A dumb line filter

vcf-filter.pl

#/usr/bin/perl

use strict;
use warnings;

#The names of the input files are provided on the command line
if (@ARGV == 2) {
	# Read input files

	my $ids_file = $ARGV[0];
	# <ids.txt>
	#rs61733845
	#rs16823940
	#...

	my $vcf_vile = $ARGV[1];
	# <YRI.exon.2010_03.sites.vcf>
	#22	43691009	rs8135982	C	T	.	PASS	AA=C;AC=13;AN=132;DP=723
	#22	48958132	rs35195493	C	G	.	PASS	AA=C;AC=4;AN=178;DP=3609
	#...


	my @ids = (); 								#This will contain the IDs from ids.txt
	
	open (ids_handle, $ids_file);
	
	while (my $line = <ids_handle>) {

		chomp($line);							#Remove the whitespace from the line 
		push(@ids, $line);						#Add the ID to the list of IDs
	}
	close(ids_handle);


	#Search the VCF for matching IDs
	open(vcf_handle, $vcf_vile);

	while (my $line = <vcf_handle>) {
		foreach my $id (@ids) {						#try to match each of the IDs
			if ($line =~ /\Q$id\E/) {				#check if line contains ID
				print "$line";				#print it if we found it
			}
		}
	}
	close(vcf_handle);

} else {
	die "USAGE: vcf-search ids.txt input.vcf\n";
}