forked from Ensembl/VEP_plugins
-
Notifications
You must be signed in to change notification settings - Fork 0
/
dbNSFP.pm
297 lines (211 loc) · 7.84 KB
/
dbNSFP.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
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
=head1 LICENSE
Copyright [1999-2015] Wellcome Trust Sanger Institute and the EMBL-European Bioinformatics Institute
Copyright [2016] 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
Will McLaren <[email protected]>
=cut
=head1 NAME
dbNSFP
=head1 SYNOPSIS
mv dbNSFP.pm ~/.vep/Plugins
perl variant_effect_predictor.pl -i variations.vcf --plugin dbNSFP,/path/to/dbNSFP.gz,col1,col2
=head1 DESCRIPTION
A VEP plugin that retrieves data for missense variants from a tabix-indexed
dbNSFP file.
Please cite the dbNSFP publication alongside the VEP if you use this resource:
http://www.ncbi.nlm.nih.gov/pubmed/21520341
The tabix utility must be installed in your path to use this plugin. The dbNSFP
data file can be downloaded from
https://sites.google.com/site/jpopgen/dbNSFP.
The file must be processed and indexed by tabix before use by this plugin:
> wget ftp://dbnsfp:[email protected]/dbNSFPv3.2a.zip
> unzip dbNSFPv3.2a.zip
> head -n1 dbNSFP3.2a_variant.chr1 > h
> cat dbNSFP3.2a_variant.chr* | grep -v ^#chr | sort -k1,1 -k2,2n - | cat h - | bgzip -c > dbNSFP.gz
> tabix -s 1 -b 2 -e 2 dbNSFP.gz
When running the plugin you must list at least one column to retrieve from the
dbNSFP file, specified as parameters to the plugin e.g.
--plugin dbNSFP,/path/to/dbNSFP.gz,LRT_score,GERP++_RS
Tabix also allows the data file to be hosted on a remote server. This plugin is
fully compatible with such a setup - simply use the URL of the remote file:
--plugin dbNSFP,http://my.files.com/dbNSFP.gz,col1,col2
Note that transcript sequences referred to in dbNSFP may be out of sync with
those in the latest release of Ensembl; this may lead to discrepancies with
scores retrieved from other sources.
If the dbNSFP README file is found in the same directory as the data file,
column descriptions will be read from this and incorporated into the VEP output
file header.
=cut
package dbNSFP;
use strict;
use warnings;
use Bio::EnsEMBL::Utils::Sequence qw(reverse_comp);
use Bio::EnsEMBL::Variation::Utils::BaseVepTabixPlugin;
use base qw(Bio::EnsEMBL::Variation::Utils::BaseVepTabixPlugin);
sub new {
my $class = shift;
my $self = $class->SUPER::new(@_);
$self->expand_left(0);
$self->expand_right(0);
# get dbNSFP file
my $file = $self->params->[0];
$self->add_file($file);
# get headers
open HEAD, "tabix -fh $file 1:1-1 2>&1 | ";
while(<HEAD>) {
next unless /^\#/;
chomp;
$self->{headers} = [split];
}
close HEAD;
die "ERROR: Could not read headers from $file\n" unless defined($self->{headers}) && scalar @{$self->{headers}};
# check alt and Ensembl_transcriptid headers
foreach my $h(qw(alt Ensembl_transcriptid)) {
die "ERROR: Could not find required column $h in $file\n" unless grep {$_ eq $h} @{$self->{headers}};
}
# get required columns
my $i = 1;
while(defined($self->params->[$i])) {
my $col = $self->params->[$i];
die "ERROR: Column $col not found in header for file $file. Available columns are:\n".join(",", @{$self->{headers}})."\n" unless grep {$_ eq $col} @{$self->{headers}};
$self->{cols}->{$self->params->[$i]} = 1;
$i++;
}
die "ERROR: No columns selected to fetch. Available columns are:\n".join(",", @{$self->{headers}})."\n" unless defined($self->{cols}) && scalar keys %{$self->{cols}};
