def plot_2Dimg_logp_predictions():
# Load LogP data
print('Loading data')
(_, _), (x_test, y_test) = get_data('data/ncidb_2Dimg.npz')
# Load Experimental LogP data
print('Loading data')
(_, _), (exp_x_test,
exp_y_test) = get_data('data/ncidb_experim_data_2Dimg.npz',
split=0.2)
print('Normalize input dividing it by 255')
# Input data normalization
# Transform all input matrix elements in values belonging to [0,1] interval
x_test /= 255
exp_x_test /= 255
# Get input and output dims
n_h, n_w, n_c = x_test[0].shape
n_y = y_test[0].shape[0]
# Declare weights file path
weights_file_path = 'weights/incep_resnet_compact_v4_logp_best_val_r2.h5'
exp_weights_file_path = 'weights/incep_resnet_compact_v4_exp_logp_trsf_lrng_small_lr_best_val_r2.h5'
# Load best LogP data predictor
incep_mdl = incep_model_logp(n_h, n_w, n_c, n_y, lmbda=0)
incep_mdl.load_weights(weights_file_path)
# Load best Experimental LogP data predictor
exp_incep_mdl = incep_model_logp(n_h,
n_w,
n_c,
n_y,
lmbda=0,
frozen_index=7)
exp_incep_mdl.load_weights(exp_weights_file_path)
# Predict both LogP and experimental LogP
y_pred = incep_mdl.predict(x_test)
exp_y_pred = exp_incep_mdl.predict(exp_x_test)
# Plot scatter
fig = plt.figure()
plt.scatter(y_test, y_pred, label="LogP model (Test Set). $R^2$: 0.852")
plt.scatter(exp_y_test,
exp_y_pred,
label="Experimental LogP model (Test Set). $R^2$: 0.964")
plt.title("Predicted LogP values from 2D molecule images")
plt.xlabel("True values")
plt.ylabel("Predicted values")
plt.plot([-20, 40], [-20, 40], '--', color='red')
plt.legend()
# Save the plot
plt.savefig("output/2Dimg_logp_predictions.png")
plt.close(fig)
def plot_fingerprints_logp_predictions():
# Load LogP data
print('Loading data')
(_, _), (x_test, y_test) = get_data('data/ncidb_fingerprints.npz')
# Load Experimental LogP data
print('Loading data')
(_, _), (exp_x_test,
exp_y_test) = get_data('data/ncidb_experim_data_fingerprints.npz',
split=0.2)
# Get input and output dims
n_x = x_test[0].shape[0]
n_y = y_test[0].shape[0]
# Declare weights file path
weights_file_path = 'weights/fcnn_logp_6l_best_val_r2.h5'
exp_weights_file_path = 'weights/fcnn_exp_logp_6l_trsf_lrng_best_val_r2.h5'
# Load best LogP data predictor
fcnn_mdl = fcnn_model_logp(n_x, n_y, lmbda=0)
fcnn_mdl.load_weights(weights_file_path)
# Load best Experimental LogP data predictor
exp_fcnn_mdl = fcnn_model_logp(n_x, n_y, lmbda=0, frozen_layers=4)
exp_fcnn_mdl.load_weights(exp_weights_file_path)
# Predict both LogP and experimental LogP
y_pred = fcnn_mdl.predict(x_test)
exp_y_pred = exp_fcnn_mdl.predict(exp_x_test)
# Plot scatter
fig = plt.figure()
plt.scatter(y_test, y_pred, label="LogP model (Test Set). $R^2$: 0.839")
plt.scatter(exp_y_test,
exp_y_pred,
label="Experimental LogP model (Test Set). $R^2$: 0.923")
plt.title("Predicted LogP values from molecular fingerprints")
plt.xlabel("True values")
plt.ylabel("Predicted values")
plt.plot([-20, 40], [-20, 40], '--', color='red')
plt.legend()
# Save the plot
plt.savefig("output/1Dfingerprints_logp_predictions.png")
plt.close(fig)
def main(train=False):
""" Main function """
# get train and test dataset
print('Loading data')
(x_train,
y_train), (x_test,
y_test) = get_data('data/tox21_10k_data_all_2Dimg_ml.npz')
print('Normalize input dividing it by 255')
# Input data normalization
# Transform all input matrix elements in values belonging to [0,1] interval
x_train /= 255
x_test /= 255
n_h, n_w, n_c = x_train[0].shape
n_y = y_train[0].shape[0]
# Build model
incep_tox21 = incep_model_tox21(n_h, n_w, n_c, n_y, lmbda=0)
epochs = 100
if train:
# Train model
print('\ntrain the model')
