diff read_duplication.xml @ 3:71ed55a3515a draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rseqc commit 37fb1988971807c6a072e1afd98eeea02329ee83
author iuc
date Tue, 14 Mar 2017 10:22:57 -0400
parents f92b87abef3d
children d7f6b3653d84
line wrap: on
line diff
--- a/read_duplication.xml	Thu Jul 18 11:01:08 2013 -0500
+++ b/read_duplication.xml	Tue Mar 14 10:22:57 2017 -0400
@@ -1,50 +1,63 @@
-<tool id="read_duplication" name="Read Duplication">
-	<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="2.3.7">rseqc</requirement>
-	</requirements>
-	<command interpreter="python"> read_duplication.py -i $input -o output -u $upLimit
-	</command>
-	<inputs>
-		<param name="input" type="data" format="bam,sam" label="input bam/sam file" />
-		<param name="upLimit" type="integer" label="Upper Limit of Plotted Duplicated Times (default=500)" value="500" />
-	</inputs>
-	<outputs>
-		<data format="xls" name="outputxls" from_work_dir="output.dup.pos.DupRate.xls"/>
-		<data format="xls" name="outputseqxls" from_work_dir="output.dup.seq.DupRate.xls"/>
-		<data format="r" name="outputr" from_work_dir="output.DupRate_plot.r" />
-		<data format="pdf" name="outputpdf" from_work_dir="output.DupRate_plot.pdf" />
-	</outputs>
-	<tests>
-		<test>
-			<param name="input" value="Pairend_StrandSpecific_51mer_Human_hg19.bam" />
-			<output name="outputxls" file="readdupout.pos.DupRate.xls" />
-			<output name="outputseqxls" file="readdupout.seq.DupRate.xls" />
-			<output name="outputr" file="readdupout.DupRate_plot.r" />
-			<output name="outputpdf" file="readdupout.DupRate_plot.pdf" />
-		</test>
-	</tests>
-	<help>
-.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062
+<tool id="rseqc_read_duplication" name="Read Duplication" version="@WRAPPER_VERSION@">
+    <description>determines reads duplication rate with sequence-based and mapping-based strategies</description>
+
+    <macros>
+        <import>rseqc_macros.xml</import>
+    </macros>
+
+    <expand macro="requirements" />
+
+    <expand macro="stdio" />
+
+    <version_command><![CDATA[read_duplication.py --version]]></version_command>
+
+    <command><![CDATA[
+        read_duplication.py -i '${input}' -o output -u ${upLimit} -q ${mapq}
+        ]]>
+    </command>
+
+    <inputs>
+        <expand macro="bam_sam_param" />
+        <param name="upLimit" type="integer" label="Upper Limit of Plotted Duplicated Times (default=500)" value="500" help="(--up-limit)"/>
+        <expand macro="mapq_param" />
+        <expand macro="rscript_output_param" />
+    </inputs>
 
------
+    <outputs>
+        <expand macro="pdf_output_data" filename="output.DupRate_plot.pdf" />
+        <data format="xls" name="outputxls" from_work_dir="output.pos.DupRate.xls" label="${tool.name} on ${on_string} (Position xls)"/>
+        <data format="xls" name="outputseqxls" from_work_dir="output.seq.DupRate.xls" label="${tool.name} on ${on_string} (Sequence xls)"/>
+        <expand macro="rscript_output_data" filename="output.DupRate_plot.r" />
+    </outputs>
 
-About RSeQC
-+++++++++++
+    <tests>
+        <test>
+            <param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam" />
+            <param name="rscript_output" value="true" />
+            <output name="outputxls" file="output.pos.DupRate.xls" />
+            <output name="outputseqxls" file="output.seq.DupRate.xls" />
+            <output name="outputr" file="output.DupRate_plot.r" />
+            <output name="outputpdf" file="output.DupRate_plot.pdf" compare="sim_size" />
+        </test>
+    </tests>
 
-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.
+    <help><![CDATA[
+read_duplication.py
++++++++++++++++++++
 
-The RSeQC package is licensed under the GNU GPL v3 license.
+Two strategies were used to determine reads duplication rate:
+
+* 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
 ++++++++++++++
 
 Input BAM/SAM file
-	Alignment file in BAM/SAM format.
+    Alignment file in BAM/SAM format.
 
 Upper Limit of Plotted Duplicated Times (default=500)
-	Only used for plotting.
+    Only used for plotting.
 
 Output
 ++++++++++++++
@@ -54,7 +67,16 @@
 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:: $PATH_TO_IMAGES/duplicate.png
+   :height: 600 px
+   :width: 600 px
+   :scale: 80 %
+
+@ABOUT@
 
-	</help>
+]]>
+    </help>
+
+    <expand macro="citations" />
+
 </tool>