use strict;
use Data::Dumper;
my %Gene_overlap;
my %Pos_overlap;
open (MYFILE,$ARGV[0]);
my @file2 =<MYFILE>;
close MYFILE;

open (MYFILE,$ARGV[1]);
my @file1 =<MYFILE>;
close MYFILE;

foreach(@file2){
        chomp;
         my @s = split (/\t/, $_); #Splitting the Validations file for gene name and amino acid 
                
          
                  push(@{$Pos_overlap{$s[5]}{$s[0]}{$s[2]}},$s[2]);  # pushes all sample/postion/gene/ combos into a hash 
              
         } 
foreach(@file1){
         chomp;
           my @s = split (/\t/, $_); # Splitting the file to get the sample/ position / gene 
                
           
           if (exists($Pos_overlap{$s[5]})) {  # Check to see if this gene is also found in the file2 
                    print $_ ."\t" . (keys %{$Pos_overlap{$s[5]}}); # Prints how many times the exact combination of Gene and a unique sample is seen (but samples identity across files does not matter, just how many unique ones there are
    ### This is the part I can't get to work######                
                    if (exists($Pos_overlap{$s[5]}{$s[2]})) {  # Checks if  the exact variant/position combination is present in both files 
                      #  print "\t" . (keys %{$Pos_overlap{$s[5]}{$s[2]}}) . "\n"; #prints how many times variant seen or would also be acceptable to just print a "1", saying that it does exist across both files


                    }
                    else {print "\t0\n";} # prints 0 if no gene/position found 
            }
            else {print $_ . "\t0\t0\n";} #if no gene overlap