#!/usr/bin/perl -w
use strict;
use Data::Dumper;
#open file
open(IN,"CCDS.20090902.txt") or die " Can't open ccds file: $!";
# initialize the hash
my %geneids =();
#open the file and push the info from the designated columns into it
# remove header
my $firstline = <IN>;
chomp $firstline; 
while(<IN>){
	chomp; # remove the newline character
	my @fields = split (/\t/, $_);
	#extract the columns that we are interested in.
	my($key, $value) = ($fields[2], $fields[3]);
	# Populate the key value pairs of the hash with $gene and $id
	$geneids{$key} = $value;
	print "$key\t$value\n";
}
# We can also get the size of the hash
print "Hash size: ", scalar keys %geneids, "\n";
close();
__DATA__
#chromosome	nc_accession	gene	gene_id	ccds_id	ccds_status
1	NC_000001.8	NCRNA00115	79854	CCDS1.1	Withdrawn
1	NC_000001.10	SAMD11	148398	CCDS2.2	Public
1	NC_000001.10	NOC2L	26155	CCDS3.1	Public
1	NC_000001.10	PLEKHN1	84069	CCDS4.1	Public
1	NC_000001.10	HES4	57801	CCDS5.1	Public
1	NC_000001.10	ISG15	9636	CCDS6.1	Public
1	NC_000001.10	C1orf159	54991	CCDS7.2	Public
1	NC_000001.10	TTLL10	254173	CCDS8.1	Public
1	NC_000001.10	TNFRSF18	8784	CCDS9.1	Public
1	NC_000001.10	TNFRSF18	8784	CCDS10.1	Public
1	NC_000001.10	TNFRSF4	7293	CCDS11.1	Public
1	NC_000001.10	SDF4	51150	CCDS12.1	Public
1	NC_000001.10	B3GALT6	126792	CCDS13.1	Public
1	NC_000001.10	UBE2J2	118424	CCDS14.1	Public