#!/usr/bin/perl -w 

##########INPUT Sequence, concatenated into a single string##########
#skip annotation lines in case of fasta. if multiple annotation lines, concatenate these too. 
#
unless(@ARGV==1) {die "please provide name of the file in the command line!!\n";}
my$filename=$ARGV[0]; #takes filenname from input line
open(IN, "< $filename") or die "cannot open $filename:$!"; #assigns filehandle IN to filename or dies

my$seq=''; #assigns empty string
my$line='';
my$name='';
my@bases=(); #assigns empty list

while(defined($line=<IN>)){

	chomp($line);
	if ($line=~/^>/) {  #look for beginning of line starting with > (^ is an anchor for the beginning of the line)
		$name .= $line;
		}
	else {
		$seq .= $line ;
		}
}
#  clean up sequence
#  check for all CAPS, report non ATGCs, remove white spaces
#
$seq =~ tr/atgc/ATGC/; #translates all ATGC to upper case
$seq =~ s/\s//g;# substitutes all white spaces \s with nothing globally in $seq
####################sequence to array
@bases=split(//,$seq);  #splits string into separate elements (bases)

$num_bases=@bases; #length of array

###################calculate GC content 
$n=3;#if you want different n-mers change this number 
%nlet=(); #reset things
$nmer='';

for ($i=0; $i<$num_bases+1-$n; $i++)  #go through @bases and form nlets of consecutive nucleotides
 	{ 
	for ($k=0;$k<$n;$k+=1){ #joins $n consecutive nucleotides
		
		$nmer .= $bases[$i+$k];#form nlet 
		}
	$nlet{$nmer} += 1; #increase nlet counter for one particular nlet by one
	$nmer='';
 
}
#print hash
@nlet_present = sort {$nlet{$b} <=> $nlet{$a} or $a cmp $b } (keys(%nlet));
foreach (@nlet_present){
        print "$_  occurred $nlet{$_} times\n";
};



#print %triplet;