Bio/Seq/LargeSeq.pm

   1 #
   2 # BioPerl module for Bio::Seq::LargeSeq
   3 #
   4 # Please direct questions and support issues to <bioperl-l@bioperl.org>
   5 #
   6 # Cared for by Ewan Birney, Jason Stajich
   7 #
   8 # Copyright Ewan Birney, 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::Seq::LargeSeq - SeqI compliant object that stores sequence as
  17 files in /tmp
  18
  19 =head1 SYNOPSIS
  20
  21   # normal primary seq usage
  22
  23 =head1 DESCRIPTION
  24
  25 This object stores a sequence as a series of files in a temporary
  26 directory. The aim is to allow someone the ability to store very large
  27 sequences (eg, E<gt> 100MBases) in a file system without running out
  28 of memory (eg, on a 64 MB real memory machine!).
  29
  30 Of course, to actually make use of this functionality, the programs
  31 which use this object B<must> not call $primary_seq-E<gt>seq otherwise
  32 the entire sequence will come out into memory and probably paste your
  33 machine. However, calls $primary_seq-E<gt>subseq(10,100) will cause
  34 only 90 characters to be brought into real memory.
  35
  36 =head1 FEEDBACK
  37
  38 =head2 Mailing Lists
  39
  40 User feedback is an integral part of the evolution of this and other
  41 Bioperl modules. Send your comments and suggestions preferably to one
  42 of the Bioperl mailing lists.  Your participation is much appreciated.
  43
  44   bioperl-l@bioperl.org                  - General discussion
  45   http://bioperl.org/wiki/Mailing_lists  - About the mailing lists
  46
  47 =head2 Support
  48
  49 Please direct usage questions or support issues to the mailing list:
  50
  51 I<bioperl-l@bioperl.org>
  52
  53 rather than to the module maintainer directly. Many experienced and
  54 reponsive experts will be able look at the problem and quickly
  55 address it. Please include a thorough description of the problem
  56 with code and data examples if at all possible.
  57
  58 =head2 Reporting Bugs
  59
  60 Report bugs to the Bioperl bug tracking system to help us keep track
  61 the bugs and their resolution.  Bug reports can be submitted via the
  62 web:
  63
  64   https://github.com/bioperl/bioperl-live/issues
  65
  66 =head1 AUTHOR - Ewan Birney
  67
  68 Email birney@ebi.ac.uk
  69
  70 =head1 APPENDIX
  71
  72 The rest of the documentation details each of the object
  73 methods. Internal methods are usually preceded with a _
  74
  75 =cut
  76
  77
  78 # Let the code begin...
  79
  80
  81 package Bio::Seq::LargeSeq;
  82 use vars qw($AUTOLOAD);
  83 use strict;
  84
  85 # Object preamble
  86
  87 use Bio::Seq::LargePrimarySeq;
  88
  89 use base qw(Bio::Seq Bio::Seq::LargeSeqI);
  90
  91
  92 sub new {
  93     my ($class, @args) = @_;
  94     my $self = $class->SUPER::new(@args);
  95
  96     my ($pseq) = $self->_rearrange([qw(PRIMARYSEQ)], @args);
  97
  98     if( ! defined $pseq ) {
  99         $pseq = Bio::Seq::LargePrimarySeq->new(@args);
 100     }
 101     $self->primary_seq($pseq);
 102
 103     return $self;
 104 }
 105
 106
 107 =head2 trunc
 108
 109  Title   : trunc
 110  Usage   : $subseq = $myseq->trunc(10,100);
 111  Function: Provides a truncation of a sequence,
 112
 113  Example :
 114  Returns : a fresh Bio::SeqI object
 115  Args    :
 116
 117 =cut
 118
 119 sub trunc {
 120     my ($self, $s, $e) = @_;
 121     return new Bio::Seq::LargeSeq
 122         ('-display_id' => $self->display_id,
 123          '-accession_number' => $self->accession_number,
 124          '-desc' => $self->desc,
 125          '-alphabet' => $self->alphabet,
 126          -primaryseq => $self->primary_seq->trunc($s,$e));
 127 }
 128
 129 =head2 Bio::Seq::LargePrimarySeq methods
 130
 131 =cut
 132
 133 =head2 add_sequence_as_string
 134
 135  Title   : add_sequence_as_string
 136  Usage   : $seq->add_sequence_as_string("CATGAT");
 137  Function: Appends additional residues to an existing LargePrimarySeq object.
 138            This allows one to build up a large sequence without storing
 139            entire object in memory.
 140  Returns : Current length of sequence
 141  Args    : string to append
 142
 143 =cut
 144
 145 sub add_sequence_as_string {
 146     my ($self,$str) = @_;
 147     return $self->primary_seq->add_sequence_as_string($str);
 148 }
 149
 150 1;