forked from Ensembl/VEP_plugins
-
Notifications
You must be signed in to change notification settings - Fork 0
/
ClinPred.pm
executable file
·140 lines (105 loc) · 3.91 KB
/
ClinPred.pm
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
=head1 LICENSE
Copyright [1999-2015] Wellcome Trust Sanger Institute and the EMBL-European Bioinformatics Institute
Copyright [2016-2023] EMBL-European Bioinformatics Institute
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
=head1 CONTACT
Ensembl <http://www.ensembl.org/info/about/contact/index.html>
=cut
=head1 NAME
ClinPred
=head1 SYNOPSIS
mv ClinPred.pm ~/.vep/Plugins
./vep -i variations.vcf --plugin ClinPred,file=ClinPred_tabbed.tsv.gz
=head1 DESCRIPTION
This is a plugin for the Ensembl Variant Effect Predictor (VEP) that adds pre-calculated scores from ClinPred.
ClinPred is a prediction tool to identify disease-relevant nonsynonymous variants.
This Plugin is only available for GRCh37
Please cite the ClinPred publication alongside the VEP if you use this resource:
https://www.sciencedirect.com/science/article/pii/S0002929718302714
ClinPred scores can be downloaded from
https://sites.google.com/site/clinpred/download
The following steps are neccessary to tabix the ClinPred.txt.gz file before running the plugin:
gzip -d ClinPred.txt.gz # to unzip the text file
cat ClinPred.txt | tr " " "\t" > ClinPred_tabbed.tsv # to change the file to a tabbed delimited file
sed '1s/.*/#&/' ClinPred_tabbed.tsv > tabbed_ClinPred.tsv # to add a # in the first line of the file
sed '1s/C/c/' tabbed_ClinPred.tsv > ClinPred_tabbed.tsv # to convert the Chr to chr
bgzip ClinPred_tabbed.tsv
tabix -f -s 1 -b 2 -e 2 ClinPred_tabbed.tsv.gz
The tabix utility must be installed in your path to use this plugin.
Check https://github.com/samtools/htslib.git for instructions.
=cut
package ClinPred;
use strict;
use warnings;
use Bio::EnsEMBL::Variation::Utils::BaseVepTabixPlugin;
use base qw(Bio::EnsEMBL::Variation::Utils::BaseVepTabixPlugin);
my %INCLUDE_SO = map {$_ => 1} qw(missense_variant stop_lost stop_gained start_lost);
sub new {
my $class = shift;
my $self = $class->SUPER::new(@_);
$self->expand_left(0);
$self->expand_right(0);
$self->get_user_params();
my $params = $self->params_to_hash();
my $file;
if (!keys %$params) {
$file = $self->params->[0];
$params->{file} = $file;
} else {
$file = $params->{file};
}
$self->add_file($file);
my $assembly = $self->{config}->{assembly};
if ($assembly ne "GRCh37") {
die "Assembly is not GRCh37, ClinPred only works with GRCh37. \n";
}
return $self;
}
sub feature_types {
return ['Transcript'];
}
sub get_header_info {
return { ClinPred => "Prediction tool to identify disease-relevant nonsynonymous single-nucleotide variants" };
}
sub run{
my ($self, $tva) = @_;
return {} unless grep {$INCLUDE_SO{$_->SO_term}} @{$tva->get_all_OverlapConsequences};
my $vf = $tva->variation_feature;
my $allele = $tva->variation_feature_seq;
return {} unless $allele =~ /^[ACGT]$/;
my ($vf_start, $vf_end) = ($vf->{start}, $vf->{end});
($vf_start, $vf_end) = ($vf_end, $vf_start) if ($vf_start > $vf_end);
my ($res) = grep{
$_->{alt} eq $allele &&
$_->{start} == $vf_start &&
$_->{end} == $vf_end
} @{$self->get_data($vf->{chr}, $vf_start, $vf_end)};
return $res ? $res->{result} : {};
}
sub parse_data {
my ($self, $line) = @_;
my ($chr, $start, $ref, $alt, $clinpred_score ) = split("\t", $line);
return {
start => $start,
end => $start,
alt => $alt,
result => {
ClinPred => $clinpred_score,
}
};
}
sub get_start {
return $_[1]->{start};
}
sub get_end {
return $_[1]->{end};
}
1;