class FineTuner():
def __init__(self, experiment_name='ForwardRNN'):
self._encoder = SMILESEncoder()
# Read all parameter from the .ini file
self._config = configparser.ConfigParser()
self._config.read('../experiments/' + experiment_name + '.ini')
self._model_type = self._config['MODEL']['model']
self._experiment_name = experiment_name
self._hidden_units = int(self._config['MODEL']['hidden_units'])
self._file_name = '../data/' + self._config['DATA']['data']
self._encoding_size = int(self._config['DATA']['encoding_size'])
self._molecular_size = int(self._config['DATA']['molecular_size'])
self._epochs = int(self._config['TRAINING']['epochs'])
# self._n_folds = int(self._config['TRAINING']['n_folds'])
self._learning_rate = float(self._config['TRAINING']['learning_rate'])
self._batch_size = int(self._config['TRAINING']['batch_size'])
self._samples = int(self._config['EVALUATION']['samples'])
self._T = float(self._config['EVALUATION']['temp'])
self._starting_token = self._encoder.encode([self._config['EVALUATION']['starting_token']])
# Read starting model
self._start_model = self._config['FINETUNING']['start_model']
if self._model_type == 'FBRNN':
self._model = FBRNN(self._molecular_size, self._encoding_size,
self._learning_rate, self._hidden_units)
elif self._model_type == 'ForwardRNN':
self._model = ForwardRNN(self._molecular_size, self._encoding_size,
self._learning_rate, self._hidden_units)
elif self._model_type == 'BIMODAL':
self._model = BIMODAL(self._molecular_size, self._encoding_size,
self._learning_rate, self._hidden_units)
elif self._model_type == 'NADE':
self._generation = self._config['MODEL']['generation']
self._missing_token = self._encoder.encode([self._config['TRAINING']['missing_token']])
self._model = NADE(self._molecular_size, self._encoding_size, self._learning_rate,
self._hidden_units, self._generation, self._missing_token)
self._data = self._encoder.encode_from_file(self._file_name)
def fine_tuning(self, stor_dir='../evaluation/', restart=False):
'''Perform fine-tuning and store statistic,
NOTE: Directory should be prepared with the correct name and model
NOTE: Molecules are not generated or validation is not performed. To sample molecules sampler should be used'
:param stor_dir: directory to store data
:return:
'''
# Create directories
if not os.path.exists(stor_dir + '/' + self._experiment_name + '/models'):
os.makedirs(stor_dir + '/' + self._experiment_name + '/models')
if not os.path.exists(stor_dir + '/' + self._experiment_name + '/statistic'):
os.makedirs(stor_dir + '/' + self._experiment_name + '/statistic')
if not os.path.exists(stor_dir + '/' + self._experiment_name + '/molecules'):
os.makedirs(stor_dir + '/' + self._experiment_name + '/molecules')
# Compute labels
label = np.argmax(self._data, axis=-1).astype(int)
# Special preprocessing in the case of NADE random
if self._model_type == 'NADE' and self._generation == 'random':
# First column stores correct SMILES and second column stores SMILES with missing values
label = np.argmax(self._data[:, 0], axis=-1).astype(int)
aug = self._data.shape[1] - 1
label = np.repeat(label[:, np.newaxis, :], aug, axis=1)
self._data = self._data[:, 1:]
# Build model
self._model.build(stor_dir + '/' + self._experiment_name + '/' + self._start_model)
# Store total Statistics
tot_stat = []
# only single fold
fold = 1
for i in range(self._epochs):
print('Fold:', fold)
print('Epoch:', i)
if restart:
# Read existing files
tmp_stat_file = pd.read_csv(
stor_dir + '/' + self._experiment_name + '/statistic/stat_fold_' + str(fold) + '.csv',
header=None).to_numpy()
# Check if current epoch is successfully completed else continue with normal training
if check_model(self._model_type, self._experiment_name, stor_dir, fold, i) and check_molecules(
