Bio/DB/RefSeq.pm

   1 #
   2 #
   3 # BioPerl module for Bio::DB::EMBL
   4 #
   5 # Please direct questions and support issues to <bioperl-l@bioperl.org>
   6 #
   7 # Cared for by Heikki Lehvaslaiho <heikki-at-bioperl-dot-org>
   8 #
   9 # Copyright Jason Stajich
  10 #
  11 # You may distribute this module under the same terms as perl itself
  12
  13 # POD documentation - main docs before the code
  14
  15 =head1 NAME
  16
  17 Bio::DB::RefSeq - Database object interface for RefSeq retrieval
  18
  19 =head1 SYNOPSIS
  20
  21   use Bio::DB::RefSeq;
  22
  23   $db = Bio::DB::RefSeq->new();
  24
  25   # most of the time RefSeq_ID eq RefSeq acc
  26   $seq = $db->get_Seq_by_id('NM_006732'); # RefSeq ID
  27   print "accession is ", $seq->accession_number, "\n";
  28
  29   # or changeing to accession number and Fasta format ...
  30   $db->request_format('fasta');
  31   $seq = $db->get_Seq_by_acc('NM_006732'); # RefSeq ACC
  32   print "seq is ", $seq->seq, "\n";
  33
  34   # especially when using versions, you better be prepared
  35   # in not getting what what want
  36   eval {
  37       $seq = $db->get_Seq_by_version('NM_006732.1'); # RefSeq VERSION
  38   };
  39   print "accesion is ", $seq->accession_number, "\n" unless $@;
  40
  41   # or ... best when downloading very large files, prevents
  42   # keeping all of the file in memory
  43
  44   # also don't want features, just sequence so let's save bandwith
  45   # and request Fasta sequence
  46   $db = Bio::DB::RefSeq->new(-retrievaltype => 'tempfile' ,
  47                                -format => 'fasta');
  48   my $seqio = $db->get_Stream_by_id(['NM_006732', 'NM_005252'] );
  49   while( my $seq  =  $seqio->next_seq ) {
  50         print "seqid is ", $seq->id, "\n";
  51   }
  52
  53 =head1 DESCRIPTION
  54
  55 Allows the dynamic retrieval of sequence objects L<Bio::Seq> from the
  56 RefSeq database using the dbfetch script at EBI:
  57
  58 http://www.ebi.ac.uk/Tools/dbfetch/dbfetch
  59
  60 In order to make changes transparent we have host type (currently only
  61 ebi) and location (defaults to ebi) separated out.  This allows later
  62 additions of more servers in different geographical locations.
  63
  64 The functionality of this module is inherited from L<Bio::DB::DBFetch>
  65 which implements L<Bio::DB::WebDBSeqI>.
  66
  67 This module retrieves entries from EBI although it
  68 retrives database entries produced at NCBI. When read into bioperl
  69 objects, the parser for GenBank format it used. RefSeq is a
  70 NONSTANDARD GenBank file so be ready for surprises.
  71
  72 =head1 FEEDBACK
  73
  74 =head2 Mailing Lists
  75
  76 User feedback is an integral part of the evolution of this and other
  77 Bioperl modules. Send your comments and suggestions preferably to one
  78 of the Bioperl mailing lists.  Your participation is much appreciated.
  79
  80   bioperl-l@bioperl.org                  - General discussion
  81   http://bioperl.org/wiki/Mailing_lists  - About the mailing lists
  82
  83 =head2 Support
  84
  85 Please direct usage questions or support issues to the mailing list:
  86
  87 I<bioperl-l@bioperl.org>
  88
  89 rather than to the module maintainer directly. Many experienced and
  90 reponsive experts will be able look at the problem and quickly
  91 address it. Please include a thorough description of the problem
  92 with code and data examples if at all possible.
  93
  94 =head2 Reporting Bugs
  95
  96 Report bugs to the Bioperl bug tracking system to help us keep track
  97 the bugs and their resolution.  Bug reports can be submitted via the
  98 web:
  99
 100   https://github.com/bioperl/bioperl-live/issues
 101
 102 =head1 AUTHOR - Heikki Lehvaslaiho
 103
 104 Email Heikki Lehvaslaiho E<lt>heikki-at-bioperl-dot-orgE<gt>
 105
 106 =head1 APPENDIX
 107
 108 The rest of the documentation details each of the object
 109 methods. Internal methods are usually preceded with a _
 110
 111 =cut
 112
 113 # Let the code begin...
 114
 115 package Bio::DB::RefSeq;
 116 use strict;
 117 use vars qw($MODVERSION %HOSTS %FORMATMAP $DEFAULTFORMAT);
 118
 119 $MODVERSION = '0.1';
 120
 121 use base qw(Bio::DB::DBFetch);
 122
 123 BEGIN {
 124     # you can add your own here theoretically.
 125     %HOSTS = (
 126                'dbfetch' => {
 127                    baseurl => 'http://%s/Tools/dbfetch/dbfetch?db=refseq&style=raw',
 128                    hosts   => {
 129                        'ebi'  => 'www.ebi.ac.uk'
 130                        }
 131                }
 132               );
 133     %FORMATMAP = ( 'embl'    => 'embl',
 134                    'genbank' => 'genbank',
 135                    'fasta' => 'fasta'
 136                    );
 137     $DEFAULTFORMAT = 'genbank';
 138 }
 139
 140 sub new {
 141     my ($class, @args ) = @_;
 142     my $self = $class->SUPER::new(@args);
 143
 144     $self->{ '_hosts' } = {};
 145     $self->{ '_formatmap' } = {};
 146
 147     $self->hosts(\%HOSTS);
 148     $self->formatmap(\%FORMATMAP);
 149     $self->{'_default_format'} = $DEFAULTFORMAT;
 150
 151     return $self;
 152 }
 153
 154
 155 sub get_seq_stream {
 156    my ($self,%qualifiers) = @_;
 157    if( exists $qualifiers{'-uids'} ) {
 158        if( ref($qualifiers{'-uids'}) =~ /ARRAY/i ) {
 159            foreach my $u ( @{$qualifiers{'-uids'}} ) {
 160                $u =~ s/^(\S+)\|//;
 161            }
 162        } else {
 163            $qualifiers{'-uids'} =~ s/^(\S+)\|//;
 164        }
 165    }
 166    $self->SUPER::get_seq_stream(%qualifiers);
 167 }
 168
 169 1;