31
|
1 <tool id="RPKM_count" name="RPKM Count" version="1.1">
|
29
|
2 <description>calculates raw count and RPKM values for transcript at exon, intron, and mRNA level</description>
|
|
3 <requirements>
|
31
|
4 <requirement type="package" version="1.7.1">numpy</requirement>
|
29
|
5 <requirement type="package" version="2.3.7">rseqc</requirement>
|
|
6 </requirements>
|
31
|
7 <command>
|
|
8 ln -s "${input}" "local_input.bam" &&
|
|
9 ln -s "${input.metadata.bam_index}" "local_input.bam.bai" &&
|
|
10 RPKM_count.py -i "local_input.bam" -o output -r $refgene
|
29
|
11
|
|
12 #if str($strand_type.strand_specific) == "pair"
|
|
13 -d
|
|
14 #if str($strand_type.pair_type) == "sd"
|
|
15 '1++,1--,2+-,2-+'
|
|
16 #else
|
|
17 '1+-,1-+,2++,2--'
|
|
18 #end if
|
|
19 #end if
|
|
20
|
|
21 #if str($strand_type.strand_specific) == "single"
|
|
22 -d
|
|
23 #if str($strand_type.single_type) == "s"
|
|
24 '++,--'
|
|
25 #else
|
|
26 '+-,-+'
|
|
27 #end if
|
|
28 #end if
|
|
29
|
|
30 #if $skiphits
|
|
31 -u
|
|
32 #end if
|
|
33
|
|
34 #if $onlyexonic
|
|
35 -e
|
|
36 #end if
|
|
37
|
|
38 </command>
|
|
39 <inputs>
|
|
40 <param name="input" type="data" format="bam" label="input bam/sam file" />
|
|
41 <param name="refgene" type="data" format="bed" label="Reference gene model" />
|
|
42 <conditional name="strand_type">
|
|
43 <param name="strand_specific" type="select" label="Strand-specific?" value="None">
|
|
44 <option value="none">None</option>
|
|
45 <option value="pair">Pair-End RNA-seq</option>
|
|
46 <option value="single">Single-End RNA-seq</option>
|
|
47 </param>
|
|
48 <when value="pair">
|
|
49 <param name="pair_type" type="select" display="radio" label="Pair-End Read Type (format: mapped --> parent)" value="sd">
|
|
50 <option value="sd"> read1 (positive --> positive; negative --> negative), read2 (positive --> negative; negative --> positive)</option>
|
|
51 <option value="ds">read1 (positive --> negative; negative --> positive), read2 (positive --> positive; negative --> negative)</option>
|
|
52 </param>
|
|
53 </when>
|
|
54 <when value="single">
|
|
55 <param name="single_type" type="select" display="radio" label="Single-End Read Type (format: mapped --> parent)" value="s">
|
|
56 <option value="s">positive --> positive; negative --> negative</option>
|
|
57 <option value="d">positive --> negative; negative --> positive</option>
|
|
58 </param>
|
|
59 </when>
|
|
60 <when value="none"></when>
|
|
61 </conditional>
|
|
62 <param name="skiphits" type="boolean" value="false" label="Skip Multiple Hit Reads" />
|
|
63 <param name="onlyexonic" type="boolean" value="false" label="Only use exonic (UTR exons and CDS exons) reads, otherwise use all reads" />
|
|
64 </inputs>
|
|
65 <outputs>
|
|
66 <data format="xls" name="outputxls" from_work_dir="output_read_count.xls"/>
|
|
67 </outputs>
|
31
|
68 <stdio>
|
|
69 <exit_code range="1:" level="fatal" description="An error occured during execution, see stderr and stdout for more information" />
|
|
70 <regex match="[Ee]rror" source="both" description="An error occured during execution, see stderr and stdout for more information" />
|
|
71 </stdio>
|
29
|
72 <help>
|
31
|
73 RPKM_count.py
|
|
74 +++++++++++++
|
29
|
75
|
31
|
76 Given a BAM file and reference gene model, this program will calculate the raw count and RPKM
|
|
77 values for transcript at exon, intron and mRNA level. For strand specific RNA-seq data,
|
|
78 program will assign read to its parental gene according to strand rule, if you don't know the
|
|
79 strand rule, run infer_experiment.py. Please note that chromosome ID, genome cooridinates
|
|
80 should be concordant between BAM and BED files.
|
29
|
81
|
|
82 Inputs
|
|
83 ++++++++++++++
|
|
84
|
|
85 Input BAM/SAM file
|
|
86 Alignment file in BAM/SAM format.
|
|
87
|
|
88 Reference gene model
|
|
89 Gene model in BED format.
|
|
90
|
|
91 Strand sequencing type (default=none)
|
|
92 See Infer Experiment tool if uncertain.
|
|
93
|
|
94 Options
|
|
95 ++++++++++++++
|
|
96
|
|
97 Skip Multiple Hit Reads
|
|
98 Use Multiple hit reads or use only uniquely mapped reads.
|
|
99
|
|
100 Only use exonic reads
|
|
101 Renders program only used exonic (UTR exons and CDS exons) reads, otherwise use all reads.
|
|
102
|
|
103 Sample Output
|
|
104 ++++++++++++++
|
|
105
|
31
|
106 ===== ======== ======== ===================== ===== =========== ============= ============= ======== =========
|
|
107 chrom start end accession score gene strand tag count (+) tag count (-) RPKM (+) RPKM (-)
|
|
108 ===== ======== ======== ===================== ===== =========== ============= ============= ======== =========
|
|
109 chr1 29213722 29313959 NM_001166007_intron_1 0 '+' 431 4329 0.086 0.863
|
|
110 chr1 29314417 29319841 NM_001166007_intron_2 0 '+' 31 1 0.114 0.004
|
|
111 chr1 29320054 29323726 NM_001166007_intron_3 0 '+' 32 0 0.174 0.000
|
|
112 chr1 29213602 29213722 NM_001166007_exon_1 0 '+' 164 0 27.321 0.000
|
|
113 chr1 29313959 29314417 NM_001166007_exon_2 0 '+' 1699 4 74.158 0.175
|
|
114 chr1 29319841 29320054 NM_001166007_exon_3 0 '+' 528 1 49.554 0.094
|
|
115 ===== ======== ======== ===================== ===== =========== ============= ============= ======== =========
|
29
|
116
|
31
|
117 -----
|
|
118
|
|
119 About RSeQC
|
|
120 +++++++++++
|
|
121
|
|
122 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.
|
|
123
|
|
124 The RSeQC package is licensed under the GNU GPL v3 license.
|
|
125
|
|
126 .. image:: http://rseqc.sourceforge.net/_static/logo.png
|
|
127
|
|
128 .. _RSeQC: http://rseqc.sourceforge.net/
|
|
129
|
|
130
|
29
|
131 </help>
|
|
132 </tool>
|