|
46
|
1 <tool id="htseqsams2mxlocal" name="SAM/BAM to count matrix" version="0.5">
|
|
43
|
2 <description>using HTSeq code</description>
|
|
|
3 <stdio>
|
|
|
4 <regex match=".*" source="both" level="warning" description="chatter from HTSeq:"/>
|
|
|
5 </stdio>
|
|
|
6 <requirements>
|
|
|
7 <requirement type="package" version="0.7.6">pysam</requirement>
|
|
47
|
8 <requirement type="package" version="1.2.1">matplotlib</requirement>
|
|
43
|
9 <requirement type="package" version="0.5.4p3">htseq</requirement>
|
|
|
10 </requirements>
|
|
|
11 <command interpreter="python">
|
|
|
12 htseqsams2mx.py -g "$gfffile" -o "$outfile" -m "$model" --id_attribute "$id_attr" --feature_type "$feature_type"
|
|
49
|
13 --mapqMin $mapqMin
|
|
43
|
14 #for $s in $samfiles:
|
|
49
|
15 #if $s.ext != 'data':
|
|
|
16 --samf "'${s}','${s.name}','${s.ext}','${s.metadata.bam_index}'"
|
|
43
|
17 #end if
|
|
|
18 #end for
|
|
|
19 #if $filter_extras:
|
|
|
20 --filter_extras "$filter_extras"
|
|
|
21 #end if
|
|
|
22 </command>
|
|
|
23 <inputs>
|
|
|
24 <param format="gtf" name="gfffile" type="data" label="Gene model (GFF) file to count reads over from your current history" size="100" />
|
|
|
25 <param name="mapqMin" label="Filter reads with mapq below than this value"
|
|
|
26 help="0 to count any mapping quality read. Otherwise only reads at or above specified mapq will be counted"
|
|
|
27 type="integer" value="5"/>
|
|
|
28 <param name="title" label="Name for this job's output file" type="text" size="80" value="bams to DGE count matrix"/>
|
|
|
29 <param name="stranded" value="false" type="boolean" label="Reads are stranded - use strand in counting" display="checkbox"
|
|
|
30 truevalue="yes" falsevalue="no" checked="no" help="Check this ONLY if you know your sequences are strand specific" />
|
|
|
31 <param name="model" type="select" label="Model for counting reads over the supplied gene model- see HTSeq docs"
|
|
|
32 help="If in doubt, union is a reasonable default but intersection-strict avoids double counting over overlapping exons">
|
|
|
33 <option value="union" selected="true">union</option>
|
|
|
34 <option value="intersection-strict">intersection-strict</option>
|
|
|
35 <option value="intersection-nonempty">intersection-nonempty</option>
|
|
|
36 </param>
|
|
|
37 <param name="id_attr" type="select" label="GTF attribute to output as the name for each contig - see HTSeq docs"
|
|
|
38 help="If in doubt, use gene name or if you need the id in your GTF, gene id">
|
|
|
39 <option value="gene_name" selected="true">gene name</option>
|
|
|
40 <option value="gene_id">gene id</option>
|
|
|
41 <option value="transcript_id">transcript id</option>
|
|
|
42 <option value="transcript_name">transcript name</option>
|
|
|
43 </param>
|
|
|
44 <param name="feature_type" type="select" label="GTF feature type for counting reads over the supplied gene model- see HTSeq docs"
|
|
|
45 help="GTF feature type to count over - exon is a good choice with gene name as the contig to count over">
|
|
|
46 <option value="exon" selected="true">exon</option>
|
|
|
47 <option value="CDS">CDS</option>
|
|
|
48 <option value="UTR">UTR</option>
|
|
|
49 <option value="transcript">transcript</option>
|
|
|
50 </param>
|
|
|
51 <param name="filter_extras" type="select" label="Filter any read with one or more flags"
|
|
|
52 help="eg the XS tag created by bowtie for multiple reads" optional="true" mutliple="true">
|
|
|
53 <option value="">None</option>
|
|
|
54 <option value="XS">XS:i > 0 - More than one mapping position Bowtie</option>
|
|
|
55 <option value="XS:A">Might be useful for tophat</option>
|
|
|
56 </param>
|
|
|
57
|
|
49
|
58 <param name="samfiles" type="data" label="bam/sam file from your history" format="sam,bam" size="100" multiple="true"/>
|
|
43
|
59 </inputs>
|
|
|
60 <outputs>
|
|
|
61 <data format="tabular" name="outfile" label="${title}_htseqsams2mx.xls" />
|
|
|
62 </outputs>
|
|
|
63 <tests>
|
|
|
64 <test>
|
|
|
65 <param name="feature_type" value="exon" />
|
|
|
66 <param name="gfffile" value="rn4_chr20_100k.gtf" />
