def _featurize(self, datapoint, **kwargs): # -> Optional[np.ndarray]:
"""
Compute featurization for a single mol/protein complex
Parameters
----------
datapoint: Tuple[str, str]
Filenames for molecule and protein.
"""
if 'complex' in kwargs:
datapoint = kwargs.get("complex")
raise DeprecationWarning(
'Complex is being phased out as a parameter, please pass "datapoint" instead.'
)
try:
fragments = rdkit_utils.load_complex(datapoint,
add_hydrogens=False)
except MoleculeLoadException:
logger.warning(
"This molecule cannot be loaded by Rdkit. Returning None")
return None
pairwise_features = []
# We compute pairwise contact fingerprints
centroid = compute_contact_centroid(fragments, cutoff=self.cutoff)
if self.reduce_to_contacts:
fragments = reduce_molecular_complex_to_contacts(
fragments, self.cutoff)
for (frag1_ind,
frag2_ind) in itertools.combinations(range(len(fragments)), 2):
frag1, frag2 = fragments[frag1_ind], fragments[frag2_ind]
distances = compute_pairwise_distances(frag1[0], frag2[0])
frag1_xyz = subtract_centroid(frag1[0], centroid)
frag2_xyz = subtract_centroid(frag2[0], centroid)
xyzs = [frag1_xyz, frag2_xyz]
# rdks = [frag1[1], frag2[1]]
pairwise_features.append(
np.concatenate([
sum([
voxelize(convert_atom_pair_to_voxel,
hash_function=None,
box_width=self.box_width,
voxel_width=self.voxel_width,
coordinates=xyz,
feature_list=hbond_list,
nb_channel=1) for xyz in xyzs
]) for hbond_list in compute_hydrogen_bonds(
frag1, frag2, distances, self.distance_bins,
self.angle_cutoffs)
],
axis=-1))
# Features are of shape (voxels_per_edge, voxels_per_edge, voxels_per_edge, 1) so we should concatenate on the last axis.
return np.concatenate(pairwise_features, axis=-1)
def _featurize(self, mol_pdb: str, protein_pdb: str):
"""
Compute featurization for a molecular complex
Parameters
----------
mol_pdb: str
Filename for ligand molecule
protein_pdb: str
Filename for protein molecule
"""
molecular_complex = (mol_pdb, protein_pdb)
try:
fragments = load_complex(molecular_complex, add_hydrogens=False)
except MoleculeLoadException:
logger.warning(
"This molecule cannot be loaded by Rdkit. Returning None")
return None
pairwise_features: List[np.ndarray] = []
# We compute pairwise contact fingerprints
centroid = compute_contact_centroid(fragments, cutoff=self.cutoff)
for (frag1, frag2) in itertools.combinations(fragments, 2):
distances = compute_pairwise_distances(frag1[0], frag2[0])
frag1_xyz = subtract_centroid(frag1[0], centroid)
frag2_xyz = subtract_centroid(frag2[0], centroid)
xyzs = [frag1_xyz, frag2_xyz]
pairwise_features.append(
sum([
voxelize(convert_atom_to_voxel,
xyz,
self.box_width,
self.voxel_width,
hash_function=hash_ecfp,
feature_dict=ecfp_dict,
nb_channel=self.size)
for xyz, ecfp_dict in zip(
xyzs,
featurize_contacts_ecfp(frag1,
frag2,
distances,
cutoff=self.cutoff,
ecfp_degree=self.radius))
]))
if self.flatten:
return np.concatenate(
[features.flatten() for features in pairwise_features])
else:
