def wnngip_cv_eval(method, dataset,output_dir, cv_data, X, D, T, cvs, para):
max_metric, metric_opt, optArg = 0, [], []
for x in np.arange(0.1, 1.1, 0.1):
for y in np.arange(0.0, 1.1, 0.1):
tic = time.clock()
model = WNNGIP(T=x, sigma=1, alpha=y)
cmd = "Dataset:"+dataset+" CVS: "+str(cvs)+"\n"+str(model)
print cmd
aupr_vec, auc_vec, ndcg_vec , ndcg_inv_vec, results = train(model, cv_data, X, D, T)
aupr_avg, aupr_conf = mean_confidence_interval(aupr_vec)
auc_avg, auc_conf = mean_confidence_interval(auc_vec)
ndcg_avg, ndcg_conf = mean_confidence_interval(ndcg_vec)
ndcg_inv_avg, ndcg_inv_conf = mean_confidence_interval(ndcg_inv_vec)
with open(os.path.join(output_dir,"optPar", "proc_"+dataset+"_"+str(cvs)+"_"+method+".txt"), "a") as procFile:
procFile.write(str(model)+": ")
procFile.write("auc:%.6f, aupr: %.6f,ndcg: %.6f,ndcg_inv: %.6f, Time:%.6f\n" % (auc_avg, aupr_avg, ndcg_avg, ndcg_inv_avg, time.clock()-tic))
print "auc:%.6f, aupr: %.6f,ndcg: %.6f,ndcg_inv: %.6f, Time:%.6f\n" % (auc_avg, aupr_avg, ndcg_avg, ndcg_inv_avg, time.clock()-tic)
metric = ndcg_inv_avg + ndcg_avg
if metric > max_metric:
max_metric = metric
metric_opt= [cmd, auc_avg, aupr_avg, ndcg_avg, ndcg_inv_avg ]
optArg = {"x":x, "y":y}
#each time a better solution is found, the params are stored
with open(os.path.join(output_dir,"optPar", "res_"+dataset+"_"+str(cvs)+"_"+method+".txt"), "w") as resFile:
resFile.write(str(optArg)+"\n"+str(metric_opt))
cmd = "Optimal parameter setting:\n%s\n" % metric_opt[0]
cmd += "auc: %.6f, aupr: %.6f, ndcg:%.6f, ndcg_inv:%.6f\n" % (metric_opt[1], metric_opt[2], metric_opt[3], metric_opt[4])
print cmd
def wnngip_cv_eval(method, dataset, cv_data, X, D, T, cvs, para):
max_auc, auc_opt = 0, []
for x in np.arange(0.1, 1.0, 0.1, dtype='float'):
for y in np.arange(0.0, 1.1, 0.1, dtype='float'):
for z in np.arange(0.1, 1.1, 0.1, dtype='float'):
for k in np.arange(0.1, 1.1, 0.1, dtype='float'):
tic = time.clock()
model = WNNGIP(T=x, sigma=z, alpha=y, gamma=k)
cmd = "Dataset:" + dataset + " CVS: " + str(
cvs) + "\n" + str(model)
print(cmd)
aupr_vec, auc_vec, acc_vec, sen_vec, spec_vec = train(
model, cv_data, X, D, T)
aupr_avg, aupr_conf = mean_confidence_interval(aupr_vec)
auc_avg, auc_conf = mean_confidence_interval(auc_vec)
acc_avg, acc_st = mean_confidence_interval(acc_vec)
sen_avg, sen_st = mean_confidence_interval(sen_vec)
spec_avg, spec_st = mean_confidence_interval(spec_vec)
# print("AUPR: %s, AUC:%s, ACC:%s, SEN:%s, Spec:%s, Time:%s" % (aupr_avg, auc_avg, acc_avg, sen_avg, spec_avg, time.clock() - tic))
if auc_avg > max_auc:
max_auc = auc_avg
auc_opt = [
cmd, auc_avg, aupr_avg, acc_avg, sen_avg, spec_avg
]
cmd = "Optimal parameter setting:\n%s\n" % auc_opt[0]
cmd += "auc: %.6f, aupr: %.6f, acc:%.6f, sen:%.6f, spec:%.6f\n" % (
auc_opt[1], auc_opt[2], auc_opt[3], auc_opt[4], auc_opt[5])
print(cmd)
def wnngip_cv_eval(method, dataset, cv_data, X, D, T, cvs, para, logger):
start = time.time()
max_auc, auc_opt = 0, []
for x in np.arange(0.1, 1.1, 0.1):
for y in np.arange(0.0, 1.1, 0.1):
tic = time.time()
model = WNNGIP(T=x, sigma=1, alpha=y)
cmd = "Dataset:" + dataset + " CVS: " + str(cvs) + "\n" + str(
model)
logger.info(cmd)
aupr_vec, auc_vec = train(model, cv_data, X, D, T)
aupr_avg, aupr_conf = mean_confidence_interval(aupr_vec)
auc_avg, auc_conf = mean_confidence_interval(auc_vec)
logger.info(
"auc:%.6f, aupr: %.6f, auc_conf:%.6f, aupr_conf:%.6f, Time:%.6f\n"
% (auc_avg, aupr_avg, auc_conf, aupr_conf, time.time() - tic))
if auc_avg > max_auc:
max_auc = auc_avg
auc_opt = [cmd, auc_avg, aupr_avg, auc_conf, aupr_conf]
end = time.time()
cmd = "Optimal parameter setting:\n%s\n" % auc_opt[0]
cmd += "auc: %.6f, aupr: %.6f, auc_conf:%.6f, aupr_conf:%.6f, time:%.6f\n" % (
auc_opt[1], auc_opt[2], auc_opt[3], auc_opt[4], end - start)
logger.info('')
logger.info(cmd)
def get_model(method, para, par, dataset):
if method == 'wnngip':
model = WNNGIP(T=par[0], sigma=1, alpha=par[1])
elif method == 'gip':
model = GIP(T=par[0], sigma=1, alpha=par[1])
elif method == 'nngip':
model = NNGIP(T=par[0], sigma=1, alpha=par[1], NN=par[2])
elif method == 'nnwnngip':
model = NNWNNGIP(T=par[0], sigma=1, alpha=par[1], NN=par[2])
elif method == 'nrlmf':
model = NRLMF(cfix=para['c'],
K1=para['K1'],
K2=para['K2'],
num_factors=par[0],
lambda_d=2**(par[1]),
lambda_t=2**(par[1]),
alpha=2**(par[2]),
beta=2**(par[3]),
theta=2**(par[4]),
max_iter=100)
elif method == 'nnkronsvm':
model = NNKronSVM(C=par[0],
NbNeg=para['NbNeg'],
NegNei=par[2],
PosNei=par[1],
dataset=dataset,
n_proc=1)
elif method == 'nnkronsvmgip':
model = NNKronSVMGIP(C=par[0],
NbNeg=para['NbNeg'],
NegNei=par[2],
PosNei=par[1],
dataset=dataset,
n_proc=1)
elif method == 'nnkronwnnsvmgip':
model = NNKronWNNSVMGIP(C=par[0],
t=par[3],
NbNeg=para['NbNeg'],
NegNei=par[2],
PosNei=par[1],
dataset=dataset,
n_proc=1)
elif method == 'nnkronwnnsvm':
model = NNKronWNNSVM(C=par[0],
t=par[3],
NbNeg=para['NbNeg'],
NegNei=par[2],
PosNei=par[1],
dataset=dataset,
n_proc=1)
return model
def wnngip_cv_eval(method, dataset, output_dir, cv_data, X, D, T, cvs, para):
max_metric, metric_opt, optArg = 0, [], []
for x in np.arange(0.1, 1.1, 0.1):
for y in np.arange(0.0, 1.1, 0.1):
tic = time.clock()
model = WNNGIP(T=x, sigma=1, alpha=y, hyperParamLearn=True)
aupr_vec, auc_vec, ndcg_vec, ndcg_inv_vec, results = train(
model, cv_data, X, D, T, hyperParamLearn=True)
aupr_avg, aupr_conf = mean_confidence_interval(aupr_vec)
auc_avg, auc_conf = mean_confidence_interval(auc_vec)
metric = aupr_avg + auc_avg
if metric > max_metric:
max_metric = metric
metric_opt = [auc_avg, aupr_avg]
