def run(self, name, datafiles, goldnet_file):
import numpy
os.chdir(os.environ["gene_path"])
datastore = ReadData(datafiles[0], "steadystate")
for file in datafiles[1:]:
datastore.combine(ReadData(file, "steadystate"))
datastore.normalize()
settings = {}
settings = ReadConfig(settings)
# TODO: CHANGE ME
settings["global"]["working_dir"] = os.getcwd() + '/'
# Setup job manager
print "Starting new job manager"
jobman = JobManager(settings)
# Make GENIE3 jobs
genie3 = GENIE3()
genie3.setup(datastore, settings, name)
print "Queuing job..."
jobman.queueJob(genie3)
print jobman.queue
print "Running queue..."
jobman.runQueue()
jobman.waitToClear()
print "Queue finished"
job = jobman.finished[0]
print job.alg.gene_list
print job.alg.read_output(settings)
jobnet = job.alg.network
print "PREDICTED NETWORK:"
print job.alg.network.network
print jobnet.original_network
if goldnet_file != None:
goldnet = Network()
goldnet.read_goldstd(goldnet_file)
print "GOLD NETWORK:"
print goldnet.network
print jobnet.analyzeMotifs(goldnet).ToString()
print jobnet.calculateAccuracy(goldnet)
return jobnet.original_network
os.mkdir(settings["global"]["output_dir"]) # Read in the gold standard network #goldnet = Network() #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() # Read in the gold standard network goldnet = Network() goldnet.read_goldstd(settings["global"]["large_network_goldnet_file"]) ko_file = settings["global"]["large_network_knockout_file"].split() kd_file = settings["global"]["large_network_knockdown_file"].split() ts_file = settings["global"]["large_network_timeseries_file"].split() wt_file = settings["global"]["large_network_wildtype_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") wildtype_storage.combine(knockout_storage) wildtype_storage.combine(knockdown_storage)
wildtypes[name] = ReadData(exp_data_directory + '/' + name + '/' + wildtype_filename, "wildtype")
#wildtypes[name].normalize()
multifactorials[name] = ReadData(exp_data_directory + '/' + name + '/' + multifactorial_filename, "multifactorial")
#multifactorials[name].normalize()
goldnets[name] = exp_data_directory + '/' + name + '/' + goldstandard_filename
jobman = JobManager(settings)
# Get TFS from the goldstandard
tfs = {}
for name in data.keys():
t = []
goldnet = Network()
goldnet.read_goldstd(goldnets[name])
for gene1 in goldnet.network:
for gene2 in goldnet.network[gene1]:
if goldnet.network[gene1][gene2] > 0:
t.append(gene1)
tfs[name] = list(set(t))
goldnet = Network()
goldnet.read_goldstd(goldnets[data.keys()[0]])
genie3nets = {}
ts_storage = data[name]
settings["global"]["time_series_delta_t"] = (1008.0 / (len(ts_storage[0].experiments)-1))
#combined = timeseries_as_steady_state[name][0]
from JobManager import *
from Network import *
from Generate_Grid import *
from tdaracne import *
from dfg4grn import *
from banjo import *
from ReadConfig import *
settings = {}
settings = ReadConfig(settings)
settings["global"]["working_dir"] = os.getcwd() + "/"
goldnet = Network()
goldnet.read_goldstd("datasets/dream4_10/dream4_10_gold.tsv")
# 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"])
ts_filenames = settings["global"]["time_series_files"].split()
delta_t = [50] * 20
settings["global"]["time_series_delta_t"] = delta_t
# Read data into program
timeseries_storage = ReadData(ts_filenames[0], True)
def run(self, kofile, tsfile, wtfile, datafiles, name, goldnet_file, normalize=False):
os.chdir(os.environ["gene_path"])
knockout_storage = ReadData(kofile, "knockout")
print "Reading in knockout data"
wildtype_storage = ReadData(wtfile, "steadystate")
if datafiles == []:
other_storage = None
else:
other_storage = ReadData(datafiles[0], "steadystate")
for file in datafiles[1:]:
other_storage.combine(ReadData(file, "steadystate"))
timeseries_storage = None
if tsfile != None:
timeseries_storage = ReadData(tsfile, "timeseries")
#for ts in timeseries_storage:
#ts.normalize()
#if normalize:
#knockout_storage.normalize()
#wildtype_storage.normalize()
#other_storage.normalize()
settings = {}
settings = ReadConfig(settings)
# TODO: CHANGE ME
settings["global"]["working_dir"] = os.getcwd() + '/'
# Setup job manager
print "Starting new job manager"
jobman = JobManager(settings)
# Make inferelator jobs
inferelatorjob = inferelator()
inferelatorjob.setup(knockout_storage, wildtype_storage, settings, timeseries_storage, other_storage, name)
print "Queuing job..."