self._experiment_name, stor_dir, fold, i) and tmp_stat_file.shape[0] > i:
# Load model
self._model.build(
stor_dir + '/' + self._experiment_name + '/models/model_fold_' + str(fold) + '_epochs_' + str(i))
# Fill statistic and loss list
tot_stat.append(tmp_stat_file[i, 1:].reshape(1, -1).tolist())
# Skip this epoch
continue
else:
restart = False
# Train model (Data reshaped from (N_samples, N_augmentation, molecular_size, encoding_size)
# to (all_SMILES, molecular_size, encoding_size))
statistic = self._model.train(self._data.reshape(-1, self._molecular_size, self._encoding_size),
label.reshape(-1, self._molecular_size), epochs=1,
batch_size=self._batch_size)
tot_stat.append(statistic.tolist())
# Store model
self._model.save(
stor_dir + '/' + self._experiment_name + '/models/model_fold_' + str(fold) + '_epochs_' + str(i) )
# Sample new molecules
new_molecules = []
for s in range(self._samples):
mol = self._encoder.decode(self._model.sample(self._starting_token, self._T))
new_molecules.append(clean_molecule(mol[0], self._model_type))
# Store new molecules
new_molecules = np.array(new_molecules)
pd.DataFrame(new_molecules).to_csv(
stor_dir + '/' + self._experiment_name + '/molecules/molecule_fold_' + str(fold) + '_epochs_' + str(
i) + '.csv', header=None)
# Store statistic
store_stat = np.array(tot_stat).reshape(i + 1, -1)
pd.DataFrame(np.array(store_stat)).to_csv(
stor_dir + '/' + self._experiment_name + '/statistic/stat_fold_' + str(fold) + '.csv',
header=None)
class Sampler():
def __init__(self, experiment_name):
self._encoder = SMILESEncoder()
# Read parameter used during training
self._config = configparser.ConfigParser()
self._config.read('../experiments/' + experiment_name + '.ini')
self._model_type = self._config['MODEL']['model']
self._experiment_name = experiment_name
self._hidden_units = int(self._config['MODEL']['hidden_units'])
self._file_name = self._config['DATA']['data']
self._encoding_size = int(self._config['DATA']['encoding_size'])
self._molecular_size = int(self._config['DATA']['molecular_size'])
self._epochs = int(self._config['TRAINING']['epochs'])
self._n_folds = int(self._config['TRAINING']['n_folds'])
self._learning_rate = float(self._config['TRAINING']['learning_rate'])
self._batch_size = int(self._config['TRAINING']['batch_size'])
self._samples = int(self._config['EVALUATION']['samples'])
self._T = float(self._config['EVALUATION']['temp'])
self._starting_token = self._encoder.encode(
[self._config['EVALUATION']['starting_token']])
if self._model_type == 'FBRNN':
self._model = FBRNN(self._molecular_size, self._encoding_size,
self._learning_rate, self._hidden_units)
elif self._model_type == 'ForwardRNN':
self._model = ForwardRNN(self._molecular_size, self._encoding_size,
self._learning_rate, self._hidden_units)
elif self._model_type == 'BIMODAL':
self._model = BIMODAL(self._molecular_size, self._encoding_size,
self._learning_rate, self._hidden_units)
elif self._model_type == 'NADE':
self._generation = self._config['MODEL']['generation']
self._missing_token = self._encoder.encode(
[self._config['TRAINING']['missing_token']])
self._model = NADE(self._molecular_size, self._encoding_size,
self._learning_rate, self._hidden_units,
self._generation, self._missing_token)
# Read data
if os.path.isfile('../data/' + self._file_name + '.csv'):
self._data = pd.read_csv('../data/' + self._file_name + '.csv',
header=None).values[:, 0]
elif os.path.isfile('../data/' + self._file_name + '.tar.xz'):
# Skip first line since empty and last line since nan
self._data = pd.read_csv('../data/' + self._file_name + '.tar.xz',
compression='xz',
header=None).values[1:-1, 0]
# Clean data from start, end and padding token
for i, mol_dat in enumerate(self._data):
self._data[i] = clean_molecule(mol_dat, self._model_type)
