| line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
|
1
|
|
|
|
|
|
|
=head1 NAME |
|
2
|
|
|
|
|
|
|
|
|
3
|
|
|
|
|
|
|
Bio::ASN1::EntrezGene::Indexer - Indexes NCBI Entrez Gene files. |
|
4
|
|
|
|
|
|
|
|
|
5
|
|
|
|
|
|
|
=head1 SYNOPSIS |
|
6
|
|
|
|
|
|
|
|
|
7
|
|
|
|
|
|
|
use Bio::ASN1::EntrezGene::Indexer; |
|
8
|
|
|
|
|
|
|
|
|
9
|
|
|
|
|
|
|
# creating & using the index is just a few lines |
|
10
|
|
|
|
|
|
|
my $inx = Bio::ASN1::EntrezGene::Indexer->new( |
|
11
|
|
|
|
|
|
|
-filename => 'entrezgene.idx', |
|
12
|
|
|
|
|
|
|
-write_flag => 'WRITE'); # needed for make_index call, but if opening |
|
13
|
|
|
|
|
|
|
# existing index file, don't set write flag! |
|
14
|
|
|
|
|
|
|
$inx->make_index('Homo_sapiens', 'Mus_musculus', 'Rattus_norvegicus'); |
|
15
|
|
|
|
|
|
|
my $seq = $inx->fetch(10); # Bio::Seq obj for Entrez Gene #10 |
|
16
|
|
|
|
|
|
|
# alternatively, if one prefers just a data structure instead of objects |
|
17
|
|
|
|
|
|
|
$seq = $inx->fetch_hash(10); # a hash produced by Bio::ASN1::EntrezGene |
|
18
|
|
|
|
|
|
|
# that contains all data in the Entrez Gene record |
|
19
|
|
|
|
|
|
|
|
|
20
|
|
|
|
|
|
|
# note that in case you wonder, you can get the files 'Homo_sapiens' |
|
21
|
|
|
|
|
|
|
# from NCBI Entrez Gene ftp download, DATA/ASN/Mammalia directory |
|
22
|
|
|
|
|
|
|
|
|
23
|
|
|
|
|
|
|
=head1 PREREQUISITE |
|
24
|
|
|
|
|
|
|
|
|
25
|
|
|
|
|
|
|
Bio::ASN1::EntrezGene, Bioperl version that contains Stefan Kirov's |
|
26
|
|
|
|
|
|
|
entrezgene.pm and all dependencies therein. |
|
27
|
|
|
|
|
|
|
|
|
28
|
|
|
|
|
|
|
=head1 INSTALLATION |
|
29
|
|
|
|
|
|
|
|
|
30
|
|
|
|
|
|
|
Same as Bio::ASN1::EntrezGene |
|
31
|
|
|
|
|
|
|
|
|
32
|
|
|
|
|
|
|
=head1 DESCRIPTION |
|
33
|
|
|
|
|
|
|
|
|
34
|
|
|
|
|
|
|
Bio::ASN1::EntrezGene::Indexer is a Perl Indexer for NCBI Entrez Gene genome |
|
35
|
|
|
|
|
|
|
databases. It processes an ASN.1-formatted Entrez Gene record and stores the |
|
36
|
|
|
|
|
|
|
file position for each record in a way compliant with Bioperl standard (in |
|
37
|
|
|
|
|
|
|
fact its a subclass of Bioperl's index objects). |
|
38
|
|
|
|
|
|
|
|
|
39
|
|
|
|
|
|
|
Note that this module does not parse record, because it needs to run fast and |
|
40
|
|
|
|
|
|
|
grab only the gene ids. For parsing record, use Bio::ASN1::EntrezGene, or |
|
41
|
|
|
|
|
|
|
better yet, use Bio::SeqIO, format 'entrezgene'. |