jobman.queueJob(inferelatorjob)
print jobman.queue
print "Running queue..."
jobman.runQueue()
jobman.waitToClear()
print "Queue finished"
job = jobman.finished[0]
#print job.alg.gene_list
#print job.alg.read_output(settings)
jobnet = job.alg.network
#print "PREDICTED NETWORK:"
#print job.alg.network.network
print jobnet.original_network
if goldnet_file != None:
goldnet = Network()
goldnet.read_goldstd(goldnet_file)
#print "GOLD NETWORK:"
#print goldnet.network
#print jobnet.analyzeMotifs(goldnet).ToString()
print jobnet.calculateAccuracy(goldnet)
import AnalyzeResults
tprs, fprs, rocs = AnalyzeResults.GenerateMultiROC(jobman.finished, goldnet )
ps, rs, precs = AnalyzeResults.GenerateMultiPR(jobman.finished, goldnet)
print "Area Under ROC"
print rocs
print "Area Under PR"
print precs
return jobnet.original_network
#pert_data = ReadData(exp_data_directory + "/" + exp_set + "/" + '/TS/' + multifactorial_filename, "multifactorial") #multifactorials.normalize() ts_pert_data["goldnet_file"] = exp_data_directory + "/" + exp_set + "/" + '/TS/' + goldstandard_filename ko_pert_data["ss_data"] = ReadData(exp_data_directory + "/" + exp_set + "/" + '/TS/' + wildtype_filename, "wildtype") ko_pert_data["multifactorial_data"] = ReadData(exp_data_directory + "/" + exp_set + "/" + '/TS/' + multifactorial_filename, "multifactorial") ko_pert_data["knockout_data"] = ReadData(exp_data_directory + "/" + exp_set + "/" + '/TS/' + knockout_filename, "knockout") ko_pert_data["combined"] = ReadData(exp_data_directory + "/" + exp_set + "/" + '/TS/' + knockout_filename, "knockout") ko_pert_data["combined"].combine(ko_pert_data["multifactorial_data"]) pert_data["multifactorial_data"] = ReadData(exp_data_directory + "/" + exp_set + "/" + '/TS/' + multifactorial_filename, "multifactorial") pert_data["knockout_data"] = ReadData(exp_data_directory + "/" + exp_set + "/" + '/TS/' + knockout_filename, "knockout") goldnet = Network() goldnet.read_goldstd(ts_pert_data["goldnet_file"]) ###################### # Clip down the pert data so it is the correct size for the exp ###################### # This is the num for everything to use ts_only_data["timeseries"] = [ts_only_data["timeseries"][0]] ts_data_num_exp = len(ts_only_data["timeseries"]) * len(ts_only_data["timeseries"][0].experiments) ts_only_data["multifactorial_data"].experiments = ts_only_data["multifactorial_data"].experiments[0:len(ts_only_data["multifactorial_data"].experiments) - ts_data_num_exp] ts_pert_data["timeseries"] = ts_pert_data["timeseries"][0:len(ts_pert_data["timeseries"]) / 2] num_ts_pert = len(ts_pert_data["timeseries"]) * len(ts_pert_data["timeseries"][0].experiments)
def run(self, datafiles=None, name=None, goldnet_file=None, topd=None, restk=None):
import numpy
os.chdir(os.environ["gene_path"])
print "Reading in data"
data_storage = ReadData(datafiles[0], "steadystate")
for file in datafiles[1:]:
data_storage.combine(ReadData(file, "steadystate"))
settings = {}
settings = ReadConfig(settings)
# TODO: CHANGE ME
settings["global"]["working_dir"] = os.getcwd() + "/"
# Setup job manager
print "Starting new job manager"
jobman = JobManager(settings)
# Make nir jobs
nirjob = NIR()
nirjob.setup(data_storage, settings, name, topd, restk)
print "Queuing job..."
jobman.queueJob(nirjob)
print jobman.queue
print "Running queue..."
