annotate basil.xml @ 0:341246805ea1 draft

planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
author iuc
date Thu, 30 May 2019 21:14:37 -0400
parents
children 16eccd223c6e
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
1 <tool id="basil" name="basil" version="1.2.0">
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
2 <description>Breakpoint detection, including large insertions</description>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
3 <requirements>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
4 <requirement type="package" version="1.2.0">anise_basil</requirement>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
5 </requirements>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
6 <version_command>basil --version 2>&amp;1 | grep 'basil version' | cut -f 3 -d ' '</version_command>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
7 <command detect_errors="aggressive"><![CDATA[
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
8 ln -s '$ref' 'ref.fa' &&
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
9 ln -s '$bam' 'in.bam' &&
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
10 ln -s '$vcf' 'out.vcf' &&
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
11 basil
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
12 --input-reference 'ref.fa'
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
13 --input-mapping 'in.bam'
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
14 --out-vcf 'out.vcf'
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
15 --oea-min-support-each-side '$min_oea_each_side'
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
16 ]]></command>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
17 <inputs>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
18 <param name="ref" argument="--input-reference" type="data" format="Fasta" label="Reference Sequence File" help="FASTA file with the reference."/>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
19 <param name="bam" argument="--input-mapping" type="data" format="sam,bam" label="Alignment File" help="SAM/BAM file to use as the input."/>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
20 <param name="min_oea_each_side" argument="--oea-min-support-each-side" type="integer" value="2" label="Minimum supporting reads, each side" help="Smallest number of OEA (one-end-anchor) reads on each side to support an insertion. In range [1..inf]. This is the minimum number of supporting reads (without mapped partners) on each side of an insertion breakpoint required to not be filtered." />
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
21 </inputs>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
22 <outputs>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
23 <data name="vcf" format="vcf" />
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
24 </outputs>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
25 <tests>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
26 <test>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
27 <param name="ref" value="ref.fa"/>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
28 <param name="bam" value="simulated.bam"/>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
29 <param name="min_oea_each_side" value="2"/>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
30 <output name="vcf" file="basil.vcf"/>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
31 </test>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
32 </tests>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
33 <help><![CDATA[
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
34 BASIL is a method to detect breakpoints for structural variants (including insertion breakpoints) from aligned paired HTS reads in BAM format. Use BASIL to analyze BAM files for tentative insertion sites.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
35
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
36 Note that BASIL will in general detect all kinds of breakpoints, e.g. for inversions on real-world data.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
37
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
38 BASIL VCF fields
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
39
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
40 A typical line in BASIL might look as follows.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
41
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
42 1 5001 site_0 T <INS> . PASS IMPRECISE;SVTYPE=INS GSCORE:CLEFT:CRIGHT:OEALEFT:OEARIGHT 46.4256:10:12:35:32
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
43
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
44 The first seven columns are as usually in VCF files (ref name, 1-based position, reference base, abbreviation for long insertion, no assigned quality, passing all filters, imprecise insertion SV).
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
45
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
46 The eighth column contains the names of the score values given in the ninth column:
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
47
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
48 GSCORE Geometric mean of the sum of "1 + $score" for all of the following scores.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
49 CLEFT Number of clipping signatures supporting the site from the left side.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
50 CRIGHT Number of clipping signatures supporting the site from the right side.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
51 OEALEFT Number of OEA alignments supporting the site from the left.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
52 OEARIGHT Number of OEA alignmetns supproting the site from the right.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
53
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
54 Generally, one should filter for a minimum support of OEA records on each side, e.g. a value of 10 makes sense for a 30x coverage and showed good results on simulated data.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
55
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
56 For a ranking, GSCORE is a suitable measure but we did not develop any statistical model for BASIL matches and it is a mean of pseudocounts only. It carries no statistically precise meaning.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
57 ]]></help>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
58 <citations>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
59 <citation type="doi">10.1093/bioinformatics/btv051</citation>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
60 </citations>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
61 </tool>