|
0
|
1 #
|
|
|
2 # $Id: EMBL.pm,v 1.12.2.1 2003/06/25 13:44:18 heikki Exp $
|
|
|
3 #
|
|
|
4 # BioPerl module for Bio::DB::EMBL
|
|
|
5 #
|
|
|
6 # Cared for by Heikki Lehvaslaiho <Heikki@ebi.ac.uk>
|
|
|
7 #
|
|
|
8 # Copyright Jason Stajich
|
|
|
9 #
|
|
|
10 # You may distribute this module under the same terms as perl itself
|
|
|
11
|
|
|
12 # POD documentation - main docs before the code
|
|
|
13
|
|
|
14 =head1 NAME
|
|
|
15
|
|
|
16 Bio::DB::EMBL - Database object interface for EMBL entry retrieval
|
|
|
17
|
|
|
18 =head1 SYNOPSIS
|
|
|
19
|
|
|
20 use Bio::DB::EMBL;
|
|
|
21
|
|
|
22 $embl = new Bio::DB::EMBL;
|
|
|
23
|
|
|
24 # remember that EMBL_ID does not equal GenBank_ID!
|
|
|
25 $seq = $embl->get_Seq_by_id('BUM'); # EMBL ID
|
|
|
26 print "cloneid is ", $seq->id, "\n";
|
|
|
27
|
|
|
28 # or changeing to accession number and Fasta format ...
|
|
|
29 $embl->request_format('fasta');
|
|
|
30 $seq = $embl->get_Seq_by_acc('J02231'); # EMBL ACC
|
|
|
31 print "cloneid is ", $seq->id, "\n";
|
|
|
32
|
|
|
33 # especially when using versions, you better be prepared
|
|
|
34 # in not getting what what want
|
|
|
35 eval {
|
|
|
36 $seq = $embl->get_Seq_by_version('J02231.1'); # EMBL VERSION
|
|
|
37 };
|
|
|
38 print "cloneid is ", $seq->id, "\n" unless $@;
|
|
|
39
|
|
|
40 # or ... best when downloading very large files, prevents
|
|
|
41 # keeping all of the file in memory
|
|
|
42
|
|
|
43 # also don't want features, just sequence so let's save bandwith
|
|
|
44 # and request Fasta sequence
|
|
|
45 $embl = new Bio::DB::EMBL(-retrievaltype => 'tempfile' ,
|
|
|
46 -format => 'fasta');
|
|
|
47 my $seqio = $embl->get_Stream_by_batch(['AC013798', 'AC021953'] );
|
|
|
48 while( my $clone = $seqio->next_seq ) {
|
|
|
49 print "cloneid is ", $clone->id, "\n";
|
|
|
50 }
|
|
|
51
|
|
|
52 =head1 DESCRIPTION
|
|
|
53
|
|
|
54 Allows the dynamic retrieval of sequence objects L<Bio::Seq> from the
|
|
|
55 EMBL database using the dbfetch script at EBI:
|
|
|
56 L<http://www.ebi.ac.uk/cgi-bin/dbfetch>.
|
|
|
57
|
|
|
58 In order to make changes transparent we have host type (currently only
|
|
|
59 ebi) and location (defaults to ebi) separated out. This allows later
|
|
|
60 additions of more servers in different geographical locations.
|
|
|
61
|
|
|
62 The functionality of this module is inherited from L<Bio::DB::DBFetch>
|
|
|
63 which implements L<Bio::DB::WebDBSeqI>.
|
|
|
64
|
|
|
65 =head1 FEEDBACK
|
|
|
66
|
|
|
67 =head2 Mailing Lists
|
|
|
68
|
|
|
69 User feedback is an integral part of the evolution of this and other
|
|
|
70 Bioperl modules. Send your comments and suggestions preferably to one
|
|
|
71 of the Bioperl mailing lists. Your participation is much appreciated.
|
|
|
72
|
|
|
73 bioperl-l@bioperl.org - General discussion
|
|
|
74 http://bio.perl.org/MailList.html - About the mailing lists
|
|
|
75
|
|
|
76 =head2 Reporting Bugs
|
|
|
77
|
|
|
78 Report bugs to the Bioperl bug tracking system to help us keep track
|
|
|
79 the bugs and their resolution.
|
|
|
80 Bug reports can be submitted via email or the web:
|
|
|
81
|
|
|
82 bioperl-bugs@bio.perl.org
|
|
|
83 http://bugzilla.bioperl.org/
|
|
|
84
|
|
|
85 =head1 AUTHOR - Heikki Lehvaslaiho
|
|
|
86
|
|
|
87 Email Heikki Lehvaslaiho E<lt>Heikki@ebi.ac.ukE<gt>
|
|
|
88
|
|
|
89 =head1 APPENDIX
|
|
|
90
|
|
|
91 The rest of the documentation details each of the object
|
|
|
92 methods. Internal methods are usually preceded with a _
|
|
|
93
|
|
|
94 =cut
|
|
|
95
|
|
|
96 # Let the code begin...
