def test_graph_conv_atom_features(self):
tasks, dataset, transformers, metric = self.get_dataset('regression',
'Raw',
num_tasks=1)
atom_feature_name = 'feature'
y = []
for mol in dataset.X:
atom_features = []
for atom in mol.GetAtoms():
val = np.random.normal()
mol.SetProp(
"atom %08d %s" % (atom.GetIdx(), atom_feature_name),
str(val))
atom_features.append(np.random.normal())
y.append(np.sum(atom_features))
featurizer = ConvMolFeaturizer(atom_properties=[atom_feature_name])
X = featurizer.featurize(dataset.X)
dataset = deepchem.data.NumpyDataset(X, np.array(y))
batch_size = 50
model = GraphConvModel(
len(tasks),
number_atom_features=featurizer.feature_length(),
batch_size=batch_size,
mode='regression')
model.fit(dataset, nb_epoch=1)
y_pred1 = model.predict(dataset)
model.save()
model2 = TensorGraph.load_from_dir(model.model_dir)
y_pred2 = model2.predict(dataset)
self.assertTrue(np.all(y_pred1 == y_pred2))
def test_graph_conv_atom_features():
tasks, dataset, transformers, metric = get_dataset('regression',
'Raw',
num_tasks=1)
atom_feature_name = 'feature'
y = []
for mol in dataset.X:
atom_features = []
for atom in mol.GetAtoms():
val = np.random.normal()
mol.SetProp("atom %08d %s" % (atom.GetIdx(), atom_feature_name),
str(val))
atom_features.append(np.random.normal())
y.append([np.sum(atom_features)])
featurizer = ConvMolFeaturizer(atom_properties=[atom_feature_name])
X = featurizer.featurize(dataset.X)
dataset = dc.data.NumpyDataset(X, np.array(y))
batch_size = 50
model = GraphConvModel(len(tasks),
number_atom_features=featurizer.feature_length(),
batch_size=batch_size,
mode='regression')
model.fit(dataset, nb_epoch=1)
y_pred1 = model.predict(dataset)
def test_graph_conv_atom_features(self):
tasks, dataset, transformers, metric = self.get_dataset(
'regression', 'Raw', num_tasks=1)
atom_feature_name = 'feature'
y = []
for mol in dataset.X:
atom_features = []
for atom in mol.GetAtoms():
val = np.random.normal()
mol.SetProp("atom %08d %s" % (atom.GetIdx(), atom_feature_name),
str(val))
atom_features.append(np.random.normal())
y.append([np.sum(atom_features)])
featurizer = ConvMolFeaturizer(atom_properties=[atom_feature_name])
X = featurizer.featurize(dataset.X)
dataset = dc.data.NumpyDataset(X, np.array(y))
batch_size = 50
model = GraphConvModel(
len(tasks),
number_atom_features=featurizer.feature_length(),
batch_size=batch_size,
mode='regression')
model.fit(dataset, nb_epoch=1)
y_pred1 = model.predict(dataset)
model.save()
model2 = TensorGraph.load_from_dir(model.model_dir)
y_pred2 = model2.predict(dataset)
self.assertTrue(np.allclose(y_pred1, y_pred2))
def test_graph_conv_model_no_task():
tasks, dataset, _, __ = get_dataset('classification', 'GraphConv')
batch_size = 10
model = GraphConvModel(len(tasks),
batch_size=batch_size,
batch_normalize=False,
mode='classification')
model.fit(dataset, nb_epoch=20)
# predict datset with no y (ensured by tasks = [])
bace_url = "https://deepchemdata.s3-us-west-1.amazonaws.com/datasets/bace.csv"
dc.utils.data_utils.download_url(url=bace_url, name="bace_tmp.csv")
loader = dc.data.CSVLoader(tasks=[],
smiles_field='mol',
featurizer=dc.feat.ConvMolFeaturizer())
td = loader.featurize(
os.path.join(dc.utils.data_utils.get_data_dir(), "bace_tmp.csv"))
model.predict(td)
def test_neural_fingerprint_retrieval(self):
tasks, dataset, transformers, metric = self.get_dataset(
'classification', 'GraphConv')
fp_size = 3
batch_size = 50
model = GraphConvModel(len(tasks),
batch_size=batch_size,
dense_layer_size=3,
mode='classification')
model.fit(dataset, nb_epoch=1)
neural_fingerprints = model.predict(dataset,
outputs=model.neural_fingerprint)
neural_fingerprints = np.array(neural_fingerprints)[:len(dataset)]