# Define checkpoints
# Create save weights checkpoint callback function
weights_ckpt = keras.callbacks.ModelCheckpoint(
'weights/%s_{epoch:d}.h5' % MODEL_NAME,
save_weights_only=True,
period=5)
# Create save best weights checkpoint callback function
best_ckpt = keras.callbacks.ModelCheckpoint(
'weights/%s_best_val_r2.h5' % MODEL_NAME,
monitor='val_masked_f1',
verbose=1,
save_best_only=True,
mode='max')
# Adjust Batch size based on GPUs number
batch_size = 64 * GPUs or 32
history = incep_tox21.fit(
x_train,
y_train,
epochs=epochs,
validation_split=0.1,
batch_size=batch_size,
callbacks=[weights_ckpt, best_ckpt] # Save weights
)
# Get data from history
metrics = ['masked_f1', 'loss', 'masked_accuracy']
save_history(history,
"output/%s_%s_history.json" % (MODEL_NAME, epochs))
plot_data(history, MODEL_NAME, epochs, metrics=metrics)
else:
# Load the model weights
weights_file_path = os.path.abspath(
os.path.join(os.curdir, 'weights/%s_%s.h5' % (MODEL_NAME, epochs)))
if not os.path.exists(weights_file_path):
raise Exception(
"The weights file path specified does not exists: %s" %
os.path.exists(weights_file_path))
incep_mdl.load_weights(weights_file_path)
print('\ntest the model')
test_loss, test_f1_score, test_acc = incep_tox21.evaluate(x_test, y_test)
print('\n#######################################')
print('Test loss:', test_loss)
print('Test accuracy:', test_acc)
print('Test F1 score:', test_f1_score)
print('\n#######################################')
each_metric(x_test, y_test, incep_tox21)
def main(train=False):
""" Main function """
# Get train and test dataset
(x_train, y_train), (x_test, y_test) = get_data('data/ncidb_fingerprints.npz')
n_x = x_train[0].shape[0]
n_y = y_train[0].shape[0]
# Build model
fcnn_mdl = fcnn_model_logp(n_x, n_y, lmbda=0)
epochs = 50
if train:
# Train model
print('\ntrain the model')
# Define checkpoints
# Create save weights checkpoint callback function
weights_ckpt = keras.callbacks.ModelCheckpoint(
'weights/%s_{epoch:d}.h5' % MODEL_NAME,
save_weights_only=True,
period=5
)
# Create save best weights checkpoint callback function
best_ckpt = keras.callbacks.ModelCheckpoint(
'weights/%s_best_val_r2.h5' % MODEL_NAME,
monitor='val_r_squared',
verbose=1,
save_best_only=True,
mode='max'
)
history = fcnn_mdl.fit(x_train,
y_train,
epochs=epochs,
validation_split=0.1,
callbacks=[weights_ckpt, best_ckpt] # Save weights
)
#Get data from history
metrics = ['mean_absolute_error', 'r_squared', 'loss']
save_history(history, "output/%s_%s_history.json" % (MODEL_NAME, epochs))
plot_data(history, MODEL_NAME, epochs, metrics=metrics)
else:
# Load the model weights
weights_file_path = os.path.abspath(os.path.join(os.curdir, 'weights/%s_%s.h5' % (MODEL_NAME, epochs)))
if not os.path.exists(weights_file_path):
raise Exception(
"The weights file path specified does not exists: %s"
% os.path.exists(weights_file_path)
)
fcnn_mdl.load_weights(weights_file_path)
print('\ntest the model')
test_loss, test_mae, test_r_squared = fcnn_mdl.evaluate(x_test, y_test)
print('\n#######################################')
print('Test loss:', test_loss)
print('Test mae:', test_mae)
print('Test R2:', test_r_squared)
def main(train=False, weights_file_path=None):
""" Main function """
# get train and test dataset
print('Loading data')
(x_train, y_train), (x_test, y_test) = get_data('data/ncidb_2Dimg.npz')
print('Normalize input dividing it by 255')
# Input data normalization
# Transform all input matrix elements in values belonging to [0,1] interval
x_train /= 255
x_test /= 255
n_h, n_w, n_c = x_train[0].shape
n_y = y_train[0].shape[0]
# Build model
incep_mdl = incep_model_logp(n_h, n_w, n_c, n_y, lmbda=0)
epochs = 100
