def set2(main_seed_list,all_nodes,candidate_list_one,candidate_list_two,G,iterations):
print "Set 2..."
path_to_save = "result/set2/scores/rwr_result_set2_"
print "Selecting same degree nodes"
same_degree_nodes=[]
while len(same_degree_nodes)<5:
node = random.choice(all_nodes)
for i in main_seed_list:
if G.degree(node)==G.degree(i):
same_degree_nodes.append(node)
break
print "Got the same degree nodes"
candidate_list=candidate_list_one+same_degree_nodes
seed_list = [x for x in same_degree_nodes if x not in main_seed_list]
print "Got candidate list and seed list\n Will now run RWR"
wk = Walker(G)
wk.run_walker(seed_list,0.7,candidate_list,path_to_save,iterations)
print "Successfully run RWR and saved scores\n Will now save the 5 genes"
fp = open("result/set2/genes/gene_"+str(iterations)+".txt","w")
for i in same_degree_nodes:
fp.write(i+"\n")
print "Done saving now returning"
def set1(main_seed_list, candidate_list_one, candidate_list_two, G,
iterations):
#path where to save the scores
path_to_save = "result/rwr/set1/scores/rwr_result_set1_"
#creating the candidate list
candidate_list = candidate_list_one + candidate_list_two
#creating seed list after filtering out the 5 genes from the main seed list
seed_list = []
for i in main_seed_list:
flag = False
for j in candidate_list:
if i == j:
flag = True
break
if flag == False:
seed_list.append(i)
print "set 1 seed = " + str(len(seed_list))
print "Will now run RWR"
wk = Walker(G)
wk.run_walker(seed_list, 0.7, candidate_list, path_to_save, iterations)
print "Successfully run RWR and saved scores\n Will now save the 5 genes"
#for saving the 5 disease associated genes
fp = open("result/rwr/set1/genes/gene_" + str(iterations) + ".txt", "w")
for i in candidate_list_two:
fp.write(i + "\n")
print "Done saving now returning"
return
def set2(main_seed_list,candidate_list_one,candidate_list_two,hist_seed_list,G,iterations):
path_to_save = "result/rwr/set2/scores/rwr_result_set2_"
candidate_list = candidate_list_one+candidate_list_two
same_degree_nodes = candidate_list_two
print "Got candidate list and seed list\n Will now run RWR for set2"
wk = Walker(G)
wk.run_walker(main_seed_list,0.7,candidate_list,path_to_save,iterations)
ranks = []
for z in same_degree_nodes:
flag=False
result_file = pd.read_csv("result/rwr/set2/scores/rwr_result_set2_"+str(iterations)+".txt",delim_whitespace="",header=None)
result_file = list(result_file[0])
for i in range(len(result_file)):
if z == result_file[i]:
flag=True
break
if flag == True:
ranks.append(i)
print "Successfully run RWR and saved scores\n Will now save the 5 genes for set2"
fp = open("result/rwr/set2/genes/gene_"+str(iterations)+".txt","w")
for i in range(len(same_degree_nodes)):
fp.write(hist_seed_list[i]+","+same_degree_nodes[i]+","+str(ranks[i])+"\n")
fp.close()
print "Done saving now returning for set2"
def set1(main_seed_list, candidate_list_one, candidate_list_two, G,
iterations):
print "Set 1..."
