diff read_duplication.xml @ 31:cc5eaa9376d8

Lance's updates
author nilesh
date Wed, 02 Oct 2013 02:20:04 -0400
parents 80f857718ca0
children 580ee0c4bc4e
line wrap: on
line diff
--- a/read_duplication.xml	Thu Jul 11 12:33:27 2013 -0400
+++ b/read_duplication.xml	Wed Oct 02 02:20:04 2013 -0400
@@ -1,32 +1,34 @@
-<tool id="read_duplication" name="Read Duplication">
+<tool id="read_duplication" name="Read Duplication" version="1.1">
 	<description>determines reads duplication rate with sequence-based and mapping-based strategies</description>
 	<requirements>
-		<requirement type="package" version="2.15.1">R</requirement>
+		<requirement type="package" version="2.11.0">R</requirement>
+		<requirement type="package" version="1.7.1">numpy</requirement>
 		<requirement type="package" version="2.3.7">rseqc</requirement>
 	</requirements>
-	<command interpreter="python"> read_duplication.py -i $input -o output -u $upLimit
+	<command> read_duplication.py -i $input -o output -u $upLimit
 	</command>
 	<inputs>
 		<param name="input" type="data" format="bam,sam" label="input bam/sam file" />
 		<param name="upLimit" type="integer" label="Upper Limit of Plotted Duplicated Times (default=500)" value="500" />
 	</inputs>
 	<outputs>
-		<data format="xls" name="outputxls" from_work_dir="output.dup.pos.DupRate.xls"/>
-		<data format="xls" name="outputseqxls" from_work_dir="output.dup.seq.DupRate.xls"/>
-		<data format="r" name="outputr" from_work_dir="output.DupRate_plot.r" />
-		<data format="pdf" name="outputpdf" from_work_dir="output.DupRate_plot.pdf" />
+		<data format="xls" name="outputxls" from_work_dir="output.dup.pos.DupRate.xls" label="${tool.name} on ${on_string} (Position XLS)"/>
+		<data format="xls" name="outputseqxls" from_work_dir="output.dup.seq.DupRate.xls" label="${tool.name} on ${on_string} (Sequence XLS)"/>
+		<data format="r" name="outputr" from_work_dir="output.DupRate_plot.r" label="${tool.name} on ${on_string} (R Script)" />
+		<data format="pdf" name="outputpdf" from_work_dir="output.DupRate_plot.pdf" label="${tool.name} on ${on_string} (PDF)" />
 	</outputs>
+    <stdio>
+        <exit_code range="1:" level="fatal" description="An error occured during execution, see stderr and stdout for more information" />
+        <regex match="[Ee]rror" source="both" description="An error occured during execution, see stderr and stdout for more information" />
+    </stdio>
 	<help>
-.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062
+read_duplication.py
++++++++++++++++++++
 
------
+Two strategies were used to determine reads duplication rate: 
 
-About RSeQC
-+++++++++++
-
-The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation.
-
-The RSeQC package is licensed under the GNU GPL v3 license.
+* Sequence based: reads with exactly the same sequence content are regarded as duplicated reads. 
+* Mapping based: reads mapped to the same genomic location are regarded as duplicated reads. For splice reads, reads mapped to the same starting position and splice the same way are regarded as duplicated reads. 
 
 Inputs
 ++++++++++++++
@@ -45,7 +47,24 @@
 3. output.DupRate_plot.r: R script to generate pdf file
 4. output.DupRate_plot.pdf: graphical output generated from R script
 
-.. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/duplicate.png
+.. image:: http://rseqc.sourceforge.net/_images/duplicate.png
+   :height: 600 px
+   :width: 600 px
+   :scale: 80 %    
+
+-----
+
+About RSeQC 
++++++++++++
+
+The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation.
+
+The RSeQC package is licensed under the GNU GPL v3 license.
+
+.. image:: http://rseqc.sourceforge.net/_static/logo.png
+
+.. _RSeQC: http://rseqc.sourceforge.net/
+
 
 	</help>
 </tool>