#!/usr/bin/perl -w

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

# subs_count_dna.pl
# Version 1

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

# Description - this program counts the number of bases
# A, T, C, and G in the file 'new_dna_seq'.

# ATAATTTGCAGCTAAGGTGCG
# TTTGGGCCCACTCGAGAGGGC
# CCACTTCGTACCTCGCGCTTG

# The subroutine # has two arguments: a base and a sequence.
# The subroutine # returns the count of the base in the sequence.
# Print the resluts as:
#
#             ATAATTTGCAGCTAAGGTGCG
#             A:6 T:6 C:3 G:5
#

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

use strict;

print "\n";

# -------------------------------------------------------------
# Open 'new_dna_seq' file, if open fails, call die.
# -------------------------------------------------------------

my $fname = 'new_dna_seq.txt';

open( new_dna_seq, $fname )
  or die ("open() failed for '$fname'\nReason: $!\n\n");

my $line;

# -------------------------------------------------------------
# While loop reads new_dna_seq.txt and calls base_counter
# base_counter counts bases and prints results to screen
# -------------------------------------------------------------

while ( $line = <new_dna_seq> ) {
    chomp($line);
    print "$line\n";
    my $base;
    my @bases = qw(A T C G);
    foreach $base (@bases) {
        print "$base:", &base_counter( $base, $line ), " ";
    }
    print "\n\n";
}

# ---------------------------------------------------------------
# This subroutine counts number of bases per sequence
# ---------------------------------------------------------------

sub base_counter {
    my ( $base, $dna_sequence ) = @_;
    return ( $dna_sequence =~ s/$base/$base/ig );
}

# ---------------------------------------------------------------
# Close the new_dna_seq file
# ---------------------------------------------------------------

close(new_dna_seq);
print "\n";

__END__