jobman.runQueue()
jobman.waitToClear()
print "Queue finished"
job = jobman.finished[0]
print job.alg.gene_list
print job.alg.read_output(settings)
jobnet = job.alg.network
print "PREDICTED NETWORK:"
print job.alg.network.network
if goldnet_file != None:
goldnet = Network()
goldnet.read_goldstd(goldnet_file)
# print "GOLD NETWORK:"
# print goldnet.network
# print jobnet.analyzeMotifs(goldnet).ToString()
print jobnet.calculateAccuracy(goldnet)
import AnalyzeResults
tprs, fprs, rocs = AnalyzeResults.GenerateMultiROC(
jobman.finished, goldnet, True, job.alg.output_dir + "/ROC.pdf"
)
ps, rs, precs = AnalyzeResults.GenerateMultiPR(
jobman.finished, goldnet, True, job.alg.output_dir + "/PR.pdf"
)
print "Area Under ROC"
print rocs
print "Area Under PR"
print precs
return job.alg.network.network
# 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":
# Instantsiate settings file
settings = {}
settings = ReadConfig(settings)
settings["global"]["working_dir"] = os.getcwd() + '/'
# 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
goldnet = Network()
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()
# Read in the gold standard network
#goldnet = Network()
#goldnet.read_goldstd(settings["global"]["large_network_goldnet_file"])
#ko_file = settings["global"]["large_network_knockout_file"].split()
#kd_file = settings["global"]["large_network_knockdown_file"].split()
#ts_file = settings["global"]["large_network_timeseries_file"].split()
from JobManager import *
from Network import *
from Generate_Grid import *
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 ReadConfig import *
settings = {}
settings = ReadConfig(settings)
settings["global"]["working_dir"] = os.getcwd() + '/'
goldnet = Network()
goldnet.read_goldstd(settings["global"]["small_network_goldnet_file"])
# 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"])
knockdown_filenames = settings["global"]["small_network_knockdown_file"].split()
knockdown_storage = ReadData(knockdown_filenames[0], "knockdown")
from nirest import *
settings = ReadConfig(settings, "./config/default_values/nirest.cfg")
settings = ReadConfig(settings, settings["nirest"]["config"])
def get_example_data_files(name, settings):
# Read in gold standard network
goldnet = Network()
dko_file = None
if name == "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()
mf_file = settings["global"]["small_network_multifactorial_file"].split()
elif name == "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()
mf_file = settings["global"]["medium_network_multifactorial_file"].split()
elif name == "medium_2":
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()
mf_file = settings["global"]["medium2_network_multifactorial_file"].split()
elif name == "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()
dko_file = settings["global"]["dream410_network_doubleknockout_file"].split()
dko_idx_file = settings["global"]["dream410_network_doubleknockout_index_file"].split()
elif name == "dream410_2":
goldnet.read_goldstd(settings["global"]["dream410_2_network_goldnet_file"])
#Get a list of the knockout files
ko_file = settings["global"]["dream410_2_network_knockout_file"].split()
kd_file = settings["global"]["dream410_2_network_knockdown_file"].split()
ts_file = settings["global"]["dream410_2_network_timeseries_file"].split()
wt_file = settings["global"]["dream410_2_network_wildtype_file"].split()
mf_file = settings["global"]["dream410_2_network_multifactorial_file"].split()
elif name == "dream410_3":
goldnet.read_goldstd(settings["global"]["dream410_3_network_goldnet_file"])
#Get a list of the knockout files
ko_file = settings["global"]["dream410_3_network_knockout_file"].split()
kd_file = settings["global"]["dream410_3_network_knockdown_file"].split()
ts_file = settings["global"]["dream410_3_network_timeseries_file"].split()
wt_file = settings["global"]["dream410_3_network_wildtype_file"].split()
mf_file = settings["global"]["dream410_3_network_multifactorial_file"].split()
elif name == "dream410_4":
goldnet.read_goldstd(settings["global"]["dream410_4_network_goldnet_file"])
#Get a list of the knockout files
ko_file = settings["global"]["dream410_4_network_knockout_file"].split()
kd_file = settings["global"]["dream410_4_network_knockdown_file"].split()
