def HIV_CV(DB, data_type, list_ID, list_y, list_SMILES, dict_id2smile, n_folds):
if data_type == 'kernel':
if not os.path.isfile('data/' + DB + '/' + DB + '_K.npy'):
K = mol_build_K(list_SMILES)
np.save('data/' + DB + '/' + DB + '_K', K)
else:
K = np.load('data/' + DB + '/' + DB + '_K.npy')
list_assignment = np.zeros(K.shape[0])
for y in [0, 1]:
indices = np.where(list_y == y)[0]
K_local = K[indices, :]
K_local = K_local[:, indices]
local_assignment = Khierarchical_cluster(K_local, n_folds)
list_assignment[indices] = local_assignment
elif data_type == 'features':
if not os.path.isfile('data/' + DB + '/' + DB + '_X.npy'):
X = mol_build_X(list_SMILES)
np.save('data/' + DB + '/' + DB + '_X', X)
else:
X = np.load('data/' + DB + '/' + DB + '_X.npy')
list_assignment = np.zeros(X.shape[0])
for y in [0, 1]:
indices = np.where(list_y == y)[0]
X_local = X[indices, :]
local_assignment = Xkmeans_cluster(X_local, n_folds)
list_assignment[indices] = local_assignment
elif data_type == 'standard':
if not os.path.isfile('data/' + DB + '/' + DB + '_X.npy'):
X = mol_build_X(list_SMILES)
np.save('data/' + DB + '/' + DB + '_X', X)
else:
X = np.load('data/' + DB + '/' + DB + '_X.npy')
list_assignment = np.zeros(X.shape[0])
skf = model_selection.StratifiedKFold(n_folds, shuffle=True, random_state=92)
skf.get_n_splits(X, list_y)
ifold = 0
for train_index, test_index in skf.split(X, list_y):
list_assignment[test_index] = ifold
ifold += 1
# import pdb; pdb.Pdb().set_trace()
c = collections.Counter(list_assignment)
print(c)
folds = [np.where(list_assignment == cle)[0] for cle in list(c.keys())]
fo = open('data/' + DB + '/' + DB + '_folds.txt', 'w')
for ifold in range(n_folds):
fo.write("ifold" + str(ifold) + '\n')
fo.write(str(collections.Counter(list_y[folds[ifold]])) + '\n')
print(ifold, collections.Counter(list_y[folds[ifold]]))
fo.write('\n')
return folds
def AtomizationEnergy_CV(DB, data_type, list_ID, list_y, list_SMILES,
dict_id2smile, n_folds):
if data_type == 'kernel':
if not os.path.isfile('data/' + DB + '/' + DB + '_K.npy'):
K = mol_build_K(list_SMILES)
np.save('data/' + DB + '/' + DB + '_K', K)
else:
K = np.load('data/' + DB + '/' + DB + '_K.npy')
list_assignment = Khierarchical_cluster(K, n_folds)
elif data_type == 'features':
if not os.path.isfile('data/' + DB + '/' + DB + '_X.npy'):
X = mol_build_X(list_SMILES)
np.save('data/' + DB + '/' + DB + '_X', X)
else:
X = np.load('data/' + DB + '/' + DB + '_X.npy')
list_assignment = Xkmeans_cluster(X, n_folds)
elif data_type == 'standard':
if not os.path.isfile('data/' + DB + '/' + DB + '_X.npy'):
X = mol_build_X(list_SMILES)
np.save('data/' + DB + '/' + DB + '_X', X)
else:
X = np.load('data/' + DB + '/' + DB + '_X.npy')
list_assignment = np.zeros(X.shape[0])
skf = model_selection.KFold(n_folds, shuffle=True, random_state=92)
skf.get_n_splits(X)
ifold = 0
for train_index, test_index in skf.split(X):
list_assignment[test_index] = ifold
ifold += 1
# import pdb; pdb.Pdb().set_trace()
c = collections.Counter(list_assignment)
print(c)
folds = [np.where(list_assignment == cle)[0] for cle in list(c.keys())]
fo = open('data/' + DB + '/' + DB + '_folds.txt', 'w')
fo.write(str(c) + '\n')
fo.close()
return folds
def PCBA_CV(DB, data_type, list_ID, list_y, list_SMILES, dict_id2smile, n_folds):
if data_type == 'kernel':
if not os.path.isfile('data/' + DB + '/' + DB + '_K.npy'):
K = mol_build_K(list_SMILES)
np.save('data/' + DB + '/' + DB + '_K', K)
else:
K = np.load('data/' + DB + '/' + DB + '_K.npy')
if DB == 'PCBA':
