Mercurial > repos > nilesh > rseqc

comparison junction_saturation.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 f242ee103277
comparison
equal deleted inserted replaced
48:2e6190c29c54 49:6b33e31bda10
1 <tool id="rseqc_junction_saturation" name="Junction Saturation" version="2.4"> 1 <tool id="rseqc_junction_saturation" name="Junction Saturation" version="2.4galaxy1">
2 <description>detects splice junctions from each subset and compares them to reference gene model</description> 2 <description>detects splice junctions from each subset and compares them 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> junction_saturation.py -i $input -o output -r $refgene -m $intronSize -v $minSplice
9 13
14 <expand macro="stdio" />
15
16 <version_command><![CDATA[junction_saturation.py --version]]></version_command>
17
18 <command><![CDATA[
19 junction_saturation.py
20 --input-file $input
21 --refgene $refgene
22 --out-prefix output
23 --min-intron $min_intron
24 --min-coverage $min_coverage
25 --mapq $mapq
10 #if $percentiles.specifyPercentiles 26 #if $percentiles.specifyPercentiles
11 -l $percentiles.lowBound -u $percentiles.upBound -s $percentiles.percentileStep 27 --percentile-floor $percentiles.lowBound
28 --percentile-ceiling $percentiles.upBound
29 --percentile-step $percentiles.percentileStep
12 #end if 30 #end if
31 ]]>
32 </command>
13 33
14 </command>
15 <stdio>
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> 34 <inputs>
20 <param name="input" type="data" format="bam,sam" label="input bam/sam file" /> 35 <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" /> 36 <param name="refgene" type="data" format="bed" label="reference gene model" help="(--refgene)"/>
22 <param name="intronSize" type="integer" label="Minimum intron size (bp, default=50)" value="50"/> 37 <param name="min_intron" type="integer" value="50" label="Minimum intron length (bp, default=50)" help="(--min-intron)" />
23 <param name="minSplice" type="integer" label="Minimum coverage (default=1)" value="1" /> 38 <param name="min_coverage" type="integer" label="Minimum number of supporting reads to call a junction (default=1)" value="1" help="(--min-coverage)" />
39 <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 <conditional name="percentiles"> 40 <conditional name="percentiles">
25 <param name="specifyPercentiles" type="boolean" label="Specify sampling bounds and frequency" value="false"/> 41 <param name="specifyPercentiles" type="boolean" label="Specify sampling bounds and frequency" value="false"/>
26 <when value="true"> 42 <when value="true">
27 <param name="lowBound" type="integer" value="5" label="Lower Bound Sampling Frequency (bp, default=5)" /> 43 <param name="lowBound" type="integer" value="5" label="Lower Bound Sampling Frequency (bp, default=5)" help="(--percentile-floor)">
28 <param name="upBound" type="integer" value="100" label="Upper Bound Sampling Frequency (bp, default=100)" /> 44 <validator type="in_range" min="0" max="100" />
29 <param name="percentileStep" type="integer" value="5" label="Sampling increment (default=5)" /> 45 </param>
46 <param name="upBound" type="integer" value="100" label="Upper Bound Sampling Frequency (bp, default=100)" help="(--percentile-ceiling)">
47 <validator type="in_range" min="0" max="100" />
48 </param>
49 <param name="percentileStep" type="integer" value="5" label="Sampling increment (default=5)" help="(--percentile-step)">
50 <validator type="in_range" min="0" max="100" />
51 </param>
30 </when> 52 </when>
31 </conditional> 53 </conditional>
32 </inputs> 54 </inputs>
55
33 <outputs> 56 <outputs>
34 <data format="txt" name="outputr" from_work_dir="output.junctionSaturation_plot.r" label="${tool.name} on ${on_string} (R Script)"/> 57 <data format="txt" name="outputr" from_work_dir="output.junctionSaturation_plot.r" label="${tool.name} on ${on_string} (R Script)"/>
35 <data format="pdf" name="outputpdf" from_work_dir="output.junctionSaturation_plot.pdf" label="${tool.name} on ${on_string} (PDF)"/> 58 <data format="pdf" name="outputpdf" from_work_dir="output.junctionSaturation_plot.pdf" label="${tool.name} on ${on_string} (PDF)"/>