def sample(self,
N=100,
stor_dir='../evaluation',
T=0.7,
fold=[1],
epoch=[9],
valid=True,
novel=True,
unique=True,
write_csv=True):
'''Sample from a model where the number of novel valid unique molecules is fixed
:param stor_dir: directory where the generated SMILES are saved
:param N: number of samples
:param T: Temperature
:param fold: Folds to use for sampling
:param epoch: Epochs to use for sampling
:param valid: If True, only accept valid SMILES
:param novel: If True, only accept novel SMILES
:param unique: If True, only accept unique SMILES
:param write_csv If True, the generated SMILES are written in stor_dir
:return: res_molecules: list with all the generated SMILES
'''
res_molecules = []
print('Sampling: started')
for f in fold:
for e in epoch:
self._model.build(stor_dir + '/' + self._experiment_name +
'/models/model_fold_' + str(f) + '_epochs_' +
str(e))
new_molecules = []
while len(new_molecules) < N:
new_mol = self._encoder.decode(
self._model.sample(self._starting_token, T))
# Remove remains from generation
new_mol = clean_molecule(new_mol[0], self._model_type)
# If not valid, get new molecule
if valid and not check_valid(new_mol):
continue
# If not unique, get new molecule
if unique and (new_mol in new_molecules):
continue
# If not novel, get molecule
if novel and (new_mol in self._data):
continue
# If all conditions checked, add new molecule
new_molecules.append(new_mol)
# Prepare name for file
name = 'molecules_fold_' + str(f) + '_epochs_' + str(
e) + '_T_' + str(T) + '_N_' + str(N) + '.csv'
if unique:
name = 'unique_' + name
if valid:
name = 'valid_' + name
if novel:
name = 'novel_' + name
# Store final molecules
if write_csv:
if not os.path.exists(stor_dir + '/' +
self._experiment_name +
'/molecules/'):
os.makedirs(stor_dir + '/' + self._experiment_name +
'/molecules/')
mol = np.array(new_molecules).reshape(-1)
pd.DataFrame(mol).to_csv(stor_dir + '/' +
self._experiment_name +
'/molecules/' + name,
header=None)
res_molecules.append(new_molecules)
print('Sampling: done')
return res_molecules
class Trainer():
def __init__(self, experiment_name='ForwardRNN'):
self._encoder = SMILESEncoder()
# Read all parameter from the .ini file
self._config = configparser.ConfigParser()
self._config.read('../experiments/' + experiment_name + '.ini')
self._model_type = self._config['MODEL']['model']
self._experiment_name = experiment_name
self._hidden_units = int(self._config['MODEL']['hidden_units'])
self._file_name = '../data/' + self._config['DATA']['data']
self._encoding_size = int(self._config['DATA']['encoding_size'])
self._molecular_size = int(self._config['DATA']['molecular_size'])
self._epochs = int(self._config['TRAINING']['epochs'])
self._n_folds = int(self._config['TRAINING']['n_folds'])
self._learning_rate = float(self._config['TRAINING']['learning_rate'])
self._batch_size = int(self._config['TRAINING']['batch_size'])
self._samples = int(self._config['EVALUATION']['samples'])
self._T = float(self._config['EVALUATION']['temp'])
self._starting_token = self._encoder.encode(
[self._config['EVALUATION']['starting_token']])
if self._model_type == 'FBRNN':
self._model = FBRNN(self._molecular_size, self._encoding_size,
self._learning_rate, self._hidden_units)
elif self._model_type == 'ForwardRNN':
self._model = ForwardRNN(self._molecular_size, self._encoding_size,
self._learning_rate, self._hidden_units)
elif self._model_type == 'BIMODAL':
self._model = BIMODAL(self._molecular_size, self._encoding_size,
self._learning_rate, self._hidden_units)
elif self._model_type == 'NADE':
self._generation = self._config['MODEL']['generation']
self._missing_token = self._encoder.encode(
[self._config['TRAINING']['missing_token']])
self._model = NADE(self._molecular_size, self._encoding_size,
