<![CDATA[
#!/usr/bin/perl -w
use strict;
# documentation written in pod, perldoc perlpod
=head1 NAME
BioFunctions.pm
=head1 DESCRIPTION
Library of sequence functions: upper-case conversion, DNA2RNA translation,
find Kozak motif, find_poly_tails, remove_poly_tails, count Kozak motif.
=head1 SYNOPSIS
use BioFunctions qw/:all/;
use BioFunctions qw/upper_case translate_DNA_to_RNA find_KOZAK_motif find_poly_tail remove_poly_tails count_KOZAK show_eg/;
=head1 USAGE
show_eg(`podselect -s "EXAMPLES" $0`);
my $RNA = translate_DNA_to RNA ($DNA_sequence);
=head1 NOTES
Kozak consensus or Kozak sequence, is a sequence which occurs on eukaryotic mRNA and composed of three bases of the start codon (AUG). The Kozak consensus sequence plays a major role in the initiation of the translation process.
=head1 AUTHOR
Student example from course work.
=head1 FUNCTIONS
Function signatures follow:
=over 4
=cut
package BioFunctions;
BEGIN {
use Exporter( );
our ($VERSION, @ISA, @EXPORT, @EXPORT_OK, %EXPORT_TAGS);
$VERSION = "1.00";
@ISA = qw/Exporter/;
@EXPORT = ( ); # don't export without asking
# create Export tags for convenience
%EXPORT_TAGS = (
all => [ qw/ get_DNA_sequence upper_case translate_DNA_to_RNA find_KOZAK_motif find_poly_tails remove_poly_tails count_KOZAK show_eg / ],
);
@EXPORT_OK = qw/ get_DNA_sequence upper_case translate_DNA_to_RNA find_KOZAK_motif find_poly_tails remove_poly_tails count_KOZAK show_eg /;
}
=item my $text = upper_case($DNA_sequence);
This function converts $dna sequence from lower to upper case.
Puts the string into all caps and return value.
=cut
sub upper_case {
my ($DNA_sequence) = @_;
return uc($DNA_sequence);
}
=item $data = translate_DNA_to_RNA($DNA_sequence);
Translate DNA to mRNA by substituting U for T amino acids
Returns only upper case sequences
=cut
sub translate_DNA_to_RNA {
my ($DNA_sequence) = @_;
my $RNA = upper_case($DNA_sequence);
$RNA =~ s/T/U/g;
return $RNA;
}
=item $text= find_KOZAK_motif($DNA_sequence);
Check for presence of Kozak sequence
"Found" or "Not Found" returned for any sequence having an AUG in it
=cut
sub find_KOZAK_motif {
my ($seq) = @_;
$seq = translate_DNA_to_RNA($seq);
if ( $seq =~ /AUG/i ) {
return("Found");
} else {
return ("Not Found");
}
}
=item $text= find_poly_tails($DNA_sequence);
Check for presence of Kozak sequence
"Found" or "Not Found" returned for any sequence having an AUG in it
=cut
sub find_poly_tails{
my ($seq) = @_;
$seq = translate_DNA_to_RNA($seq);
if ( $seq =~ /[A]{10}/i ) {
return("Found");
} else {
return ("Not Found");
}
}
=item my $text = count_KOZAK(DNA_sequence);
Calculates KOZAK motifs(AUG)
=cut
sub count_KOZAK {
my ($seq) = @_;
$seq = translate_DNA_to_RNA($seq);
my $count = 0;
my $length_of_RNA = length $seq;
$count = ( ) = $seq =~ /AUG/mig;
return $count;
}
=item my $text = remove_poly_tail($DNA_sequence);
Removes polyA tails from the sequence if any
=cut
sub remove_poly_tails {
my ($seq) = @_;
# sequence out spaces to match repeated poly A motif
$seq =~ s/\s//g;
$seq = translate_DNA_to_RNA($seq);
my $poly_motif='AAAAAAAAAA';
$seq =~ s/$poly_motif//ig;
return $seq;
}
=item my $text = get_DNA_sequence($filename);
Read it into array
Create a long string and
Remove the white spaces
=cut
sub get_DNA_sequence { my ($DNA_filename) = @_;
unless ( open(DNA_1,$DNA_filename) ) {
print "Can not open this file:$DNA_filename: $!\n";
exit(1); }
my @DNA = <DNA_1>;
my $DNA_sequence = join('',@DNA);
$DNA_sequence =~ s/\s//g;
close(DNA_1);
return $DNA_sequence;
}
=item my $text = show_eg($text);
Exit with text of examples without a header
and remove last blank line.
=cut
sub show_eg {
my @lines =@_;
# remove 1st and last lines
pop @lines;
shift @lines;
print @lines;
exit (0);
}
1; # successful -- library loaded
]]>