optArg = {"x": x, "y": y}
cmd = "Optimal parameter setting:\n"
cmd += "x:%.6f, y:%.6f, auc: %.6f, aupr: %.6f\n" % (
optArg["x"], optArg["y"], metric_opt[0], metric_opt[1])
print cmd
return optArg
def thear(method, dataset, data_dir, output_dir, cvs, sp_arg, model_settings,
predict_num, seeds, seedsOptPar, args):
intMat, drugMat, targetMat = load_data_from_file(
dataset, os.path.join(data_dir, 'datasets'))
drug_names, target_names = get_drugs_targets_names(
dataset, os.path.join(data_dir, 'datasets'))
invert = 0
if (method == 'inv_brdti'):
invert = 1
if predict_num == 0:
if cvs == 1: # CV setting CVS1
X, D, T, cv = intMat, drugMat, targetMat, 1
if cvs == 2: # CV setting CVS2
X, D, T, cv = intMat, drugMat, targetMat, 0
if cvs == 3: # CV setting CVS3
X, D, T, cv, invert = intMat.T, targetMat, drugMat, 0, 1
if cvs == 4:
X, D, T, cv = intMat, drugMat, targetMat, 2
cv_data = cross_validation(X, seeds, cv, invert, num=10)
if invert:
X, D, T = intMat, drugMat, targetMat
#cv_data_optimize_params = cross_validation(X, seedsOptPar, cv, invert, num=5)
if sp_arg == 0 and predict_num == 0:
if (method == "vbmklmf"):
cv_eval.vbmklmf_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args)
if (method == "ensambledti"):
cv_eval.vbmklmf_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args)
if method == 'netcbp':
cv_eval.netcbp_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args)
# if method == 'ndaf':
# cv_eval.ndaf_cv_eval(method, dataset, cv_data, X, D, T, cvs, args)
if method == 'grmf':
cv_eval.grmf_cv_eval(method, dataset, cv_data, X, D, T, cvs, args)
if method == 'pudt':
cv_eval.pudt_cv_eval(method, dataset, cv_data, X, D, T, cvs, args)
if method == 'daspfind':
cv_eval.daspfind_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args)
if method == 'dnilmf':
cv_eval.dnilmf_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args)
if method == 'dthybrid':
cv_eval.dthybrid_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args)
if method == 'kronrlsmkl':
cv_eval.kronrismkl_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args)
if (method == 'brdti'):
cv_eval.brdti_cv_eval(method, dataset, cv_data, X, D, T, cvs, args)
if (method == 'ddr'):
cv_eval.ddr_cv_eval(method, dataset, cv_data, X, D, T, cvs, args)
if (method == 'brdti'):
cv_eval.brdti_cv_eval(method, dataset, cv_data, X, D, T, cvs, args)
if (method == 'inv_brdti'):
cv_eval.brdti_cv_eval(method, dataset, cv_data, X, D, T, cvs, args)
if method == 'nrlmf':
cv_eval.nrlmf_cv_eval(method, dataset, cv_data, X, D, T, cvs, args)
if method == 'netlaprls':
cv_eval.netlaprls_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args)
if method == 'blmnii':
cv_eval.blmnii_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args)
if method == 'wnngip':
cv_eval.wnngip_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args)
if method == 'kbmf':
cv_eval.kbmf_cv_eval(method, dataset, cv_data, X, D, T, cvs, args)
if method == 'cmf':
cv_eval.cmf_cv_eval(method, dataset, cv_data, X, D, T, cvs, args)
if sp_arg == 1 or predict_num > 0:
tic = time.clock()
if (method == "netcbp"):
model = NetCBP()
# if (method=="ndaf"):
# model = NDAF()
if (method == "grmf"):
model = GRMF(cv=cvs)
if (method == "pudt"):
model = PUDT(dataset=dataset)
if (method == "vbmklmf"):
model = VBMKLMF(dataset=dataset, cvs=cvs)
if (method == 'dnilmf'):
model = DNILMF(dataset=dataset)
if (method == 'kronrlsmkl'):
model = KronRLsMKL(dataset=dataset)
if (method == 'dthybrid'):
model = DTHYBRID(dataset=dataset)
if (method == 'daspfind'):
model = DASPFIND(alpha=args['alpha'])
if (method == 'brdti') | (method == 'inv_brdti'):
#model = BRDTI(D=args['D'],learning_rate= args['learning_rate'],max_iters=args['max_iters'],simple_predict=args['simple_predict'],bias_regularization=args['bias_regularization'],global_regularization=args['global_regularization'],cbSim=args['cbSim'],cb_alignment_regularization_user=args['cb_alignment_regularization_user'],cb_alignment_regularization_item=args['cb_alignment_regularization_item'])
model = BRDTI(args)
if method == 'nrlmf':
model = NRLMF(cfix=args['c'],
K1=args['K1'],
K2=args['K2'],
num_factors=args['r'],
lambda_d=args['lambda_d'],
lambda_t=args['lambda_t'],
alpha=args['alpha'],
beta=args['beta'],
theta=args['theta'],
max_iter=args['max_iter'])
if method == 'ddr':
model = DDR(dataset=dataset, cv=cvs)
if method == 'netlaprls':
model = NetLapRLS(gamma_d=args['gamma_d'],
gamma_t=args['gamma_t'],
beta_d=args['beta_t'],
beta_t=args['beta_t'])
if method == 'blmnii':
model = BLMNII(alpha=args['alpha'],
gamma=args['gamma'],
sigma=args['sigma'],
avg=args['avg'])
if method == 'wnngip':
model = WNNGIP(T=args['T'],
sigma=args['sigma'],
alpha=args['alpha'])
if method == 'kbmf':
model = KBMF(num_factors=args['R'])
if method == 'cmf':
model = CMF(K=args['K'],
lambda_l=args['lambda_l'],
lambda_d=args['lambda_d'],
lambda_t=args['lambda_t'],
max_iter=args['max_iter'])
if (method == 'ensambledti'):
model = EnsambleDTI(args=args, dataset=dataset)
cmd = str(model)
if predict_num == 0:
print("Dataset:" + dataset + " CVS:" + str(cvs) + "\n" + cmd)
aupr_vec, auc_vec = train(model, cv_data, X, D, T, cvs, dataset)
aupr_avg, aupr_conf = mean_confidence_interval(aupr_vec)
auc_avg, auc_conf = mean_confidence_interval(auc_vec)
print(
"auc:%.6f, aupr: %.6f, auc_conf:%.6f, aupr_conf:%.6f, Time:%.6f"
% (auc_avg, aupr_avg, auc_conf, aupr_conf, time.clock() - tic))
write_metric_vector_to_file(
auc_vec,
os.path.join(
output_dir,
method + "_auc_cvs" + str(cvs) + "_" + dataset + ".txt"))
write_metric_vector_to_file(
aupr_vec,
os.path.join(
output_dir,