# if Kmedoid
# list_assignment, medoids = Kmedoid_cluster(K, n_folds)
# if agglomerative clustering
list_assignment = Khierarchical_cluster(K, n_folds)
else:
list_assignment = np.zeros(K.shape[0])
for y in [0, 1]:
indices = np.where(list_y == y)[0]
K_local = K[indices, :]
K_local = K_local[:, indices]
local_assignment = Khierarchical_cluster(K_local, n_folds)
list_assignment[indices] = local_assignment
elif data_type == 'features':
if not os.path.isfile('data/' + DB + '/' + DB + '_X.npy'):
X = mol_build_X(list_SMILES)
np.save('data/' + DB + '/' + DB + '_X', X)
else:
X = np.load('data/' + DB + '/' + DB + '_X.npy')
if DB == 'PCBA':
list_assignment = Xkmeans_cluster(X, n_folds)
else:
list_assignment = np.zeros(X.shape[0])
for y in [0, 1]:
indices = np.where(list_y == y)[0]
X_local = X[indices, :]
local_assignment = Xkmeans_cluster(X_local, n_folds)
list_assignment[indices] = local_assignment
elif data_type == 'standard':
# if not os.path.isfile('data/' + DB + '/' + DB + '_X.npy'):
# X = mol_build_X(list_SMILES)
# np.save('data/' + DB + '/' + DB + '_X', X)
# else:
# X = np.load('data/' + DB + '/' + DB + '_X.npy')
list_ID = pickle.load(open('data/' + DB + '/' + DB + '_list_ID.data', 'rb'))
list_y = np.array(pickle.load(open('data/' + DB + '/' + DB + '_list_y.data', 'rb')))
X = np.zeros((len(list_ID), 1))
list_assignment = np.zeros(X.shape[0])
if DB not in ['PCBA', 'PCBA10', 'PCBA100']:
skf = model_selection.StratifiedKFold(n_folds, shuffle=True, random_state=92)
skf.get_n_splits(X, list_y)
ifold = 0
for train_index, test_index in skf.split(X, list_y):
list_assignment[test_index] = ifold
ifold += 1
else:
skf = model_selection.KFold(n_folds, shuffle=True, random_state=92)
skf.get_n_splits(X)
ifold = 0
for train_index, test_index in skf.split(X):
list_assignment[test_index] = ifold
ifold += 1
# import pdb; pdb.Pdb().set_trace()
c = collections.Counter(list_assignment)
print(c)
folds = [np.where(list_assignment == cle)[0] for cle in list(c.keys())]
fo = open('data/' + DB + '/' + DB + '_folds.txt', 'w')
for ifold in range(n_folds):
fo.write("ifold" + str(ifold) + '\n')
if DB in ['PCBA', 'PCBA10', 'PCBA100']:
for iclass in range(list_y.shape[1]):
fo.write("iclass " + str(iclass) + ' ' +
str(collections.Counter(list_y[folds[ifold], iclass])) + '\n')
print("iclass " + str(iclass) + ' ' +
str(collections.Counter(list_y[folds[ifold], iclass])))
else:
fo.write(str(collections.Counter(list_y[folds[ifold]])) + '\n')
print(ifold, collections.Counter(list_y[folds[ifold]]))
fo.write('\n')
return folds
open('data/' + DB + '/' + DB + '_Kprot.data', 'rb'))
elif DB in LIST_PROT_DATASETS + LIST_AA_DATASETS:
list_ID = pickle.load(
open('data/' + DB + '/' + DB + '_list_ID.data', 'rb'))
dict_prot2ind = {prot: ind for ind, prot in enumerate(list_ID)}
Kprot = pickle.load(
open('data/' + DB + '/' + DB + '_Kprot.data', 'rb'))
Kmol, dict_mol2ind = None, None
elif DB in LIST_MOL_DATASETS:
if DB not in ['HIV']:
Kmol = pickle.load(
open('data/' + DB + '/' + DB + '_Kmol.data', 'rb'))
else:
list_SMILES = pickle.load(
open('data/' + DB + '/' + DB + '_list_SMILES.data', 'rb'))
Kmol = mol_build_K(list_SMILES)
Kprot, dict_prot2ind = None, None
list_ID = pickle.load(
open('data/' + DB + '/' + DB + '_list_ID.data', 'rb'))
dict_mol2ind = {mol: ind for ind, mol in enumerate(list_ID)}
nfolds, seed = 5, 92
x_tr, y_tr, x_val, y_val, x_te, y_te = \
get_fold_data(DB, nfolds, fold_val, fold_te, setting, ratio_tr, ratio_te)
# import pdb; pdb.Pdb().set_trace()
K_tr, K_val, K_te = \
get_kernels(DB, x_tr, x_te, x_val, Kmol, Kprot, dict_prot2ind, dict_mol2ind)
if args.cv_val:
list_perf = cv(DB, K_tr, y_tr, K_val, y_val)