def map_function(data_tuple, featurizer):
featurizer = NNScoreComplexFeaturizer()
ind, ligand_pdb, protein_pdb = data_tuple
print("Mapping on ind %d" % ind)
print("ind, type(ligand_pdb), type(protein_pdb): %s " % str(
(ind, type(ligand_pdb), type(protein_pdb))))
return featurizer.featurize_complexes([ligand_pdb], [protein_pdb])
def map_function(data_tuple, featurizer):
featurizer = NNScoreComplexFeaturizer()
ind, ligand_pdb, protein_pdb = data_tuple
print("Mapping on ind %d" % ind)
print("ind, type(ligand_pdb), type(protein_pdb): %s " %
str((ind, type(ligand_pdb), type(protein_pdb))))
return featurizer.featurize_complexes([ligand_pdb], [protein_pdb])
def setUp(self):
"""
Create internal featurizer.
"""
self.nnscore_featurizer = NNScoreComplexFeaturizer()
### 3zso comes from PDBBind-CN
_3zso_protein_pdb_file = os.path.join(data_dir(), "3zso_protein.pdb")
with open(_3zso_protein_pdb_file) as f:
_3zso_protein_pdb = f.readlines()
# The ligand is also specified by pdbbind
_3zso_ligand_pdb_file = os.path.join(data_dir(), "3zso_ligand_hyd.pdb")
with open(_3zso_ligand_pdb_file) as f:
_3zso_ligand_pdb = f.readlines()
self.test_cases = [("3zso", _3zso_ligand_pdb, _3zso_protein_pdb)]
class TestNNScoreComplexFeaturizer(unittest.TestCase):
"""
Test NNScoreComplexFeaturizer.
"""
def setUp(self):
"""
Create internal featurizer.
"""
self.nnscore_featurizer = NNScoreComplexFeaturizer()
### 3zso comes from PDBBind-CN
_3zso_protein_pdb_file = os.path.join(data_dir(), "3zso_protein.pdb")
with open(_3zso_protein_pdb_file) as f:
_3zso_protein_pdb = f.readlines()
# The ligand is also specified by pdbbind
_3zso_ligand_pdb_file = os.path.join(data_dir(), "3zso_ligand_hyd.pdb")
with open(_3zso_ligand_pdb_file) as f:
_3zso_ligand_pdb = f.readlines()
self.test_cases = [("3zso", _3zso_ligand_pdb, _3zso_protein_pdb)]
def testNNScore(self):
"""
Run simple tests with NNScore.
"""
# Currently, just verifies that nothing crashes.
for _, ligand_pdb, protein_pdb in self.test_cases:
_ = self.nnscore_featurizer.featurize_complexes(
[ligand_pdb], [protein_pdb])
def test_singletask_mlp_NNScore_regression_API(self):
"""Test of singletask MLP NNScore regression API."""
splittype = "scaffold"
compound_featurizers = []
complex_featurizers = [NNScoreComplexFeaturizer()]
input_transforms = ["normalize", "truncate"]
output_transforms = ["normalize"]
task_types = {"label": "regression"}
model_params = {
"nb_hidden": 10,
"activation": "relu",
"dropout": .5,
"learning_rate": .01,
"momentum": .9,
"nesterov": False,
"decay": 1e-4,
"batch_size": 5,
"nb_epoch": 2,
"init": "glorot_uniform",
"nb_layers": 1,
"batchnorm": False
}
input_file = "nnscore_example.pkl.gz"
protein_pdb_field = "protein_pdb"
ligand_pdb_field = "ligand_pdb"
train_dataset, test_dataset = self._featurize_train_test_split(
splittype,
compound_featurizers,
complex_featurizers,
input_transforms,
output_transforms,
input_file,
task_types.keys(),
protein_pdb_field=protein_pdb_field,
ligand_pdb_field=ligand_pdb_field)
model_params["data_shape"] = train_dataset.get_data_shape()
model = SingleTaskDNN(task_types, model_params)
self._create_model(train_dataset, test_dataset, model)
print("About to load dataset form disk.")
dataset = load_from_disk(dataset_file)
print("Loaded dataset.")
grid_featurizer = GridFeaturizer(voxel_width=16.0,
feature_types="voxel_combined",
voxel_feature_types=[
"ecfp", "splif", "hbond", "pi_stack",
"cation_pi", "salt_bridge"
],
ecfp_power=9,
splif_power=9,
parallel=True,
flatten=True)
compound_featurizers = [CircularFingerprint(size=1024)]
complex_featurizers = [grid_featurizer, NNScoreComplexFeaturizer()]
#Make a directory in which to store the featurized complexes.
base_dir = "../../../grid_nnscore_circular_features"
if not os.path.exists(base_dir):
os.makedirs(base_dir)
data_dir = os.path.join(base_dir, "data")
if not os.path.exists(data_dir):
os.makedirs(data_dir)
featurized_samples_file = os.path.join(data_dir, "featurized_samples.joblib")
feature_dir = os.path.join(base_dir, "features")
if not os.path.exists(feature_dir):
os.makedirs(feature_dir)