#!/usr/local/bin/perl
#
#	gene_names2orf2gene.pl
#
#	Parse the gene_names file from Wormbase/sanger, and
#	turn it into the old format of orf2gene
#
#	The new gene_names file looks like:  (tab separated fields)
#	abl-1	Caenorhabditis elegans	Gene	M79.1b,M79.1c,M79.1a			X:10596707..10614654 bp (-)
#
#	orf2gene looks like:
#	Locus : "abl-1"
#	Genomic_Sequence	 "M79.1a"
#	Genomic_Sequence	 "M79.1b"
#	Genomic_Sequence	 "M79.1c"


use strict;

while(<>) {
	chomp;
	my @a = split("\t");
	if( $a[0] ) {
		if( $a[3] =~ /,/ ) {
			my @b = split(",", $a[3] );
			if( $#b > 0 ) {
		printf("Locus : \"%s\"\n", $a[0] );
			for( my $i = 0; $i <= $#b; ++$i ) {
		printf("Genomic_Sequence\t \"%s\"\n", $b[$i] );
			}
		printf("\n");
			}
		} else {
			if( $a[3] ) {
		printf("Locus : \"%s\"\n", $a[0] );
		printf("Genomic_Sequence\t \"%s\"\n\n", $a[3] );
			}
		}
	}
}