method + "_aupr_cvs" + str(cvs) + "_" + dataset + ".txt"))
elif predict_num > 0:
print("Dataset:" + dataset + "\n" + cmd)
seed = 7771 if method == 'cmf' else 22
model.fix_model(intMat, intMat, drugMat, targetMat, seed)
x, y = np.where(intMat == 0)
scores = model.predict_scores(zip(x, y), 5)
ii = np.argsort(scores)[::-1]
predict_pairs = [(drug_names[x[i]], target_names[y[i]], scores[i])
for i in ii[:predict_num]]
new_dti_file = os.path.join(
output_dir, "_".join([method, dataset, "new_dti.txt"]))
novel_prediction_analysis(predict_pairs, new_dti_file,
os.path.join(data_dir, 'biodb'))
def main(argv):
try:
opts, args = getopt.getopt(argv, "m:d:f:c:s:o:n:p", ["method=", "dataset=", "data-dir=", "cvs=", "specify-arg=", "method-options=", "predict-num=", "output-dir=", ])
except getopt.GetoptError:
sys.exit()
data_dir = 'data'
output_dir = 'output'
cvs, sp_arg, model_settings, predict_num = 1, 1, [], 0
seeds = [7771, 8367, 22, 1812, 4659]#
seedsOptPar = [156]
# seeds = np.random.choice(10000, 5, replace=False)
for opt, arg in opts:
if opt == "--method":
method = arg
if opt == "--dataset":
dataset = arg
if opt == "--data-dir":
data_dir = arg
if opt == "--output-dir":
output_dir = arg
if opt == "--cvs":
cvs = int(arg)
if opt == "--specify-arg":
sp_arg = int(arg)
if opt == "--method-options":
model_settings = [s.split('=') for s in str(arg).split()]
if opt == "--predict-num":
predict_num = int(arg)
if not os.path.isdir(output_dir):
os.makedirs(output_dir)
if not os.path.isdir(os.path.join(output_dir,"optPar")):
os.makedirs(os.path.join(output_dir,"optPar"))
if method == 'aladin':
args = {'k': 3, 'seedList': [1], 'featureSetSize': -1, 'model': "ECKNN", 'avg': True, 'hpLearning': 0, 'useKNN': 0}
if method == 'netlaprls':
args = {'gamma_d': 10, 'gamma_t': 10, 'beta_d': 1e-5, 'beta_t': 1e-5}
if method == 'blmnii':
args = {'alpha': 0.7, 'gamma': 1.0, 'sigma': 1.0, 'avg': False}
if method == 'wnngip':
args = {'T': 0.8, 'sigma': 1.0, 'alpha': 0.8}
#print(model_settings)
for key, val in model_settings:
args[key] = float(eval(val))
intMat, drugMat, targetMat = load_data_from_file(dataset, os.path.join(data_dir, 'datasets'))
drug_names, target_names = get_drugs_targets_names(dataset, os.path.join(data_dir, 'datasets'))
global global_dataset
global_dataset = dataset
invert = 0
if predict_num == 0:
if cvs == 1: # CV setting 1 (predicting DTIs)
X, D, T, cv = intMat, drugMat, targetMat, 1
if cvs == 2: # CV setting 2 (novel drugs)
X, D, T, cv = intMat, drugMat, targetMat, 0
if cvs == 3: # CV setting 3 (novel targets)
X, D, T, cv = intMat.T, targetMat, drugMat, 0
cv_data = cross_validation(X, seeds, cv, invert, num=5)
if sp_arg == 1 or predict_num > 0:
tic = time.clock()
if method == 'aladin':
model = ALADIN(k=args['k'], seedList=args['seedList'], featureSetSize=args['featureSetSize'], model=args['model'], avg=args['avg'], hpLearning=args['hpLearning'], useKNN=args['useKNN'])
if method == 'netlaprls':
model = NetLapRLS(gamma_d=args['gamma_d'], gamma_t=args['gamma_t'], beta_d=args['beta_t'], beta_t=args['beta_t'])
if method == 'blmnii':
model = BLMNII(alpha=args['alpha'], gamma=args['gamma'], sigma=args['sigma'], avg=args['avg'])
if method == 'wnngip':
model = WNNGIP(T=args['T'], sigma=args['sigma'], alpha=args['alpha'])
cmd = str(model)
#predict hidden part of the current datasets
if predict_num == 0:
print "Dataset:"+dataset+" CVS:"+str(cvs)+"\n"+cmd
name_extension = ""
if method == 'aladin':
if args['hpLearning'] > 0:
name_extension = "_ens"
elif args['k'] == 3:
name_extension = "_k3"
elif args['k'] == 5:
name_extension = "_k5"
elif args['model'] == 5:
name_extension = "_k5"
if args["useKNN"] == 1:
name_extension = name_extension + "KNN"
if dataset == "kinase":
X[X == 0] = -1
aupr_vec, auc_vec, ndcg_vec, ndcg_inv_vec, results = train(model, cv_data, X, D, T)
aupr_avg, aupr_conf = mean_confidence_interval(aupr_vec)
auc_avg, auc_conf = mean_confidence_interval(auc_vec)
ndcg_avg, ndcg_conf = mean_confidence_interval(ndcg_vec)
ndcg_inv_avg, ndcg_inv_conf = mean_confidence_interval(ndcg_inv_vec)
resfile = os.path.join('output','rawResults', method+name_extension+"_res_"+str(cvs)+"_"+dataset+".csv")
outd = open(resfile, "w")
outd.write(('drug;target;true;predict\n'))
for r in results:
outd.write('%s;%s;%s;%s\n' % (r[0],r[1],r[2],r[3]) )
print "auc:%.6f, aupr: %.6f, ndcg: %.6f, ndcg_inv: %.6f, auc_conf:%.6f, aupr_conf:%.6f, ndcg_conf:%.6f, ndcg_inv_conf:%.6f, Time:%.6f" % (auc_avg, aupr_avg, ndcg_avg, ndcg_inv_avg, auc_conf, aupr_conf, ndcg_conf, ndcg_inv_conf, time.clock()-tic)
write_metric_vector_to_file(auc_vec, os.path.join(output_dir, method+name_extension+"_auc_cvs"+str(cvs)+"_"+dataset+".txt"))
write_metric_vector_to_file(aupr_vec, os.path.join(output_dir, method+name_extension+"_aupr_cvs"+str(cvs)+"_"+dataset+".txt"))
#write_metric_vector_to_file(ndcg_vec, os.path.join(output_dir, method+"_k357_ndcg_cvs"+str(cvs)+"_"+dataset+".txt"))
#write_metric_vector_to_file(ndcg_inv_vec, os.path.join(output_dir, method+"_k357_ndcg_inv_cvs"+str(cvs)+"_"+dataset+".txt"))
#predict novel DTIs
elif predict_num > 0:
print "Dataset:"+dataset+"\n"+cmd
seed = 376
model.fix_model(intMat, intMat, drugMat, targetMat, seed)
npa = newDTIPrediction()
x, y = np.where(intMat == 0)
scores = model.predict_scores(zip(x, y), 1)
sz = np.array(zip(x,y,scores))
sz_croped = sz[sz[:,2].argsort()[::-1],:]
sz_croped = sz_croped[xrange(0,predict_num),:]
npa.verify_novel_interactions(method, dataset, sz_croped, predict_num, drug_names, target_names)
def main(argv):
try:
opts, args = getopt.getopt(argv, m:d:f:c:s:o:n:p, ["method=", "dataset=", "data-dir=", "cvs=", "specify-arg=", "method-options=", "predict-num=", "output-dir=", ])
