|
0
|
1 <tool id="bamtools_split_ref" name="Split BAM by Reference" 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 ln -s '${input_bam}' 'localbam.bam' &&
|
|
|
9 ln -s '${input_bam.metadata.bam_index}' 'localbam.bam.bai' &&
|
|
|
10 bamtools split -reference
|
|
|
11 -in localbam.bam
|
|
|
12 -stub split_bam
|
|
|
13 ## Preserve order from metadata in the output collection
|
|
|
14 #import re
|
|
|
15 #set $name = $re.sub('\W','_',$re.sub('\.bam$','',$input_bam.name))
|
|
|
16 #if str($refs) != 'None':
|
|
|
17 #set $ref_list = ' '.join(str($refs).split(","))
|
|
|
18 #else
|
|
|
19 #set $ref_list = ' '.join([$re.sub('^.*__sq__(.+)__sq__.*$','\\1',n) if n.find('__sq__') >= 0 else n for n in str($input_bam.metadata.reference_names).split(',')])
|
|
|
20 #end if
|
|
|
21 && mkdir -p outputs
|
|
|
22 && (export I=0;
|
|
|
23 for i in $ref_list;
|
|
|
24 do I=\$((++I)); SN=`printf "split_bam.REF_%s.bam" "\$i"`;
|
|
|
25 if [ -e \$SN ]; then FN=`printf "outputs/split_bam%05d%s.%s.bam" \$((I)) '$name' "\$i"`; mv \$SN \$FN; fi;
|
|
|
26 done)
|
|
|
27 ]]>
|
|
|
28 </command>
|
|
|
29 <inputs>
|
|
|
30 <param name="input_bam" type="data" format="bam" label="BAM dataset to split by reference"/>
|
|
|
31 <param name="refs" type="select" optional="True" multiple="True" label="Select references (chromosomes and contigs) you would like to restrict bam to" >
|
|
|
32 <help><![CDATA[Click and type in the box above to see options. You can select multiple entries.
|
|
|
33 If "No options available" is displayed, you need to re-detect metadata on the input dataset.
|
|
|
34 ]]></help>
|
|
|
35 <options>
|
|
|
36 <filter type="data_meta" ref="input_bam" key="reference_names" />
|
|
|
37 </options>
|
|
|
38 </param>
|
|
|
39 </inputs>
|
|
|
40 <outputs>
|
|
|
41 <collection name="output_bams" type="list" label="${input_bam.name} Split List">
|
|
|
42 <discover_datasets pattern="split_bam\d*(?P<designation>.+)\.bam" ext="bam" directory="outputs" visible="false"/>
|
|
|
43 </collection>
|
|
|
44 </outputs>
|
|
|
45 <tests>
|
|
|
46 <test>
|
|
|
47 <param name="input_bam" ftype="bam" value="bamtools-input2.bam"/>
|
|
|
48 <output_collection name="output_bams" type="list">
|
|
|
49 <element name="bamtools_input2.chr1" file="bamtools_input2.chr1" compare="sim_size" delta="500" />
|
|
|
50 </output_collection>
|
|
|
51 </test>
|
|
|
52 </tests>
|
|
|
53 <help>
|
|
|
54 **What is does**
|
|
|
55
|
|
|
56 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).
|
|
|
57
|
|
|
58 -----
|
|
|
59
|
|
|
60 .. class:: warningmark
|
|
|
61
|
|
|
62 **DANGER: Multiple Outputs**
|
|
|
63
|
|
|
64 As described below, splitting a BAM dataset(s) on reference name or a tag value can produce very large numbers of outputs. Read below and know what you are doing.
|
|
|
65
|
|
|
66 -----
|
|
|
67
|
|
|
68 **How it works**
|
|
|
69
|
|
|
70 Split alignments by reference name into a dataset list collection. The collection will be in the same order as the input BAM references.
|
|
|
71
|
|
|
72 In cases of unfinished genomes with very large number of reference sequences (scaffolds)
|
|
|
73 it can generate thousands (if not millions) of output datasets.
|
|
|
74
|
|
|
75
|
|
|
76 -----
|
|
|
77
|
|
|
78 .. class:: infomark
|
|
|
79
|
|
|
80 **More information**
|
|
|
81
|
|
|
82 Additional information about BAMtools can be found at https://github.com/pezmaster31/bamtools/wiki
|
|
|
83
|
|
|
84 </help>
|
|
|
85 <citations>
|
|
|
86 <citation type="doi">10.1093/bioinformatics/btr174</citation>
|
|
|
87 </citations>
|
|
|
88 </tool>
|
