#!/usr/bin/perl -w
# Determining frequency of nucleotides

# Get the name of the file with the DNA sequence data
print "Please type the filename of the DNA sequence data: ";
$dna_filename = <STDIN>;
chomp $dna_filename;

# open the file, or exit
unless ( open(DNAFILE, $dna_filename) ) {
    print "Cannot open file \"$dna_filename\"\n\n";
    exit;
}

# Read the DNA sequence data from the file, and store it
# into the array variable @DNA
@DNA = <DNAFILE>;
close DNAFILE;

# Collect all the array elements and join them into a scalar
$DNA = join( '', @DNA);

# Remove whitespace
$DNA =~ s/\s//g;

# Now explode the scalar into an array where each character (nucleotide)
# of the scalar (DNA) is now an element in the array.
# This will make it easy to look at each position.
# Notice that we're reusing the array variable @DNA for this purpose.
@DNA = split( '', $DNA );

# Initialize the counts.
# Notice that we can use scalar variables to hold numbers.
$count_of_A = 0;
$count_of_C = 0;
$count_of_G = 0;
$count_of_T = 0;
$errors     = 0;

# In a loop, look at each base in turn, determine which of the
# four types of nucleotides it is, and increment the
# appropriate count.
foreach $base (@DNA) {

    if     ( $base eq 'A' ) {
        ++$count_of_A;
    } elsif ( $base eq 'C' ) {
        ++$count_of_C;
    } elsif ( $base eq 'G' ) {
        ++$count_of_G;
    } elsif ( $base eq 'T' ) {
        ++$count_of_T;
    } else {
        print "Error - Unknown base: $base\n";
        ++$errors;
    }
}

# print the results
print "A = $count_of_A\n";
print "C = $count_of_C\n";
print "G = $count_of_G\n";
print "T = $count_of_T\n";

if ($errors) {
	print "There were $errors unrecognized bases.\n";
}