|
0
|
1 <tool id="bamSplitTag" name="Split BAM by Tag" version="2.4.0">
|
|
|
2 <description>into dataset list collection</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="2.4.0">bamtools</requirement>
|
|
|
5 </requirements>
|
|
|
6 <command>
|
|
|
7 <![CDATA[
|
|
|
8 #import re
|
|
|
9 #set $name = 'split_bam' + $re.sub('\W','_',$re.sub('\.bam$','',$input_bam.name))
|
|
|
10 ln -s '${input_bam}' 'localbam.bam' &&
|
|
|
11 ln -s '${input_bam.metadata.bam_index}' 'localbam.bam.bai' &&
|
|
|
12 bamtools split -tag $tag_name
|
|
|
13 -in 'localbam.bam'
|
|
|
14 -stub '$name'
|
|
|
15 ]]>
|
|
|
16 </command>
|
|
|
17 <inputs>
|
|
|
18 <param name="input_bam" type="data" format="bam" label="BAM dataset to split by tag value"/>
|
|
|
19 <param name="tag_name" type="text" value="NM" label="Enter tag name here" help="For example, to split on NM tag enter "NM""/>
|
|
|
20 </inputs>
|
|
|
21 <outputs>
|
|
|
22 <collection name="output_bams" type="list" label="${input_bam.name} Split List">
|
|
|
23 <discover_datasets pattern="split_bam(?P<designation>.+)\.bam" ext="bam" visible="false"/>
|
|
|
24 </collection>
|
|
|
25 </outputs>
|
|
|
26 <tests>
|
|
|
27 <test>
|
|
|
28 <param name="input_bam" ftype="bam" value="bamtools-input-tags.bam"/>
|
|
|
29 <param name="tag_name" value="XG"/>
|
|
|
30 <output_collection name="output_bams" type="list">
|
|
|
31 <element name="bamtools_input_tags.TAG_XG_V.bam" file="bamtools_input_tags.TAG_XG_V.bam" compare="sim_size" delta="500" />
|
|
|
32 </output_collection>
|
|
|
33 </test>
|
|
|
34
|
|
|
35 </tests>
|
|
|
36 <help>
|
|
|
37 **What is does**
|
|
|
38
|
|
|
39 BAMTools split is a utility for splitting BAM files. It is based on BAMtools suite of tools by Derek Barnett (https://github.com/pezmaster31/bamtools).
|
|
|
40
|
|
|
41 -----
|
|
|
42
|
|
|
43 .. class:: warningmark
|
|
|
44
|
|
|
45 **DANGER: Multiple Outputs**
|
|
|
46
|
|
|
47 As described below, splitting a BAM dataset(s) on tag value can produce very large numbers of outputs. Read below and know what you are doing.
|
|
|
48
|
|
|
49 -----
|
|
|
50
|
|
|
51 **How it works**
|
|
|
52
|
|
|
53 Split alignments by tag name into a dataset list collection.
|
|
|
54
|
|
|
55 This can generate a huge number of output datasets depending on the number of distinct values of the TAG.
|
|
|
56
|
|
|
57
|
|
|
58 -----
|
|
|
59
|
|
|
60 .. class:: infomark
|
|
|
61
|
|
|
62 **More information**
|
|
|
63
|
|
|
64 Additional information about BAMtools can be found at https://github.com/pezmaster31/bamtools/wiki
|
|
|
65
|
|
|
66 </help>
|
|
|
67 <citations>
|
|
|
68 <citation type="doi">10.1093/bioinformatics/btr174</citation>
|
|
|
69 </citations>
|
|
|
70 </tool>
|
