0 25 27 60454 2 2 3 2 2 3 3 3 2 3 1 1 2 1 2 2 3 3 2 1 2 1 1 1 2 3
0 19 33 60466 2 2 3 2 2 2 3 3 3 3 1 1 2 1 2 3 3 3 2 1 2 3 2 2 3 3
0 25 27 60692 2 2 3 2 2 3 3 3 2 3 1 1 2 1 2 2 3 3 2 1 2 1 1 1 2 3
0 50 2 60727 1 1 1 1 1 2 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
0 48 4 60814 1 1 1 1 1 1 2 1 1 3 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 1
0 46 6 60866 1 1 1 1 1 1 1 3 1 1 1 1 1 1 1 2 2 2 1 1 1 1 1 1 1 2
0 25 27 60882 2 2 3 2 2 3 3 3 2 3 1 1 2 1 2 2 3 3 2 1 2 1 1 1 2 3
0 48 4 60888 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 2 2 1 1 1 1 1 1 1 1 2
0 50 2 60909 1 1 1 1 1 2 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
####
chrX 1 1000001
chrX 100001 1100001
chrX 200001 1200001
chrX 300001 1300001
chrX 400001 1400001
chrX 500001 1500001
chrX 600001 1600001
chrX 700001 1700001
chrX 800001 1800001
##
##
my $placeholder = 0;
my $count = 0;
#my $window = "1Mbwindow_overlapping100kb";
my $interval_directory = "/Users/logancurtis-whitchurch/Desktop/IB_Senior_Thesis/galaxy_chrX_data/";
my $input_interval = "$interval_directory"."chrX_"."$window".".txt";
my $cg_input = "/Users/logancurtis-whitchurch/Desktop/IB_Senior_Thesis/CompleteGenomics/All26.females/CGS.All26.txt";
#my $output_directory = "/Users/logancurtis-whitchurch/Desktop/IB_Senior_Thesis/temps/overlapping/1Mb/";
open (INTERVAL, "$input_interval") or die "can't open $input_interval\n";
my $interval = ;
my (@find_interval, $start, $end);
open (CG, "<$cg_input") or die "can't open $cg_input\n";
my @SNPs = ;
close(CG);
foreach my $interval (){
@find_interval = split(/\t/, $interval);
$start = $find_interval[1];
$end = $find_interval[2];
my $tmp = "temp_file_"."$count".".txt";
my $output_file = "$output_directory" . "$tmp";
open (OUT, ">>$output_file");
my $switch = 1;
while ($switch == 1) {
my @get_SNPs = split(/\t/, $SNPs[$placeholder]);
my $position = $get_SNPs[3];
if (($position < $start) && ($position < $end)) {
$placeholder++;
}
if (($position >= $start) && ($position <= $end)) {
print OUT "@get_SNPs";
$placeholder++;
}
else {
$switch =! 1;
}
}
$count++;
}
close(INTERVAL);