#!/usr/bin/env python

#get_gene_names.py is a script for mapping gene symbols
#and names to Entrez Gene ids
#Copyright (C) 2007  Daniel Shriner

#This program is free software; you can redistribute it and/or
#modify it under the terms of the GNU General Public License
#as published by the Free Software Foundation; either version 2
#of the License, or (at your option) any later version.

#This program is distributed in the hope that it will be useful,
#but WITHOUT ANY WARRANTY; without even the implied warranty of
#MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#GNU General Public License for more details.

#The text of the GNU General Public License, version 2, is available
#as http://www.gnu.org/copyleft or by writing to the Free Software
#Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.

import sys,gzip,os

names = []

#Load the gene_info file
try:
	f1 = gzip.open('gene_info.hs.09May06.gz','rb')
except IOError:
	print >> sys.stderr, 'Error opening gene_info file.\n'
	sys.exit(1)

entry = []
while 1:
	line = f1.readline()
	if not line: break
	line = line.split('\t')
	entry = [line[1],line[2],line[8]]
	names.append(entry)
f1.close()

#Open the input file of gene ids
try:
	f2 = open('adj_genes.txt','r')
except IOError:
	print >> sys.stderr, 'Error opening adj_genes.txt.\n'
	sys. exit(1)

#Open an output file for printing out gene info
try:
	f3 = open('adj_gene_names.txt','w')
except IOError:
	print >> sys.stderr, 'Error opening output file.\n'
	sys.exit(1)

while 1:
	line = f2.readline()
	if not line: break
	line = line.split('\t')
	line[1] = line[1][:-1]
	if line[1]=='NA':
		print >> f3, '%s\tNA\tNA\tNA' % line[0]
	else:
		i = 0
		while 1:
			if i < len(names):
				if line[1]==names[i][0]:
					print >> f3, '%s\t%s\t%s\t%s' % (line[0],line[1],names[i][1],names[i][2])
				i += 1
			else: break

f2.close()
f3.close()
os.remove('adj_genes.txt')
os.rename('adj_gene_names.txt','adj_genes.txt')