except getopt.GetoptError:
sys.exit()
data_dir = 'data'
output_dir = 'output'
cvs, sp_arg, model_settings, predict_num = 1, 1, [], 0
seeds = [7771, 8367, 22, 1812, 4659]
seedsOptPar = [156]
# seeds = np.random.choice(10000, 5, replace=False)
for opt, arg in opts:
if opt == "--method":
method = arg
if opt == "--dataset":
dataset = arg
if opt == "--data-dir":
data_dir = arg
if opt == "--output-dir":
output_dir = arg
if opt == "--cvs":
cvs = int(arg)
if opt == "--specify-arg":
sp_arg = int(arg)
if opt == "--method-options":
model_settings = [s.split('=') for s in str(arg).split()]
if opt == "--predict-num":
predict_num = int(arg)
if not os.path.isdir(output_dir):
os.makedirs(output_dir)
if not os.path.isdir(os.path.join(output_dir,"optPar")):
os.makedirs(os.path.join(output_dir,"optPar"))
# default parameters for each methods
if (method == 'brdti') | (method == 'inv_brdti') :
args = {
'D':100,
'learning_rate':0.1,
'max_iters' : 100,
'simple_predict' :False,
'bias_regularization':1,
'global_regularization':10**(-2),
"cbSim": "knn",
'cb_alignment_regularization_user' :1,
'cb_alignment_regularization_item' :1}
if method == 'netlaprls':
args = {'gamma_d': 10, 'gamma_t': 10, 'beta_d': 1e-5, 'beta_t': 1e-5}
if method == 'blmnii':
args = {'alpha': 0.7, 'gamma': 1.0, 'sigma': 1.0, 'avg': False}
if method == 'wnngip':
args = {'T': 0.8, 'sigma': 1.0, 'alpha': 0.8}
if method == 'cmf':
args = {'K': 100, 'lambda_l': 0.5, 'lambda_d': 0.125, 'lambda_t': 0.125, 'max_iter': 100}
#print(model_settings)
for key, val in model_settings:
args[key] = float(eval(val))
intMat, drugMat, targetMat = load_data_from_file(dataset, os.path.join(data_dir, 'datasets'))
drug_names, target_names = get_drugs_targets_names(dataset, os.path.join(data_dir, 'datasets'))
invert = 0
if (method == 'inv_brdti') :
invert = 1
if predict_num == 0:
if cvs == 1: # CV setting CVS1
X, D, T, cv = intMat, drugMat, targetMat, 1
if cvs == 2: # CV setting CVS2
X, D, T, cv = intMat, drugMat, targetMat, 0
if cvs == 3: # CV setting CVS3
X, D, T, cv = intMat.T, targetMat, drugMat, 0
cv_data = cross_validation(X, seeds, cv, invert)
cv_data_optimize_params = cross_validation(X, seedsOptPar, cv, invert, num=5)
if sp_arg == 0 and predict_num == 0:
if (method == 'brdti'):
cv_eval.brdti_cv_eval(method, dataset,output_dir, cv_data_optimize_params, X, D, T, cvs, args)
if (method == 'inv_brdti'):
cv_eval.brdti_cv_eval(method, dataset,output_dir, cv_data_optimize_params, X.T, T, D, cvs, args)
if method == 'netlaprls':
cv_eval.netlaprls_cv_eval(method, dataset,output_dir, cv_data_optimize_params, X, D, T, cvs, args)
if method == 'blmnii':
cv_eval.blmnii_cv_eval(method, dataset,output_dir, cv_data_optimize_params, X, D, T, cvs, args)
if method == 'wnngip':
cv_eval.wnngip_cv_eval(method, dataset,output_dir, cv_data_optimize_params, X, D, T, cvs, args)
if method == 'cmf':
cv_eval.cmf_cv_eval(method, dataset,output_dir, cv_data_optimize_params, X, D, T, cvs, args)
if sp_arg == 1 or predict_num > 0:
tic = time.clock()
if (method == 'brdti')|(method == 'inv_brdti'):
model = BRDTI(args)
if method == 'netlaprls':
model = NetLapRLS(gamma_d=args['gamma_d'], gamma_t=args['gamma_t'], beta_d=args['beta_t'], beta_t=args['beta_t'])
if method == 'blmnii':
model = BLMNII(alpha=args['alpha'], gamma=args['gamma'], sigma=args['sigma'], avg=args['avg'])
if method == 'wnngip':
model = WNNGIP(T=args['T'], sigma=args['sigma'], alpha=args['alpha'])
if method == 'cmf':
model = CMF(K=args['K'], lambda_l=args['lambda_l'], lambda_d=args['lambda_d'], lambda_t=args['lambda_t'], max_iter=args['max_iter'])
cmd = str(model)
#predict hidden part of the current datasets
if predict_num == 0:
print "Dataset:"+dataset+" CVS:"+str(cvs)+"\n"+cmd
if (method == 'inv_brdti') :
aupr_vec, auc_vec, ndcg_inv_vec, ndcg_vec, results = train(model, cv_data, X.T, T, D)
else:
aupr_vec, auc_vec, ndcg_vec, ndcg_inv_vec, results = train(model, cv_data, X, D, T)
aupr_avg, aupr_conf = mean_confidence_interval(aupr_vec)
auc_avg, auc_conf = mean_confidence_interval(auc_vec)
ndcg_avg, ndcg_conf = mean_confidence_interval(ndcg_vec)
ndcg_inv_avg, ndcg_inv_conf = mean_confidence_interval(ndcg_inv_vec)
resfile = os.path.join('output','rawResults', method+"_res_"+str(cvs)+"_"+dataset+".csv")
outd = open(resfile, "w")
outd.write(('drug;target;true;predict\n'))
for r in results:
outd.write('%s;%s;%s;%s\n' % (r[0],r[1],r[2],r[3]) )
print "auc:%.6f, aupr: %.6f, ndcg: %.6f, ndcg_inv: %.6f, auc_conf:%.6f, aupr_conf:%.6f, ndcg_conf:%.6f, ndcg_inv_conf:%.6f, Time:%.6f" % (auc_avg, aupr_avg, ndcg_avg, ndcg_inv_avg, auc_conf, aupr_conf, ndcg_conf, ndcg_inv_conf, time.clock()-tic)
write_metric_vector_to_file(auc_vec, os.path.join(output_dir, method+"_auc_cvs"+str(cvs)+"_"+dataset+".txt"))
write_metric_vector_to_file(aupr_vec, os.path.join(output_dir, method+"_aupr_cvs"+str(cvs)+"_"+dataset+".txt"))
write_metric_vector_to_file(ndcg_vec, os.path.join(output_dir, method+"_ndcg_cvs"+str(cvs)+"_"+dataset+".txt"))
write_metric_vector_to_file(ndcg_inv_vec, os.path.join(output_dir, method+"_ndcg_inv_cvs"+str(cvs)+"_"+dataset+".txt"))
#predict novel DTIs
elif predict_num > 0:
print "Dataset:"+dataset+"\n"+cmd
seed = 376
if invert: #predicting drugs for targets
model.fix_model(intMat.T, intMat.T, targetMat, drugMat, seed)
npa = newDTIPrediction()
x, y = np.where(intMat == 0)
scores = model.predict_scores(zip(y, x), 1)
sz = np.array(zip(x,y,scores))
else: #predicting targets for drugs
model.fix_model(intMat, intMat, drugMat, targetMat, seed)
