def bond_features(bond: Chem.rdchem.Bond,
args) -> List[Union[bool, int, float]]:
"""
Builds a feature vector for a bond.
:param bond: A RDKit bond.
:return: A list containing the bond features.
"""
bond_fdim = get_bond_fdim(args)
if bond is None:
fbond = [1] + [0] * (bond_fdim - 1)
else:
bt = bond.GetBondType()
fbond = [
0, # bond is not None
bt == Chem.rdchem.BondType.SINGLE,
bt == Chem.rdchem.BondType.DOUBLE,
bt == Chem.rdchem.BondType.TRIPLE,
bt == Chem.rdchem.BondType.AROMATIC,
(bond.GetIsConjugated() if bt is not None else 0),
(bond.IsInRing() if bt is not None else 0)
]
# if args.chiral_features:
# fbond += onek_encoding_unk(int(bond.GetStereo()), list(range(6))) # remove global cis/trans tags
return fbond
def bond_features(bond: Chem.rdchem.Bond,
distance_path: int = None,
distance_3d: int = None) -> List[Union[bool, int, float]]:
"""
Builds a feature vector for a bond.
:param bond: A RDKit bond.
:param distance_path: The topological (path) distance between the atoms in the bond.
Note: This is always 1 if the atoms are actually bonded and >1 for "virtual" edges between non-bonded atoms.
:param distance_3d: The bin index of the 3D distance in THREE_D_DISTANCE_BINS.
:return: A PyTorch tensor containing the bond features.
"""
if bond is None:
fbond = [1] + [0] * (BOND_FDIM - 1)
else:
bt = bond.GetBondType()
fbond = [
0, # bond is not None
bt == Chem.rdchem.BondType.SINGLE,
bt == Chem.rdchem.BondType.DOUBLE,
bt == Chem.rdchem.BondType.TRIPLE,
bt == Chem.rdchem.BondType.AROMATIC,
(bond.GetIsConjugated() if bt is not None else 0),
(bond.IsInRing() if bt is not None else 0)
]
fbond += onek_encoding_unk(int(bond.GetStereo()), list(range(6)))
if distance_path is not None:
fbond += onek_encoding_unk(distance_path, PATH_DISTANCE_BINS)
if distance_3d is not None:
fbond += onek_encoding_unk(distance_3d, THREE_D_DISTANCE_BINS)
return fbond
def getBondFeatures(b: Chem.rdchem.Bond):
return [
b.GetBeginAtomIdx(),
b.GetEndAtomIdx(),
b.GetBondTypeAsDouble(),
int(b.GetIsAromatic()),
int(b.GetIsConjugated())
]
def get_path_bond_feature(bond: Chem.rdchem.Bond):
"""Given a rdkit bond object, returns the bond features for that bond.
When the given input is none, returns a 0-vector"""
if bond is None:
return torch.zeros(N_BOND_FEATS)
else:
bond_type = onek_unk_encoding(bond.GetBondType(), BOND_TYPES)
conj = [int(bond.GetIsConjugated())]
ring = [int(bond.IsInRing())]
return torch.Tensor(bond_type + conj + ring)
def decrease_bond(bond: Chem.rdchem.Bond) -> Optional[Union[list, Chem.rdchem.Bond]]:
"""Remove one single bond from the input bond. Note that you should
first kekulize your molecules and remove non-standard bond.
Args:
bond: a bond.
"""
if bond.GetBondType() == TRIPLE_BOND:
return DOUBLE_BOND
if bond.GetBondType() == DOUBLE_BOND:
return SINGLE_BOND
if bond.GetBondType() == SINGLE_BOND:
return None
return bond
def get_bond_features(bond: Chem.rdchem.Bond) -> List[Union[bool, int, float]]:
bond_type = bond.GetBondType()
features = [
0, # bond is not None
bond_type == Chem.rdchem.BondType.SINGLE,
bond_type == Chem.rdchem.BondType.DOUBLE,
bond_type == Chem.rdchem.BondType.TRIPLE,
bond_type == Chem.rdchem.BondType.AROMATIC,
(bond.GetIsConjugated() if bond_type is not None else 0),
(bond.IsInRing() if bond_type is not None else 0)
]
features += one_hot_vector(int(bond.GetStereo()),
list(range(6)),
extra_category=True)
return features
def get_bond_features(bond:Chem.rdchem.Bond) -> np.ndarray:
"Concats all bond features together and returns numpy array of bools"
potential_bond_types_list = [Chem.rdchem.BondType.SINGLE,
Chem.rdchem.BondType.DOUBLE,
Chem.rdchem.BondType.TRIPLE,
Chem.rdchem.BondType.AROMATIC]
encoded_bond_type_list = one_of_k(bond.GetBondType(),
potential_bond_types_list)
feature_vector = np.array(encoded_bond_type_list +
[bond.GetIsConjugated()] +
[bond.IsInRing()])
return feature_vector
def bond_features(bond: Chem.rdchem.Bond) -> List[Union[bool, int, float]]:
if bond is None:
fbond = [1] + [0] * (BOND_FDIM - 1)
else:
bt = bond.GetBondType()
fbond = [
0, # bond is not None
bt == Chem.rdchem.BondType.SINGLE,
bt == Chem.rdchem.BondType.DOUBLE,
bt == Chem.rdchem.BondType.TRIPLE,
bt == Chem.rdchem.BondType.AROMATIC,
(bond.GetIsConjugated() if bt is not None else 0),
(bond.IsInRing() if bt is not None else 0)
]
fbond += onek_encoding_unk(int(bond.GetStereo()), list(range(6)))
return fbond
def bond_features(bond: Chem.rdchem.Bond) -> List[int]:
"""
Builds a feature vector for a bond.