|
|
49
|
67 <param name="samfiles" value="rn4chr20test1.bam,rn4chr20test2.bam" ftype="bam"/>
|
|
43
|
68 <param name="id_attr" value="gene_name" />
|
|
|
69 <param name="model" value="union" />
|
|
|
70 <param name="stranded" value="no" />
|
|
|
71 <param name="title" value="htseqtest" />
|
|
|
72 <param name="mapqMin" value="0" />
|
|
|
73
|
|
|
74 <output name="outfile" file="htseqsams2mx_test1_out.xls" lines_diff="1"/>
|
|
|
75 </test>
|
|
|
76 </tests>
|
|
|
77 <help>
|
|
|
78
|
|
|
79 **What this tool does**
|
|
|
80
|
|
|
81 Counts reads in multiple sam/bam format mapped files and generates a matrix ideal for edgeR and other count based tools
|
|
|
82 It uses HTSeq to count your sam reads over a gene model supplied as a GTF file
|
|
|
83 The output is a tabular text (columnar - spreadsheet) file containing the
|
|
|
84 count matrix for downstream processing. Each row contains the counts from each sample for each
|
|
|
85 of the non-emtpy GTF input file contigs matching the GTF attribute choice above.
|
|
|
86 You probably want to use gene level GTF output attribute and count reads that overlap
|
|
|
87 GTF exons for RNA-seq. Or you can count over exons by using transcript level output names or ids. Etc.
|
|
|
88
|
|
|
89 ----
|
|
|
90
|
|
|
91 **Author's plea on replicates**
|
|
|
92
|
|
|
93 If you want to interpret the downstream p values in terms of rejecting or accepting the null hypothesis
|
|
|
94 under random sampling with replacement from the universe of possible biological/experimental replicates from which your data was derived,
|
|
|
95 which is what published p values are often assumed to do, then you need biological
|
|
|
96 (or for cell culture material experimental) replicates.
|
|
|
97
|
|
|
98 Using technical or no replicates means the downstream p values are not interpretable the way most people would assume
|
|
|
99 they are - ie as the probability of obtaining a result as or more extreme as your experimental data
|
|
|
100 in millions of experiments conducted using the same methods under the null hypothesis.
|
|
|
101
|
|
|
102 There is no way around this and it is scientific fraud to ignore this issue and publish bogus p values derived from
|
|
|
103 technical or no replicates without making the lack of biological or experimental error in the p value calculations
|
|
|
104 clear to your readers so they can adjust their expectations. However, the buck stops here at higher level inference.
|
|
|
105 If you have no replicates, you must not use this tool as the p values are uninterpretable. So there.
|
|
|
106
|
|
|
107 See your stats 101 notes on the central limit theorem and test statistics for a refresher or talk to a
|
|
|
108 statistician if this makes no sense please.
|
|
|
109
|
|
|
110 **Attribution**
|
|
|
111
|
|
|
112 This Galaxy tool relies on HTSeq_ from http://www-huber.embl.de/users/anders/HTSeq/doc/index.html
|
|
|
113 for the tricky work of counting. That code includes the following attribution:
|
|
|
114
|
|
|
115 ## Written by Simon Anders (sanders@fs.tum.de), European Molecular Biology
|
|
|
116 ## Laboratory (EMBL). (c) 2010. Released under the terms of the GNU General
|
|
|
117 ## Public License v3. Part of the 'HTSeq' framework, version HTSeq-0.5.4p3
|
|
|
118
|
|
|
119 It will be automatically installed if you use the toolshed as in general, you probably should.
|
|
|
120 HTSeq_ must be installed with this tool if you install manually.
|
|
|
121
|
|
|
122 Otherwise, all code and documentation comprising this tool including the requirement
|
|
|
123 for more than one sample bam
|
|
|
124 was written by Ross Lazarus and is
|
|
|
125 licensed to you under the LGPL_ like other rgenetics artefacts
|
|
|
126
|
|
|
127 Sorry, I don't use readgroups so had no reason to code read groups. Contributions welcome. Send code
|
|
|
128
|
|
|
129 .. _LGPL: http://www.gnu.org/copyleft/lesser.html
|
|
|
130 .. _HTSeq: http://www-huber.embl.de/users/anders/HTSeq/doc/index.html
|
|
|
131 </help>
|
|
|
132
|
|
|
133 </tool>
|