|
|
|
97
|
|
|
98 package Bio::DB::EMBL;
|
|
|
99 use strict;
|
|
|
100 use vars qw(@ISA $MODVERSION %HOSTS %FORMATMAP $DEFAULTFORMAT);
|
|
|
101
|
|
|
102 $MODVERSION = '0.2';
|
|
|
103 use Bio::DB::DBFetch;
|
|
|
104 use Bio::DB::RefSeq;
|
|
|
105
|
|
|
106 @ISA = qw(Bio::DB::DBFetch);
|
|
|
107
|
|
|
108 BEGIN {
|
|
|
109 # you can add your own here theoretically.
|
|
|
110 %HOSTS = (
|
|
|
111 'dbfetch' => {
|
|
|
112 baseurl => 'http://%s/cgi-bin/dbfetch?db=embl&style=raw',
|
|
|
113 hosts => {
|
|
|
114 'ebi' => 'www.ebi.ac.uk'
|
|
|
115 }
|
|
|
116 }
|
|
|
117 );
|
|
|
118 %FORMATMAP = ( 'embl' => 'embl',
|
|
|
119 'fasta' => 'fasta'
|
|
|
120 );
|
|
|
121 $DEFAULTFORMAT = 'embl';
|
|
|
122 }
|
|
|
123
|
|
|
124 =head2 new
|
|
|
125
|
|
|
126 Title : new
|
|
|
127 Usage : $gb = Bio::DB::GenBank->new(@options)
|
|
|
128 Function: Creates a new genbank handle
|
|
|
129 Returns : New genbank handle
|
|
|
130 Args : -delay number of seconds to delay between fetches (3s)
|
|
|
131
|
|
|
132 NOTE: There are other options that are used internally.
|
|
|
133
|
|
|
134 =cut
|
|
|
135
|
|
|
136 sub new {
|
|
|
137 my ($class, @args ) = @_;
|
|
|
138 my $self = $class->SUPER::new(@args);
|
|
|
139
|
|
|
140 $self->{ '_hosts' } = {};
|
|
|
141 $self->{ '_formatmap' } = {};
|
|
|
142
|
|
|
143 $self->hosts(\%HOSTS);
|
|
|
144 $self->formatmap(\%FORMATMAP);
|
|
|
145 $self->{'_default_format'} = $DEFAULTFORMAT;
|
|
|
146
|
|
|
147 return $self;
|
|
|
148 }
|
|
|
149
|
|
|
150
|
|
|
151 =head2 Bio::DB::WebDBSeqI methods
|
|
|
152
|
|
|
153 Overriding WebDBSeqI method to help newbies to retrieve sequences.
|
|
|
154 EMBL database is all too often passed RefSeq accessions. This
|
|
|
155 redirects those calls. See L<Bio::DB::RefSeq>.
|
|
|
156
|
|
|
157
|
|
|
158 =head2 get_Stream_by_acc
|
|
|
159
|
|
|
160 Title : get_Stream_by_acc
|
|
|
161 Usage : $seq = $db->get_Seq_by_acc([$acc1, $acc2]);
|
|
|
162 Function: Gets a series of Seq objects by accession numbers
|
|
|
163 Returns : a Bio::SeqIO stream object
|
|
|
164 Args : $ref : a reference to an array of accession numbers for
|
|
|
165 the desired sequence entries
|
|
|
166 Note : For GenBank, this just calls the same code for get_Stream_by_id()
|
|
|
167
|
|
|
168 =cut
|
|
|
169
|
|
|
170 sub get_Stream_by_acc {
|
|
|
171 my ($self, $ids ) = @_;
|
|
|
172 my $newdb = $self->_check_id($ids);
|
|
|
173 if ($newdb && $newdb->isa('Bio::DB::RefSeq')) {
|
|
|
174 return $newdb->get_seq_stream('-uids' => $ids, '-mode' => 'single');
|
|
|
175 } else {
|
|
|
176 return $self->get_seq_stream('-uids' => $ids, '-mode' => 'single');
|
|
|
177 }
|
|
|
178 }
|
|
|
179
|
|
|
180
|
|
|
181 =head2 _check_id
|
|
|
182
|
|
|
183 Title : _check_id
|
|
|
184 Usage :
|
|
|
185 Function:
|
|
|
186 Returns : A Bio::DB::RefSeq reference or throws
|
|
|
187 Args : $id(s), $string
|
|
|
188 =cut
|
|
|
189
|
|
|
190 sub _check_id {
|
|
|
191 my ($self, $ids) = @_;
|
|
|
192
|
|
|
193 # NT contigs can not be retrieved
|
|
|
194 $self->throw("NT_ contigs are whole chromosome files which are not part of regular".
|
|
|
195 "database distributions. Go to ftp://ftp.ncbi.nih.gov/genomes/.")
|
|
|
196 if $ids =~ /NT_/;
|
|
|
197
|
|
|
198 # Asking for a RefSeq from EMBL/GenBank
|
|
|
199
|
|
|
200 if ($ids =~ /N._/) {
|
|
|
201 $self->warn("[$ids] is not a normal sequence database but a RefSeq entry.".
|
|
|
202 " Redirecting the request.\n")
|
|
|
203 if $self->verbose >= 0;
|
|
|
204 return new Bio::DB::RefSeq(-verbose => $self->verbose);
|
|
|
205 }
|
|
|
206 }
|
|
|
207
|
|
|
208
|
|
|
209 1;
|
