annotate RPKM_saturation.xml @ 29:907d4b021ff6

Uploaded
author nilesh
date Thu, 11 Jul 2013 12:31:33 -0400
parents
children cc5eaa9376d8
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
29
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
1 <tool id="RPKM_saturation" name="RPKM Saturation">
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
2 <description>calculates raw count and RPKM values for transcript at exon, intron, and mRNA level</description>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
3 <requirements>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
4 <requirement type="package" version="2.15.1">R</requirement>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
5 <requirement type="package" version="2.3.7">rseqc</requirement>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
6 </requirements>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
7 <command interpreter="python"> RPKM_saturation.py -i $input -o output -r $refgene
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
8
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
9 #if str($strand_type.strand_specific) == "pair"
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
10 -d
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
11 #if str($strand_type.pair_type) == "sd"
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
12 '1++,1--,2+-,2-+'
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
13 #else
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
14 '1+-,1-+,2++,2--'
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
15 #end if
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
16 #end if
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
17
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
18 #if str($strand_type.strand_specific) == "single"
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
19 -d
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
20 #if str($strand_type.single_type) == "s"
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
21 '++,--'
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
22 #else
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
23 '+-,-+'
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
24 #end if
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
25 #end if
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
26
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
27 -l $percentileFloor -u $percentileCeiling -s $percentileStep -c $rpkmCutoff
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
28
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
29 </command>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
30 <inputs>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
31 <param name="input" type="data" format="bam" label="input bam/sam file" />
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
32 <param name="refgene" type="data" format="bed" label="Reference gene model" />
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
33 <conditional name="strand_type">
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
34 <param name="strand_specific" type="select" label="Strand-specific?" value="None">
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
35 <option value="none">None</option>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
36 <option value="pair">Pair-End RNA-seq</option>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
37 <option value="single">Single-End RNA-seq</option>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
38 </param>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
39 <when value="pair">
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
40 <param name="pair_type" type="select" display="radio" label="Pair-End Read Type (format: mapped --> parent)" value="sd">
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
41 <option value="sd"> read1 (positive --> positive; negative --> negative), read2 (positive --> negative; negative --> positive)</option>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
42 <option value="ds">read1 (positive --> negative; negative --> positive), read2 (positive --> positive; negative --> negative)</option>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
43 </param>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
44 </when>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
45 <when value="single">
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
46 <param name="single_type" type="select" display="radio" label="Single-End Read Type (format: mapped --> parent)" value="s">
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
47 <option value="s">positive --> positive; negative --> negative</option>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
48 <option value="d">positive --> negative; negative --> positive</option>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
49 </param>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
50 </when>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
51 <when value="none"></when>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
52 </conditional>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
53 <param name="percentileFloor" type="integer" value="5" label="Begin sampling from this percentile (default=5)" />
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
54 <param name="percentileCeiling" type="integer" value="100" label="End sampling at this percentile (default=100)" />
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
55 <param name="percentileStep" type="integer" value="5" label="Sampling step size (default=5)" />
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
56 <param name="rpkmCutoff" type="text" value="0.01" label="Ignore transcripts with RPKM smaller than this number (default=0.01)" />
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
57 </inputs>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
58 <outputs>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
59 <data format="xls" name="outputxls" from_work_dir="output.eRPKM.xls"/>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
60 <data format="xls" name="outputrawxls" from_work_dir="output.rawCount.xls"/>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
61 <data format="r" name="outputr" from_work_dir="output.saturation.r"/>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
62 <data format="pdf" name="outputpdf" from_work_dir="output.saturation.pdf"/>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
63 </outputs>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
64 <help>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
65 .. image:: https://code.google.com/p/rseqc/logo?cct=1336721062
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
66
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
67 -----
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
68
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
69 About RSeQC
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
70 +++++++++++
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
71
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
72 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.
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
73
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
74 The RSeQC package is licensed under the GNU GPL v3 license.
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
75
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
76 Inputs
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
77 ++++++++++++++
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
78
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
79 Input BAM/SAM file
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
80 Alignment file in BAM/SAM format.
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
81
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
82 Reference gene model
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
83 Gene model in BED format.
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
84
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
85 Strand sequencing type (default=none)
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
86 See Infer Experiment tool if uncertain.
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
87
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
88 Options
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
89 ++++++++++++++
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
90
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
91 Skip Multiple Hit Reads
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
92 Use Multiple hit reads or use only uniquely mapped reads.
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
93
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
94 Only use exonic reads
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
95 Renders program only used exonic (UTR exons and CDS exons) reads, otherwise use all reads.
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
96
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
97 Output
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
98 ++++++++++++++
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
99
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
100 1. output..eRPKM.xls: RPKM values for each transcript
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
101 2. output.rawCount.xls: Raw count for each transcript
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
102 3. output.saturation.r: R script to generate plot
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
103 4. output.saturation.pdf:
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
104
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
105 .. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/saturation.png
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
106
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
107 - All transcripts were sorted in ascending order according to expression level (RPKM). Then they are divided into 4 groups:
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
108 1. Q1 (0-25%): Transcripts with expression level ranked below 25 percentile.
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
109 2. Q2 (25-50%): Transcripts with expression level ranked between 25 percentile and 50 percentile.
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
110 3. Q3 (50-75%): Transcripts with expression level ranked between 50 percentile and 75 percentile.
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
111 4. Q4 (75-100%): Transcripts with expression level ranked above 75 percentile.
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
112 - BAM/SAM file containing more than 100 million alignments will make module very slow.
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
113 - Follow example below to visualize a particular transcript (using R console)::
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
114 - output example
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
115 .. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/saturation_eg.png
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
116
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
117 </help>
907d4b021ff6 Uploaded
nilesh
parents:
diff changeset
118 </tool>