import time
import string
import sys

start_time = time.time()

def generate_gene_lists(core_file_name, list_file_name): #A function for generating lists of core genes and genes to rank.
	temp_core = []
	temp_list = []
	core_file = open(core_file_name, 'r')
	list_file = open(list_file_name, 'r')
	for line in core_file:
		gene_name = line.strip()
		print gene_name
		temp_core.append(gene_name)
	core_file.close()
	for line in list_file:
		gene_name = line.strip()
		temp_list.append(gene_name)
	list_file.close()
	return temp_core, temp_list
	
def extract_from_core_gene(temp_core_path, temp_gene_list, temp_core_gene): #A function for extracting a list of genes from a core gene connectome and then sorting by distance.
	temp_list = []
	flag = 0
	print "Prioritizing list in core gene " + temp_core_gene + "\tseconds from start:\t" + str(time.time()-start_time)
	header = "Target\tDistance\tRank\tP-value(percentile)\tBRP\tMedian_ratio\tAverage_ratio\tSphere\tRoute\tDegrees_separation\n"
	for gene in temp_gene_list:
		try:
			temp_core_file = open(temp_core_path, 'r')
			counter = 1
			flag = 0
			for line in temp_core_file:
				counter = counter + 1
				line_stripped = line.strip()
				words = line_stripped.split("\t")
				temp_gene = words[0]
				found_flag = 0
				if (gene == temp_gene): #Gene found in connectome
					found_flag = 1
					words[1] = float(words[1])
					words[2] = int(words[2])
					words[3] = float(words[3])
					words[4] = float(words[4])
					words[5] = float(words[5])
					words[6] = float(words[6])
					words[7] = int(words[7])
					words[9] = int(words[9])
					temp_list.append(words)
					if (counter > 1):
						to_write = '\t'.join(str(e) for e in words)
						to_write = temp_core_gene + "\t" + to_write + "\n"
						file1.write(to_write)
					flag = 1
					break
			temp_core_file.close()
		except:
			flag = -1 #Connectome file doesn't exist

###########Main program#########

HGC_path = '/Volumes/SSD2/Connectome/10.0/All_connectomes_v10.0/' #Path to all gene specific connectomes
core_list, gene_list = generate_gene_lists("core_genes.txt", "candidate_genes.txt") #Create lists of core genes and genes to be ranked 
#print core_list
file1 = open("candidates_in_core_genes.txt", 'w')
header = "Core\tTarget\tDistance\tRank\tP-value(percentile)\tBRP\tMedian_ratio\tAverage_ratio\tSphere\tRoute\tDegrees_separation\n"
file1.write(header)
for core_gene in core_list: #Going through all core genes
	core_path = HGC_path + core_gene + ".txt"
	extract_from_core_gene(core_path, gene_list, core_gene)
print "Run complete in:\t" + str(time.time()-start_time) + "\tseconds"
file1.close()