from __future__ import print_function
from __future__ import division
from __future__ import unicode_literals
import os
import shutil
import numpy as np
import deepchem as dc
from tox21_datasets import load_tox21
# Only for debug!
np.random.seed(123)
# Load Tox21 dataset
n_features = 1024
tox21_tasks, tox21_datasets, transformers = load_tox21()
train_dataset, valid_dataset, test_dataset = tox21_datasets
# Fit models
metric = dc.metrics.Metric(dc.metrics.roc_auc_score,
np.mean,
mode="classification")
model = dc.models.TensorflowMultiTaskClassifier(len(tox21_tasks),
n_features,
layer_sizes=[1000],
dropouts=[.25],
learning_rate=0.001,
batch_size=50,
verbosity="high")
# Set some global variables up top
verbosity = "high"
#Make directories to store the raw and featurized datasets.
base_dir = "/tmp/tox21_tf"
data_dir = os.path.join(base_dir, "dataset")
model_dir = os.path.join(base_dir, "model")
# This is for good debug (to make sure nasty state isn't being passed around)
if os.path.exists(base_dir):
shutil.rmtree(base_dir)
os.makedirs(base_dir)
# Load Tox21 dataset
n_features = 1024
tox21_tasks, tox21_datasets, transformers = load_tox21(data_dir, reload=False)
# Do train/valid split.
train_dataset, valid_dataset = tox21_datasets
# Fit models
classification_metric = Metric(metrics.roc_auc_score, np.mean,
verbosity=verbosity,
mode="classification")
tensorflow_model = TensorflowMultiTaskClassifier(
len(tox21_tasks), n_features, model_dir, dropouts=[.25],
learning_rate=0.0003, weight_init_stddevs=[1.],
batch_size=32, verbosity=verbosity)
model = TensorflowModel(tensorflow_model, model_dir)
# Fit trained model
d[label] = to_one_hot(y_b[:, index])
d[task_weights] = w_b
multiConvMol = ConvMol.agglomerate_mols(X_b)
d[atom_features] = multiConvMol.get_atom_features()
d[degree_slice] = multiConvMol.deg_slice
d[membership] = multiConvMol.membership
for i in range(1, len(multiConvMol.get_deg_adjacency_lists())):
d[deg_adjs[i -
1]] = multiConvMol.get_deg_adjacency_lists()[i]
yield d
return model, feed_dict_generator, labels, task_weights
# Load Tox21 dataset
tox21_tasks, tox21_datasets, transformers = load_tox21(featurizer='GraphConv')
train_dataset, valid_dataset, test_dataset = tox21_datasets
print(train_dataset.data_dir)
print(valid_dataset.data_dir)
# Fit models
metric = dc.metrics.Metric(dc.metrics.roc_auc_score,
np.mean,
mode="classification")
# Batch size of models
batch_size = 50
model, generator, labels, task_weights = graph_conv_model(
batch_size, tox21_tasks)
Script that trains multitask models on Tox21 dataset.
"""
from __future__ import print_function
from __future__ import division
from __future__ import unicode_literals
import numpy as np
import deepchem as dc
from tox21_datasets import load_tox21
# Only for debug!
np.random.seed(123)
# Load Tox21 dataset
n_features = 1024
tox21_tasks, tox21_datasets, transformers = load_tox21()
train_dataset, valid_dataset, test_dataset = tox21_datasets
# Fit models
metric = dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean)
model = dc.models.TensorflowMultiTaskClassifier(
len(tox21_tasks), n_features, layer_sizes=[1000], dropouts=[.25],
learning_rate=0.001, batch_size=50)
# Fit trained model
model.fit(train_dataset)
model.save()
print("Evaluating model")
train_scores = model.evaluate(train_dataset, [metric], transformers)
"""
Script that trains graph-conv models on Tox21 dataset.
"""
from __future__ import print_function
from __future__ import division
from __future__ import unicode_literals
import numpy as np
np.random.seed(123)
import tensorflow as tf
tf.set_random_seed(123)
import deepchem as dc
from tox21_datasets import load_tox21
# Load Tox21 dataset
tox21_tasks, tox21_datasets, transformers = load_tox21(featurizer='GraphConv')
train_dataset, valid_dataset, test_dataset = tox21_datasets
# Fit models
metric = dc.metrics.Metric(
dc.metrics.roc_auc_score, np.mean, mode="classification")
# Number of features on conv-mols
n_feat = 75
# Batch size of models
batch_size = 50
graph_model = dc.nn.SequentialGraph(n_feat)
graph_model.add(dc.nn.GraphConv(64, n_feat, activation='relu'))
graph_model.add(dc.nn.BatchNormalization(epsilon=1e-5, mode=1))
graph_model.add(dc.nn.GraphPool())
graph_model.add(dc.nn.GraphConv(64, 64, activation='relu'))
import numpy as np
import json
np.random.seed(123)
import tensorflow as tf
tf.set_random_seed(123)
import deepchem as dc
from tox21_datasets import load_tox21
from deepchem.models.tensorgraph.models.graph_models import PetroskiSuchTensorGraph
model_dir = "/tmp/graph_conv"
# Load Tox21 dataset
tox21_tasks, tox21_datasets, transformers = load_tox21(featurizer='AdjMatrix')
train_dataset, valid_dataset, test_dataset = tox21_datasets
print(train_dataset.data_dir)
print(valid_dataset.data_dir)
# Fit models
metric = dc.metrics.Metric(dc.metrics.roc_auc_score,
np.mean,
mode="classification")
# Batch size of models
batch_size = 128
model = PetroskiSuchTensorGraph(len(tox21_tasks),
batch_size=batch_size,
mode='classification')