# Features are of shape (voxels_per_edge, voxels_per_edge,
# voxels_per_edge, num_feat) so we should concatenate on the last
# axis.
return np.concatenate(pairwise_features, axis=-1)
def _featurize(self, mol_pdb: str, protein_pdb: str) -> np.ndarray:
"""
Compute featurization for a single mol/protein complex
Parameters
----------
mol_pdb: str
Filename for ligand molecule
protein_pdb: str
Filename for protein molecule
"""
molecular_complex = (mol_pdb, protein_pdb)
try:
fragments = rdkit_utils.load_complex(
molecular_complex, add_hydrogens=False)
except MoleculeLoadException:
logger.warning("This molecule cannot be loaded by Rdkit. Returning None")
return None
pairwise_features = []
# We compute pairwise contact fingerprints
centroid = compute_contact_centroid(fragments, cutoff=self.cutoff)
if self.reduce_to_contacts:
fragments = reduce_molecular_complex_to_contacts(fragments, self.cutoff)
for (frag1_ind, frag2_ind) in itertools.combinations(
range(len(fragments)), 2):
frag1, frag2 = fragments[frag1_ind], fragments[frag2_ind]
distances = compute_pairwise_distances(frag1[0], frag2[0])
frag1_xyz = subtract_centroid(frag1[0], centroid)
frag2_xyz = subtract_centroid(frag2[0], centroid)
xyzs = [frag1_xyz, frag2_xyz]
# rdks = [frag1[1], frag2[1]]
pairwise_features.append(
np.concatenate(
[
sum([
voxelize(
convert_atom_pair_to_voxel,
hash_function=None,
box_width=self.box_width,
voxel_width=self.voxel_width,
coordinates=xyz,
feature_list=hbond_list,
nb_channel=1) for xyz in xyzs
]) for hbond_list in compute_hydrogen_bonds(
frag1, frag2, distances, self.distance_bins,
self.angle_cutoffs)
],
axis=-1))
# Features are of shape (voxels_per_edge, voxels_per_edge, voxels_per_edge, 1) so we should concatenate on the last axis.
return np.concatenate(pairwise_features, axis=-1)
def _featurize(self, complex: Tuple[str, str]) -> Optional[np.ndarray]:
"""
Compute featurization for a single mol/protein complex
Parameters
----------
complex: Tuple[str, str]
Filenames for molecule and protein.
"""
try:
fragments = rdkit_utils.load_complex(complex, add_hydrogens=False)
except MoleculeLoadException:
logger.warning(
"This molecule cannot be loaded by Rdkit. Returning None")
return None
pairwise_features = []
# We compute pairwise contact fingerprints
centroid = compute_contact_centroid(fragments, cutoff=self.cutoff)
for (frag1_ind,
frag2_ind) in itertools.combinations(range(len(fragments)), 2):
frag1, frag2 = fragments[frag1_ind], fragments[frag2_ind]
# distances = compute_pairwise_distances(frag1[0], frag2[0])
frag1_xyz = subtract_centroid(frag1[0], centroid)
frag2_xyz = subtract_centroid(frag2[0], centroid)
xyzs = [frag1_xyz, frag2_xyz]
# rdks = [frag1[1], frag2[1]]
pairwise_features.append(
sum([
voxelize(convert_atom_to_voxel,
hash_function=None,
box_width=self.box_width,
voxel_width=self.voxel_width,
coordinates=xyz,
feature_dict=cation_pi_dict,
nb_channel=1) for xyz, cation_pi_dict in zip(
xyzs,
compute_binding_pocket_cation_pi(
frag1[1],
frag2[1],
dist_cutoff=self.cutoff,
angle_cutoff=self.angle_cutoff,
))
]))
# Features are of shape (voxels_per_edge, voxels_per_edge, voxels_per_edge, 1) so we should concatenate on the last axis.
return np.concatenate(pairwise_features, axis=-1)
def _featurize(self, datapoint, **kwargs):
"""
Compute featurization for a molecular complex
Parameters
----------
datapoint: Tuple[str, str]
Filenames for molecule and protein.
"""
if 'complex' in kwargs:
datapoint = kwargs.get("complex")
raise DeprecationWarning(
'Complex is being phased out as a parameter, please pass "datapoint" instead.'
)
try:
fragments = load_complex(datapoint, add_hydrogens=False)
except MoleculeLoadException:
logger.warning(
"This molecule cannot be loaded by Rdkit. Returning None")
return None
pairwise_features = []
# We compute pairwise contact fingerprints
centroid = compute_contact_centroid(fragments, cutoff=self.cutoff)
for (frag1, frag2) in itertools.combinations(fragments, 2):
distances = compute_pairwise_distances(frag1[0], frag2[0])
frag1_xyz = subtract_centroid(frag1[0], centroid)
frag2_xyz = subtract_centroid(frag2[0], centroid)
xyzs = [frag1_xyz, frag2_xyz]
pairwise_features.append(
np.concatenate([
voxelize(convert_atom_pair_to_voxel,
hash_function=hash_ecfp_pair,
coordinates=xyzs,
box_width=self.box_width,
voxel_width=self.voxel_width,
feature_dict=splif_dict,
nb_channel=self.size) for splif_dict in
featurize_splif(frag1, frag2, self.contact_bins, distances,
self.radius)
],
axis=-1))
# Features are of shape (voxels_per_edge, voxels_per_edge, voxels_per_edge, 1) so we should concatenate on the last axis.
