view release on metacpan or  search on metacpan

ABI.pm  view on Meta::CPAN

# Malay <malay@bioinformatics.org>
# Copyright (c) 2002, 2003, 2004, 2005, 2006 Malay Kumar Basu
# You may distribute this module under the same terms as perl itself
# Thanks to David H. Klatte for all the hard work!
package ABI;
use IO::File;
use Carp;
use strict;

=head1 NAME

ABI.pm - Perl module to parse chromatogram files generated by
Applied Biosystems (ABI) automated DNA sequencing machine.

Please cite:
ABI.pm - Perl module to parse chromatogram files generated by
Applied Biosystems (ABI) automated DNA sequencing machine.
by Malay K Basu (malay@bioinformatics.org); source code available at:
http://search.cpan.org/~malay

=head1 VERSION

Version 1.0

=cut

our $VERSION = '1.0';

=head1 SYNOPSIS

  my $abi = ABI->new(-file=>"mysequence.abi");
  my $seq = $abi->get_sequence(); # To get the sequence
  my @trace_a = $abi->get_trace("A"); # Get the raw traces for "A"
  my @trace_g = $abi->get_trace("G"); # Get the raw traces for "G"
  my @base_calls = $abi->get_base_calls(); # Get the base calls

=head1 DESCRIPTION

An ABI chromatogram file is in binary format. It contain several 
information only some of which is required for normal use. This
module only gives access to the most used information stored in
ABI file. All the accesses are read only.

If you have edited the file using a trace editor, then you can use the corresponding 
method to access the edited sequence and base calls.



=head1 CONSTRUCTOR

=head2 new()

  Usage : $abi = ABI->new(-file=>"filename");
          $abi = ABI->new("filename"); # same thing

=cut

sub new {
	my $class = shift;
	my $self  = {};
	bless $self, ref($class) || $class;
	$self->_init(@_);

	#print "****", $self->{_mac_header}, "\n";
	return $self;
}

sub _init {
	my ( $self, @args ) = @_;
	my ($file) = $self->_rearrange( ["FILE"], @args );
	if ( !defined($file) ) {
		croak "Can't open the input file\n";
	} else {
		$self->set_file_handle($file);
	}
	$self->{_sequence}             = "";
	$self->{_sequence_corrected}   = "";
	$self->{_sample}               = "";
	$self->{A}                     = [];
	$self->{T}                     = [];
	$self->{G}                     = [];
	$self->{C}                     = [];
	$self->{_basecalls}            = [];
	$self->{_basecalls_corrected}  = [];
	$self->{_trace_length}         = 0;
	$self->{_seq_length}           = 0;
	$self->{_seq_length_corrected} = 0;
	$self->{_abs_index}            = 26;
	$self->{_index}                = undef;
	$self->{PLOC1}                 = undef;
	$self->{PLOC}                  = undef;
	$self->{_a_start}              = undef;
	$self->{_g_start}              = undef;
	$self->{_c_start}              = undef;
	$self->{_t_start}              = undef;
	$self->{DATA9}                 = undef;
	$self->{DATA10}                = undef;
	$self->{DATA11}                = undef;
	$self->{DATA12}                = undef;
	$self->{PBAS1}                 = undef;
	$self->{PBAS2}                 = undef;
	$self->{FWO}                   = undef;
	$self->{_mac_header}           = 0;
	$self->{_maximum_trace}        = 0;

	if ( $self->_is_abi() ) {

		#print "ABI FILE\n";
		$self->_set_index();
		$self->_set_base_calls();
		$self->_set_corrected_base_calls();
		$self->_set_seq();
		$self->_set_corrected_seq();
		$self->_set_traces();
		$self->_set_max_trace();
		$self->_set_sample_name();
		close( $self->{_fh} );
	}
	return $self;
}