ts_file = settings["global"]["dream410_4_network_timeseries_file"].split()
wt_file = settings["global"]["dream410_4_network_wildtype_file"].split()
mf_file = settings["global"]["dream410_4_network_multifactorial_file"].split()
elif name == "dream410_5":
goldnet.read_goldstd(settings["global"]["dream410_5_network_goldnet_file"])
#Get a list of the knockout files
ko_file = settings["global"]["dream410_5_network_knockout_file"].split()
kd_file = settings["global"]["dream410_5_network_knockdown_file"].split()
ts_file = settings["global"]["dream410_5_network_timeseries_file"].split()
wt_file = settings["global"]["dream410_5_network_wildtype_file"].split()
mf_file = settings["global"]["dream410_5_network_multifactorial_file"].split()
elif name == "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()
elif name == "dream4100_2":
goldnet.read_goldstd(settings["global"]["dream4100_2_network_goldnet_file"])
#Get a list of the knockout files
ko_file = settings["global"]["dream4100_2_network_knockout_file"].split()
kd_file = settings["global"]["dream4100_2_network_knockdown_file"].split()
ts_file = settings["global"]["dream4100_2_network_timeseries_file"].split()
wt_file = settings["global"]["dream4100_2_network_wildtype_file"].split()
mf_file = settings["global"]["dream4100_2_network_multifactorial_file"].split()
elif name == "dream4100_3":
goldnet.read_goldstd(settings["global"]["dream4100_3_network_goldnet_file"])
#Get a list of the knockout files
ko_file = settings["global"]["dream4100_3_network_knockout_file"].split()
kd_file = settings["global"]["dream4100_3_network_knockdown_file"].split()
ts_file = settings["global"]["dream4100_3_network_timeseries_file"].split()
wt_file = settings["global"]["dream4100_3_network_wildtype_file"].split()
mf_file = settings["global"]["dream4100_3_network_multifactorial_file"].split()
elif name == "dream4100_4":
goldnet.read_goldstd(settings["global"]["dream4100_4_network_goldnet_file"])
#Get a list of the knockout files
ko_file = settings["global"]["dream4100_4_network_knockout_file"].split()
kd_file = settings["global"]["dream4100_4_network_knockdown_file"].split()
ts_file = settings["global"]["dream4100_4_network_timeseries_file"].split()
wt_file = settings["global"]["dream4100_4_network_wildtype_file"].split()
mf_file = settings["global"]["dream4100_4_network_multifactorial_file"].split()
elif name == "dream4100_5":
goldnet.read_goldstd(settings["global"]["dream4100_5_network_goldnet_file"])
#Get a list of the knockout files
ko_file = settings["global"]["dream4100_5_network_knockout_file"].split()
kd_file = settings["global"]["dream4100_5_network_knockdown_file"].split()
ts_file = settings["global"]["dream4100_5_network_timeseries_file"].split()
wt_file = settings["global"]["dream4100_5_network_wildtype_file"].split()
mf_file = settings["global"]["dream4100_5_network_multifactorial_file"].split()
elif name == "ecoli400":
goldnet.read_goldstd(settings["global"]["ecoli400_goldnet_file"])
#Get a list of the knockout files
ko_file = settings["global"]["ecoli400_knockout_file"].split()
kd_file = settings["global"]["ecoli400_knockdown_file"].split()
ts_file = settings["global"]["ecoli400_timeseries_file"].split()
wt_file = settings["global"]["ecoli400_wildtype_file"].split()
mf_file = settings["global"]["ecoli400_multifactorial_file"].split()
else:
print "ERROR: Dataset {0} not found, exiting.".format(name)
exit()
if dko_file != None:
return ko_file, kd_file, ts_file, wt_file, mf_file, goldnet, dko_file, dko_idx_file
else:
return ko_file, kd_file, ts_file, wt_file, mf_file, goldnet
wildtypes[name] = ReadData(exp_data_directory + '/' + name + '/' + wildtype_filename, "wildtype")
#wildtypes[name].normalize()
multifactorials[name] = ReadData(exp_data_directory + '/' + name + '/' + multifactorial_filename, "multifactorial")
#multifactorials[name].normalize()
goldnets[name] = exp_data_directory + '/' + name + '/' + goldstandard_filename
jobman = JobManager(settings)
# Get TFS from the goldstandard
tfs = {}
for name in data.keys():
t = []
goldnet = Network()
goldnet.read_goldstd(goldnets[name])
for gene1 in goldnet.network:
for gene2 in goldnet.network[gene1]:
if goldnet.network[gene1][gene2] > 0:
t.append(gene1)
tfs[name] = list(set(t))