rprob = 0.1
while rprob <= 0.9:
path_to_save = "result/" + str(iterations + 1) + "/rprob_"
candidate_list = candidate_list_one + candidate_list_two
seed_list = []
for i in main_seed_list:
flag = False
for j in candidate_list:
if i == j:
flag = True
break
if flag == False:
seed_list.append(i)
print "Will now run RWR"
wk = Walker(G)
wk.run_walker(seed_list, rprob, candidate_list, path_to_save, rprob)
print "Successfully run RWR and saved scores\n Will now save the 5 genes"
rprob += 0.1
fp = open("result/" + str(iterations + 1) + "/gene.txt", "w")
for i in candidate_list_two:
fp.write(i + "\n")
print "Returning"
def set1_swapped(main_seed_list,candidate_list_one,candidate_list_two,G,iteration):
path_to_save = "result/rwr/edge_swap_result/edge_swap/set1/scores/rwr_result_set1_"
candidate_list = candidate_list_one+candidate_list_two
seed_list = []
for i in main_seed_list:
flag = False
for j in candidate_list:
if i==j:
flag = True
break
if flag==False:
seed_list.append(i)
print "Running RWR for Set1_EdgeSwap"
wk = Walker(G)
wk.run_walker(seed_list,0.7,candidate_list,path_to_save,iteration)
print "RWR done for set1-edge swapped"
fp = open("result/rwr/edge_swap_result/original/set1/genes/gene_"+str(iteration)+".txt","w")
for i in candidate_list_two:
fp.write(i+"\n")
fp.close()
print "Done saving genes for Set1_edge_swapped"
return
def set2_swapped(main_seed_list,candidate_list_one,same_degree_nodes,G,iteration):
path_to_save = "result/rwr/edge_swap_result/edge_swap/set2/scores/rwr_result_set2_"
candidate_list = candidate_list_one+same_degree_nodes
print "Running rwr for set2_swapped"
wk = Walker(G)
wk.run_walker(main_seed_list,0.7,candidate_list,path_to_save,iteration)
ranks = []
for z in same_degree_nodes:
flag = False
result_file = pd.read_csv("result/rwr/edge_swap_result/edge_swap/set2/scores/rwr_result_set2_"+str(iteration)+".txt",delim_whitespace="",header=None)
result_file = list(result_file[0])
for i in range(len(result_file)):
if z==result_file[i]:
flag = True
break
if flag == True:
ranks.append(i)
print "RWR Done for set2-edgeswapped"
fp = open("result/rwr/edge_swap_result/edge_swap/set2/genes/gene_"+str(iteration)+".txt","w")
for i in range(len(same_degree_nodes)):
fp.write(hist_seed_list[i]+","+same_degree_nodes[i]+","+str(ranks[i])+"\n")
print "Done Writing..."
return
def set2_original(main_seed_list,all_nodes,candidate_list_one,G,iteration):
path_to_save = "result/rwr/edge_swap_result/original/set2/scores/rwr_result_set2_"
print "Selecting same degree nodes"
candidate_list = list(candidate_list_one)
hist_seed_list = []
same_degree_nodes = []
while len(candidate_list)<=99:
hist = random.choice(main_seed_list)
deg_match = sr.ret_same_deg(hist)
flag1 = False
flag2 = False
for node in candidate_list:
if node == deg_match:
flag1 = True
break
for node in hist_seed_list:
if node == hist:
flag2 = True
break
if flag1==False and flag2==False:
hist_seed_list.append(hist)
same_degree_nodes.append(deg_match)
candidate_list.append(deg_match)
for i in range(len(same_degree_nodes)):
print str(hist_seed_list[i])+" "+str(G.degree(hist_seed_list[i]))+" "+str(same_degree_nodes[i])+" "+str(G.degree(same_degree_nodes[i]))
print "Running RWR for Set2_original"
wk = Walker(G)
wk.run_walker(main_seed_list,0.7,candidate_list,path_to_save,iteration)
ranks = []
for z in same_degree_nodes:
flag = False
result_file = pd.read_csv("result/rwr/edge_swap_result/original/set2/scores/rwr_result_set2_"+str(iteration)+".txt",delim_whitespace="",header=None)
result_file = list(result_file[0])
for i in range(len(result_file)):
if z == result_file[i]:
flag = True
break
if flag == True:
ranks.append(i)
print "Ran RWR and saved scores. Will now save gene list for Set2_original"
fp = open("result/rwr/edge_swap_result/original/set2/genes/gene_"+str(iteration)+".txt","w")
for i in range(len(same_degree_nodes)):
fp.write(hist_seed_list[i]+","+same_degree_nodes[i]+","+str(ranks[i])+"\n")
print "done writing.."
