def _featurize(self, complex: Tuple[str, str]):
"""
Compute featurization for a molecular complex
Parameters
----------
complex: Tuple[str, str]
Filenames for molecule and protein.
"""
try:
fragments = 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
for (frag1, frag2) in itertools.combinations(fragments, 2):
# Get coordinates
distances = compute_pairwise_distances(frag1[0], frag2[0])
vector = [
vectorize(hash_ecfp, feature_dict=ecfp_dict, size=self.size)
for ecfp_dict in featurize_contacts_ecfp(
frag1,
frag2,
distances,
cutoff=self.cutoff,
ecfp_degree=self.radius)
]
pairwise_features += vector
pairwise_features = np.concatenate(pairwise_features)
return pairwise_features
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
for (frag1, frag2) in itertools.combinations(fragments, 2):
# Get coordinates
distances = compute_pairwise_distances(frag1[0], frag2[0])
# distances = compute_pairwise_distances(prot_xyz, lig_xyz)
vectors = [
vectorize(hash_ecfp_pair,
feature_dict=splif_dict,
size=self.size)
for splif_dict in featurize_splif(
frag1, frag2, self.contact_bins, distances, self.radius)
]
pairwise_features += vectors
pairwise_features = np.concatenate(pairwise_features)
return pairwise_features
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 _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: 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)
if self.reduce_to_contacts:
fragments = reduce_molecular_complex_to_contacts(
fragments, self.cutoff)
# We compute pairwise contact fingerprints
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([
np.array([len(hbond_list)])
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, 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
for (frag1, frag2) in itertools.combinations(fragments, 2):
# Get coordinates
distances = compute_pairwise_distances(frag1[0], frag2[0])
vector = [
vectorize(hash_ecfp, feature_dict=ecfp_dict, size=self.size)
for ecfp_dict in featurize_contacts_ecfp(
frag1,
frag2,
distances,
cutoff=self.cutoff,
ecfp_degree=self.radius)
]
pairwise_features += vector
pairwise_features = np.concatenate(pairwise_features)
return pairwise_features
def test_get_contact_atom_indices(self): complexes = rdkit_utils.load_complex([self.protein_file, self.ligand_file]) contact_indices = get_contact_atom_indices(complexes) assert len(contact_indices) == 2
def test_load_complex(self):
complexes = rdkit_utils.load_complex(
(self.protein_file, self.ligand_file),
add_hydrogens=False,
calc_charges=False)
assert len(complexes) == 2