goldnet = Network()
goldnet.read_goldstd(goldnets[exp_name])
ts_storage = data[exp_name]
settings["global"]["time_series_delta_t"] = int((1008.0 / (len(ts_storage[0].experiments)-1)))
print settings["global"]["time_series_delta_t"]
from tdaracne import *
from ReadConfig import *
# Initialize settings file
settings = {}
settings = ReadConfig(settings)
settings["global"]["working_dir"] = os.getcwd() + '/'
settings["global"]["experiment_name"] = "TDARACNE-"+sys.argv[1]
if len(sys.argv) > 2:
settings["global"]["experiment_name"] += "-" + sys.argv[2]
goldnet = Network()
goldnet.read_goldstd("datasets/dream4_10/dream4_10_gold.tsv")
# 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"])
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"])
# ko_file, kd_file, ts_file, wt_file, mf_file, goldnet = get_example_data_files(sys.argv[1], settings)
ko_file = "algorithms/genenetweaver/InSilicoSize10-Ecoli1_knockouts.tsv"
kd_file = "algorithms/genenetweaver/InSilicoSize10-Ecoli1_knockdowns.tsv"
wt_file = "algorithms/genenetweaver/InSilicoSize10-Ecoli1_wildtype.tsv"
ts_file = "algorithms/genenetweaver/InSilicoSize10-Ecoli1_dream4_timeseries.tsv"
goldnet.read_goldstd("algorithms/genenetweaver/InSilicoSize10-Ecoli1_goldstandard.tsv")
# Read data into program
# Where the format is "FILENAME" "DATATYPE"
knockout_storage = ReadData(ko_file, "knockout")
knockdown_storage = ReadData(kd_file, "knockdown")
timeseries_storage = ReadData(ts_file, "timeseries")
wildtype_storage = ReadData(wt_file, "wildtype")
# Setup job manager
jobman = JobManager(settings)
# Make MCZ job
mczjob = MCZ()
from JobManager import *
from Network import *
from Generate_Grid import *
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 ReadConfig import *
settings = {}
settings = ReadConfig(settings)
settings["global"]["working_dir"] = os.getcwd() + '/'
goldnet = Network()
goldnet.read_goldstd("datasets/Small_Network/Ecoli-1_goldstandard.tsv")
print goldnet.network
# 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"])
settings["global"]["time_series_files"] = "datasets/Small_Network/Ecoli-1_dream4_timeseries.tsv"
ts_filenames = settings["global"]["time_series_files"].split()
delta_t = [50]*20
settings["global"]["time_series_delta_t"] = delta_t
#delta_t = settings["global"]["time_series_delta_t"].split()
print delta_t
timeseries_storage = []
wildtypes[name] = ReadData(exp_data_directory + '/' + name + '/' + wildtype_filename, "wildtype")
#wildtypes[name].normalize()
multifactorials[name] = ReadData(exp_data_directory + '/' + name + '/' + multifactorial_filename, "multifactorial")
#multifactorials[name].normalize()
goldnets[name] = exp_data_directory + '/' + name + '/' + goldstandard_filename
jobman = JobManager(settings)
# Get TFS from the goldstandard
tfs = {}
for name in data.keys():
t = []
goldnet = Network()
goldnet.read_goldstd(goldnets[name])
for gene1 in goldnet.network:
for gene2 in goldnet.network[gene1]:
if goldnet.network[gene1][gene2] > 0:
t.append(gene1)
tfs[name] = list(set(t))
for key in goldnets.keys():
goldnet = Network()
goldnet.read_goldstd(goldnets[key])
goldnets[key] = goldnet
genie3nets = {}
for i in range(20):
#for ts in data:
#ts.normalize()
knockouts = ReadData(exp_data_directory + '/' + knockout_filename, "knockout")
#knockouts.normalize()
knockdowns = ReadData(exp_data_directory + '/' + knockdown_filename, "knockdown")
#knockdowns.normalize()
ss_data = ReadData(exp_data_directory + '/' + wildtype_filename, "wildtype")
#wildtypes.normalize()
multifactorial_data = ReadData(exp_data_directory + '/' + multifactorial_filename, "multifactorial")
#pert_data = ReadData(exp_data_directory + '/' + multifactorial_filename, "multifactorial")
pert_data = ReadData(exp_data_directory + '/' + knockout_filename, "knockout")
#multifactorials.normalize()
goldnet_file = exp_data_directory + '/' + goldstandard_filename
goldnet = Network()
goldnet.read_goldstd(goldnet_file)
# Initialize settings file
settings = {}
settings = ReadConfig(settings)
settings["global"]["working_dir"] = os.getcwd() + '/'
settings["global"]["experiment_name"] = "Kranthi-SimDex-NBoot-{0}".format(nboot)
settings["global"]["n_processors"] = 1
# Set up output directory
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"])
