#!/usr/bin/perl

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

# count_nucleotides.pl
# Version 1

# Robert D. Cormia
# UCSC Programming for Bioinformatics II
# October 10, 2003

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


# 2. In this exercise we will work with the concept of counting nucleotides.
# Write a Perl program called 'count_nucleotides' to count the nucleotides
# in a data file which looks like this (found in sample.nucleotides):
#
# ACTGCCACCAGGTCCTCGCGGTAGTCA
# GACGGTCAGCCGCGTTTATCGTCCTGA
# CCTCCGCGTAGGACGTCGTTGTTCTAG
#
# Print the sequence in each line followed by the counts.
# Print the total number of nucleotides, in this fashion:
#
# Seq is: ACTGCCACCAGGTCCTCGCGGTAGTCA
# A:5 C:10 G:7 T:5
# …
# …
# Total Counts => A:12 C:26 G:23 T:20

#  ----------------------------------------------------------------
#
#  Pseudocode
#
#  Open file
#  Read file (line by line)
#  For each line, read characters into an array
#  Run 'count_nuceotides()' subroutine against data
#  Store the results of ATCG count for each string
#  Print the results of ATCG count for each string
#
# -----------------------------------------------------------------

use strict;

my $line;
my @lines;
my @seq;
my %count;
my %tcount;
my $nuc;

print "This program will count nucleotides\n";

# Nucleotide counting code

open (INPUT, "sample_nucleotides.txt") or die "Cannot open file: $!";

@lines = <INPUT>;
close INPUT;

print "Got all of the sequence\n";

# Input lines of sequence into array lines.

chomp @lines;
#$line = uc (join '', @lines);

foreach (@lines) {
    # Remove invalid characters
    $_ =~ s/[^ATCGNX]//g;

    # test for possible blank line and skip if true
    if ($_ eq "") { next; }

    # Separate nucleotide line into character array
    @seq = split //, $_;

    # Increment a count for each element in the sequence
    foreach ( @seq ) { $count{$_}++ }

    # print out the reslts for each line
    print "\n";
    print "Seq is: $_\n";
    print "Nucleotide count: ", scalar(@seq), " bases\n";
    print '-'x60, "\n";
    foreach $nuc ( sort keys %count ) {
	printf "\t$nuc:\t%4d\t(%.1f%%)\n", $count{$nuc}, 100*$count{$nuc}/@seq;
	$tcount{$nuc} += $count{$nuc};
	$count{$nuc} = 0;
    }
}

# print the totals
# print "\n\nTOTAL Nuclotides ??????\n";
# foreach $nuc ( sort keys %tcount ) {
#    printf "\t$nuc:\t%4d\t(%.1f%%)\n", $tcount{$nuc}, 100*$tcount{$nuc}/@seq;
# }

__END__