def test_get_molnet_bbbp_dataset_with_smiles():
# test default behavior
pp = AtomicNumberPreprocessor()
datasets = molnet.get_molnet_dataset('bbbp', preprocessor=pp,
return_smiles=True)
assert 'smiles' in datasets.keys()
assert 'dataset' in datasets.keys()
smileses = datasets['smiles']
datasets = datasets['dataset']
assert len(smileses) == 3
assert len(datasets) == 3
# Test each train, valid and test dataset
for i, dataset in enumerate(datasets):
# --- Test dataset is correctly obtained ---
index = np.random.choice(len(dataset), None)
atoms, label = dataset[index]
assert atoms.ndim == 1 # (atom, )
assert atoms.dtype == np.int32
# (atom from, atom to) or (edge_type, atom from, atom to) assert label.ndim == 1
assert label.shape[0] == 1
assert label.dtype == np.int32
assert len(dataset) == expect_bbbp_lengths[i]
assert len(smileses[i]) == expect_bbbp_lengths[i]
def test_get_molnet_bbbp_dataset_change_split_ratio():
# test default behavior
pp = AtomicNumberPreprocessor()
datasets = molnet.get_molnet_dataset('bbbp',
preprocessor=pp,
frac_train=0.5,
frac_valid=0.3,
frac_test=0.2)
assert 'smiles' in datasets.keys()
assert 'dataset' in datasets.keys()
datasets = datasets['dataset']
assert len(datasets) == 3
assert type(datasets[0]) == NumpyTupleDataset
assert type(datasets[1]) == NumpyTupleDataset
assert type(datasets[2]) == NumpyTupleDataset
# Test each train, valid and test dataset
for i, dataset in enumerate(datasets):
# --- Test dataset is correctly obtained ---
index = numpy.random.choice(len(dataset), None)
atoms, label = dataset[index]
assert atoms.ndim == 1 # (atom, )
assert atoms.dtype == numpy.int32
# (atom from, atom to) or (edge_type, atom from, atom to)
assert label.ndim == 1
assert label.shape[0] == 1
assert label.dtype == numpy.int32
assert len(dataset) == expect_bbbp_lengths2[i]
def test_get_molnet_qm7_dataset():
# test default behavior
pp = AtomicNumberPreprocessor()
datasets = molnet.get_molnet_dataset('qm7', preprocessor=pp)
assert 'smiles' in datasets.keys()
assert 'dataset' in datasets.keys()
datasets = datasets['dataset']
assert len(datasets) == 3
assert type(datasets[0]) == NumpyTupleDataset
assert type(datasets[1]) == NumpyTupleDataset
assert type(datasets[2]) == NumpyTupleDataset
# Test each train, valid and test dataset
for i, dataset in enumerate(datasets):
# --- Test dataset is correctly obtained ---
index = numpy.random.choice(len(dataset), None)
atoms, label = dataset[index]
assert atoms.ndim == 1 # (atom, )
assert atoms.dtype == numpy.int32
# (atom from, atom to) or (edge_type, atom from, atom to)
assert label.ndim == 1
assert label.shape[0] == 1
assert label.dtype == numpy.float32
# --- Test number of dataset ---
assert len(dataset) == expect_qm7_lengths[i]
def test_get_molnet_grid_featurized_pdbbind_dataset():
# test default behavioer
datasets = molnet.get_molnet_dataset('pdbbind_grid',
pdbbind_subset='core',
split='random')
assert 'dataset' in datasets.keys()
datasets = datasets['dataset']
assert len(datasets) == 3
assert type(datasets[0]) == NumpyTupleDataset
assert type(datasets[1]) == NumpyTupleDataset
assert type(datasets[2]) == NumpyTupleDataset
# Test each train, valid and test dataset
for i, dataset in enumerate(datasets):
# --- Test dataset is correctly obtained ---
index = numpy.random.choice(len(dataset), None)
atoms, label = dataset[index]
assert atoms.ndim == 1 # (atom, )
assert atoms.dtype == numpy.int32
# (atom from, atom to) or (edge_type, atom from, atom to)
assert label.ndim == 1
assert label.shape[0] == 1
assert label.dtype == numpy.float32
# --- Test number of dataset ---
assert len(dataset) == expect_featurized_pdbbind_lengths[i]
def test_get_molnet_pdbbind_dataset_with_pdb_id():
# test default behavior
pp = AtomicNumberPreprocessor()
time_list = numpy.random.randint(1000, size=168).tolist()
datasets = molnet.get_molnet_dataset('pdbbind_smiles',
preprocessor=pp,
pdbbind_subset='core',
return_pdb_id=True,
time_list=time_list,
split='random')
assert 'smiles' in datasets.keys()
assert 'dataset' in datasets.keys()
assert 'pdb_id' in datasets.keys()
pdb_ids = datasets['pdb_id']
datasets = datasets['dataset']
assert len(pdb_ids) == 3
assert len(datasets) == 3
# Test each train, valid and test dataset
for i, dataset in enumerate(datasets):
# --- Test dataset is correctly obtained ---
index = numpy.random.choice(len(dataset), None)
atoms, label = dataset[index]
assert label.ndim == 1 # (atom, )
assert atoms.dtype == numpy.int32
# (atom from, atom to) or (edge_type, atom from, atom to)
assert label.ndim == 1
assert label.shape[0] == 1
assert label.dtype == numpy.float32
# --Test number of dataset ---
assert len(dataset) == expect_pdbbind_lengths[i]
assert len(pdb_ids[i]) == expect_pdbbind_lengths[i]
def main():
# Supported preprocessing/network list
parser = argparse.ArgumentParser(
description='Regression with own dataset.')
parser.add_argument('--gpu', '-g', type=int, default=-1)
parser.add_argument('--method',
type=str,
default='nfpdrop',
choices=['nfpdrop', 'ggnndrop', 'nfp', 'ggnn'])
parser.add_argument('--epoch', '-e', type=int, default=20)
parser.add_argument('--seed', '-s', type=int, default=777)
parser.add_argument('--layer', '-n', type=int, default=3)
parser.add_argument('--batchsize', '-b', type=int, default=32)
parser.add_argument('--m', '-m', type=int, default=30)
args = parser.parse_args()
dataset_name = 'delaney'
# labels = "measured log solubility in mols per litre"
labels = None
# Dataset preparation
print('Preprocessing dataset...')
method = args.method
if 'nfp' in method:
preprocess_method = 'nfp'
elif 'ggnn' in method:
preprocess_method = 'ggnn'
else:
raise ValueError('Unexpected method', method)
preprocessor = preprocess_method_dict[preprocess_method]()
data = get_molnet_dataset(dataset_name,
preprocessor,
labels=labels,
return_smiles=True,
frac_train=1.0,
frac_valid=0.0,
frac_test=0.0)
dataset = data['dataset'][0]
smiles = data['smiles'][0]
epoch = args.epoch
gpu = args.gpu
n_unit_list = [32]
random_state = np.random.RandomState(args.seed)
n = len(dataset)
M = args.m
order = np.arange(n)
random_state.shuffle(order)
batchsize = args.batchsize
for n_unit in n_unit_list:
n_layer = args.layer
n_split = 5
for idx in range(n_split):
print('Start training: ', idx + 1, "/", n_split)
dir_path = get_dir_path(batchsize, n_unit, n_layer, M, method)
os.makedirs(dir_path, exist_ok=True)
np.save(os.path.join(dir_path, "smiles.npy"), np.array(smiles))
train(gpu, method, epoch, batchsize, n_unit, n_layer, dataset,
smiles, M, n_split, idx, order)