self._learning_rate, self._hidden_units,
self._generation, self._missing_token)
self._data = self._encoder.encode_from_file(self._file_name)
def complete_run(self, stor_dir='../evaluation/', restart=False):
'''Training without validation on complete data'''
# Create directories
if not os.path.exists(stor_dir + '/' + self._experiment_name +
'/models'):
os.makedirs(stor_dir + '/' + self._experiment_name + '/models')
if not os.path.exists(stor_dir + '/' + self._experiment_name +
'/molecules'):
os.makedirs(stor_dir + '/' + self._experiment_name + '/molecules')
if not os.path.exists(stor_dir + '/' + self._experiment_name +
'/statistic'):
os.makedirs(stor_dir + '/' + self._experiment_name + '/statistic')
# Compute labels
label = np.argmax(self._data, axis=-1).astype(int)
# Special preprocessing in the case of NADE
if self._model_type == 'NADE' and self._generation == 'random':
# First column stores correct SMILES and second column stores SMILES with missing values
label = np.argmax(self._data[:, 0], axis=-1).astype(int)
aug = self._data.shape[1] - 1
label = np.repeat(label[:, np.newaxis, :], aug, axis=1)
self._data = self._data[:, 1:]
# Build model
self._model.build()
# Store total Statistics
tot_stat = []
# only single fold
fold = 1
# Shuffle data before training (Data reshaped from (N_samples, N_augmentation, molecular_size, encoding_size)
# to (all_SMILES, molecular_size, encoding_size))
self._data, label = shuffle(
self._data.reshape(-1, self._molecular_size, self._encoding_size),
label.reshape(-1, self._molecular_size))
for i in range(self._epochs):
print('Fold:', fold)
print('Epoch:', i)
# With restart read existing files
if restart:
tmp_stat_file = pd.read_csv(
stor_dir + '/' + self._experiment_name +
'/statistic/stat_fold_' + str(fold) + '.csv',
header=None).to_numpy()
# Check if current epoch is successfully completed else continue with normal training
if check_model(self._model_type, self._experiment_name,
stor_dir, fold, i) and check_molecules(
self._experiment_name, stor_dir, fold,
i) and tmp_stat_file.shape[0] > i:
# Load model
self._model.build(stor_dir + '/' + self._experiment_name +
'/models/model_fold_' + str(fold) +
'_epochs_' + str(i))
# Fill statistic and loss list
tot_stat.append(tmp_stat_file[i, 1:].reshape(1,
-1).tolist())
continue
# Continue with normal training
else:
restart = False
# Train model
statistic = self._model.train(self._data,
label,
epochs=1,
batch_size=self._batch_size)
tot_stat.append(statistic.tolist())
# Store model
self._model.save(stor_dir + '/' + self._experiment_name +
'/models/model_fold_' + str(fold) + '_epochs_' +
str(i))
# Sample new molecules
new_molecules = []
for s in range(self._samples):
mol = self._encoder.decode(
self._model.sample(self._starting_token, self._T))
new_molecules.append(clean_molecule(mol[0], self._model_type))
# Store new molecules
new_molecules = np.array(new_molecules)
pd.DataFrame(new_molecules).to_csv(
stor_dir + '/' + self._experiment_name +
'/molecules/molecule_fold_' + str(fold) + '_epochs_' + str(i) +
'.csv',
header=None)
# Store statistic
store_stat = np.array(tot_stat).reshape(i + 1, -1)
pd.DataFrame(np.array(store_stat)).to_csv(
stor_dir + '/' + self._experiment_name +
'/statistic/stat_fold_' + str(fold) + '.csv',
header=None)
def single_run(self, stor_dir='../evaluation/', restart=False):
'''Training with validation and store data'''
# Create directories
if not os.path.exists(stor_dir + '/' + self._experiment_name +
'/models'):
os.makedirs(stor_dir + '/' + self._experiment_name + '/models')
if not os.path.exists(stor_dir + '/' + self._experiment_name +
'/molecules'):
os.makedirs(stor_dir + '/' + self._experiment_name + '/molecules')
if not os.path.exists(stor_dir + '/' + self._experiment_name +
'/statistic'):
