Bio/DB/RefSeq.pm

   1 #
   2 # $Id$
   3 #
   4 # BioPerl module for Bio::DB::EMBL
   5 #
   6 # Cared for by Heikki Lehvaslaiho <heikki-at-bioperl-dot-org>
   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::RefSeq - Database object interface for RefSeq retrieval
  17
  18 =head1 SYNOPSIS
  19
  20   use Bio::DB::RefSeq;
  21
  22   $db = Bio::DB::RefSeq->new();
  23
  24   # most of the time RefSeq_ID eq RefSeq acc
  25   $seq = $db->get_Seq_by_id('NM_006732'); # RefSeq ID
  26   print "accession is ", $seq->accession_number, "\n";
  27
  28   # or changeing to accession number and Fasta format ...
  29   $db->request_format('fasta');
  30   $seq = $db->get_Seq_by_acc('NM_006732'); # RefSeq ACC
  31   print "seq is ", $seq->seq, "\n";
  32
  33   # especially when using versions, you better be prepared
  34   # in not getting what what want
  35   eval {
  36       $seq = $db->get_Seq_by_version('NM_006732.1'); # RefSeq VERSION
  37   };
  38   print "accesion is ", $seq->accession_number, "\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   $db = Bio::DB::RefSeq->new(-retrievaltype => 'tempfile' ,
  46                                -format => 'fasta');
  47   my $seqio = $db->get_Stream_by_id(['NM_006732', 'NM_005252'] );
  48   while( my $seq  =  $seqio->next_seq ) {
  49         print "seqid is ", $seq->id, "\n";
  50   }
  51
  52 =head1 DESCRIPTION
  53
  54 Allows the dynamic retrieval of sequence objects L<Bio::Seq> from the
  55 RefSeq database using the dbfetch script at EBI:
  56 L<http:E<sol>E<sol>www.ebi.ac.ukE<sol>cgi-binE<sol>dbfetch>.
  57
  58 In order to make changes transparent we have host type (currently only
  59 ebi) and location (defaults to ebi) separated out.  This allows later
  60 additions of more servers in different geographical locations.
  61
  62 The functionality of this module is inherited from L<Bio::DB::DBFetch>
  63 which implements L<Bio::DB::WebDBSeqI>.
  64
  65 This module retrieves entries from EBI although it
  66 retrives database entries produced at NCBI. When read into bioperl
  67 objects, the parser for GenBank format it used. RefSeq is a
  68 NONSTANDARD GenBank file so be ready for surprises.
  69
  70 =head1 FEEDBACK
  71
  72 =head2 Mailing Lists
  73
  74 User feedback is an integral part of the evolution of this and other
  75 Bioperl modules. Send your comments and suggestions preferably to one
  76 of the Bioperl mailing lists.  Your participation is much appreciated.
  77
  78   bioperl-l@bioperl.org                  - General discussion
  79   http://bioperl.org/wiki/Mailing_lists  - About the mailing lists
  80
  81 =head2 Reporting Bugs
  82
  83 Report bugs to the Bioperl bug tracking system to help us keep track
  84 the bugs and their resolution.  Bug reports can be submitted via the
  85 web:
  86
  87   http://bugzilla.open-bio.org/
  88
  89 =head1 AUTHOR - Heikki Lehvaslaiho
  90
  91 Email Heikki Lehvaslaiho E<lt>heikki-at-bioperl-dot-orgE<gt>
  92
  93 =head1 APPENDIX
  94
  95 The rest of the documentation details each of the object
  96 methods. Internal methods are usually preceded with a _
  97
  98 =cut
  99
 100 # Let the code begin...
 101
 102 package Bio::DB::RefSeq;
 103 use strict;
 104 use vars qw($MODVERSION %HOSTS %FORMATMAP $DEFAULTFORMAT);
 105
 106 $MODVERSION = '0.1';
 107
 108 use base qw(Bio::DB::DBFetch);
 109
 110 BEGIN {
 111     # you can add your own here theoretically.
 112     %HOSTS = (
 113                'dbfetch' => {
 114                    baseurl => 'http://%s/cgi-bin/dbfetch?db=refseq&style=raw',
 115                    hosts   => {
 116                        'ebi'  => 'www.ebi.ac.uk'
 117                        }
 118                }
 119               );
 120     %FORMATMAP = ( 'embl'    => 'embl',
 121                    'genbank' => 'genbank',
 122                    'fasta' => 'fasta'
 123                    );
 124     $DEFAULTFORMAT = 'genbank';
 125 }
 126
 127 sub new {
 128     my ($class, @args ) = @_;
 129     my $self = $class->SUPER::new(@args);
 130
 131     $self->{ '_hosts' } = {};
 132     $self->{ '_formatmap' } = {};
 133
 134     $self->hosts(\%HOSTS);
 135     $self->formatmap(\%FORMATMAP);
 136     $self->{'_default_format'} = $DEFAULTFORMAT;
 137
 138     return $self;
 139 }
 140
 141
 142 sub get_seq_stream {
 143    my ($self,%qualifiers) = @_;
 144    if( exists $qualifiers{'-uids'} ) {
 145        if( ref($qualifiers{'-uids'}) =~ /ARRAY/i ) {
 146            foreach my $u ( @{$qualifiers{'-uids'}} ) {
 147                $u =~ s/^(\S+)\|//;
 148            }
 149        } else {
 150            $qualifiers{'-uids'} =~ s/^(\S+)\|//;
 151        }
 152    }
 153    $self->SUPER::get_seq_stream(%qualifiers);
 154 }
 155
 156 1;