if train:
# Train model
print('\ntrain the model')
# Define checkpoints
# Create save weights checkpoint callback function
weights_ckpt = keras.callbacks.ModelCheckpoint(
'weights/%s_{epoch:d}.h5' % MODEL_NAME,
save_weights_only=True,
period=5)
# Create save best weights checkpoint callback function
best_ckpt = keras.callbacks.ModelCheckpoint(
'weights/%s_best_val_r2.h5' % MODEL_NAME,
monitor='val_r_squared',
verbose=1,
save_best_only=True,
mode='max')
csv_logger = keras.callbacks.CSVLogger('output/%s_%s_history.csv' %
(MODEL_NAME, epochs))
# Adjust Batch size based on GPUs number
batch_size = 64 * GPUs or 32
if weights_file_path:
incep_mdl.load_weights(weights_file_path)
history = incep_mdl.fit(
x_train,
y_train,
epochs=epochs,
validation_split=0.1,
batch_size=batch_size,
callbacks=[weights_ckpt, best_ckpt, csv_logger] # Save weights
)
#Get data from history
metrics = ['mean_absolute_error', 'r_squared', 'loss']
save_history(history,
"output/%s_%s_history.json" % (MODEL_NAME, epochs))
plot_data(history, MODEL_NAME, epochs, metrics=metrics)
else:
# Load the model weights
if not weights_file_path:
weights_file_path = os.path.abspath(
os.path.join(os.curdir,
'weights/%s_%s.h5' % (MODEL_NAME, epochs)))
if not os.path.exists(weights_file_path):
raise Exception(
"The weights file path specified does not exists: %s" %
os.path.exists(weights_file_path))
incep_mdl.load_weights(weights_file_path)
print('\ntest the model')
test_loss, test_mae, test_r_squared = incep_mdl.evaluate(x_test, y_test)
print('\n#######################################')
print('Test loss:', test_loss)
print('Test mae:', test_mae)
print('Test R2:', test_r_squared)
def main(train=False):
""" Main function """
# Get train and test dataset
(x_train,
y_train), (x_test,
y_test) = get_data('data/tox21_10k_data_all_fingerprints.npz')
#set different data path if run with missing labels
if ml == True:
(x_train, y_train), (x_test, y_test) = get_data(
'data/tox21_10k_data_all_fingerprints_multi.npz')
n_x = x_train[0].shape[0]
n_y = y_train[0].shape[0]
#get the classifier
fcnn_clf = fcnn_classifier_tox21(n_x, n_y)
if ml == True:
fcnn_clf = fcnn_classifier_tox21_ml(n_x, n_y)
epochs = 50
if train:
# Train classifier
print('\ntrain the classifier')
# Define checkpoints
# Create save weights checkpoint callback function
weights_ckpt = keras.callbacks.ModelCheckpoint(
'weights/%s_{epoch:d}.h5' % MODEL_NAME,
save_weights_only=True,
period=5)
# Create save best weights checkpoint callback function
best_ckpt = keras.callbacks.ModelCheckpoint(
'weights/%s_best_f1_score.h5' % MODEL_NAME,
monitor='val_f1_score',
verbose=1,
save_best_only=True,
mode='max')
history = fcnn_clf.fit(
x_train,
y_train,
epochs=epochs,
validation_split=0.1,
callbacks=[weights_ckpt, best_ckpt] # Save weights
)
# Get data from history
metrics = ['f1_score', 'loss']
save_history(history,
"output/%s_%s_history.json" % (MODEL_NAME, epochs))
plot_data(history, MODEL_NAME, epochs, metrics=metrics)
else:
# Load the model weights
weights_file_path = os.path.abspath(
os.path.join(os.curdir, 'weights/fcnn_tox21_%s.h5' % epochs))
if not os.path.exists(weights_file_path):
raise Exception(
"The weights file path specified does not exists: %s" %
os.path.exists(weights_file_path))
fcnn_clf.load_weights(weights_file_path)
print('\ntest the classifier')
print('\n#######################################')
test_loss, test_f1_score = fcnn_clf.evaluate(x_test, y_test)
print('\n#######################################')
print('Test loss:', test_loss)
print('Test F1 score:', test_f1_score)
print('\n#######################################')
each_metric(x_test, y_test, fcnn_clf)
