#!/usr/bin/perl
use strict;
use warnings;
use Data::Dumper;

my %bact = (first  => 'CAGGTGGCAT',
			second => 'CATTGAAGCT',
			third  => 'CTAAGTTCAG',
			fourth => 'CTAAGAACGT',
			fifth  => 'CTGGAGGACT',
			);
my @counts = (0) x 5;
my %bact_data;
foreach my $id (keys %bact) {
	$bact_data{$id}{DNA} = $bact{$id};
}

foreach my $id (keys %bact) {
	if (($bact{$id} =~ m/^CAGGTGGCAT/)) { 
		$bact_data{$id}{DNA} = $bact{$id};
		$bact_data{$id}{set} = 1;
		$counts[0]++;
		$bact_data{$id}{count} = $counts[0];
	} elsif (($bact{$id} =~ m/^CATTGAAGCT/)) {
		$bact_data{$id}{DNA} = $bact{$id};
		$bact_data{$id}{set} = 2;
		$counts[1]++;
		$bact_data{$id}{count} = $counts[1];
	} elsif (($bact{$id} =~ m/^CTAAGTTCAG/)) {
		$bact_data{$id}{DNA} = $bact{$id};
		$bact_data{$id}{set} = 3;
		$counts[2]++;
		$bact_data{$id}{count} = $counts[2];
	} elsif (($bact{$id} =~ m/^CTAAGAACGT/)) {
		$bact_data{$id}{DNA} = $bact{$id};
		$bact_data{$id}{set} = 4;
		$counts[3]++;
		$bact_data{$id}{count} = $counts[3];
	} else {
		$bact_data{$id}{DNA} = $bact{$id};
		$bact_data{$id}{set} = 5;
		$counts[4]++;
		$bact_data{$id}{count} = $counts[4];
	}
}

print "---------------------------------------------------------------\n";
print "-------- ABUNDANCE OF SEQUENCES WTHIN EACH SUBGROUP  ----------\n";	
print "number of sequences in set 1 CAGGTGGCAT sub group = $counts[0] \n";
print "number of sequences in set 2 CATTGAAGCT sub group = $counts[1] \n";
print "number of sequences in set 3 CTAAGTTCAG sub group = $counts[2] \n";
print "number of sequences in set 4 CTAAGAACGT sub group = $counts[3] \n";
print "number of sequences in set 5 CTGGAGGACT sub group = $counts[4] \n";
print "---------------------------------------------------------------\n";
print Dumper(\%bact_data);