changeset 7:015db5db052c

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/metagene_readthrough.xml	Mon Oct 20 11:07:49 2014 -0400
@@ -0,0 +1,60 @@
+<tool id="readthrough_analysis" name="Stop_supp">
+	<description> Analyse Ribo-seq alignment to detect readthrough events</description>
+	<requirements>
+	    <requirement type="package">samtools</requirement>
+	    <requirement type="python-module">HTseq</requirement>
+	    <requirement type="python-module">pysam</requirement>
+	    <requirement type="python-module">csv</requirement>
+	    <requirement type="python-module">Bio</requirement>
+	</requirements>
+	<command interpreter="python"> 
+		metagene_readthrough.py --gff $gff --fasta $fasta --bam $mapping --dirout=$output,$output.files_path
+
+	</command>
+
+	<inputs>
+		<param name="gff" type="data" label="References Input Annotation File (gff)" format="gff" />
+		<param name="fasta" type="data" label="Reference in fasta format" format="fasta" />
+		<param name="mapping" type="data" label="Bam Input File" format="bam" />
+	</inputs>
+            
+	<outputs>
+		<data format="html"  name="output" label="[RP]Readthrough results on  ${on_string}"/>
+	</outputs>
+        
+	<help>
+Summary
+-------          
+This tool uses Ribo-seq data (bam file) to extract potential genes with readthrough events from a reference annotation file (GFF3).
+
+C-terminal protein extensions were identified as previously described (Dunn J.G. and al, 2013). Only uniquely mapped footprints whose size is in the range 25 to 34 are considered.
+A gene is read-though if :
+
+ i) It is covered by more than 128 footprints.
+
+ ii) There are footprints after stop codon.
+
+ iii) There are footprints overlapping the next in frame stop codon.
+
+ iv) There is not Methionine in the next five codons downstream the official stop codon of CDS.
+
+ v) The coverage is homogeneous within the extension.
+
+Stop codon readthrough was estimated by calculating a ratio between footprints in the C-terminal extension and in the CDS. Ribosome density footprints were estimated in RPKM (reads per kilobase per million). 
+To control variability due to stop codon peaks, footprints mapping to stop codons are excluded to RPKM computing.
+
+Output 
+------- 
+This tool produces html file with plots for each readthrough gene.
+
+
+Dependances
+------------
+
+.. class:: warningmark
+
+This tool depends on Python (>=2.7) and following packages : numpy 1.8.0, Biopython 1.58, matplotlib 1.3.1, HTSeq and pysam. Samtools is used for bam manipulation.
+
+	</help>
+</tool>
+