#!/usr/bin/perl -w

#################################################

# gen_seqs.pl
# Version 1

# Robert D. Cormia
# UCSC Programming for Bioinformatics III
# October 31, 2003

# Write a Perl program that will do the following:
# Define a scalar $dna = 'CGACGTCTTCTCAGGCGA
#
# Create sequences which are are one character long through
# 18 characters long. For example:
#
# 1 Char sequence: C G A C G T etc
# 2 Char sequence: CG GA AC etc. and not CG CA CC etc
# 3 Char sequence: CGA GAC ACG CGT etc

# 16 Char sequence: CGACGTCTTCTCAGGC GACGTCTTCTCAGGCG
# 17 Char sequence: CGACGTCTTCTCAGGCG GACGTCTTCTCAGGCGA
# 18 Char sequence: CGACGTCTTCTCAGGCGA GACGTCTTCTCAGGCG

# Do not leave smaller sequences at the end, i.e. three-characters
# long should not have two or one-character sequences at the end.

#################################################

use strict;

print "\n";

# ---------------------------------------------------------------
# Define the $dna scalar, determine the dna
# ---------------------------------------------------------------

my $dna        = 'CGACGTCTTCTCAGGCGA';
my $dna_length = length($dna);
my $position;

# ---------------------------------------------------------------
# Create subsequences that range from one-base long through
# 18 bases long. Push them onto the array subsequences. Print
# results to the screen.
# ---------------------------------------------------------------

for ( $position = 1 ; $position <= $dna_length ; ++$position ) {
    my @subsequences = ();
    my $skip         = 0;

    while ( $dna =~ /.{$skip}(.{$position})/ ) {
        push ( @subsequences, $1 );
        ++$skip;
    }
    print "$position", "-base long: @subsequences \n";
}

__END__