-
Notifications
You must be signed in to change notification settings - Fork 117
/
FlagLRG.pm
125 lines (76 loc) · 2.57 KB
/
FlagLRG.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
=head1 LICENSE
Copyright 2018 QIMR Berghofer Medical Research 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
Stephen Kazakoff <[email protected]>
=cut
=head1 NAME
FlagLRG
=head1 SYNOPSIS
mv FlagLRG.pm ~/.vep/Plugins
./vep -i variants.vcf --plugin FlagLRG,/path/to/list_LRGs_transcripts_xrefs.txt
=head1 DESCRIPTION
A VEP plugin that retrieves the LRG ID matching either the RefSeq or Ensembl
transcript IDs.
You can obtain the 'list_LRGs_transcripts_xrefs.txt' using:
> wget https://ftp.ebi.ac.uk/pub/databases/lrgex/list_LRGs_transcripts_xrefs.txt
=cut
package FlagLRG;
use strict;
use warnings;
use Text::CSV;
use Bio::EnsEMBL::Variation::Utils::BaseVepPlugin;
use base qw(Bio::EnsEMBL::Variation::Utils::BaseVepPlugin);
sub new {
my $class = shift;
my $self = $class->SUPER::new(@_);
my $params = $self->params;
my $file = shift @$params;
die("ERROR: FlagLRG $file not found\n") unless $file && -e $file;
open(my $fh, $file) or die $!;
chomp(my $header_line = <$fh>);
$header_line =~ s/^#\s*//;
chomp(my $column_names = <$fh>);
$column_names =~ s/^#\s*//;
my $tsv = Text::CSV->new({ binary => 1, auto_diag => 1, sep_char => "\t" });
$tsv->parse($column_names);
$tsv->column_names($tsv->fields);
while (my $href = $tsv->getline_hr($fh)) {
my $lrg_tr = $href->{'LRG'} . $href->{'LRG_TRANSCRIPT'};
my $refseq_tr = $href->{'REFSEQ_TRANSCRIPT'};
my $ensembl_tr = $href->{'ENSEMBL_TRANSCRIPT'};
$self->{cache}{$refseq_tr} = $lrg_tr unless $refseq_tr eq '-';
$self->{cache}{$ensembl_tr} = $lrg_tr unless $ensembl_tr eq '-';
}
close $fh;
$self->{header_line} = $header_line;
return $self;
}
sub feature_types {
return ['Transcript'];
}
sub get_header_info {
my $self = shift;
return {
FlagLRG => $self->{header_line},
};
}
sub run {
my ($self, $tva) = @_;
my $tr = $tva->transcript;
my $tr_id = $tr->stable_id;
$tr_id .= '.'.$tr->version unless $tr_id =~ /\.\d+$/;
if (defined(my $lrg_tr = $self->{cache}{$tr_id})) {
return { FlagLRG => $lrg_tr };
}
return {};
}
1;