diff variant_effect_predictor/Bio/Seq/LargeSeq.pm @ 0:2bc9b66ada89 draft default tip

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/variant_effect_predictor/Bio/Seq/LargeSeq.pm	Thu Apr 11 06:29:17 2013 -0400
@@ -0,0 +1,141 @@
+# $Id: LargeSeq.pm,v 1.11 2002/10/22 07:38:40 lapp Exp $
+#
+# BioPerl module for Bio::Seq::LargeSeq
+#
+# Cared for by Ewan Birney, Jason Stajich
+#
+# Copyright Ewan Birney, Jason Stajich
+#
+# You may distribute this module under the same terms as perl itself
+
+# POD documentation - main docs before the code
+
+=head1 NAME
+
+Bio::Seq::LargeSeq - SeqI compliant object that stores sequence as files in /tmp 
+
+=head1 SYNOPSIS
+
+  # normal primary seq usage
+
+=head1 DESCRIPTION
+
+This object stores a sequence as a series of files in a temporary
+directory. The aim is to allow someone the ability to store very large
+sequences (eg, E<gt> 100MBases) in a file system without running out of memory
+(eg, on a 64 MB real memory machine!). 
+
+Of course, to actually make use of this functionality, the programs
+which use this object B<must> not call $primary_seq-E<gt>seq otherwise the
+entire sequence will come out into memory and probably paste your
+machine. However, calls $primary_seq-E<gt>subseq(10,100) will cause only
+90 characters to be brought into real memory.
+
+=head1 FEEDBACK
+
+=head2 Mailing Lists
+
+User feedback is an integral part of the evolution of this
+and other Bioperl modules. Send your comments and suggestions preferably
+ to one of the Bioperl mailing lists.
+Your participation is much appreciated.
+
+  [e-mail]          - General discussion
+  http://www.bioperl.org/MailList.html             - About the mailing lists
+
+=head2 Reporting Bugs
+
+Report bugs to the Bioperl bug tracking system to help us keep track
+ the bugs and their resolution.
+ Bug reports can be submitted via email or the web:
+
+  [e-mail]
+  http://bugzilla.bioperl.org/
+
+=head1 AUTHOR - Ewan Birney
+
+Email [e-mail]
+
+=head1 APPENDIX
+
+The rest of the documentation details each of the object methods. Internal methods are usually preceded with a _
+
+=cut
+
+
+# Let the code begin...
+
+
+package Bio::Seq::LargeSeq;
+use vars qw($AUTOLOAD @ISA);
+use strict;
+
+# Object preamble - inherits from Bio::Root::Objecttest 8, 
+
+use Bio::Seq::LargePrimarySeq;
+use Bio::Seq;
+
+@ISA = qw(Bio::Seq);
+
+
+sub new {
+    my ($class, @args) = @_;
+    my $self = $class->SUPER::new(@args);
+    
+    my ($pseq) = $self->_rearrange([qw(PRIMARYSEQ)], @args);
+
+    if( ! defined $pseq ) {
+	$pseq = new Bio::Seq::LargePrimarySeq(@args);
+    }
+    $self->primary_seq($pseq);
+
+    return $self;
+}
+
+
+=head2 trunc
+
+ Title   : trunc
+ Usage   : $subseq = $myseq->trunc(10,100);
+ Function: Provides a truncation of a sequence,
+
+ Example :
+ Returns : a fresh Bio::SeqI object
+ Args    :
+
+=cut
+
+sub trunc {
+    my ($self, $s, $e) = @_;
+    return new Bio::Seq::LargeSeq(
+				  '-display_id' => $self->display_id,
+				  '-accession_number' => $self->accession_number,
+				  '-desc' => $self->desc,
+				  '-alphabet' => $self->alphabet,
+				  -primaryseq => 
+				  $self->primary_seq->trunc($s,$e));
+
+}
+
+=head2 Bio::Seq::LargePrimarySeq methods
+
+=cut
+
+=head2 add_sequence_as_string
+
+ Title   : add_sequence_as_string
+ Usage   : $seq->add_sequence_as_string("CATGAT");
+ Function: Appends additional residues to an existing LargePrimarySeq object.  
+           This allows one to build up a large sequence without storing
+           entire object in memory.
+ Returns : Current length of sequence
+ Args    : string to append
+
+=cut
+
+sub add_sequence_as_string {
+    my ($self,$str) = @_;
+    return $self->primary_seq->add_sequence_as_string($str);
+}
+
+1;