|
42
|
|
|
|
|
|
|
|
|
43
|
|
|
|
|
|
|
It takes this module (version 1.07) 21 seconds to index the human genome |
|
44
|
|
|
|
|
|
|
Entrez Gene file (Apr. 5/2005 download) on one 2.4 GHz Intel Xeon processor. |
|
45
|
|
|
|
|
|
|
|
|
46
|
|
|
|
|
|
|
=head1 SEE ALSO |
|
47
|
|
|
|
|
|
|
|
|
48
|
|
|
|
|
|
|
For details on various parsers I generated for Entrez Gene, example scripts that |
|
49
|
|
|
|
|
|
|
uses/benchmarks the modules, please see L<http://sourceforge.net/projects/egparser/>. |
|
50
|
|
|
|
|
|
|
Those other parsers etc. are included in V1.05 download. |
|
51
|
|
|
|
|
|
|
|
|
52
|
|
|
|
|
|
|
=head1 AUTHOR |
|
53
|
|
|
|
|
|
|
|
|
54
|
|
|
|
|
|
|
Dr. Mingyi Liu <mingyi.liu@gpc-biotech.com> |
|
55
|
|
|
|
|
|
|
|
|
56
|
|
|
|
|
|
|
=head1 COPYRIGHT |
|
57
|
|
|
|
|
|
|
|
|
58
|
|
|
|
|
|
|
The Bio::ASN1::EntrezGene module and its related modules and scripts |
|
59
|
|
|
|
|
|
|
are copyright (c) 2005 Mingyi Liu, GPC Biotech AG and Altana Research |
|
60
|
|
|
|
|
|
|
Institute. All rights reserved. I created these modules when working |
|
61
|
|
|
|
|
|
|
on a collaboration project between these two companies. Therefore a |
|
62
|
|
|
|
|
|
|
special thanks for the two companies to allow the release of the code |
|
63
|
|
|
|
|
|
|
into public domain. |
|
64
|
|
|
|
|
|
|
|
|
65
|
|
|
|
|
|
|
You may use and distribute them under the terms of the Perl itself or |
|
66
|
|
|
|
|
|
|
GPL (L<http://www.gnu.org/copyleft/gpl.html>). |
|
67
|
|
|
|
|
|
|
|
|
68
|
|
|
|
|
|
|
=head1 CITATION |
|
69
|
|
|
|
|
|
|
|
|
70
|
|
|
|
|
|
|
Liu, M and Grigoriev, A (2005) "Fast Parsers for Entrez Gene" |
|
71
|
|
|
|
|
|
|
Bioinformatics. In press |
|
72
|
|
|
|
|
|
|
|
|
73
|
|
|
|
|
|
|
=head1 OPERATION SYSTEMS SUPPORTED |
|
74
|
|
|
|
|
|
|
|
|
75
|
|
|
|
|
|
|
Any OS that Perl & Bioperl run on. |
|
76
|
|
|
|
|
|
|
|
|
77
|
|
|
|
|
|
|
=head1 METHODS |
|
78
|
|
|
|
|
|
|
|
|
79
|
|
|
|
|
|
|
=cut |
|
80
|
|
|
|
|
|
|
|
|
81
|
|
|
|
|
|
|
package Bio::ASN1::EntrezGene::Indexer; |
|
82
|
|
|
|
|
|
|
|
|
83
|
1
|
|
|
1
|
|
14
|
use strict; |
|
|
1
|
|
|
|
|
10
|
|
|
|
1
|
|
|
|
|
15
|
|
|
84
|
1
|
|
|
1
|
|
14
|
use Carp qw(carp croak); |
|
|
1
|
|
|
|
|
9
|
|
|
|
1
|
|
|
|
|
19
|
|
|
85
|
1
|
|
|
1
|
|
15
|
use vars qw ($VERSION @ISA); |
|
|
1
|
|
|
|
|
9
|
|
|
|
1
|
|
|
|
|
14
|
|
|
86
|
1
|
|
|
1
|
|
21
|
use Bio::ASN1::EntrezGene; |
|
|
1
|
|
|
|
|
10
|
|
|
|
1
|
|
|
