comparison geneBody_coverage.xml @ 49:6b33e31bda10 draft

Uploaded tar based on https://github.com/lparsons/galaxy_tools/tree/master/tools/rseqc 1a3c419bc0ded7c40cb2bc3e7c87bfb01ddfeba2
author lparsons
date Thu, 16 Jul 2015 17:43:43 -0400
parents 2e6190c29c54
children f242ee103277
comparison
equal deleted inserted replaced
48:2e6190c29c54 49:6b33e31bda10
1 <tool id="rseqc_geneBody_coverage" name="Gene Body Converage (BAM)" version="2.4"> 1 <tool id="rseqc_geneBody_coverage" name="Gene Body Converage (BAM)" version="2.4galaxy1">
2 <description> 2 <description>
3 Read coverage over gene body. 3 Read coverage over gene body.
4 </description> 4 </description>
5
6 <macros>
7 <import>rseqc_macros.xml</import>
8 </macros>
9
5 <requirements> 10 <requirements>
6 <requirement type="package" version="3.0.3">R</requirement> 11 <expand macro="requirement_package_r" />
7 <requirement type="package" version="1.7.1">numpy</requirement> 12 <expand macro="requirement_package_numpy" />
8 <requirement type="package" version="2.4">rseqc</requirement> 13 <expand macro="requirement_package_rseqc" />
9 </requirements> 14 </requirements>
10 <command> 15
16 <expand macro="stdio" />
17
18 <version_command><![CDATA[geneBody_coverage.py --version]]></version_command>
19
20 <command><![CDATA[
11 #set $safename = ''.join(c in '_0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ' and c or '_' for c in $input.display_name) 21 #set $safename = ''.join(c in '_0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ' and c or '_' for c in $input.display_name)
12 #set $fname = "d1_" + str($safename) + ".bam" 22 #set $fname = "d1_" + str($safename) + ".bam"
13 ln -s '${input}' '${fname}' &amp;&amp; 23 ln -s '${input}' '${fname}' &&
14 ln -s '${input.metadata.bam_index}' '${fname}.bai' &amp;&amp; 24 ln -s '${input.metadata.bam_index}' '${fname}.bai' &&
15 echo '${fname}' > input_list.txt &amp;&amp; 25 echo '${fname}' > input_list.txt &&
16 #for $i, $additional_input in enumerate($additionalinputs): 26 #for $i, $additional_input in enumerate($additionalinputs):
17 #set $index = $i+2 27 #set $index = $i+2
18 #set $safename = ''.join(c in '_0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ' and c or '_' for c in $additional_input.file.display_name) 28 #set $safename = ''.join(c in '_0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ' and c or '_' for c in $additional_input.file.display_name)
19 #set $fname = 'd' + str($index) + '_' + str($safename) + ".bam" 29 #set $fname = 'd' + str($index) + '_' + str($safename) + ".bam"
20 ln -s '$additional_input.file' '${fname}' &amp;&amp; 30 ln -s '$additional_input.file' '${fname}' &&
21 ln -s '$additional_input.file.metadata.bam_index' '${fname}.bai' &amp;&amp; 31 ln -s '$additional_input.file.metadata.bam_index' '${fname}.bai' &&
22 echo '${fname}' >> input_list.txt &amp;&amp; 32 echo '${fname}' >> input_list.txt &&
23 #end for 33 #end for
24 geneBody_coverage.py -i input_list.txt -r $refgene --minimum_length $minimum_length -o output 34 geneBody_coverage.py -i input_list.txt -r $refgene --minimum_length $minimum_length -o output
35 ]]>
25 </command> 36 </command>
26 <stdio> 37
27 <exit_code range="1:" level="fatal" description="An error occured during execution, see stderr and stdout for more information" />
28 <regex match="[Ee]rror" source="both" description="An error occured during execution, see stderr and stdout for more information" />
29 </stdio>
30 <inputs> 38 <inputs>
31 <param name="input" type="data" label="Additional input .bam files" format="bam" /> 39 <param name="input" type="data" label="Input .bam File" format="bam" help="(--input-file)"/>
32 <repeat name="additionalinputs" title="Input .bam file"> 40 <repeat name="additionalinputs" title="Additional input .bam files">
33 <param name="file" type="data" label="Input .bam file" format="bam" /> 41 <param name="file" type="data" label="Additional input .bam file" format="bam" />
34 </repeat> 42 </repeat>
35 <param name="refgene" type="data" label="Reference Genome" format="bed" /> 43 <param name="refgene" type="data" format="bed" label="reference gene model" help="(--refgene)"/>
36 <param name="minimum_length" type="integer" value="100" label="Minimum mRNA length" help="Minimum mRNA length (bp). mRNA that are shorter than this value will be skipped (default is 100)." /> 44 <param name="minimum_length" type="integer" value="100" label="Minimum mRNA length in bp (default: 100)" help="mRNA that are shorter than this value will be skipped (--minimum_length)." />
37 </inputs> 45 </inputs>
46
38 <outputs> 47 <outputs>
