#!/usr/bin/perl -w
use strict;
use Data::Dumper;

my ( $data, $line, $gi, $humangi, %info); 

$data = '/DATA/proteinfile.txt'; 
open INFILE, '<', $data or die "Failed at opening $data!\n";

# Construct the hash with GIs as keys and sequences as values
while ( <INFILE> ) {
$line = $_;
chomp($line);
    last if m!END!;
	
	if($line=~m/HUMAN/){
		
		($humangi) = ($line=~m/^\S+\|(\d+)/)
	
		}
	
	if($line=~m/^\S+\|(\d+)/)
	   {
	    if(defined($1))
		 { 
		  $gi=$1;
		 }	
	   }
	else
	   {
	    $info{$gi}=$line;
	   }
}
	#print Dumper (\%info);

	print "$humangi\n";

close(INFILE);

my $data2 = '/DATA/variantlist.txt'; 
open INFILE2, '<', $data2 or die "Failed at opening $data2!\n";

my $data3 = '/DATA/VariantOutput.txt'; 
open OUTFILE, '>', $data3 or die "Failed at opening $data3!\n";

while ( <INFILE2>){
# Grab a variant from the file (in this example: P82L)
my $Variant = $_;

# Split the variant into three parts
my ($source, $position, $sink) = split(/(\d+)(\w)/, $Variant);

print "$source , $ position , $sink\n";
# Check whether HS has the source (i.e., P) at the given position (i.e., 82)
my @temp = $info{$humangi};

	if ( $temp[$position] eq $source) {
	
	 print "Yep, $source has been confirmed!\n";
	}
	
	else {
		
	print "There is something wrong!\n";
	}

# Scan the rest of the sequences to check what amino acid they have at the given position
for my $gi ( keys %info ) {
        my @value = $info{$gi};
		
		my @VariantList = ();
		
		push ( @VariantList, $value[$position]); 
		
		if ($value[$position] eq $sink){ # Note the cases where we observe the sink (i.e., L) at this position
			
			print OUTFILE "A pathogenic deviation has been found at site $position - from $source to $sink !\n" . " And the corresponding gi for this deviation is: $gi\n";
			
			}
}

#print OUTFILE "Variant list contains: @VariantList\n";
}
close(INFILE2);