|
|
69
|
|
|
87
|
1
|
|
|
1
|
|
17
|
use Bio::Index::AbstractSeq; |
|
|
0
|
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
88
|
|
|
|
|
|
|
|
|
89
|
|
|
|
|
|
|
@ISA = qw(Bio::Index::AbstractSeq); |
|
90
|
|
|
|
|
|
|
$VERSION = '1.09'; |
|
91
|
|
|
|
|
|
|
|
|
92
|
|
|
|
|
|
|
sub _version |
|
93
|
|
|
|
|
|
|
{ |
|
94
|
|
|
|
|
|
|
return $VERSION; |
|
95
|
|
|
|
|
|
|
} |
|
96
|
|
|
|
|
|
|
|
|
97
|
|
|
|
|
|
|
sub _type_stamp |
|
98
|
|
|
|
|
|
|
{ |
|
99
|
|
|
|
|
|
|
return '__EntrezGene_ASN1__'; |
|
100
|
|
|
|
|
|
|
} |
|
101
|
|
|
|
|
|
|
|
|
102
|
|
|
|
|
|
|
sub _index_file |
|
103
|
|
|
|
|
|
|
{ |
|
104
|
|
|
|
|
|
|
my($self, $file, $idx) = @_; |
|
105
|
|
|
|
|
|
|
my $position; |
|
106
|
|
|
|
|
|
|
open(IN, $file) || $self->throw("Can't open $file - $!"); |
|
107
|
|
|
|
|
|
|
local $/ = "Entrezgene ::= {"; |
|
108
|
|
|
|
|
|
|
while(<IN>) |
|
109
|
|
|
|
|
|
|
{ |
|
110
|
|
|
|
|
|
|
chomp; |
|
111
|
|
|
|
|
|
|
$self->add_record($1, $idx, $position) if (/[,{}]\s+geneid\s*(\d+)\s+[,{}]/i); |
|
112
|
|
|
|
|
|
|
$position = tell(IN) - 16; |
|
113
|
|
|
|
|
|
|
} |
|
114
|
|
|
|
|
|
|
close(IN); |
|
115
|
|
|
|
|
|
|
return 1; |
|
116
|
|
|
|
|
|
|
} |
|
117
|
|
|
|
|
|
|
|
|
118
|
|
|
|
|
|
|
sub _file_format |
|
119
|
|
|
|
|
|
|
{ |
|
120
|
|
|
|
|
|
|
return 'entrezgene'; |
|
121
|
|
|
|
|
|
|
} |
|
122
|
|
|
|
|
|
|
|
|
123
|
|
|
|
|
|
|
=head2 fetch |
|
124
|
|
|
|
|
|
|
|
|
125
|
|
|
|
|
|
|
Parameters: $geneid - id for the Entrez Gene record to be retrieved |
|
126
|
|
|
|
|
|
|
Example: my $hash = $indexer->fetch(10); # get Entrez Gene #10 |
|
127
|
|
|
|
|
|
|
Function: fetch the data for the given Entrez Gene id. |
|
128
|
|
|
|
|
|
|
Returns: A Bio::Seq object produced by Bio::SeqIO::entrezgene |
|
129
|
|
|
|
|
|
|
Notes: One needs to have Bio::SeqIO::entrezgene installed before |
|
130
|
|
|
|
|
|
|
calling this function! |
|
131
|
|
|
|
|
|
|
|
|
132
|
|
|
|
|
|
|
=cut |
|
133
|
|
|
|
|
|
|
|
|
134
|
|
|
|
|
|
|
=head2 fetch_hash |
|
135
|
|
|
|
|
|
|
|
|
136
|
|
|
|
|
|
|
Parameters: $geneid - id for the Entrez Gene record to be retrieved |
|
137
|
|
|
|
|
|
|
Example: my $hash = $indexer->fetch_hash(10); # get Entrez Gene #10 |
|
138
|
|
|
|
|
|
|
Function: fetch a hash produced by Bio::ASN1::EntrezGene for given Entrez |
|
139
|
|
|
|
|
|
|
Gene id. |
|
140
|
|
|
|
|
|
|
Returns: A data structure containing all data items from the Entrez |