return hist_seed_list,same_degree_nodes
def set3(hist_seed_list, same_degree_nodes, candidate_list_one, seed_list,
iterations):
candidate_list = hist_seed_list + same_degree_nodes + candidate_list_one
path_to_save = "result/rwr/set3/scores/rwr_result_set3_"
wk = Walker(G)
wk.Walker(seed_list, 0.7, candidate_list, path_to_save, iterations)
ranks1 = []
for x in same_degree_nodes:
flag = False
result_file = pd.read_csv("result/rwr/set3/rwr_result_set3_" +
str(iterations) + ".txt",
delim_whitespace="",
header=None)
col1 = result_file[0]
col2 = result_file[1]
for i in range(len(result_file)):
if x == col1[i]:
flag = True
break
if flag == True:
ranks.append(col2[i])
ranks2 = []
for x in hist_seed_list:
flag = False
result_file = pd.read_csv("result/rwr/set3/rwr_result_set3_" +
str(iterations) + ".txt",
delim_whitespace="",
header=None)
col1 = result_file[0]
col2 = result_file[1]
for i in range(len(result_file)):
if x == col1[i]:
flag = True
break
if flag == True:
ranks2.append(col2[i])
fp = open("result/rwr/set3/genes/gene_" + str(iterations) + ".txt", "wb")
for i in range(len(same_degree_nodes)):
fp.write(
str(hist_seed_list[i]) + "," + str(ranks1[i]) + "," +
str(same_degree_nodes[i]) + "," + str(ranks2[i]) + "\n")
def set3(main_seed_list,all_nodes,candidate_list_one,G,iterations):
print "Set 3..."
path_to_save = "result/set3/scores/rwr_result_set3_"
print "selecting random genes"
candidate_list_two = random.sample(all_nodes,5)
candidate_list = candidate_list_one+candidate_list_two
seed_list = [x for x in candidate_list_two if x not in main_seed_list]
print "Will now run RWR"
wk = Walker(G)
wk.run_walker(seed_list,0.7,candidate_list,path_to_save,iterations)
print "Successfully run RWR and saved scores\n Will now save the 5 genes"
fp = open("result/set3/genes/gene_"+str(iterations)+".txt","w")
for i in candidate_list_two:
fp.write(i+"\n")
print "Done saving now returning"
def set1(main_seed_list,candidate_list_one,candidate_list_two,G,iterations):
print "Set 1..."
#path where to save the scores
path_to_save = "result/set1/scores/rwr_result_set1_"
#creating the candidate list
candidate_list = candidate_list_one + candidate_list_two
#creating seed list after filtering out the 5 genes from the main seed list
seed_list = [x for x in candidate_list_two if x not in main_seed_list]
print "Will now run RWR"
wk = Walker(G)
wk.run_walker(seed_list,0.7,candidate_list,path_to_save,iterations)
print "Successfully run RWR and saved scores\n Will now save the 5 genes"
#for saving the 5 disease associated genes
fp = open("result/set1/genes/gene_"+str(iterations)+".txt","w")
for i in candidate_list_two:
fp.write(i+"\n")
print "Done saving now returning"
return
import pandas as pd
import networkx as nx
from rwr import Walker
candidate_list_temp = pd.read_csv("candidate_list.txt",delim_whitespace="",header=None)
candidate_list_temp = candidate_list[0]
candidate_list_one = random.sample(candidate_list_temp,98)
candidate_list_two = ['DRD4','DAO']
candidate_list = candidate_list_one+candidate_list_two
seed_list = pd.read_csv("seed_list.txt",delim_whitespace="",header=None)
seed_list = seed_list[0]
G = nx.read_gpickle("HPRD-Biogrid.pkl")
rprob = 0.1
wk = Walker(G)
while rprob<1.0:
print rprob
wk.run_walker(seed_list,rprob,candidate_list,"result/rprob_",rprob)
rprob+=0.1