Mercurial > repos > nilesh > rseqc

comparison geneBody_coverage.xml @ 51:09846d5169fa draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rseqc commit 37fb1988971807c6a072e1afd98eeea02329ee83
author iuc
date Tue, 14 Mar 2017 10:23:21 -0400
parents f242ee103277
children 34e4c586e3c0
comparison
equal deleted inserted replaced
50:f242ee103277 51:09846d5169fa
1 <tool id="rseqc_geneBody_coverage" name="Gene Body Converage (BAM)" version="2.4galaxy2"> 1 <tool id="rseqc_geneBody_coverage" name="Gene Body Converage (BAM)" version="@WRAPPER_VERSION@">
2 <description> 2 <description>
3 Read coverage over gene body. 3 Read coverage over gene body.
4 </description> 4 </description>
5 5
6 <macros> 6 <macros>
7 <import>rseqc_macros.xml</import> 7 <import>rseqc_macros.xml</import>
8 </macros> 8 </macros>
9 9
10 <requirements> 10 <expand macro="requirements" />
11 <expand macro="requirement_package_r" />
12 <expand macro="requirement_package_numpy" />
13 <expand macro="requirement_package_rseqc" />
14 </requirements>
15 11
16 <expand macro="stdio" /> 12 <expand macro="stdio" />
17 13
18 <version_command><![CDATA[geneBody_coverage.py --version]]></version_command> 14 <version_command><![CDATA[geneBody_coverage.py --version]]></version_command>
19 15
20 <command><![CDATA[ 16 <command><![CDATA[
17 #import re
18 #set $input_list = []
21 #for $i, $input in enumerate($inputs): 19 #for $i, $input in enumerate($inputs):
22 #set $index = $i+1 20 #set $safename = re.sub('[^\w\-_]', '_', $input.element_identifier)
23 #set $safename = ''.join(c in '_0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ' and c or '_' for c in $input.display_name) 21 #if $safename in $input_list:
24 #set $fname = 'd' + str($index) + '_' + str($safename) + ".bam" 22 #set $safename = str($safename) + "." + str($i)
25 ln -s '$input' '${fname}' && 23 #end if
26 ln -s '$input.metadata.bam_index' '${fname}.bai' && 24 $input_list.append($safename)
27 echo '${fname}' >> input_list.txt && 25 ln -sf '${input}' '${safename}.bam' &&
26 ln -sf '${input.metadata.bam_index}' '${safename}.bam.bai' &&
27 echo '${safename}.bam' >> 'input_list.txt' &&
28 #end for 28 #end for
29 geneBody_coverage.py -i input_list.txt -r $refgene --minimum_length $minimum_length -o output 29 geneBody_coverage.py -i 'input_list.txt' -r '${refgene}' --minimum_length ${minimum_length} -o output
30 ]]> 30 ]]>
31 </command> 31 </command>
32 32
33 <inputs> 33 <inputs>
34 <param name="inputs" type="data" label="Input .bam File(s)" format="bam" help="(--input-file)" multiple="true"/> 34 <param name="inputs" type="data" label="Input .bam file(s)" format="bam" help="(--input-file)" multiple="true"/>
35 <param name="refgene" type="data" format="bed" label="reference gene model" help="(--refgene)"/> 35 <expand macro="refgene_param" />
36 <param name="minimum_length" type="integer" value="100" label="Minimum mRNA length in bp (default: 100)" help="mRNA that are shorter than this value will be skipped (--minimum_length)." /> 36 <param name="minimum_length" type="integer" value="100" label="Minimum mRNA length (default: 100)" help="Minimum mRNA length in bp, mRNA that are shorter than this value will be skipped (--minimum_length)." />
37 <expand macro="rscript_output_param" />
37 </inputs> 38 </inputs>
38 39
39 <outputs> 40 <outputs>
40 <data name="outputcurvespdf" format="pdf" from_work_dir="output.geneBodyCoverage.curves.pdf" label="${tool.name} on ${on_string} (Curves PDF)" /> 41 <data name="outputcurvespdf" format="pdf" from_work_dir="output.geneBodyCoverage.curves.pdf" label="${tool.name} on ${on_string} (Curves pdf)" />
41 <data name="outputheatmappdf" format="pdf" from_work_dir="output.geneBodyCoverage.heatMap.pdf" label="${tool.name} on ${on_string} (HeatMap PDF)"> 42 <data name="outputheatmappdf" format="pdf" from_work_dir="output.geneBodyCoverage.heatMap.pdf" label="${tool.name} on ${on_string} (HeatMap pdf)">
42 <filter>len(inputs) >= 3</filter> 43 <filter>len(inputs) >= 3</filter>
43 </data> 44 </data>
44 <data name="outputr" format="txt" from_work_dir="output.geneBodyCoverage.r" label="${tool.name} on ${on_string} (R Script)" /> 45 <expand macro="rscript_output_data" filename="output.geneBodyCoverage.r" />
45 <data name="outputtxt" format="txt" from_work_dir="output.geneBodyCoverage.txt" label="${tool.name} on ${on_string} (Text)" /> 46 <data name="outputtxt" format="txt" from_work_dir="output.geneBodyCoverage.txt" label="${tool.name} on ${on_string} (text)" />
46 </outputs> 47 </outputs>
47 48
48 <!-- PDF Files contain R version, must avoid checking for diff --> 49 <!-- PDF Files contain R version, must avoid checking for diff -->
49 <tests> 50 <tests>
50 <test> 51 <test>
51 <param name="inputs" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/> 52 <param name="inputs" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam" />
