#!/usr/bin/perl
use warnings;
use strict;

print 'Enter protein sequence filename: ';
chomp( my $prot_filename = <STDIN> );

open my $PROTFILE, '<', $prot_filename
  or die "Cannot open '$prot_filename' because: $!";

my $out_filename = 'duplicate_gene_entries_in_'.$prot_filename;
open my $OUTFILE, '>', $out_filename
  or die "Cannot open '$out_filename' because: $!";

$/ = ''; # Set paragraph mode


my %seen;
my $header;
my $count_in;
my $count_out;
my $gn;
while (<>) {
    if (/^>.* GN=([^ ]+)/) {
        $gn = $1;
        $header = exists $seen{$gn} ? undef : $_;
    } elsif ($header) {
        undef $seen{$gn};
        print $header, $_;
    }
}
close $OUTFILE;
close $PROTFILE;
printf "%d total records read from '%s'\n",$count_in,$prot_filename;
printf "%d records written to '%s' after removing duplicate entries\n",$count_out,$out_filename;