36 </outputs> 59 </outputs>
37 <help> 60
61 <tests>
62 <test>
63 <param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
64 <param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed"/>
65 <output name="outputr" file="output.junctionSaturation_plot.r"/>
66 </test>
67 </tests>
68
69 <help><![CDATA[
38 junction_saturation.py 70 junction_saturation.py
39 ++++++++++++++++++++++ 71 ++++++++++++++++++++++
40 72
41 It's very important to check if current sequencing depth is deep enough to perform 73 It's very important to check if current sequencing depth is deep enough to perform
42 alternative splicing analyses. For a well annotated organism, the number of expressed genes 74 alternative splicing analyses. For a well annotated organism, the number of expressed genes
44 splice junctions can be predetermined from reference gene model. All (annotated) splice 76 splice junctions can be predetermined from reference gene model. All (annotated) splice
45 junctions should be rediscovered from a saturated RNA-seq data, otherwise, downstream 77 junctions should be rediscovered from a saturated RNA-seq data, otherwise, downstream
46 alternative splicing analysis is problematic because low abundance splice junctions are 78 alternative splicing analysis is problematic because low abundance splice junctions are
47 missing. This module checks for saturation by resampling 5%, 10%, 15%, ..., 95% of total 79 missing. This module checks for saturation by resampling 5%, 10%, 15%, ..., 95% of total
48 alignments from BAM or SAM file, and then detects splice junctions from each subset and 80 alignments from BAM or SAM file, and then detects splice junctions from each subset and
49 compares them to reference gene model. 81 compares them to reference gene model.
50 82
51 Inputs 83 Inputs
52 ++++++++++++++ 84 ++++++++++++++
53 85
54 Input BAM/SAM file 86 Input BAM/SAM file
73 2. output.junctionSaturation_plot.pdf 105 2. output.junctionSaturation_plot.pdf
74 106
75 .. image:: http://rseqc.sourceforge.net/_images/junction_saturation.png 107 .. image:: http://rseqc.sourceforge.net/_images/junction_saturation.png
76 :height: 600 px 108 :height: 600 px
77 :width: 600 px 109 :width: 600 px
78 :scale: 80 % 110 :scale: 80 %
79 111
80 In this example, current sequencing depth is almost saturated for "known junction" (red line) detection because the number of "known junction" reaches a plateau. In other words, nearly all "known junctions" (expressed in this particular tissue) have already been detected, and continue sequencing will not detect additional "known junction" and will only increase junction coverage (i.e. junction covered by more reads). While current sequencing depth is not saturated for novel junctions (green). 112 In this example, current sequencing depth is almost saturated for "known junction" (red line) detection because the number of "known junction" reaches a plateau. In other words, nearly all "known junctions" (expressed in this particular tissue) have already been detected, and continue sequencing will not detect additional "known junction" and will only increase junction coverage (i.e. junction covered by more reads). While current sequencing depth is not saturated for novel junctions (green).
81 113
82 114
83 ----- 115 -----
84 116
85 About RSeQC 117 About RSeQC
86 +++++++++++ 118 +++++++++++
87 119
88 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. 120 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.
89 121
90 The RSeQC package is licensed under the GNU GPL v3 license. 122 The RSeQC package is licensed under the GNU GPL v3 license.
91 123
92 .. image:: http://rseqc.sourceforge.net/_static/logo.png 124 .. image:: http://rseqc.sourceforge.net/_static/logo.png
93 125
94 .. _RSeQC: http://rseqc.sourceforge.net/ 126 .. _RSeQC: http://rseqc.sourceforge.net/
127 ]]>
128 </help>
95 129
130 <expand macro="citations" />
96 131
97
98 </help>
99 </tool> 132 </tool>