-
Notifications
You must be signed in to change notification settings - Fork 6
/
TestPredict.py
119 lines (96 loc) · 4.48 KB
/
TestPredict.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
import os, sys
def get_immediate_subdirectories(dir):
return [name for name in os.listdir(dir) if os.path.isdir(os.path.join(dir, name))]
sys.path += get_immediate_subdirectories("./")
from datetime import datetime
from DataStore import *
from ReadData import *
from JobManager import *
from Network import *
from Generate_Grid import *
from AnalyzeResults import *
from mcz import *
from clr import *
from convex_optimization import *
from genie3 import *
from dfg4grn import *
from ReadConfig import *
# Instantsiate settings file
settings = {}
settings = ReadConfig(settings)
settings["global"]["working_dir"] = os.getcwd() + '/'
settings["global"]["experiment_name"] = "DFG-Prediction-"+sys.argv[1]
if len(sys.argv) > 2:
settings["global"]["experiment_name"] += "-" + sys.argv[2]
# Create date string to append to output_dir
t = datetime.now().strftime("%Y-%m-%d_%H.%M.%S")
settings["global"]["output_dir"] = settings["global"]["output_dir"] + "/" + \
settings["global"]["experiment_name"] + "-" + t + "/"
os.mkdir(settings["global"]["output_dir"])
# Read in the gold standard network
# Read in the gold standard network
goldnet = Network()
#goldnet.read_goldstd(settings["global"]["large_network_goldnet_file"])
if sys.argv[1] == "small":
goldnet.read_goldstd(settings["global"]["small_network_goldnet_file"])
#Get a list of the knockout files
ko_file = settings["global"]["small_network_knockout_file"].split()
kd_file = settings["global"]["small_network_knockdown_file"].split()
ts_file = settings["global"]["small_network_timeseries_file"].split()
wt_file = settings["global"]["small_network_wildtype_file"].split()
if sys.argv[1] == "medium":
goldnet.read_goldstd(settings["global"]["medium_network_goldnet_file"])
#Get a list of the knockout files
ko_file = settings["global"]["medium_network_knockout_file"].split()
kd_file = settings["global"]["medium_network_knockdown_file"].split()
ts_file = settings["global"]["medium_network_timeseries_file"].split()
wt_file = settings["global"]["medium_network_wildtype_file"].split()
if sys.argv[1] == "medium2":
goldnet.read_goldstd(settings["global"]["medium2_network_goldnet_file"])
#Get a list of the knockout files
ko_file = settings["global"]["medium2_network_knockout_file"].split()
kd_file = settings["global"]["medium2_network_knockdown_file"].split()
ts_file = settings["global"]["medium2_network_timeseries_file"].split()
wt_file = settings["global"]["medium2_network_wildtype_file"].split()
if sys.argv[1] == "dream410":
goldnet.read_goldstd(settings["global"]["dream410_network_goldnet_file"])
#Get a list of the knockout files
ko_file = settings["global"]["dream410_network_knockout_file"].split()
kd_file = settings["global"]["dream410_network_knockdown_file"].split()
ts_file = settings["global"]["dream410_network_timeseries_file"].split()
wt_file = settings["global"]["dream410_network_wildtype_file"].split()
#mf_file = settings["global"]["dream410_network_multifactorial_file"].split()
if sys.argv[1] == "dream4100":
goldnet.read_goldstd(settings["global"]["dream4100_network_goldnet_file"])
#Get a list of the knockout files
ko_file = settings["global"]["dream4100_network_knockout_file"].split()
kd_file = settings["global"]["dream4100_network_knockdown_file"].split()
ts_file = settings["global"]["dream4100_network_timeseries_file"].split()
wt_file = settings["global"]["dream4100_network_wildtype_file"].split()
#mf_file = settings["global"]["dream4100_network_multifactorial_file"].split()
# Read data into program
# Where the format is "FILENAME" "DATATYPE"
knockout_storage = ReadData(ko_file[0], "knockout")
knockdown_storage = ReadData(kd_file[0], "knockdown")
timeseries_storage = ReadData(ts_file[0], "timeseries")
wildtype_storage = ReadData(wt_file[0], "wildtype")
#mf_storage = ReadData(mf_file[0], "multifactorial")
# Setup job manager
jobman = JobManager(settings)
# Make BANJO jobs
mczjob = MCZ()
mczjob.setup(knockout_storage, wildtype_storage, settings, timeseries_storage, knockdown_storage, "MCZ_Alone")
jobman.queueJob(mczjob)
accs = []
precs = []
settings["dfg4grn"]["eta_z"] = 0.001
settings["dfg4grn"]["lambda_w"] = 0.01
settings["dfg4grn"]["tau"] = 3
dfg = DFG4GRN()
dfg.setup(timeseries_storage, TFList(timeseries_storage[0].gene_list), settings, "DFG4GRN_Baseline", 1)
jobman.queueJob(dfg)
print jobman.queue
jobman.runQueue()
jobman.waitToClear()
mcznet = mczjob.network
dfg.predict_from_weights(mcznet, dfg.settings)