Mercurial > repos > nilesh > rseqc

comparison junction_annotation.xml @ 49:6b33e31bda10 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
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 eb339c5849bb
children 09846d5169fa
comparison
equal deleted inserted replaced
48:2e6190c29c54 49:6b33e31bda10
1 <tool id="rseqc_junction_annotation" name="Junction Annotation" version="2.4"> 1 <tool id="rseqc_junction_annotation" name="Junction Annotation" version="2.4galaxy1">
2 <description>compares detected splice junctions to reference gene model</description> 2 <description>compares detected splice junctions to reference gene model</description>
3
4 <macros>
5 <import>rseqc_macros.xml</import>
6 </macros>
7
3 <requirements> 8 <requirements>
4 <requirement type="package" version="3.0.3">R</requirement> 9 <expand macro="requirement_package_r" />
5 <requirement type="package" version="1.7.1">numpy</requirement> 10 <expand macro="requirement_package_numpy" />
6 <requirement type="package" version="2.4">rseqc</requirement> 11 <expand macro="requirement_package_rseqc" />
7 </requirements> 12 </requirements>
8 <command> 13
9 junction_annotation.py 14 <expand macro="stdio" />
10 -i $input -o output -r $refgene 15
11 #if $intron.hasIntron 16 <version_command><![CDATA[junction_annotation.py --version]]></version_command>
12 -m $intron.min_Intron 17
13 #end if 18 <command><![CDATA[
19 junction_annotation.py
20 --input-file $input
21 --refgene $refgene
22 --out-prefix output
23 --min-intron $min_intron
24 --mapq $mapq
25 ]]>
14 </command> 26 </command>
15 <stdio> 27
16 <exit_code range="1:" level="fatal" description="An error occured during execution, see stderr and stdout for more information" />
17 <regex match="[Ee]rror" source="both" description="An error occured during execution, see stderr and stdout for more information" />
18 </stdio>
19 <inputs> 28 <inputs>
20 <param name="input" type="data" format="bam,sam" label="input bam/sam file" /> 29 <param name="input" type="data" format="bam,sam" label="input bam/sam file" help="(--input-file)"/>
21 <param name="refgene" type="data" format="bed" label="reference gene model" /> 30 <param name="refgene" type="data" format="bed" label="reference gene model" help="(--refgene)"/>
22 <conditional name="intron"> 31 <param name="min_intron" type="integer" value="50" label="Minimum intron length (bp, default=50)" help="(--min-intron)" />
23 <param name="hasIntron" type="boolean" label="Specify minimum intron length" value="false"/> 32 <param name="mapq" type="integer" label="Minimum mapping quality (default=30)" help="Minimum phred scale mapping quality to consider a read 'uniquely mapped' (--mapq)" value="30" />
24 <when value="true">
25 <param name="min_Intron" type="integer" value="50" label="Minimum intron length (bp, default=50)" />
26 </when>
27 </conditional>
28 </inputs> 33 </inputs>
34
29 <outputs> 35 <outputs>
30 <data format="xls" name="outputxls" from_work_dir="output.junction.xls" label="${tool.name} on ${on_string} (XLS)"/> 36 <data format="xls" name="outputxls" from_work_dir="output.junction.xls" label="${tool.name} on ${on_string} (XLS)"/>
31 <data format="txt" name="outputr" from_work_dir="output.junction_plot.r" label="${tool.name} on ${on_string} (R Script)" /> 37 <data format="txt" name="outputr" from_work_dir="output.junction_plot.r" label="${tool.name} on ${on_string} (R Script)" />
32 <data format="pdf" name="outputpdf" from_work_dir="output.splice_events.pdf" label="${tool.name} on ${on_string} (Splice Events PDF)"/> 38 <data format="pdf" name="outputpdf" from_work_dir="output.splice_events.pdf" label="${tool.name} on ${on_string} (Splice Events PDF)"/>
33 <data format="pdf" name="outputjpdf" from_work_dir="output.splice_junction.pdf" label="${tool.name} on ${on_string} (Splice Junction PDF)" /> 39 <data format="pdf" name="outputjpdf" from_work_dir="output.splice_junction.pdf" label="${tool.name} on ${on_string} (Splice Junction PDF)" />
