use strict;
use warnings;
use diagnostics;


open PROTEOME, 'human_complete_proteome_without_isoforms.fasta';

my $peptide;
while( <PROTEOME> ) {
  chomp;
  $peptide .= $_ unless /^>/;
}

print "The proteome is loaded\n";

my %count;

my $aminoacid_ix = 0;
for( my $aminoacid_ix = 0; $aminoacid_ix < length $peptide; ++$aminoacid_ix ) {
  my $aminoacid = substr $peptide, $aminoacid_ix, 1;
  $count{$aminoacid}++;
}
print "Finished searching the document\n";
foreach my $aminoacid ( keys %count ) {
    print "$aminoacid\t occurs $count{$aminoacid} times \n";
}