return $self;
}
sub feature_types {
return ['Transcript'];
}
sub get_header_info {
my $self = shift;
if(!exists($self->{_header_info})) {
# look for readme
my $file_dir = $self->files->[0];
my %rm_descs;
# won't work for remote
if($file_dir !~ /tp\:\/\//) {
# get just dir
$file_dir =~ s/\/[^\/]+$/\//;
if(opendir DIR, $file_dir) {
my ($readme_file) = grep {/dbnsfp.*readme\.txt/i} readdir DIR;
closedir DIR;
if(open RM, $file_dir.$readme_file) {
my ($col, $reading);
# parse dbNSFP readme
# relevant lines look like:
#
# 1 column1_name: description blah blah
# blah blah blah
# 2 column2_name: description blah blah
# blah blah blah
while(<RM>) {
chomp;
s/\r$//g;
if(/^\d+\s/) {
$reading = 1;
m/^\d+\s+(.+?)\:\s+(.+)/;
$col = $1;
$rm_descs{$col} = '(from dbNSFP) '.$2;
}
elsif($reading && /\w/) {
s/^\s+//;
$rm_descs{$col} .= ' '.$_;
}
else {
$reading = 0;
}
}
close RM;
# remove multiple spaces
$rm_descs{$_} =~ s/\s+/ /g for keys %rm_descs;
}
}
}
$self->{_header_info} = {map {$_ => $rm_descs{$_} || ($_.' from dbNSFP file '.$self->{file})} keys %{$self->{cols}}};
}
return $self->{_header_info};
}
sub run {
my ($self, $tva) = @_;
# only for missense variants
return {} unless grep {$_->SO_term eq 'missense_variant'} @{$tva->get_all_OverlapConsequences};
my $vf = $tva->variation_feature;
return {} unless $vf->{start} eq $vf->{end};
# get allele, reverse comp if needed
my $allele = $tva->variation_feature_seq;
reverse_comp(\$allele) if $vf->{strand} < 0;
return {} unless $allele =~ /^[ACGT]$/;
# get transcript stable ID
my $tr_id = $tva->transcript->stable_id;
my $data;
my $pos;
foreach my $tmp_data(@{$self->get_data($vf->{chr}, $vf->{start} - 1, $vf->{end})}) {
# compare allele and transcript
if (exists $tmp_data->{'pos(1-based)'}) {
$pos = $tmp_data->{'pos(1-based)'}
} else {
# for dbNSFP version 2.9.1
$pos = $tmp_data->{'pos(1-coor)'}
}
next unless
${pos} == $vf->{start} &&
defined($tmp_data->{alt}) &&
$tmp_data->{alt} eq $allele;
# make a clean copy as we're going to edit it
%$data = %$tmp_data;
# convert data with multiple transcript values
# if($data->{Ensembl_transcriptid} =~ m/\;/) {
# # find the "index" of this transcript
# my @tr_ids = split(';', $data->{Ensembl_transcriptid});
# my $tr_index;
# for my $i(0..$#tr_ids) {
# $tr_index = $i;
# last if $tr_ids[$tr_index] =~ /^$tr_id(\.\d+)?$/;
# }
# next unless defined($tr_index);
# # now alter other fields
# foreach my $key(keys %$data) {
# if($data->{$key} =~ m/\;/) {
# my @split = split(';', $data->{$key});
# die("ERROR: Transcript index out of range") if $tr_index > $#split;
# $data->{$key} = $split[$tr_index];
# }
# }
# }
last;
}
return {} unless scalar keys %$data;
# get required data
my %return =
map {$_ => ($data->{$_} =~ s/[|]/&/gr) } # replace | with & to prevent conflict with existing field sep
map {$data->{$_} =~ s/\;/\,/g; $_ }
grep {$data->{$_} ne '.'} # ignore missing data
grep {defined($self->{cols}->{$_})} # only include selected cols
keys %$data;
return \%return;
}
sub parse_data {
my ($self, $line) = @_;
$line =~ s/\r$//g;
my @split = split /\t/, $line;
# parse data into hash of col names and values
my %data = map {$self->{headers}->[$_] => $split[$_]} (0..(scalar @{$self->{headers}} - 1));
return \%data;
}
sub get_start {
return $_[1]->{'pos(1-based)'};
}
sub get_end {
return $_[1]->{'pos(1-based)'};
}
1;