Detect HugeNET-specific RS IDs in comparison with NHGRI GWAS data

rsid-diff.pl

#! usr/bin/perl

use warnings;
use strict;

my $gwas_file=$ARGV[0];
my $hugenet_file=$ARGV[1];

my $num_args = $#ARGV + 1;

if ($num_args != 2) {
  print "\nUsage: get-unique-hugenet_snps.pl <gwas_file> <hugenet_file> \n";
  exit;
}





open HUGE , $hugenet_file or die $!;

while(my $hugeline = <HUGE>){

(my $rsNumber,my $Gene,my $Region,my $Trait,my $PubMedID,my $SampleSizeInitialReplicate,my $RiskAllele,my $pValueH) = split(/\t/,$hugeline);

#formatting the rs number since it comes with additional useles information between brackets in HugeNet file we need only the rs number

#print "rsNumber\n";

(my $hugeRS,my $useless) = split(/\(/,$rsNumber);

#print "$hugeRS\n";



open NHGRI, $gwas_file or die $!;

# UNIQ HugeNet specific SNP till proven the opposite :)

my $UNIQ = 1;

while (my $line = <NHGRI>) {

(my $PUBMEDID,my $Study,my $DiseaseTrait,my $InitialSampleSize,my $ReplicationSampleSize,my $Region,my $ReportedGene,my $Mapped_gene,my $Snp_gene_ids,my $Upstream_gene_distance,my $Downstream_gene_distance,my $StrongestSNPRiskAllele,my $SNPs,my $Snp_id_current,my $Context,my $Intergenic,my $RiskAlleleFrequency,my $pValue,my $Pvalue_mlog) = split(/\t/,$line);

if ($SNPs eq $hugeRS){
$UNIQ = 0;
print ("NHGRI ID : $SNPs\n");
last;
}
}

close (NHGRI) ;

print "HUGENET ID : $hugeRS \t $UNIQ \n";
}
close HUGE;