#!/usr/bin/perl -w

use strict;
use warnings;
use File::Path;
use vars qw(@genes_number %count $AG_value $GC_bin @arr %gc_ag);
#####################################################################################
#                         Open Input and Output Files                               #
#####################################################################################
if( @ARGV < 2){

      print "NSD analysis file needs the following arguments\n";
      print "Name of merged Static and experimental file, Name of experiment (first col of first file, Output file name\n";
      exit 0;
}
opendir (DIR, "/nsd/data") || die "Cannot open directroy data $!";
open(NSD, "firstfile.txt") || die "Cannot open file NSD file"; # NSD data
open(INPUT1,$ARGV[0]) || die "Cannot open file \"$ARGV[0]\""; # Analysis file
my $exp_name=$ARGV[1] || die "Enter the name of Experiment \"$ARGV[1]\"";
open(RESULTS, ">/nsd/data/$ARGV[2]")|| die "Cannot open the results file";
#my $GC_bin=$ARGV[3] || die "Enter the GC content that you want to anlyze \"$ARGV[2]\"";

#open(RESULTS,">result.txt")|| die "Cannot open the results file";
#my $AG_value=0;
# read all AG 90 values for all gc bins into  a hash
# then for the keys of this hash use the values for making # comparisons

my %gc_ag =();
while(<NSD>){
         chomp;
          my @current_line_nsd  = split /\t/;
            if ($exp_name eq $current_line_nsd[0]){
                       $gc_ag{$current_line_nsd[2]} = $current_line_nsd[17];

           }
    }

         foreach my $v (sort {$a<=>$b} keys %gc_ag) {
         print "$v\t$gc_ag{$v}\n";
         }

close (NSD);

#reading the second file entered by user as an argument
my %genes_number =();
while(<INPUT1>){
         chomp;
          my @current_line  = split /\t/;

          foreach my $k (sort {$a<=>$b} keys %gc_ag) {

                if ($current_line[3] == $k && $current_line[8] > $gc_ag{$k} ) {

          # push(@genes_number, $current_line[1]);

          push(@{$genes_number{$k}}, $current_line[1]);
          }
     }
}

&count_unique (@genes_number);


######################################################
sub count_unique {

     @genes_number = @_;

     my %count;

     map { $count{$_}++ } @genes_number;

      #print them out:

     map {push our @arr, ${count{$_}}} sort keys(%count);


     for (my $j=1; $j<10; $j++){
     my $counter =0;
         foreach my $element(@arr) {

                   if ($element >=$j) {
             $counter++;
        }
     }
     print "$j\t$counter\n";
}
     #print "Number of genes with more than 5 probes is: $counter\n";
     #print scalar(@arr)."\n" ;
     #map {print RESULTS "$_\n"} sort keys(%count);
     my $i =0;
         $i += keys %count;
        # print $i;

     return %count;
}

close (INPUT1);
close (RESULTS);
close (DIR);