npa = newDTIPrediction()
x, y = np.where(intMat == 0)
scores = model.predict_scores(zip(x, y), 1)
sz = np.array(zip(x,y,scores))
ndcg_d, ndcg_t, recall_d, recall_t = npa.verify_novel_interactions(method, dataset, sz, predict_num, drug_names, target_names)
st_file= os.path.join('output/newDTI', "_".join([dataset,str(predict_num), "stats.csv"]))
out = open(st_file, "a")
out.write(('%s;%f;%f;%f;%f\n' % (method,ndcg_d, ndcg_t, recall_d, recall_t)))
def main(argv):
try:
opts, args = getopt.getopt(argv, "m:d:f:c:s:o:n:p", [
"method=",
"dataset=",
"data-dir=",
"cvs=",
"specify-arg=",
"method-options=",
"predict-num=",
"output-dir=",
])
except getopt.GetoptError:
sys.exit()
data_dir = os.path.join(os.path.pardir, 'data')
output_dir = os.path.join(os.path.pardir, 'output')
cvs, sp_arg, model_settings, predict_num = 1, 1, [], 0
seeds = [7771, 8367, 22, 1812, 4659]
# seeds = np.random.choice(10000, 5, replace=False)
for opt, arg in opts:
if opt == "--method":
method = arg
if opt == "--dataset":
dataset = arg
if opt == "--data-dir":
data_dir = arg
if opt == "--output-dir":
output_dir = arg
if opt == "--cvs":
cvs = int(arg)
if opt == "--specify-arg":
sp_arg = int(arg)
if opt == "--method-options":
model_settings = [s.split('=') for s in str(arg).split()]
if opt == "--predict-num":
predict_num = int(arg)
if not os.path.isdir(output_dir):
os.makedirs(output_dir)
# default parameters for each methods
if method == 'nrlmf':
args = {
'c': 5,
'K1': 5,
'K2': 5,
'r': 50,
'lambda_d': 0.125,
'lambda_t': 0.125,
'alpha': 0.25,
'beta': 0.125,
'theta': 0.5,
'max_iter': 100
}
if method == 'netlaprls':
args = {'gamma_d': 10, 'gamma_t': 10, 'beta_d': 1e-5, 'beta_t': 1e-5}
if method == 'blmnii':
args = {'alpha': 0.7, 'gamma': 1.0, 'sigma': 1.0, 'avg': False}
if method == 'wnngip':
args = {'T': 0.8, 'sigma': 1.0, 'alpha': 0.8}
if method == 'kbmf':
args = {'R': 50}
if method == 'cmf':
args = {
'K': 50,
'lambda_l': 0.5,
'lambda_d': 0.125,
'lambda_t': 0.125,
'max_iter': 30
}
for key, val in model_settings:
args[key] = val
intMat, drugMat, targetMat = load_data_from_file(
dataset, os.path.join(data_dir, 'datasets'))
drug_names, target_names = get_drugs_targets_names(
dataset, os.path.join(data_dir, 'datasets'))
if predict_num == 0:
if cvs == 1: # CV setting CVS1
X, D, T, cv = intMat, drugMat, targetMat, 1
if cvs == 2: # CV setting CVS2
X, D, T, cv = intMat, drugMat, targetMat, 0
if cvs == 3: # CV setting CVS3
X, D, T, cv = intMat.T, targetMat, drugMat, 0
cv_data = cross_validation(X, seeds, cv)
if sp_arg == 0 and predict_num == 0:
if method == 'nrlmf':
cv_eval.nrlmf_cv_eval(method, dataset, cv_data, X, D, T, cvs, args)
if method == 'netlaprls':
cv_eval.netlaprls_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args)
if method == 'blmnii':
cv_eval.blmnii_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args)
if method == 'wnngip':
cv_eval.wnngip_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args)
if method == 'kbmf':
cv_eval.kbmf_cv_eval(method, dataset, cv_data, X, D, T, cvs, args)
if method == 'cmf':
cv_eval.cmf_cv_eval(method, dataset, cv_data, X, D, T, cvs, args)
if sp_arg == 1 or predict_num > 0:
tic = time.clock()
if method == 'nrlmf':
model = NRLMF(cfix=args['c'],
K1=args['K1'],
K2=args['K2'],
num_factors=args['r'],
lambda_d=args['lambda_d'],
lambda_t=args['lambda_t'],
alpha=args['alpha'],
beta=args['beta'],
theta=args['theta'],
max_iter=args['max_iter'])
if method == 'netlaprls':
model = NetLapRLS(gamma_d=args['gamma_d'],
gamma_t=args['gamma_t'],
beta_d=args['beta_t'],
beta_t=args['beta_t'])
if method == 'blmnii':
model = BLMNII(alpha=args['alpha'],
gamma=args['gamma'],
sigma=args['sigma'],
avg=args['avg'])
if method == 'wnngip':
model = WNNGIP(T=args['T'],
sigma=args['sigma'],
alpha=args['alpha'])
if method == 'kbmf':
model = KBMF(num_factors=args['R'])
if method == 'cmf':
model = CMF(K=args['K'],
lambda_l=args['lambda_l'],
lambda_d=args['lambda_d'],
lambda_t=args['lambda_t'],
max_iter=args['max_iter'])
cmd = str(model)
if predict_num == 0:
print "Dataset:" + dataset + " CVS:" + str(cvs) + "\n" + cmd
aupr_vec, auc_vec = train(model, cv_data, X, D, T)
aupr_avg, aupr_conf = mean_confidence_interval(aupr_vec)
auc_avg, auc_conf = mean_confidence_interval(auc_vec)
print "auc:%.6f, aupr: %.6f, auc_conf:%.6f, aupr_conf:%.6f, Time:%.6f" % (
auc_avg, aupr_avg, auc_conf, aupr_conf, time.clock() - tic)
write_metric_vector_to_file(
auc_vec,
os.path.join(
output_dir,
method + "_auc_cvs" + str(cvs) + "_" + dataset + ".txt"))
write_metric_vector_to_file(
aupr_vec,
os.path.join(
output_dir,
method + "_aupr_cvs" + str(cvs) + "_" + dataset + ".txt"))
elif predict_num > 0:
print "Dataset:" + dataset + "\n" + cmd
seed = 7771 if method == 'cmf' else 22
model.fix_model(intMat, intMat, drugMat, targetMat, seed)
x, y = np.where(intMat == 0)
scores = model.predict_scores(zip(x, y), 5)
ii = np.argsort(scores)[::-1]
predict_pairs = [(drug_names[x[i]], target_names[y[i]], scores[i])
for i in ii[:predict_num]]
new_dti_file = os.path.join(
output_dir, "_".join([method, dataset, "new_dti.txt"]))
novel_prediction_analysis(predict_pairs, new_dti_file,
os.path.join(data_dir, 'biodb'))
def main(argv):
try:
opts, args = getopt.getopt(argv, "m:d:f:c:e:s:o:n:p:g:q:r:l:w", [
"method=", "dataset=", "data-dir=", "cvs=", "external=",
"specify-arg=", "method-opt=", "predict-num=", "scoring=", "gpmi=",
"params=", "output-dir=", "log=", "workdir="
])
except getopt.GetoptError:
sys.exit()
# data_dir = os.path.join(os.path.pardir, 'data')
# output_dir = os.path.join(os.path.pardir, 'output')
method = "nrlmf"
dataset = "nr"
data_dir = '.'
