open (FH,"<uniprot_sprot.dat");
while (<FH>){
$c++;
#SQ   SEQUENCE   320 AA;  34642 MW;  9E110808B6E328E0 CRC64;
#if (/^SQ   SEQUENCE(.+)AA\;(.+)MW\;/) {
if (/^ /) {
chomp;
s/ //g;
#print "$1\t$2\n";
#print;
@aa = split(//,$_);
foreach $aa(@aa){
$count{$aa}++;
} 
#last if $c > 10000;
}
}
print "results\n";
foreach (keys %count) {
$d++;
print "$d:amino acid $_ occurs $count{$_}\n";
}