52 <param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed"/> 53 <param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed" />
53 <!-- <output name="outputcurvespdf" file="output.geneBodyCoverage.curves.pdf"/> --> 54 <param name="rscript_output" value="true" />
54 <output name="outputr" file="output.geneBodyCoverage.r"/> 55 <output name="outputcurvespdf" file="output.geneBodyCoverage.curves.pdf" compare="sim_size" />
55 <output name="outputtxt" file="output.geneBodyCoverage.txt"/> 56 <output name="outputr" file="output.geneBodyCoverage.r" />
57 <output name="outputtxt" file="output.geneBodyCoverage.txt" />
56 </test> 58 </test>
57 <test> 59 <test>
58 <param name="inputs" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam,pairend_strandspecific_51mer_hg19_chr1_1-100000.bam,pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/> 60 <param name="inputs" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam,pairend_strandspecific_51mer_hg19_chr1_1-100000.bam,pairend_strandspecific_51mer_hg19_chr1_1-100000.bam" />
59 <param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed"/> 61 <param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed" />
60 <!-- <output name="outputcurvespdf" file="output2.geneBodyCoverage.curves.pdf"/> --> 62 <param name="rscript_output" value="true" />
61 <!-- <output name="outputheatmappdf" file="output2.geneBodyCoverage.heatMap.pdf"/> --> 63 <output name="outputcurvespdf" file="output2.geneBodyCoverage.curves.pdf" compare="sim_size" />
62 <output name="outputr" file="output2.geneBodycoverage.r"/> 64 <output name="outputheatmappdf" file="output2.geneBodyCoverage.heatMap.pdf" compare="sim_size" />
63 <output name="outputtxt" file="output2.geneBodyCoverage.txt"/> 65 <output name="outputr" file="output2.geneBodyCoverage.r" />
66 <output name="outputtxt" file="output2.geneBodyCoverage.txt" />
64 </test> 67 </test>
65 68
66 </tests> 69 </tests>
67 70
68 <help><![CDATA[ 71 <help><![CDATA[
69 ## geneBody_coverage.py 72 ## geneBody_coverage.py
70 73
71 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. 74 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.
72 75
73 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. 76 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.
74 77
75 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. 78 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.
76 Coverage skewness was measured by `Pearson’s skewness coefficients <http://en.wikipedia.org/wiki/Skewness#Pearson.27s_skewness_coefficients>`_ 79 Coverage skewness was measured by `Pearson’s skewness coefficients <http://en.wikipedia.org/wiki/Skewness#Pearson.27s_skewness_coefficients>`_
77 80
78 .. image:: http://rseqc.sourceforge.net/_images/geneBody_workflow.png 81 .. image:: $PATH_TO_IMAGES/geneBody_workflow.png
79 :width: 800 px 82 :width: 800 px
80 :scale: 80 % 83 :scale: 80 %
81 84
82 85
83 ## Inputs 86 ## Inputs
84 87
85 Input BAM/SAM file 88 Input BAM/SAM file
86 Alignment file in BAM/SAM format. 89 Alignment file in BAM/SAM format.
87 90
88 Reference gene model 91 Reference gene model
89 Gene Model in BED format. 92 Gene Model in BED format.
90 93
91 Minimum mRNA length 94 Minimum mRNA length
92 Minimum mRNA length (bp). mRNA that are shorter than this value will be skipped (default is 100). 95 Minimum mRNA length (bp). mRNA that are shorter than this value will be skipped (default is 100).
93 96
94 ## Outputs 97 ## Outputs
95 98
96 Text 99 Text
97 Table that includes the data used to generate the plots 100 Table that includes the data used to generate the plots
98 101
99 R Script 102 R Script
100 R script file that reads the data and generates the plot 103 R script file that reads the data and generates the plot
101 104
102 PDF 105 PDF
103 The final plot, in PDF format 106 The final plot, in PDF format
104 107
105 Example plots: 108 Example plots:
106 .. image:: http://rseqc.sourceforge.net/_images/Aug_26.geneBodyCoverage.curves.png 109 .. image:: $PATH_TO_IMAGES/Aug_26.geneBodyCoverage.curves.png
107 :height: 600 px 110 :height: 600 px
108 :width: 600 px 111 :width: 600 px
109 :scale: 80 % 112 :scale: 80 %
110 113
111 .. image:: http://rseqc.sourceforge.net/_images/Aug_26.geneBodyCoverage.heatMap.png 114 .. image:: $PATH_TO_IMAGES/Aug_26.geneBodyCoverage.heatMap.png
112 :height: 600 px 115 :height: 600 px
113 :width: 600 px 116 :width: 600 px
114 :scale: 80 % 117 :scale: 80 %
115 118
116 ## About RSeQC 119 @ABOUT@
117 120
118 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.
119
120 The RSeQC package is licensed under the GNU GPL v3 license.
121
122 .. image:: http://rseqc.sourceforge.net/_static/logo.png
123
124 .. _RSeQC: http://rseqc.sourceforge.net/
125 ]]> 121 ]]>
126 </help> 122 </help>
127 123
128 <expand macro="citations" /> 124 <expand macro="citations" />
129 125