output_dir = '.'
cvs, sp_arg, model_settings, predict_num = 1, 1, [], 0
external = 0
scoring = 'auc'
gpmi = None
params = None
workdir = "./"
logfile = 'job.log'
seeds = [7771, 8367, 22, 1812, 4659]
# seeds = np.random.choice(10000, 5, replace=False)
for opt, arg in opts:
if opt == "--method":
method = arg
if opt == "--dataset":
dataset = arg
if opt == "--data-dir":
data_dir = arg
if opt == "--output-dir":
output_dir = arg
if opt == "--cvs":
cvs = int(arg)
if opt == "--external":
external = int(arg)
if opt == "--specify-arg":
sp_arg = int(arg)
if opt == "--method-opt":
model_settings = [s.split('=') for s in str(arg).split()]
if opt == "--predict-num":
predict_num = int(arg)
if opt == "--scoring":
scoring = str(arg)
if opt == "--gpmi":
gpmi = dict()
for s in str(arg).split():
key, val = s.split('=')
gpmi[key] = float(val)
if opt == "--params":
params = read_params(str(arg))
if opt == "--log":
logfile = str(arg)
if opt == "--workdir":
workdir = str(arg)
if not os.path.isdir(output_dir):
os.makedirs(output_dir)
# set logger
logger = logging.getLogger("logger")
logger.setLevel(logging.INFO)
filename = logfile
fh = logging.FileHandler(workdir + "/" + filename)
fh.name = filename
logger.addHandler(fh)
# default parameters for each methods
if method == 'nrlmf':
args = {
'c': 5,
'K1': 5,
'K2': 5,
'r': 50,
'lambda_d': 0.125,
'lambda_t': 0.125,
'alpha': 0.25,
'beta': 0.125,
'theta': 0.5,
'max_iter': 100
}
if method == 'nrlmfb':
args = {
'c': 5,
'K1': 5,
'K2': 5,
'r': 50,
'lambda_d': 0.125,
'lambda_t': 0.125,
'alpha': 0.25,
'beta': 0.125,
'theta': 0.5,
'max_iter': 100
}
if method == 'netlaprls':
args = {'gamma_d': 10, 'gamma_t': 10, 'beta_d': 1e-5, 'beta_t': 1e-5}
if method == 'blmnii':
args = {'alpha': 0.7, 'gamma': 1.0, 'sigma': 1.0, 'avg': False}
if method == 'wnngip':
args = {'T': 0.8, 'sigma': 1.0, 'alpha': 0.8}
if method == 'kbmf':
args = {'R': 50}
if method == 'cmf':
args = {
'K': 50,
'lambda_l': 0.5,
'lambda_d': 0.125,
'lambda_t': 0.125,
'max_iter': 30
}
for key, val in model_settings:
args[key] = float(val)
intMat, drugMat, targetMat = load_data_from_file(
dataset, os.path.join(data_dir, 'dataset'))
drug_names, target_names = get_drugs_targets_names(
dataset, os.path.join(data_dir, 'dataset'))
if predict_num == 0:
if cvs == 1: # CV setting CVS1
X, D, T, cv = intMat, drugMat, targetMat, 1
if cvs == 2: # CV setting CVS2
X, D, T, cv = intMat, drugMat, targetMat, 0
if cvs == 3: # CV setting CVS3
X, D, T, cv = intMat.T, targetMat, drugMat, 0
cv_data = cross_validation(X, seeds, cv)
if cvs == 1: ev_data = external_validation(X, seeds, cv)
if sp_arg == 0 and predict_num == 0 and external == 0:
if method == 'nrlmf':
cv_eval.nrlmf_cv_eval(method,
dataset,
cv_data,
X,
D,
T,
cvs,
args,
logger,
scoring=scoring,
gpmi=gpmi,
params=params)
if method == 'nrlmfb':
cv_eval.nrlmfb_cv_eval(method,
dataset,
cv_data,
X,
D,
T,
cvs,
args,
logger,
scoring=scoring,
gpmi=gpmi,
params=params)
if method == 'netlaprls':
cv_eval.netlaprls_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args)
if method == 'blmnii':
cv_eval.blmnii_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args)
if method == 'wnngip':
cv_eval.wnngip_cv_eval(method, dataset, cv_data, X, D, T, cvs,
args, logger)
if method == 'kbmf':
cv_eval.kbmf_cv_eval(method, dataset, cv_data, X, D, T, cvs, args)
if method == 'cmf':
cv_eval.cmf_cv_eval(method, dataset, cv_data, X, D, T, cvs, args)
if sp_arg == 0 and predict_num == 0 and external == 1:
if method == 'nrlmf':
ev_eval.nrlmf_ev_eval(method,
ev_data,
X,
D,
T,
logger,
scoring=scoring,
gpmi=gpmi,
params=params)
if method == 'nrlmfb':
ev_eval.nrlmfb_ev_eval(method,
ev_data,
X,
D,
T,
logger,
scoring=scoring,
gpmi=gpmi,
params=params)
if sp_arg == 1 or predict_num > 0:
if method == 'nrlmf':
model = NRLMF(cfix=args['c'],
K1=args['K1'],
K2=args['K2'],
num_factors=args['r'],
lambda_d=args['lambda_d'],
lambda_t=args['lambda_t'],
alpha=args['alpha'],
beta=args['beta'],
theta=args['theta'],
max_iter=args['max_iter'])
if method == 'nrlmfb':
model = NRLMFb(cfix=args['c'],
K1=args['K1'],
K2=args['K2'],
num_factors=args['r'],
lambda_d=args['lambda_d'],
lambda_t=args['lambda_t'],
alpha=args['alpha'],
beta=args['beta'],
theta=args['theta'],
max_iter=args['max_iter'],
eta1=args['eta1'],
eta2=args['eta2'])
if method == 'netlaprls':
model = NetLapRLS(gamma_d=args['gamma_d'],
gamma_t=args['gamma_t'],
beta_d=args['beta_t'],
beta_t=args['beta_t'])
if method == 'blmnii':
model = BLMNII(alpha=args['alpha'],
gamma=args['gamma'],
sigma=args['sigma'],
avg=args['avg'])
if method == 'wnngip':
model = WNNGIP(T=args['T'],
sigma=args['sigma'],
alpha=args['alpha'])
if method == 'kbmf':
model = KBMF(num_factors=args['R'])
if method == 'cmf':
model = CMF(K=args['K'],
lambda_l=args['lambda_l'],
lambda_d=args['lambda_d'],
lambda_t=args['lambda_t'],
max_iter=args['max_iter'])
cmd = str(model)
if predict_num == 0:
tic = time.time()
print("Dataset:" + dataset + " CVS:" + str(cvs) + "\n" + cmd)
aupr_vec, auc_vec = train(model, cv_data, X, D, T)
aupr_avg, aupr_conf = mean_confidence_interval(aupr_vec)
auc_avg, auc_conf = mean_confidence_interval(auc_vec)
print(
"auc:%.6f, aupr:%.6f, auc_conf:%.6f, aupr_conf:%.6f, Time:%.6f"
% (auc_avg, aupr_avg, auc_conf, aupr_conf, time.time() - tic))
# write_metric_vector_to_file(auc_vec, os.path.join(output_dir, method+"_auc_cvs"+str(cvs)+"_"+dataset+".txt"))
# write_metric_vector_to_file(aupr_vec, os.path.join(output_dir, method+"_aupr_cvs"+str(cvs)+"_"+dataset+".txt"))
logger.info(