self.assertEqual((len(dataset), fp_size * 2),
neural_fingerprints.shape)
def test_neural_fingerprint_retrieval(self):
tasks, dataset, transformers, metric = self.get_dataset(
'classification', 'GraphConv')
fp_size = 3
batch_size = 50
model = GraphConvModel(
len(tasks),
batch_size=batch_size,
dense_layer_size=3,
mode='classification')
model.fit(dataset, nb_epoch=1)
neural_fingerprints = model.predict(
dataset, outputs=model.neural_fingerprint)
neural_fingerprints = np.array(neural_fingerprints)[:len(dataset)]
self.assertEqual((len(dataset), fp_size * 2), neural_fingerprints.shape)
def test_graph_conv_model():
batch_size = 2000
model = GraphConvModel(1,
batch_size=batch_size,
mode="classification",
model_dir="/tmp/covid/model_dir")
dataset_file = "covid_mpro_combined_data_sources.csv"
tasks = ["isHit"]
featurizer = dc.feat.ConvMolFeaturizer()
loader = dc.data.CSVLoader(tasks=tasks,
smiles_field="SMILES",
featurizer=featurizer)
dataset = loader.featurize(dataset_file, shard_size=8192)
metrics = [
dc.metrics.Metric(dc.metrics.matthews_corrcoef,
np.mean,
mode="classification")
]
splitter = dc.splits.RandomSplitter()
train_dataset, valid_dataset, test_dataset = splitter.train_valid_test_split(
dataset)
model.fit(train_dataset)
pred = [x.flatten() for x in model.predict(valid_dataset)]
pred_df = pd.DataFrame(pred, columns=["neg", "pos"])
pred_df["active"] = [int(x) for x in valid_dataset.y]
pred_df["SMILES"] = valid_dataset.ids
sns.boxplot(pred_df.active, pred_df.pos)
print(model.evaluate(train_dataset, metrics))
print(model.evaluate(test_dataset, metrics))
metrics = [
dc.metrics.Metric(dc.metrics.roc_auc_score,
np.mean,
mode="classification")
]
print(model.evaluate(train_dataset, metrics))
print(model.evaluate(test_dataset, metrics))
#print(len(losses))
plt.figure(1)
fig, ax = plt.subplots(2, sharex='col', sharey='row')
x = range(num_epochs)
y_loss = losses_train
ax[0].plot(x, y_loss, c='b', alpha=0.6, label='loss_train')
ax[0].set(xlabel='epoch', ylabel='loss')
y_score = score_train
ax[1].plot(x, y_score, c='r', alpha=0.6, label='score_valid')
ax[1].set(xlabel='epoch', ylabel='R2 score')
###Real value and predicted value for target
train_y = train_dataset.y
train_pred = model.predict(train_dataset)
test1_y = test1_dataset.y
test1_pred = model.predict(test1_dataset)
test2_y = test2_dataset.y
test2_pred = model.predict(test2_dataset)
##evaluation model
dcmodel = "DeepChem"
# Scores of Train Data
train_mae = mean_absolute_error(
dc.trans.undo_transforms(train_y, [transformers_train]),
dc.trans.undo_transforms(train_pred, [transformers_train]))
train_rmse = mean_squared_error(
model.fit(dataset)
#model = GraphConvModel(1, batch_size=128,mode="classification",model_dir="/tmp/mk01/model_dir")
#model.restore()
#make predictions
featurizer = dc.feat.ConvMolFeaturizer()
df = pd.read_csv("emol_10M.csv", sep=",")
#print('num rows in file',df.size)
#df.columns=["SMILES","Name"]
rows, cols = df.shape
df["Val"] = [
0
] * rows #just add add a dummy column to keep the featurizer happy
infile_name = "emol_10M_withVal.csv"
df.to_csv(infile_name, index=False)
loader = dc.data.CSVLoader(tasks=['Val'],
smiles_field="isosmiles",
featurizer=featurizer)
dataset = loader.featurize(infile_name, shard_size=8192)
pred = model.predict(dataset)
pred_df = pd.DataFrame([x.flatten() for x in pred], columns=["Neg", "Pos"])
sns.distplot(pred_df.Pos, rug=True)
combo_df = df.join(pred_df, how="outer")
combo_df.sort_values("Pos", inplace=True, ascending=False)
#PandasTools.AddMoleculeColumnToFrame(combo_df,"isosmiles","Mol")
combo_df = combo_df.loc[combo_df['Pos'] >= 0.8]
combo_df.to_csv('emol_10M_output_hits.csv', sep=',')