|
141
|
|
|
|
|
|
|
Gene record. |
|
142
|
|
|
|
|
|
|
Notes: Alternative to fetch() |
|
143
|
|
|
|
|
|
|
|
|
144
|
|
|
|
|
|
|
=cut |
|
145
|
|
|
|
|
|
|
|
|
146
|
|
|
|
|
|
|
sub fetch_hash |
|
147
|
|
|
|
|
|
|
{ |
|
148
|
|
|
|
|
|
|
my ($self, $geneid) = @_; |
|
149
|
|
|
|
|
|
|
if (my $gene = $self->db->{$geneid}) |
|
150
|
|
|
|
|
|
|
{ |
|
151
|
|
|
|
|
|
|
my ($fileno, $position) = $self->unpack_record($gene); |
|
152
|
|
|
|
|
|
|
my $parser = Bio::ASN1::EntrezGene->new('fh' => $self->_file_handle($fileno)); |
|
153
|
|
|
|
|
|
|
seek($parser->fh, $position, 0); |
|
154
|
|
|
|
|
|
|
return $parser->next_seq; |
|
155
|
|
|
|
|
|
|
} |
|
156
|
|
|
|
|
|
|
} |
|
157
|
|
|
|
|
|
|
|
|
158
|
|
|
|
|
|
|
=head2 _file_handle |
|
159
|
|
|
|
|
|
|
|
|
160
|
|
|
|
|
|
|
Title : _file_handle |
|
161
|
|
|
|
|
|
|
Usage : $fh = $index->_file_handle( INT ) |
|
162
|
|
|
|
|
|
|
Function: Returns an open filehandle for the file |
|
163
|
|
|
|
|
|
|
index INT. On opening a new filehandle it |
|
164
|
|
|
|
|
|
|
caches it in the @{$index->_filehandle} array. |
|
165
|
|
|
|
|
|
|
If the requested filehandle is already open, |
|
166
|
|
|
|
|
|
|
it simply returns it from the array. |
|
167
|
|
|
|
|
|
|
Example : $fist_file_indexed = $index->_file_handle( 0 ); |
|
168
|
|
|
|
|
|
|
Returns : ref to a filehandle |
|
169
|
|
|
|
|
|
|
Args : INT |
|
170
|
|
|
|
|
|
|
Notes : This function is copied from Bio::Index::Abstract. Once that module |
|
171
|
|
|
|
|
|
|
changes file handle code like I do below to fit perl 5.005_03, this |
|
172
|
|
|
|
|
|
|
sub would be removed from this module |
|
173
|
|
|
|
|
|
|
|
|
174
|
|
|
|
|
|
|
=cut |
|
175
|
|
|
|
|
|
|
|
|
176
|
|
|
|
|
|
|
sub _file_handle { |
|
177
|
|
|
|
|
|
|
my( $self, $i ) = @_; |
|
178
|
|
|
|
|
|
|
|
|
179
|
|
|
|
|
|
|
unless ($self->{'_filehandle'}[$i]) { |
|
180
|
|
|
|
|
|
|
my @rec = $self->unpack_record($self->db->{"__FILE_$i"}) |
|
181
|
|
|
|
|
|
|
or $self->throw("Can't get filename for index : $i"); |
|
182
|
|
|
|
|
|
|
my $file = $rec[0]; |
|
183
|
|
|
|
|
|
|
local *FH; |
|
184
|
|
|
|
|
|
|
open *FH, $file or $self->throw("Can't read file '$file' : $!"); |
|
185
|
|
|
|
|
|
|
$self->{'_filehandle'}[$i] = *FH; |
|
186
|
|
|
|
|
|
|
} |
|
187
|
|
|
|
|
|
|
return $self->{'_filehandle'}[$i]; |
|
188
|
|
|
|
|
|
|
} |
|
189
|
|
|
|
|
|
|
|
|
190
|
|
|
|
|
|
|
1; |
|
191
|
|
|
|
|
|
|
|
|
192
|
|
|
|
|
|
|
|