cmd + ', ' +
"auc:%.6f, aupr:%.6f, auc_conf:%.6f, aupr_conf:%.6f, Time:%.6f"
% (auc_avg, aupr_avg, auc_conf, aupr_conf, time.time() - tic))
elif predict_num > 0:
print("Dataset:" + dataset + "\n" + cmd)
seed = 7771 if method == 'cmf' else 22
model.fix_model(intMat, intMat, drugMat, targetMat, seed)
x, y = np.where(intMat == 0)
scores = model.predict_scores(zip(x, y), 5)
ii = np.argsort(scores)[::-1]
predict_pairs = [(drug_names[x[i]], target_names[y[i]], scores[i])
for i in ii[:predict_num]]
new_dti_file = os.path.join(
output_dir, "_".join([method, dataset, "new_dti.txt"]))
novel_prediction_analysis(predict_pairs, new_dti_file,
os.path.join(data_dir, 'biodb'))
def main(argv):
try:
opts, args = getopt.getopt(argv, "m:d:f:c:s:o:n:p:C", [
"method=", "dataset=", "data-dir=", "cvs=", "specify-arg=",
"method-options=", "predict-num=", "output-dir=", "cv_type=",
"i_param=", "i_test="
])
except getopt.GetoptError:
sys.exit()
# data_dir = os.path.join(os.path.pardir, 'data')
# output_dir = os.path.join(os.path.pardir, 'output')
data_dir = 'data'
output_dir = 'results'
cvs, sp_arg, model_settings, predict_num = 1, 1, [], 0
# seeds = [7771, 8367, 22, 1812, 4659]
seeds = [7771, 8367, 22, 1812]
# seeds = np.random.choice(10000, 5, replace=False)
for opt, arg in opts:
print(opt, arg)
if opt == "--method":
method = arg
if '"' in method:
method = method.replace('"', '')
if opt == "--dataset":
dataset = arg
if '"' in dataset:
dataset = dataset.replace('"', '')
if opt == "--data-dir":
data_dir = arg
if opt == "--output-dir":
output_dir = arg
if opt == "--cvs":
cvs = int(arg)
if opt == "--specify-arg":
sp_arg = int(arg)
if opt == "--i_param":
i_param = int(arg)
if opt == "--i_test":
i_test = int(arg)
if opt == "--method-options":
model_settings = [s.split('=') for s in str(arg).split()]
if opt == "--predict-num":
predict_num = int(arg)
if opt == "--cv_type":
cv_type = arg
if '"' in cv_type:
cv_type = cv_type.replace('"', '')
if not os.path.isdir(output_dir):
os.makedirs(output_dir)
# default parameters for each methods
if method == 'nrlmf':
args = {
'c': 5,
'K1': 5,
'K2': 5,
'r': 50,
'lambda_d': 0.125,
'lambda_t': 0.125,
'alpha': 0.25,
'beta': 0.125,
'theta': 0.5,
'max_iter': 100
}
if method == 'netlaprls':
args = {'gamma_d': 10, 'gamma_t': 10, 'beta_d': 1e-5, 'beta_t': 1e-5}
if method == 'blmnii':
args = {'alpha': 0.7, 'gamma': 1.0, 'sigma': 1.0, 'avg': False}
if method in ['wnngip', 'gip']:
args = {'T': 0.8, 'sigma': 1.0, 'alpha': 0.8}
if method in ['nnwnngip', 'nngip']:
args = {'T': 0.8, 'sigma': 1.0, 'alpha': 0.8, 'NN': 2}
if method == 'kbmf':
args = {'R': 50}
if method == 'cmf':
args = {
'K': 50,
'lambda_l': 0.5,
'lambda_d': 0.125,
'lambda_t': 0.125,
'max_iter': 30
}
if method in ['nnkronsvm', 'nnkronsvmgip']:
args = {'C': 1., 'NbNeg': 10, 'PosNei': 10, 'NegNei': 2, 'n_proc': 1}
if method in ['nnkronwnnsvmgip', 'nnkronwnnsvm']:
args = {
'C': 1.,
't': 0.1,
'NbNeg': 10,
'PosNei': 10,
'NegNei': 2,
'n_proc': 1
}
for key, val in model_settings:
args[key] = val
if sp_arg == 2 and predict_num == 0:
print(2, 'bis')
m = get_name_method(method)
data_file = dataset + "_" + str(cvs) + "_" + cv_type + '_Model:' + m + '_' + \
str(i_param) + '_' + str(i_test)
if os.path.isfile('results/' + data_file + '.data'):
print('found', 'results/' + data_file + '.data')
exit(1)
intMat, drugMat, targetMat, limit = load_data_from_file(
dataset, os.path.join(data_dir, ''))
drug_names, target_names = get_drugs_targets_names(
dataset, os.path.join(data_dir, ''))
if predict_num == 0:
if cvs == 1: # CV setting CVS1
X, D, T, cv = intMat, drugMat, targetMat, 1
if cvs == 2: # CV setting CVS2
X, D, T, cv = intMat, drugMat, targetMat, 0
if cvs == 3: # CV setting CVS3
X, D, T, cv = intMat.T, targetMat, drugMat, 0
cv_data = cross_validation(X,
D,
T,
seeds,
cv,
limit,
10,
cv_type=cv_type)
print(intMat.shape)
if sp_arg == 0 and predict_num == 0:
print(0)
cv_eval.cv_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type)
# if method == 'nrlmf':
# cv_eval.nrlmf_cv_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type)
# if method == 'netlaprls':
# cv_eval.netlaprls_cv_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type)
# if method == 'blmnii':
# cv_eval.blmnii_cv_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type)
# if method == 'wnngip':
# cv_eval.wnngip_cv_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type)
# if method == 'gip':
# cv_eval.gip_cv_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type)
# if method == 'nngip':
# cv_eval.nngip_cv_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type)
# if method == 'nnwnngip':
# cv_eval.nnwnngip_cv_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type)
# if method == 'kbmf':
# cv_eval.kbmf_cv_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type)
# if method == 'cmf':
# cv_eval.cmf_cv_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type)
# if method == 'nnkronsvm':
# cv_eval.nnkronsvm_cv_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type)
# if method == 'nnkronsvmgip':
# cv_eval.nnkronsvmgip_cv_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type)
# if method == 'nnkronwnnsvm':
# cv_eval.nnkronwnnsvm_cv_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type)
# if method == 'nnkronwnnsvmgip':
# cv_eval.nnkronwnnsvmgip_cv_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type)
if sp_arg == 2 and predict_num == 0:
print(2)
cv_eval.eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type,
