annotate variant_effect_predictor/Bio/Index/EMBL.pm @ 0:2bc9b66ada89 draft default tip

Uploaded
author mahtabm
date Thu, 11 Apr 2013 06:29:17 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
1 # $Id: EMBL.pm,v 1.21.2.1 2003/03/19 16:23:08 heikki Exp $
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
2 #
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
3 # BioPerl module for Bio::Index::EMBL
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
4 #
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
5 # Cared for by Ewan Birney <birney@sanger.ac.uk>
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
6 #
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
7 # You may distribute this module under the same terms as perl itself
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
8
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
9 # POD documentation - main docs before the code
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
10
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
11 =head1 NAME
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
12
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
13 Bio::Index::EMBL - Interface for indexing (multiple) EMBL/Swissprot
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
14 .dat files (ie flat file embl/swissprot format).
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
15
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
16 =head1 SYNOPSIS
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
17
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
18 # Complete code for making an index for several
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
19 # EMBL files
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
20 use Bio::Index::EMBL;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
21 use strict;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
22
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
23 my $Index_File_Name = shift;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
24 my $inx = Bio::Index::EMBL->new('-filename' => $Index_File_Name,
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
25 '-write_flag' => 'WRITE');
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
26 $inx->make_index(@ARGV);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
27
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
28 # Print out several sequences present in the index
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
29 # in Fasta format
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
30 use Bio::Index::EMBL;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
31 use strict;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
32
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
33 my $Index_File_Name = shift;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
34 my $inx = Bio::Index::EMBL->new('-filename' => $Index_File_Name);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
35 my $out = Bio::SeqIO->new('-format' => 'Fasta','-fh' => \*STDOUT);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
36
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
37 foreach my $id (@ARGV) {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
38 my $seq = $inx->fetch($id); # Returns Bio::Seq object
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
39 $out->write_seq($seq);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
40 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
41
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
42 # alternatively
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
43
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
44 my $seq1 = $inx->get_Seq_by_id($id);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
45 my $seq2 = $inx->get_Seq_by_acc($acc);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
46
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
47 =head1 DESCRIPTION
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
48
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
49 Inherits functions for managing dbm files from Bio::Index::Abstract.pm,
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
50 and provides the basic funtionallity for indexing EMBL files, and
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
51 retrieving the sequence from them. Heavily snaffled from James Gilbert's
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
52 Fasta system. Note: for best results 'use strict'.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
53
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
54 =head1 FEED_BACK
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
55
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
56 =head2 Mailing Lists
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
57
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
58 User feedback is an integral part of the evolution of this and other
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
59 Bioperl modules. Send your comments and suggestions preferably to one
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
60 of the Bioperl mailing lists. Your participation is much appreciated.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
61
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
62 bioperl-l@bioperl.org - General discussion
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
63 http://bioperl.org/MailList.shtml - About the mailing lists
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
64
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
65
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
66
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
67 =head2 Reporting Bugs
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
68
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
69 Report bugs to the Bioperl bug tracking system to help us keep track
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
70 the bugs and their resolution. Bug reports can be submitted via
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
71 email or the web:
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
72
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
73 bioperl-bugs@bio.perl.org
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
74 http://bugzilla.bioperl.org/
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
75
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
76 =head1 AUTHOR - Ewan Birney
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
77
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
78 Email - birney@sanger.ac.uk
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
79
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
80 =head1 APPENDIX
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
81
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
82 The rest of the documentation details each of the object methods. Internal methods are usually preceded with a _
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
83
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
84 =cut
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
85
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
86
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
87 # Let's begin the code...
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
88
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
89
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
90 package Bio::Index::EMBL;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
91
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
92 use vars qw($VERSION @ISA);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
93 use strict;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
94
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
95 use Bio::Index::AbstractSeq;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
96 use Bio::Seq;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
97
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
98 @ISA = qw(Bio::Index::AbstractSeq);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
99
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
100 sub _type_stamp {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
101 return '__EMBL_FLAT__'; # What kind of index are we?
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
102 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
103
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
104 #
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
105 # Suggested fix by Michael G Schwern <schwern@pobox.com> to
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
106 # get around a clash with CPAN shell...
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
107 #
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
108
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
109 BEGIN {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
110 $VERSION = 0.1;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
111 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
112
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
113 sub _version {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
114 return $VERSION;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
115 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
116
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
117 =head2 _index_file
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
118
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
119 Title : _index_file
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
120 Usage : $index->_index_file( $file_name, $i )
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
121 Function: Specialist function to index EMBL format files.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
122 Is provided with a filename and an integer
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
123 by make_index in its SUPER class.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
124 Example :
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
125 Returns :
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
126 Args :
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
127
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
128 =cut
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
129
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
130 sub _index_file {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
131 my( $self,
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
132 $file, # File name
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
133 $i # Index-number of file being indexed
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
134 ) = @_;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
135
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
136 my( $begin, # Offset from start of file of the start
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
137 # of the last found record.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
138 $id, # ID of last found record.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
139 @accs, # accession of last record. Also put into the index
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
140 );
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
141
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
142 $begin = 0;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
143
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
144 open EMBL, $file or $self->throw("Can't open file for read : $file");
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
145
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
146 # Main indexing loop
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
147 $id = undef;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
148 @accs = ();
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
149 while (<EMBL>) {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
150 if( /^\/\// ) {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
151 if( ! defined $id ) {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
152 $self->throw("Got to a end of entry line for an EMBL flat file with no parsed ID. Considering this a problem!");
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
153 next;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
154 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
155 if( ! @accs ) {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
156 $self->warn("For id [$id] in embl flat file, got no accession number. Storing id index anyway");
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
157 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
158
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
159 $self->add_record($id, $i, $begin);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
160
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
161 foreach my $acc (@accs) {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
162 if( $acc ne $id ) {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
163 $self->add_record($acc, $i, $begin);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
164 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
165 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
166 } elsif (/^ID\s+(\S+)/) {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
167 $id = $1;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
168 # not sure if I like this. Assummes tell is in bytes.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
169 # we could tell before each line and save it.
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
170 $begin = tell(EMBL) - length( $_ );
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
171
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
172 } elsif (/^AC\s+(.*)?/) {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
173 push @accs , split (/[; ]+/, $1);
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
174 } else {
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
175 # do nothing
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
176 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
177 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
178
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
179 close EMBL;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
180 return 1;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
181 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
182
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
183 =head2 _file_format
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
184
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
185 Title : _file_format
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
186 Usage : Internal function for indexing system
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
187 Function: Provides file format for this database
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
188 Example :
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
189 Returns :
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
190 Args :
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
191
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
192
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
193 =cut
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
194
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
195 sub _file_format{
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
196 my ($self,@args) = @_;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
197
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
198 return 'EMBL';
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
199 }
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
200
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
201
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
202
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
203 1;
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
204
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
205
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
206
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
207
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
208
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
209
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
210
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
211
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
212
2bc9b66ada89 Uploaded
mahtabm
parents:
diff changeset
213