os.makedirs(stor_dir + '/' + self._experiment_name + '/statistic')
if not os.path.exists(stor_dir + '/' + self._experiment_name +
'/validation'):
os.makedirs(stor_dir + '/' + self._experiment_name + '/validation')
# Compute labels
label = np.argmax(self._data, axis=-1).astype(int)
# Special preprocessing in the case of NADE
if (self._model_type == 'NADE' or self._model_type
== 'NADE_v2') and self._generation == 'random':
# First column stores correct SMILES and second column stores SMILES with missing values
label = np.argmax(self._data[:, 0], axis=-1).astype(int)
aug = self._data.shape[1] - 1
label = np.repeat(label[:, np.newaxis, :], aug, axis=1)
self._data = self._data[:, 1:]
# Split data into train and test data
train_data, test_data, train_label, test_label = train_test_split(
self._data, label, test_size=1. / 5, random_state=1, shuffle=True)
# Build model
self._model.build()
# Store total Statistics
tot_stat = []
# Store validation loss
tot_loss = []
# only single fold
fold = 1
for i in range(self._epochs):
print('Fold:', fold)
print('Epoch:', i)
if restart:
# Read existing files
tmp_val_file = pd.read_csv(
stor_dir + '/' + self._experiment_name +
'/validation/val_fold_' + str(fold) + '.csv',
header=None).to_numpy()
tmp_stat_file = pd.read_csv(
stor_dir + '/' + self._experiment_name +
'/statistic/stat_fold_' + str(fold) + '.csv',
header=None).to_numpy()
# Check if current epoch is successfully completed else continue with normal training
if check_model(self._model_type, self._experiment_name,
stor_dir, fold, i) and check_molecules(
self._experiment_name, stor_dir, fold,
i) and tmp_val_file.shape[
0] > i and tmp_stat_file.shape[0] > i:
# Load model
self._model.build(stor_dir + '/' + self._experiment_name +
'/models/model_fold_' + str(fold) +
'_epochs_' + str(i))
# Fill statistic and loss list
tot_stat.append(tmp_stat_file[i, 1:].reshape(1,
-1).tolist())
tot_loss.append(tmp_val_file[i, 1])
# Skip this epoch
continue
# Continue with normal training
else:
restart = False
# Train model (Data reshaped from (N_samples, N_augmentation, molecular_size, encoding_size)
# to (all_SMILES, molecular_size, encoding_size))
statistic = self._model.train(
train_data.reshape(-1, self._molecular_size,
self._encoding_size),
train_label.reshape(-1, self._molecular_size),
epochs=1,
batch_size=self._batch_size)
tot_stat.append(statistic.tolist())
# Store model
self._model.save(stor_dir + '/' + self._experiment_name +
'/models/model_fold_' + str(fold) + '_epochs_' +
str(i))
# Test model on validation set
tot_loss.append(
self._model.validate(
test_data.reshape(-1, self._molecular_size,
self._encoding_size),
test_label.reshape(-1, self._molecular_size)))
# Sample new molecules
new_molecules = []
for s in range(self._samples):
mol = self._encoder.decode(
self._model.sample(self._starting_token, self._T))
new_molecules.append(clean_molecule(mol[0], self._model_type))
# Store new molecules
new_molecules = np.array(new_molecules)
pd.DataFrame(new_molecules).to_csv(
stor_dir + '/' + self._experiment_name +
'/molecules/molecule_fold_' + str(fold) + '_epochs_' + str(i) +
'.csv',
header=None)
# Store statistic
store_stat = np.array(tot_stat).reshape(i + 1, -1)
pd.DataFrame(np.array(store_stat)).to_csv(
stor_dir + '/' + self._experiment_name +
'/statistic/stat_fold_' + str(fold) + '.csv',
header=None)
# Store validation data
pd.DataFrame(np.array(tot_loss).reshape(
-1, 1)).to_csv(stor_dir + '/' + self._experiment_name +
'/validation/val_fold_' + str(fold) + '.csv',
header=None)
def cross_validation(self, stor_dir='../evaluation/', restart=False):
'''Perform cross-validation and store data'''
# Create directories
if not os.path.exists(stor_dir + '/' + self._experiment_name +
'/models'):
os.makedirs(stor_dir + '/' + self._experiment_name + '/models')