34 </outputs> 40 </outputs>
35 <help> 41
42 <tests>
43 <test>
44 <param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
45 <param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed"/>
46 <output name="outputxls" file="output.junction.xls"/>
47 <output name="outputr" file="output.junction_plot.r"/>
48 <output name="outputpdf" file="output.splice_events.pdf"/>
49 <output name="outputjpdf" file="output.splice_junction.pdf"/>
50 </test>
51 </tests>
52
53 <help><![CDATA[
36 junction_annotation.py 54 junction_annotation.py
37 ++++++++++++++++++++++ 55 ++++++++++++++++++++++
38 56
39 For a given alignment file (-i) in BAM or SAM format and a reference gene model (-r) in BED 57 For a given alignment file (-i) in BAM or SAM format and a reference gene model (-r) in BED
40 format, this program will compare detected splice junctions to reference gene model. splicing 58 format, this program will compare detected splice junctions to reference gene model. splicing
41 annotation is performed in two levels: splice event level and splice junction level. 59 annotation is performed in two levels: splice event level and splice junction level.
42 60
43 * splice event: An RNA read, especially long read, can be spliced 2 or more times, each time is called a splicing event; In this sense, 100 spliced reads can produce >= 100 splicing events. 61 * splice event: An RNA read, especially long read, can be spliced 2 or more times, each time is called a splicing event; In this sense, 100 spliced reads can produce >= 100 splicing events.
44 * splice junction: multiple splicing events spanning the same intron can be consolidated into one splicing junction. 62 * splice junction: multiple splicing events spanning the same intron can be consolidated into one splicing junction.
45 63
46 All detected junctions can be grouped to 3 exclusive categories: 64 All detected junctions can be grouped to 3 exclusive categories:
47 65
48 1. Annotated: The junction is part of the gene model. Both splice sites, 5' splice site 66 1. Annotated: The junction is part of the gene model. Both splice sites, 5' splice site
49 (5'SS) and 3'splice site (3'SS) can be annotated by reference gene model. 67 (5'SS) and 3'splice site (3'SS) can be annotated by reference gene model.
50 2. complete_novel: Complete new junction. Neither of the two splice sites cannot be annotated by gene model 68 2. complete_novel: Complete new junction. Neither of the two splice sites cannot be annotated by gene model
51 3. partial_novel: One of the splice site (5'SS or 3'SS) is new, while the other splice site is annotated (known) 69 3. partial_novel: One of the splice site (5'SS or 3'SS) is new, while the other splice site is annotated (known)
52 70
53 Inputs 71 Inputs
54 ++++++++++++++ 72 ++++++++++++++
55 73
56 Input BAM/SAM file 74 Input BAM/SAM file
77 4. output.splice_events.pdf: plot of splice events 95 4. output.splice_events.pdf: plot of splice events
78 96
79 .. image:: http://rseqc.sourceforge.net/_images/junction.png 97 .. image:: http://rseqc.sourceforge.net/_images/junction.png
80 :height: 400 px 98 :height: 400 px
81 :width: 850 px 99 :width: 850 px
82 :scale: 80 % 100 :scale: 80 %
83 101
84 ----- 102 -----
85 103
86 About RSeQC 104 About RSeQC
87 +++++++++++ 105 +++++++++++
88 106
89 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. 107 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.
90 108
91 The RSeQC package is licensed under the GNU GPL v3 license. 109 The RSeQC package is licensed under the GNU GPL v3 license.
92 110
93 .. image:: http://rseqc.sourceforge.net/_static/logo.png 111 .. image:: http://rseqc.sourceforge.net/_static/logo.png
94 112
95 .. _RSeQC: http://rseqc.sourceforge.net/ 113 .. _RSeQC: http://rseqc.sourceforge.net/
114 ]]>
115 </help>
96 116
117 <expand macro="citations" />
97 118
98
99
100 </help>
101 </tool> 119 </tool>