#!/usr/bin/perl -w -s
##########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 ;
		}
}

#################### move sequence to array
#  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 $seq
@bases=split(//,$seq);  #splits string into separate elements (bases)

my$num_bases=@bases; #length of array

###################calculate GC content 

my$num_GC=0;

for ($i=0; $i<($num_bases); $i++)  #counts Gs and Cs in @bases Note the number of bases is one larger than the array
 	{  
 	if(($bases[$i]=~"G") or ($bases[$i]=~"C")) #if it matches G or C increase counter
		{$num_GC++;
		}
	if (!(($bases[$i]=~"G") or ($bases[$i]=~"A") or ($bases[$i]=~"T") or ($bases[$i]=~"C")))
		{print "Warning there is a strange base $bases[$i] before position $i\n";
		my$errors++;}
	}

if (defined ($errors)){$num_bases=$num_bases-$errors};
$GC_content=($num_GC/$num_bases)*100;
print "\nThe GC content of the sequence in the file ".'"'."$filename".'"'. " is $GC_content\%.\n\n";
if (!($name eq '')) {print "Annotation line(s) in $filename was/were $name\n";}
# print "The sequence analyzed was:\n"; 
# print @bases;