view release on metacpan or  search on metacpan

lib/Bio/DB/BioFetch.pm  view on Meta::CPAN

#
# BioPerl module for Bio::DB::BioFetch
#
# Please direct questions and support issues to <bioperl-l@bioperl.org>
#
# Cared for by Lincoln Stein <lstein@cshl.org>
#
# Copyright Lincoln Stein
#
# You may distribute this module under the same terms as perl itself
#
# POD documentation - main docs before the code
#

package Bio::DB::BioFetch;
$Bio::DB::BioFetch::VERSION = '1.7.3';
use strict;

use Carp;

use HTTP::Request::Common 'POST';

=head1 NAME

Bio::DB::BioFetch - Database object interface to BioFetch retrieval

=head1 SYNOPSIS

 use Bio::DB::BioFetch;

 $bf = Bio::DB::BioFetch->new();

 $seq = $bf->get_Seq_by_id('HSFOS');  # EMBL or SWALL ID

 # change formats, storage procedures
 $bf = Bio::DB::BioFetch->new(-format        => 'fasta',
 			     -retrievaltype => 'tempfile',
  			     -db            => 'EMBL');

 $stream = $bf->get_Stream_by_id(['HSFOS','J00231']);
 while (my $s = $stream->next_seq) {
    print $s->seq,"\n";
 }
 # get a RefSeq entry
 $bf->db('refseq');
 eval {
     $seq = $bf->get_Seq_by_version('NM_006732.1'); # RefSeq VERSION
 };
 print "accession is ", $seq->accession_number, "\n" unless $@;


=head1 DESCRIPTION

Bio::DB::BioFetch is a guaranteed best effort sequence entry fetching
method.  It goes to the Web-based dbfetch server located at the EBI
(http://www.ebi.ac.uk/Tools/dbfetch/dbfetch) to retrieve sequences in the
EMBL or GenBank sequence repositories.

This module implements all the Bio::DB::RandomAccessI interface, plus
the get_Stream_by_id() and get_Stream_by_acc() methods that are found
in the Bio::DB::SwissProt interface.

=head1 FEEDBACK

=head2 Mailing Lists

User feedback is an integral part of the evolution of this and other
Bioperl modules. Send your comments and suggestions preferably to one
of the Bioperl mailing lists.  Your participation is much appreciated.


  bioperl-l@bioperl.org                  - General discussion
  http://bioperl.org/wiki/Mailing_lists  - About the mailing lists

=head2 Support

Please direct usage questions or support issues to the mailing list:

I<bioperl-l@bioperl.org>

rather than to the module maintainer directly. Many experienced and

lib/Bio/DB/BioFetch.pm  view on Meta::CPAN

 Function: Gets a Bio::Seq object by sequence version
 Returns : A Bio::Seq object
 Args    : accession.version (as a string)
 Throws  : "acc.version does not exist" exception

=cut

sub get_Seq_by_version {
   my ($self,$seqid) = @_;
   return $self->get_Seq_by_acc($seqid);
}


=head2 get_Stream_by_id

  Title   : get_Stream_by_id
  Usage   : $stream = $db->get_Stream_by_id( [$uid1, $uid2] );
  Function: Gets a series of Seq objects by unique identifiers
  Returns : a Bio::SeqIO stream object
  Args    : $ref : a reference to an array of unique identifiers for
                   the desired sequence entries

=cut

=head2 get_Stream_by_gi

  Title   : get_Stream_by_gi
  Usage   : $seq = $db->get_Seq_by_gi([$gi1, $gi2]);
  Function: Gets a series of Seq objects by gi numbers
  Returns : a Bio::SeqIO stream object
  Args    : $ref : a reference to an array of gi numbers for
                   the desired sequence entries
  Note    : For GenBank, this just calls the same code for get_Stream_by_id()

=cut

=head2 get_Stream_by_batch

  Title   : get_Stream_by_batch
  Usage   : $seq = $db->get_Stream_by_batch($ref);
  Function: Get a series of Seq objects by their IDs
  Example :
  Returns : a Bio::SeqIO stream object
  Args    : $ref : an array reference containing a list of unique
            ids/accession numbers.

In some of the Bio::DB::* moduels, get_Stream_by_id() is called
get_Stream_by_batch().  Since there seems to be no consensus, this
is provided as an alias.

=cut

*get_Stream_by_batch = \&Bio::DB::WebDBSeqI::get_Stream_by_id;

=head1 The remainder of these methods are for internal use

=head2 get_request

 Title   : get_request
 Usage   : my $url = $self->get_request
 Function: returns a HTTP::Request object
 Returns :
 Args    : %qualifiers = a hash of qualifiers (ids, format, etc)

=cut


sub get_request {
    my ($self, @qualifiers) = @_;
    my ($uids, $format) = $self->_rearrange([qw(UIDS FORMAT)],
					    @qualifiers);
    my $db     = $self->db;
    my $namespace = $self->_namespace;

    $self->throw("Must specify a value for UIDs to fetch")
	unless defined $uids;
    my $tmp;
    my $format_string = '';

    $format ||= $self->default_format;
    ($format, $tmp) = $self->request_format($format);

    my $base = $self->url_base_address;
    my $uid = join('+',ref $uids ? @$uids : $uids);
    $self->debug("\n$base$format_string&id=$uid\n");
    return POST($base,
		[ db     => $namespace,
		  id     => join('+',ref $uids ? @$uids : $uids),
		  format => $format,
		  style  => 'raw'
	     ]);
}

=head2 default_format

 Title   : default_format
 Usage   : $format = $self->default_format
 Function: return the default format
 Returns : a string
 Args    :

=cut

sub default_format {
    return 'default';
}

=head2 default_db

 Title   : default_db
 Usage   : $db = $self->default_db
 Function: return the default database
 Returns : a string
 Args    :

=cut

sub default_db     { 'embl' }

=head2 db