return np.concatenate(pairwise_features, axis=-1)
def test_subract_centroid(self):
N = 10
coords = np.random.rand(N, 3)
centroid = geometry_utils.compute_centroid(coords)
new_coords = geometry_utils.subtract_centroid(coords, centroid)
assert new_coords.shape == (N, 3)
new_centroid = geometry_utils.compute_centroid(new_coords)
assert new_centroid.shape == (3, )
np.testing.assert_almost_equal(new_centroid,
np.zeros_like(new_centroid))
def _featurize(self, mol_pdb: str, complex_pdb: str):
"""
Compute featurization for a molecular complex
Parameters
----------
mol_pdb: str
Filename for ligand molecule
complex_pdb: str
Filename for protein molecule
"""
molecular_complex = (mol_pdb, complex_pdb)
try:
fragments = load_complex(molecular_complex, add_hydrogens=False)
except MoleculeLoadException:
logger.warning(
"This molecule cannot be loaded by Rdkit. Returning None")
return None
pairwise_features = []
# We compute pairwise contact fingerprints
centroid = compute_contact_centroid(fragments, cutoff=self.cutoff)
for (frag1, frag2) in itertools.combinations(fragments, 2):
distances = compute_pairwise_distances(frag1[0], frag2[0])
frag1_xyz = subtract_centroid(frag1[0], centroid)
frag2_xyz = subtract_centroid(frag2[0], centroid)
xyzs = [frag1_xyz, frag2_xyz]
pairwise_features.append(
np.concatenate([
voxelize(convert_atom_pair_to_voxel,
hash_function=hash_ecfp_pair,
coordinates=xyzs,
box_width=self.box_width,
voxel_width=self.voxel_width,
feature_dict=splif_dict,
nb_channel=self.size) for splif_dict in
featurize_splif(frag1, frag2, self.contact_bins, distances,
self.radius)
],
axis=-1))
# Features are of shape (voxels_per_edge, voxels_per_edge, voxels_per_edge, 1) so we should concatenate on the last axis.
return np.concatenate(pairwise_features, axis=-1)
def _featurize(self, complex):
"""Computes grid featurization of protein/ligand complex.
Takes as input filenames pdb of the protein, pdb of the ligand.
This function then computes the centroid of the ligand; decrements this
centroid from the atomic coordinates of protein and ligand atoms, and then
merges the translated protein and ligand. This combined system/complex is
then saved.
This function then computes a featurization with scheme specified by the user.
Parameters
----------
complex: Tuple[str, str]
Filenames for molecule and protein.
"""
try:
mol_pdb_file, protein_pdb_file = complex
time1 = time.time()
protein_xyz, protein_rdk = load_molecule(protein_pdb_file,
calc_charges=True,
sanitize=self.sanitize)
time2 = time.time()
logger.info(
"TIMING: Loading protein coordinates took %0.3f s" %
(time2 - time1), self.verbose)
time1 = time.time()
ligand_xyz, ligand_rdk = load_molecule(mol_pdb_file,
calc_charges=True,
sanitize=self.sanitize)
time2 = time.time()
logger.info(
"TIMING: Loading ligand coordinates took %0.3f s" %
(time2 - time1), self.verbose)
except MoleculeLoadException:
logger.warning(
"Some molecules cannot be loaded by Rdkit. Skipping")
return None
time1 = time.time()
centroid = compute_centroid(ligand_xyz)
ligand_xyz = subtract_centroid(ligand_xyz, centroid)
protein_xyz = subtract_centroid(protein_xyz, centroid)
time2 = time.time()
logger.info(
"TIMING: Centroid processing took %0.3f s" % (time2 - time1),
self.verbose)
pairwise_distances = compute_pairwise_distances(
protein_xyz, ligand_xyz)
transformed_systems = {}
transformed_systems[(0, 0)] = [protein_xyz, ligand_xyz]
for i in range(self.nb_rotations):
rotated_system = rotate_molecules([protein_xyz, ligand_xyz])
transformed_systems[(i + 1, 0)] = rotated_system
features_dict = {}
for system_id, (protein_xyz,
ligand_xyz) in transformed_systems.items():
feature_arrays = []
for is_flat, function_name in self.feature_types:
result = self._compute_feature(
function_name,
protein_xyz,
protein_rdk,
ligand_xyz,
ligand_rdk,
pairwise_distances,
)
feature_arrays += result
if self.flatten:
features_dict[system_id] = np.concatenate([
feature_array.flatten()
for feature_array in feature_arrays
])
else:
features_dict[system_id] = np.concatenate(feature_arrays,
axis=-1)
# TODO(rbharath): Is this squeeze OK?
features = np.squeeze(np.array(list(features_dict.values())))
return features
