lib/Bio/SeqIO/largefasta.pm

   1 # BioPerl module for Bio::SeqIO::largefasta
   2 #
   3 # Please direct questions and support issues to <bioperl-l@bioperl.org>
   4 #
   5 # Cared for by Jason Stajich
   6 #
   7 # Copyright Jason Stajich
   8 #
   9 # You may distribute this module under the same terms as perl itself
  10 # _history
  11 #
  12 # POD documentation - main docs before the code
  13
  14 =head1 NAME
  15
  16 Bio::SeqIO::largefasta - method i/o on very large fasta sequence files
  17
  18 =head1 SYNOPSIS
  19
  20 Do not use this module directly.  Use it via the Bio::SeqIO class.
  21
  22 =head1 DESCRIPTION
  23
  24 This object can transform Bio::Seq objects to and from fasta flat
  25 file databases.
  26
  27 This module handles very large sequence files by using the
  28 Bio::Seq::LargePrimarySeq module to store all the sequence data in
  29 a file.  This can be a problem if you have limited disk space on your
  30 computer because this will effectively cause 2 copies of the sequence
  31 file to reside on disk for the life of the
  32 Bio::Seq::LargePrimarySeq object.  The default location for this is
  33 specified by the L<File::Spec>-E<gt>tmpdir routine which is usually /tmp
  34 on UNIX.  If a sequence file is larger than the swap space (capacity
  35 of the /tmp dir) this could cause problems for the machine.  It is
  36 possible to set the directory where the temporary file is located by
  37 adding the following line to your code BEFORE calling next_seq. See
  38 L<Bio::Seq::LargePrimarySeq> for more information.
  39
  40     $Bio::Seq::LargePrimarySeq::DEFAULT_TEMP_DIR = 'newdir';
  41
  42 =head1 FEEDBACK
  43
  44 =head2 Mailing Lists
  45
  46 User feedback is an integral part of the evolution of this and other
  47 Bioperl modules. Send your comments and suggestions preferably to one
  48 of the Bioperl mailing lists.  Your participation is much appreciated.
  49
  50   bioperl-l@bioperl.org                  - General discussion
  51   http://bioperl.org/wiki/Mailing_lists  - About the mailing lists
  52
  53 =head2 Support
  54
  55 Please direct usage questions or support issues to the mailing list:
  56
  57 I<bioperl-l@bioperl.org>
  58
  59 rather than to the module maintainer directly. Many experienced and
  60 reponsive experts will be able look at the problem and quickly
  61 address it. Please include a thorough description of the problem
  62 with code and data examples if at all possible.
  63
  64 =head2 Reporting Bugs
  65
  66 Report bugs to the Bioperl bug tracking system to help us keep track
  67 the bugs and their resolution.  Bug reports can be submitted via the web:
  68
  69   https://github.com/bioperl/bioperl-live/issues
  70
  71 =head1 AUTHORS - Jason Stajich
  72
  73 Email: jason@bioperl.org
  74
  75 =head1 APPENDIX
  76
  77 The rest of the documentation details each of the object
  78 methods. Internal methods are usually preceded with a _
  79
  80 =cut
  81
  82 # Let the code begin...
  83
  84 package Bio::SeqIO::largefasta;
  85 use vars qw($FASTALINELEN);
  86 use strict;
  87
  88 use Bio::Seq::SeqFactory;
  89
  90 $FASTALINELEN = 60;
  91 use base qw(Bio::SeqIO);
  92
  93 sub _initialize {
  94   my($self,@args) = @_;
  95   $self->SUPER::_initialize(@args);
  96   if( ! defined $self->sequence_factory ) {
  97       $self->sequence_factory(Bio::Seq::SeqFactory->new
  98                               (-verbose => $self->verbose(),
  99                                -type => 'Bio::Seq::LargePrimarySeq'));
 100   }
 101 }
 102
 103 =head2 next_seq
 104
 105  Title   : next_seq
 106  Usage   : $seq = $stream->next_seq()
 107  Function: returns the next sequence in the stream
 108  Returns : A Bio::Seq::LargePrimarySeq object
 109  Args    : NONE
 110
 111 =cut
 112
 113 sub next_seq {
 114     my ($self) = @_;
 115 #  local $/ = "\n";
 116     my $largeseq = $self->sequence_factory->create();
 117     my ($id,$fulldesc,$entry);
 118     my $count = 0;
 119     my $seen = 0;
 120     while( defined ($entry = $self->_readline) ) {
 121         if( $seen == 1 && $entry =~ /^\s*>/ ) {
 122             $self->_pushback($entry);
 123             return $largeseq;
 124         }
 125 #       if ( ($entry eq '>') || eof($self->_fh) ) { $seen = 1; next; }
 126         if ( ($entry eq '>')  ) { $seen = 1; next; }
 127         elsif( $entry =~ /\s*>(.+?)$/ ) {
 128             $seen = 1;
 129             ($id,$fulldesc) = ($1 =~ /^\s*(\S+)\s*(.*)$/)
 130                 or $self->warn("Can't parse fasta header");
 131             $largeseq->display_id($id);
 132             $largeseq->primary_id($id);
 133             $largeseq->desc($fulldesc);
 134         } else {
 135             $entry =~ s/\s+//g;
 136             $largeseq->add_sequence_as_string($entry);
 137         }
 138         (++$count % 1000 == 0 && $self->verbose() > 0) && print "line $count\n";
 139     }
 140     return unless $seen;
 141     return $largeseq;
 142 }
 143
 144 =head2 write_seq
 145
 146  Title   : write_seq
 147  Usage   : $stream->write_seq(@seq)
 148  Function: writes the $seq object into the stream
 149  Returns : 1 for success and 0 for error
 150  Args    : Bio::Seq object
 151
 152
 153 =cut
 154
 155 sub write_seq {
 156    my ($self,@seq) = @_;
 157    foreach my $seq (@seq) {
 158      my $top = $seq->id();
 159      if ($seq->can('desc') and my $desc = $seq->desc()) {
 160          $desc =~ s/\n//g;
 161          $top .= " $desc";
 162      }
 163      $self->_print (">",$top,"\n");
 164      my $end = $seq->length();
 165      my $start = 1;
 166      while( $start <= $end ) {
 167          my $stop = $start + $FASTALINELEN - 1;
 168          $stop = $end if( $stop > $end );
 169          $self->_print($seq->subseq($start,$stop), "\n");
 170          $start += $FASTALINELEN;
 171      }
 172    }
 173
 174    $self->flush if $self->_flush_on_write && defined $self->_fh;
 175    return 1;
 176 }
 177
 178 1;