i_param, i_test)
# if method == 'nrlmf':
# m = get_name_method(method)
# data_file = dataset + "_" + str(cvs) + "_" + cv_type + '_Model:' + m + '_' + \
# str(i_param) + '_' + str(i_test)
# if not os.path.isfile('results/' + data_file + '.data'):
# cv_eval.nrlmf_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type,
# i_param, i_test)
# if method == 'wnngip':
# m = get_name_method(method)
# data_file = dataset + "_" + str(cvs) + "_" + cv_type + '_Model:' + m + '_' + \
# str(i_param) + '_' + str(i_test)
# if not os.path.isfile('results/' + data_file + '.data'):
# cv_eval.wnngip_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type,
# i_param, i_test)
# if method == 'gip':
# m = get_name_method(method)
# data_file = dataset + "_" + str(cvs) + "_" + cv_type + '_Model:' + m + '_' + \
# str(i_param) + '_' + str(i_test)
# if not os.path.isfile('results/' + data_file + '.data'):
# cv_eval.gip_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type,
# i_param, i_test)
# if method == 'nngip':
# m = get_name_method(method)
# data_file = dataset + "_" + str(cvs) + "_" + cv_type + '_Model:' + m + '_' + \
# str(i_param) + '_' + str(i_test)
# if not os.path.isfile('results/' + data_file + '.data'):
# cv_eval.nngip_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type,
# i_param, i_test)
# if method == 'nnwnngip':
# m = get_name_method(method)
# data_file = dataset + "_" + str(cvs) + "_" + cv_type + '_Model:' + m + '_' + \
# str(i_param) + '_' + str(i_test)
# if not os.path.isfile('results/' + data_file + '.data'):
# cv_eval.nnwnngip_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type,
# i_param, i_test)
# if method == 'nnkronsvm':
# m = get_name_method(method)
# data_file = dataset + "_" + str(cvs) + "_" + cv_type + '_Model:' + m + '_' + \
# str(i_param) + '_' + str(i_test)
# if not os.path.isfile('results/' + data_file + '.data'):
# cv_eval.nnkronsvm_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type,
# i_param, i_test)
# if method == 'nnkronsvmgip':
# m = get_name_method(method)
# data_file = dataset + "_" + str(cvs) + "_" + cv_type + '_Model:' + m + '_' + \
# str(i_param) + '_' + str(i_test)
# if not os.path.isfile('results/' + data_file + '.data'):
# cv_eval.nnkronsvmgip_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type,
# i_param, i_test)
# if method == 'nnkronwnnsvm':
# m = get_name_method(method)
# data_file = dataset + "_" + str(cvs) + "_" + cv_type + '_Model:' + m + '_' + \
# str(i_param) + '_' + str(i_test)
# if not os.path.isfile('results/' + data_file + '.data'):
# cv_eval.nnkronwnnsvm_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type,
# i_param, i_test)
# if method == 'nnkronwnnsvmgip':
# m = get_name_method(method)
# data_file = dataset + "_" + str(cvs) + "_" + cv_type + '_Model:' + m + '_' + \
# str(i_param) + '_' + str(i_test)
# if not os.path.isfile('results/' + data_file + '.data'):
# cv_eval.nnkronwnnsvmgip_eval(method, dataset, cv_data, X, D, T, cvs, args, cv_type,
# i_param, i_test)
if sp_arg == 1:
tic, toc = time.clock(), time.time()
if method == 'nrlmf':
model = NRLMF(cfix=args['c'],
K1=args['K1'],
K2=args['K2'],
num_factors=args['r'],
lambda_d=args['lambda_d'],
lambda_t=args['lambda_t'],
alpha=args['alpha'],
beta=args['beta'],
theta=args['theta'],
max_iter=args['max_iter'])
if method == 'netlaprls':
model = NetLapRLS(gamma_d=args['gamma_d'],
gamma_t=args['gamma_t'],
beta_d=args['beta_t'],
beta_t=args['beta_t'])
if method == 'blmnii':
model = BLMNII(alpha=args['alpha'],
gamma=args['gamma'],
sigma=args['sigma'],
avg=args['avg'])
if method == 'wnngip':
model = WNNGIP(T=args['T'],
sigma=args['sigma'],
alpha=args['alpha'])
if method == 'gip':
model = GIP(T=args['T'], sigma=args['sigma'], alpha=args['alpha'])
if method == 'nngip':
model = NNGIP(T=args['T'],
sigma=args['sigma'],
alpha=args['alpha'],
NN=args['NN'])
if method == 'nnwnngip':
model = NNWNNGIP(T=args['T'],
sigma=args['sigma'],
alpha=args['alpha'],
NN=args['NN'])
if method == 'kbmf':
model = KBMF(num_factors=args['R'])
if method == 'cmf':
model = CMF(K=args['K'],
lambda_l=args['lambda_l'],
lambda_d=args['lambda_d'],
lambda_t=args['lambda_t'],
max_iter=args['max_iter'])
elif method == 'nnkronsvm':
model = NNKronSVM(C=args['C'],
NbNeg=args['NbNeg'],
NegNei=args['NegNei'],
PosNei=args['PosNei'],
dataset=dataset,
n_proc=args['n_proc'])
elif method == 'nnkronsvmgip':
model = NNKronSVMGIP(C=args['C'],
NbNeg=args['NbNeg'],
NegNei=args['NegNei'],
PosNei=args['PosNei'],
dataset=dataset,
n_proc=args['n_proc'])
elif method == 'nnkronwnnsvmgip':
model = NNKronWNNSVMGIP(C=args['C'],
t=args['t'],
NbNeg=args['NbNeg'],
NegNei=args['NegNei'],
PosNei=args['PosNei'],
dataset=dataset,
n_proc=args['n_proc'])
elif method == 'nnkronwnnsvm':
model = NNKronWNNSVM(C=args['C'],
t=args['t'],
NbNeg=args['NbNeg'],
NegNei=args['NegNei'],
PosNei=args['PosNei'],
dataset=dataset,
n_proc=args['n_proc'])
cmd = str(model)
print("Dataset:" + dataset + " CVS:" + str(cvs) + "\n" + cmd)
aupr_vec, auc_vec = train(model, method, dataset, cv_data, X, D, T,
cv_type)
aupr_avg, aupr_conf = mean_confidence_interval(aupr_vec)
auc_avg, auc_conf = mean_confidence_interval(auc_vec)
data_file = dataset + "_" + str(
cvs) + "_" + cv_type + '_DefaultParam_Model:' + method
tic, toc = tic - time.clock(), toc - time.time()
print(np.mean(aupr_vec), np.std(aupr_vec), np.mean(auc_vec),
np.std(auc_vec), tic, toc)
pickle.dump((aupr_vec, auc_vec, tic, toc),
open('results/' + data_file + '.data', 'wb'))