39 <data name="outputcurvespdf" format="pdf" from_work_dir="output.geneBodyCoverage.curves.pdf" label="${tool.name} on ${on_string} (Curves PDF)" /> 48 <data name="outputcurvespdf" format="pdf" from_work_dir="output.geneBodyCoverage.curves.pdf" label="${tool.name} on ${on_string} (Curves PDF)" />
40 <data name="outputheatmappdf" format="pdf" from_work_dir="output.geneBodyCoverage.heatMap.pdf" label="${tool.name} on ${on_string} (HeatMap PDF)"> 49 <data name="outputheatmappdf" format="pdf" from_work_dir="output.geneBodyCoverage.heatMap.pdf" label="${tool.name} on ${on_string} (HeatMap PDF)">
41 <filter>len(additionalinputs) >= 2</filter> 50 <filter>len(additionalinputs) >= 2</filter>
42 </data> 51 </data>
43 <data name="outputr" format="txt" from_work_dir="output.geneBodyCoverage.r" label="${tool.name} on ${on_string} (R Script)" /> 52 <data name="outputr" format="txt" from_work_dir="output.geneBodyCoverage.r" label="${tool.name} on ${on_string} (R Script)" />
44 <data name="outputtxt" format="txt" from_work_dir="output.geneBodyCoverage.txt" label="${tool.name} on ${on_string} (Text)" /> 53 <data name="outputtxt" format="txt" from_work_dir="output.geneBodyCoverage.txt" label="${tool.name} on ${on_string} (Text)" />
45 </outputs> 54 </outputs>
46 <help> 55
56 <tests>
57 <test>
58 <param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
59 <param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed"/>
60 <output name="outputcurvespdf" file="output.geneBodyCoverage.curves.pdf"/>
61 <output name="outputr" file="output.geneBodyCoverage.r"/>
62 <output name="outputtxt" file="output.geneBodyCoverage.txt"/>
63 </test>
64 <test>
65 <param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
66 <param name="file_0" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
67 <param name="file_1" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
68 <param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed"/>
69 <output name="outputcurvespdf" file="output2.geneBodyCoverage.curves.pdf"/>
70 <output name="outputcurvespdf" file="output2.geneBodyCoverage.heatMap.pdf"/>
71 <output name="outputr" file="output2.geneBodycoverage.r"/>
72 <output name="outputtxt" file="output2.geneBodyCoverage.txt"/>
73 </test>
74
75 </tests>
76
77 <help><![CDATA[
47 geneBody_coverage.py 78 geneBody_coverage.py
48 ++++++++++++++++++++ 79 ++++++++++++++++++++
49 80
50 Read coverage over gene body. This module is used to check if read coverage is uniform and if there is any 5\'/3\' bias. This module scales all transcripts to 100 nt and calculates the number of reads covering each nucleotide position. Finally, it generates plots illustrating the coverage profile along the gene body. 81 Read coverage over gene body. This module is used to check if read coverage is uniform and if there is any 5\'/3\' bias. This module scales all transcripts to 100 nt and calculates the number of reads covering each nucleotide position. Finally, it generates plots illustrating the coverage profile along the gene body.
51 82
52 If 3 or more BAM files were provided. This program generates a lineGraph and a heatmap. If fewer than 3 BAM files were provided, only lineGraph is generated. See below for examples. 83 If 3 or more BAM files were provided. This program generates a lineGraph and a heatmap. If fewer than 3 BAM files were provided, only lineGraph is generated. See below for examples.
53 84
54 When heatmap is generated, samples are ranked by the "skewness" of the coverage: Sample with best (worst) coverage will be displayed at the top (bottom) of the heatmap. 85 When heatmap is generated, samples are ranked by the "skewness" of the coverage: Sample with best (worst) coverage will be displayed at the top (bottom) of the heatmap.
55 Coverage skewness was measured by `Pearson’s skewness coefficients &lt;http://en.wikipedia.org/wiki/Skewness#Pearson.27s_skewness_coefficients>`_ 86 Coverage skewness was measured by `Pearson’s skewness coefficients <http://en.wikipedia.org/wiki/Skewness#Pearson.27s_skewness_coefficients>`_
87
88 .. image:: http://rseqc.sourceforge.net/_images/geneBody_workflow.png
89 :width: 800 px
90 :scale: 80 %
91
56 92
57 Inputs 93 Inputs
58 ++++++++++++++ 94 ++++++++++++++
59 95
60 Input BAM/SAM file 96 Input BAM/SAM file
98 The RSeQC package is licensed under the GNU GPL v3 license. 134 The RSeQC package is licensed under the GNU GPL v3 license.
99 135
100 .. image:: http://rseqc.sourceforge.net/_static/logo.png 136 .. image:: http://rseqc.sourceforge.net/_static/logo.png
101 137
102 .. _RSeQC: http://rseqc.sourceforge.net/ 138 .. _RSeQC: http://rseqc.sourceforge.net/
139 ]]>
140 </help>
103 141
142 <expand macro="citations" />
104 143
105
106 </help>
107 </tool> 144 </tool>