if not os.path.exists(stor_dir + '/' + self._experiment_name +
'/molecules'):
os.makedirs(stor_dir + '/' + self._experiment_name + '/molecules')
if not os.path.exists(stor_dir + '/' + self._experiment_name +
'/statistic'):
os.makedirs(stor_dir + '/' + self._experiment_name + '/statistic')
if not os.path.exists(stor_dir + '/' + self._experiment_name +
'/validation'):
os.makedirs(stor_dir + '/' + self._experiment_name + '/validation')
self._kf = KFold(n_splits=self._n_folds, shuffle=True, random_state=2)
# Count iterations
fold = 0
# Compute labels
label = np.argmax(self._data, axis=-1).astype(int)
# Special preprocessing in the case of NADE
if (self._model_type == 'NADE') and self._generation == 'random':
# First column stores correct SMILES and second column stores SMILES with missing values
label = np.argmax(self._data[:, 0], axis=-1).astype(int)
aug = self._data.shape[1] - 1
label = np.repeat(label[:, np.newaxis, :], aug, axis=1)
self._data = self._data[:, 1:]
# Split data into train and test data
for train, test in self._kf.split(self._data):
# Shuffle index within test and train set
np.random.shuffle(train)
np.random.shuffle(test)
fold += 1
self._model.build()
# Store total statistics
tot_stat = []
# Store validation loss
tot_loss = []
for i in range(self._epochs):
print('Fold:', fold)
print('Epoch:', i)
if restart:
tmp_val_file = pd.read_csv(
stor_dir + '/' + self._experiment_name +
'/validation/val_fold_' + str(fold) + '.csv',
header=None).to_numpy()
tmp_stat_file = pd.read_csv(
stor_dir + '/' + self._experiment_name +
'/statistic/stat_fold_' + str(fold) + '.csv',
header=None).to_numpy()
# Check if current epoch is successfully complete[0]d else continue with normal training
if check_model(
self._model_type, self._experiment_name, stor_dir,
fold, i) and check_molecules(
self._experiment_name, stor_dir, fold,
i) and tmp_val_file.shape[
0] > i and tmp_stat_file.shape[0] > i:
# Load model
self._model.build(stor_dir + '/' +
self._experiment_name +
'/models/model_fold_' + str(fold) +
'_epochs_' + str(i))
# Fill statistic and loss list
tot_stat.append(tmp_stat_file[i,
1:].reshape(1,
-1).tolist())
tot_loss.append(tmp_val_file[i, 1])
# Skip this epoch
continue
else:
restart = False
# Train model (Data reshaped from (N_samples, N_augmentation, molecular_size, encoding_size)
# to (all_SMILES, molecular_size, encoding_size))
statistic = self._model.train(
self._data[train].reshape(-1, self._molecular_size,
self._encoding_size),
label[train].reshape(-1, self._molecular_size),
epochs=1,
batch_size=self._batch_size)
tot_stat.append(statistic.tolist())
# Store model
self._model.save(stor_dir + '/' + self._experiment_name +
'/models/model_fold_' + str(fold) +
'_epochs_' + str(i))
# Test model on validation set
tot_loss.append(
self._model.validate(
self._data[test].reshape(-1, self._molecular_size,
self._encoding_size),
label[test].reshape(-1, self._molecular_size)))
# Sample new molecules
new_molecules = []
for s in range(self._samples):
mol = self._encoder.decode(
self._model.sample(self._starting_token, self._T))
new_molecules.append(
clean_molecule(mol[0], self._model_type))
# Store new molecules
new_molecules = np.array(new_molecules)
pd.DataFrame(new_molecules).to_csv(
stor_dir + '/' + self._experiment_name +
'/molecules/molecule_fold_' + str(fold) + '_epochs_' +
str(i) + '.csv',
header=None)
# Store statistic
store_stat = np.array(tot_stat).reshape(i + 1, -1)
pd.DataFrame(np.array(store_stat)).to_csv(
stor_dir + '/' + self._experiment_name +
'/statistic/stat_fold_' + str(fold) + '.csv',
header=None)
# Store validation data
pd.DataFrame(np.array(tot_loss).reshape(-1, 1)).to_csv(
stor_dir + '/' + self._experiment_name +
'/validation/val_fold_' + str(fold) + '.csv',
header=None)