:param bond: A RDKit bond.
:return: A list containing the bond features.
"""
assert bond is not None
bt = bond.GetBondType()
fbond = [
0, # bond is not None
bt == Chem.rdchem.BondType.SINGLE,
bt == Chem.rdchem.BondType.DOUBLE,
bt == Chem.rdchem.BondType.TRIPLE,
bt == Chem.rdchem.BondType.AROMATIC,
(bond.GetIsConjugated() if bt is not None else 0),
(bond.IsInRing() if bt is not None else 0)
]
fbond += onek_encoding_unk(int(bond.GetStereo()), list(range(6)))
return fbond
def get_bond_features(bond: Chem.rdchem.Bond, bt_only: bool = False):
"""Given an bond object, returns a numpy array of features.
bond can be None, in which case returns default features for a non-bond.
"""
# Bond features are bond type, conjugacy, and ring-membership
if bond is None:
bond_type = onek_unk_encoding(None, BOND_TYPES)
conj = [0]
ring = [0]
else:
bond_type = onek_unk_encoding(bond.GetBondType(), BOND_TYPES)
conj = [int(bond.GetIsConjugated())]
ring = [int(bond.IsInRing())]
if bt_only:
feature_array = bond_type
else:
feature_array = bond_type + conj + ring
return torch.Tensor(feature_array)
def bond_features(bond: Chem.rdchem.Bond) -> List[Union[bool, int, float]]:
"""
Builds a feature vector for a bond.
:param bond: An RDKit bond.
:return: A list containing the bond features.
"""
if bond is None:
fbond = [1] + [0] * (BOND_FDIM - 1)
else:
bt = bond.GetBondType()
fbond = [
0, # bond is not None
bt == Chem.rdchem.BondType.SINGLE,
bt == Chem.rdchem.BondType.DOUBLE,
bt == Chem.rdchem.BondType.TRIPLE,
bt == Chem.rdchem.BondType.AROMATIC,
(bond.GetIsConjugated() if bt is not None else 0),
(bond.IsInRing() if bt is not None else 0)
]
fbond += onek_encoding_unk(int(bond.GetStereo()), list(range(6)))
return fbond
def bond_in_member_rings(bond: Chem.rdchem.Bond):
"""
Show each bond of the molecule is involved in 3, 4, 5, 6, 7, 8 member rings
"""
vector = [
0
] * 7 # If value is not in the [3, 4, 5, 6, 7, 8], then the final element in the vector is 1.
for index, member_ring in enumerate(range(3, 9)):
if bond.IsInRingSize(member_ring):
vector[index] = 1
if vector == [0] * 7:
vector[-1] = 1
return vector
def bond_features(bond: Chem.rdchem.Bond) -> List[Union[bool, int, float]]:
"""
Builds a feature vector for a bond.
:param bond: A RDKit bond.
:return: A list containing the bond features.
"""
if bond is None:
fbond = [1] + [0] * (BOND_FDIM - 1)
else:
bt = bond.GetBondType()
fbond = [
0, # bond is not None
(bond.IsInRingSize(3) if bt is not None else 0),
(bond.IsInRingSize(4) if bt is not None else 0),
(bond.IsInRingSize(5) if bt is not None else 0),
(bond.IsInRingSize(6) if bt is not None else 0),
(bond.IsInRingSize(7) if bt is not None else 0),
(bond.IsInRingSize(8) if bt is not None else 0),
(bond.IsInRingSize(9) if bt is not None else 0),
(bond.IsInRingSize(10) if bt is not None else 0),
]
return fbond