" help="This currently works only for human, galdieria, toxoplasma and caenorhabditis." />
 
         <param name="organism" label="Model Organism" type="select" multiple="false" format="text" help="Choose a specialised trainingset.">
             <option value="human">Homo sapiens</option>
@@ -42,7 +50,7 @@
             <option value="arabidopsis">Arabidopsis thaliana</option>
             <option value="brugia ">Brugia malayi</option>
             <option value="aedes">Aedes aegypti</option>
-            <option value="tribolium">Tribolium castaneum</option>
+            <option value="tribolium2012">Tribolium castaneum</option>
             <option value="schistosoma">Schistosoma mansoni</option>
             <option value="tetrahymena">Tetrahymena thermophila</option>
             <option value="galdieria">Galdieria sulphuraria</option>
@@ -88,10 +96,14 @@
             <option value="ustilago_maydis">Ustilago maydis</option>
             <option value="yarrowia_lipolytica">Yarrowia lipolytica</option>
             <option value="nasonia">Nasonia vitripennis</option>
-            <option value="tomato ">Solanum lycopersicum</option>
+            <option value="tomato">Solanum lycopersicum</option>
             <option value="chlamydomonas">Chlamydomonas reinhardtii</option>
-            <option value="amphimedon ">Amphimedon queenslandica</option>
-            <option value="pneumocystis ">Pneumocystis jirovecii</option>
+            <option value="amphimedon">Amphimedon queenslandica</option>
+            <option value="pneumocystis">Pneumocystis jirovecii</option>
+            <option value="chicken">Gallus gallus domesticus (chicken)</option>
+            <option value="cacao">Theobroma cacao (cacao)</option>
+            <option value="heliconius_melpomene1">Heliconius melpomene</option>
+            <option value="xenoturbella">Xenoturbella</option>
         </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.">
@@ -106,16 +118,64 @@
             <option value="intronless">intronless</option>
             <option value="atleastone">atleastone</option>
             <option value="exactlyone">exactlyone</option>
+            <option value="bacterium">bacterium (beta version)</option>
         </param>
 
-	</inputs>
-	<outputs>
+        <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="gff" type="boolean" label="GFF formated output, standard is GTF (--gff3)" truevalue="--gff3=on" falsevalue="--gff3=off" checked="false" />
+
+    </inputs>
+    <outputs>
         <data format="gtf" name="output">
             <change_format>
                 <when input="gff" value="--gff3=on" format="gff" />
             </change_format>
         </data>
+        <data format="fasta" name="protein_output">
+            <filter>protein == True</filter>
+        </data>
+        <data format="fasta" name="codingseq_output">
+            <filter>codingseq == True</filter>
+        </data>
     </outputs>
+    <tests>
+        <test>
+            <param name="input_genome" value="human_augustus.fa" ftype="fasta" />
+            <param name="organism" value="human" />
+            <param name="utr" value="--UTR=on" />
+            <output name="output" file="human_augustus_utr-on.gtf" ftype="gtf" lines_diff="2"/>
+        </test>
+        <test>
+            <param name="input_genome" value="human_augustus.fa" ftype="fasta" />
+            <param name="organism" value="human" />
+            <param name="utr" value="--UTR=on" />
+            <param name="gff" value="--gff3=on" />
+            <output name="output" file="human_augustus_utr-on.gff" ftype="gff3" lines_diff="2"/>
+        </test>
+        <test>
+            <param name="input_genome" value="arabidopsis_augustus.fa" ftype="fasta" />
+            <param name="organism" value="arabidopsis" />
+            <param name="singlestrand" value="--singlestrand=true" />
+            <param name="mea" value="--mea=1" />
+            <output name="output" file="arabidopsis_augustus_utr-off_singlestrand-on_mea-on.gtf" ftype="gtf" lines_diff="2"/>
+        </test>
+        <test>
+            <param name="input_genome" value="human_augustus.fa" ftype="fasta" />
+            <param name="organism" value="human" />
+            <param name="protein" value="--protein=on" />
+            <param name="codingseq" value="--codingseq=on" />
+            <param name="introns" value="--introns=on" />
+            <param name="cds" value="--cds=on" />
+            <output name="output" file="human_augustus_protein_codingseq_introns_cds_main.gtf" ftype="gff" lines_diff="2"/>
+            <output name="codingseq_output" file="human_augustus_protein_codingseq_introns_cds_codingseq.fasta" ftype="fasta" />
+            <output name="protein_output" file="human_augustus_protein_codingseq_introns_cds_protein.fasta" ftype="fasta" />
+        </test>
+    </tests>
     <help>
 
 **What it does**
@@ -125,7 +185,7 @@
 sequence. AUGUSTUS may also incorporate hints on the gene structure coming from extrinsic sources
 such as EST, MS/MS, protein alignments and synthenic genomic alignments.
 
------	
+-----
 
 **Parameters**
 
@@ -182,5 +242,5 @@
 Bioinformatics, Vol. 19, Suppl. 2, pages ii215-ii225
 
 
-	</help>
+    </help>
 </tool>