annotate basil.xml @ 1:16eccd223c6e draft default tip

planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
author iuc
date Sun, 11 Aug 2024 21:06:06 +0000
parents 341246805ea1
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
1 <tool id="basil" name="basil" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.0">
0
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
2 <description>Breakpoint detection, including large insertions</description>
1
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
3 <macros>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
4 <token name="@TOOL_VERSION@">1.2.0</token>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
5 <token name="@VERSION_SUFFIX@">1</token>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
6 </macros>
0
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
7 <requirements>
1
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
8 <requirement type="package" version="@TOOL_VERSION@">anise_basil</requirement>
0
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
9 </requirements>
1
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
10 <version_command>basil --version 2&gt;&amp;1 | grep 'basil version' | cut -f 3 -d ' '</version_command>
0
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
11 <command detect_errors="aggressive"><![CDATA[
1
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
12 #if $reference_source.reference_source_selector == 'history':
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
13 ln -f -s '$reference_source.ref' ref.fa &&
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
14 #else:
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
15 ln -f -s '$reference_source.ref.fields.path' ref.fa &&
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
16 #end if
0
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
17 ln -s '$bam' 'in.bam' &&
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
18 ln -s '$vcf' 'out.vcf' &&
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
19 basil
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
20 --input-reference 'ref.fa'
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
21 --input-mapping 'in.bam'
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
22 --out-vcf 'out.vcf'
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
23 --oea-min-support-each-side '$min_oea_each_side'
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
24 ]]></command>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
25 <inputs>
1
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
26 <conditional name="reference_source">
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
27 <param name="reference_source_selector" type="select" label="Select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options. See `Indexes` section of help below. If you would like to perform self-mapping select `history` here, then choose your input file as reference.">
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
28 <option value="cached">Use a built-in genome index</option>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
29 <option value="history">Use a genome from history and build index</option>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
30 </param>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
31 <when value="cached">
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
32 <param name="ref" type="select" label="Using reference genome" help="Select genome from the list">
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
33 <options from_data_table="all_fasta">
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
34 <filter type="sort_by" column="2"/>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
35 <validator type="no_options" message="No reference genomes are available"/>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
36 </options>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
37 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
38 </param>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
39 </when>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
40 <when value="history">
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
41 <param name="ref" argument="--input-reference" type="data" format="Fasta" label="Reference Sequence File" help="FASTA file with the reference."/>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
42 </when>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
43 </conditional>
0
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
44 <param name="bam" argument="--input-mapping" type="data" format="sam,bam" label="Alignment File" help="SAM/BAM file to use as the input."/>
1
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
45 <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."/>
0
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
46 </inputs>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
47 <outputs>
1
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
48 <data name="vcf" format="vcf"/>
0
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
49 </outputs>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
50 <tests>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
51 <test>
1
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
52 <conditional name="reference_source">
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
53 <param name="reference_source_selector" value="history" />
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
54 <param name="ref" ftype="fasta" value="ref.fa"/>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
55 </conditional>
0
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
56 <param name="ref" value="ref.fa"/>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
57 <param name="bam" value="simulated.bam"/>
1
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
58 <param name="min_oea_each_side" value="2"/>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
59 <output name="vcf" file="basil.vcf"/>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
60 </test>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
61 <test>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
62 <conditional name="reference_source">
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
63 <param name="reference_source_selector" value="cached" />
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
64 <param name="ref" value="genome"/>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
65 </conditional>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
66 <param name="bam" value="simulated.bam"/>
16eccd223c6e planemo upload commit 49a2861a9b3480ea25f1e5526d2edf9dc8cb5334
iuc
parents: 0
diff changeset
67 <param name="min_oea_each_side" value="2"/>
0
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
68 <output name="vcf" file="basil.vcf"/>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
69 </test>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
70 </tests>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
71 <help><![CDATA[
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
72 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
73
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
74 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
75
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
76 BASIL VCF fields
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
77
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
78 A typical line in BASIL might look as follows.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
79
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
80 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
81
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
82 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
83
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
84 The eighth column contains the names of the score values given in the ninth column:
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
85
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
86 GSCORE Geometric mean of the sum of "1 + $score" for all of the following scores.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
87 CLEFT Number of clipping signatures supporting the site from the left side.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
88 CRIGHT Number of clipping signatures supporting the site from the right side.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
89 OEALEFT Number of OEA alignments supporting the site from the left.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
90 OEARIGHT Number of OEA alignmetns supproting the site from the right.
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
91
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
92 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
93
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
94 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
95 ]]></help>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
96 <citations>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
97 <citation type="doi">10.1093/bioinformatics/btv051</citation>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
98 </citations>
341246805ea1 planemo upload commit b89c8017aeef91f940543a1cc7dadb4a85290865
iuc
parents:
diff changeset
99 </tool>