def atom_features(self,
atom: Chem.rdchem.Atom) -> List[Union[bool, int, float]]:
"""
Builds a feature vector for an atom.
:param atom: An RDKit atom.
:param functional_groups: A k-hot vector indicating the functional groups the atom belongs to.
:return: A list containing the atom features.
"""
features = onek_encoding_unk(atom.GetAtomicNum() - 1, ATOM_FEATURES['atomic_num']) + \
onek_encoding_unk(atom.GetTotalDegree(), ATOM_FEATURES['degree']) + \
onek_encoding_unk(atom.GetFormalCharge(), ATOM_FEATURES['formal_charge']) + \
onek_encoding_unk(int(atom.GetChiralTag()), ATOM_FEATURES['chiral_tag']) + \
onek_encoding_unk(int(atom.GetTotalNumHs()), ATOM_FEATURES['num_Hs']) + \
onek_encoding_unk(int(atom.GetHybridization()), ATOM_FEATURES['hybridization']) + \
[1 if atom.GetIsAromatic() else 0] + \
[atom.GetMass() * 0.01]
atom_idx = atom.GetIdx()
features = features + \
onek_encoding_unk(atom.GetImplicitValence(), [0, 1, 2, 3, 4, 5, 6]) + \
[atom_idx in self.hydrogen_acceptor_match] + \
[atom_idx in self.hydrogen_donor_match] + \
[atom_idx in self.acidic_match] + \
[atom_idx in self.basic_match] + \
[self.ring_info.IsAtomInRingOfSize(atom_idx, 3),
self.ring_info.IsAtomInRingOfSize(atom_idx, 4),
self.ring_info.IsAtomInRingOfSize(atom_idx, 5),
self.ring_info.IsAtomInRingOfSize(atom_idx, 6),
self.ring_info.IsAtomInRingOfSize(atom_idx, 7),
self.ring_info.IsAtomInRingOfSize(atom_idx, 8)]
return features
def atom_features(
atom: Chem.rdchem.Atom,
mol: Chem.rdchem.Mol = None,
functional_groups: List[int] = None) -> List[Union[bool, int, float]]:
"""
Builds a feature vector for an atom.
:param atom: An RDKit atom.
:param functional_groups: A k-hot vector indicating the functional groups the atom belongs to.
:return: A list containing the atom features.
"""
features = onek_encoding_unk(atom.GetAtomicNum() - 1, ATOM_FEATURES['atomic_num']) + \
onek_encoding_unk(atom.GetTotalDegree(), ATOM_FEATURES['degree']) + \
onek_encoding_unk(int(atom.GetTotalNumHs()), ATOM_FEATURES['num_Hs']) + \
onek_encoding_unk(int(atom.GetChiralTag()), ATOM_FEATURES['chiral_tag']) + \
[1 if atom.IsInRing() else 0] + \
atom_in_member_rings(atom) + \
[atom.GetMass() * 0.01] # scaled to about the same range as other features
'''features = onek_encoding_unk(atom.GetAtomicNum() - 1, ATOM_FEATURES['atomic_num']) + \
onek_encoding_unk(atom.GetTotalDegree(), ATOM_FEATURES['degree']) + \
onek_encoding_unk(int(atom.GetChiralTag()), ATOM_FEATURES['chiral_tag']) + \
onek_encoding_unk(int(atom.GetTotalNumHs()), ATOM_FEATURES['num_Hs']) + \
onek_encoding_unk(int(atom.GetFormalCharge()), ATOM_FEATURES['formal_charge']) + \
[1 if atom.GetIsAromatic() else 0] + \
[atom.GetMass() * 0.01] # scaled to about the same range as other features'''
if functional_groups is not None:
features += functional_groups
'''if mol is not None:
#features += is_zwitterion(mol)
features += is_hetroatomic_cyclic(mol)'''
return features
def atom_features(atom: Chem.rdchem.Atom,
args) -> List[Union[bool, int, float]]:
"""
Builds a feature vector for an atom.
:param atom: An RDKit atom.
:param functional_groups: A k-hot vector indicating the functional groups the atom belongs to.
:return: A list containing the atom features.
"""
features = onek_encoding_unk(atom.GetSymbol(), ATOM_FEATURES['atomic_num']) + \
onek_encoding_unk(atom.GetTotalDegree(), ATOM_FEATURES['degree']) + \
onek_encoding_unk(atom.GetFormalCharge(), ATOM_FEATURES['formal_charge'])
features += onek_encoding_unk(int(atom.GetTotalNumHs()), ATOM_FEATURES['num_Hs']) + \
onek_encoding_unk(int(atom.GetHybridization()), ATOM_FEATURES['hybridization']) + \
[1 if atom.GetIsAromatic() else 0] + \
[atom.GetMass() * 0.01] # scaled to about the same range as other features
if args.chiral_features:
features += onek_encoding_unk(int(atom.GetChiralTag()),
ATOM_FEATURES['chiral_tag'])
if args.global_chiral_features:
if atom.HasProp('_CIPCode'):
features += onek_encoding_unk(atom.GetProp('_CIPCode'),
ATOM_FEATURES['global_chiral_tag'])
else:
features += onek_encoding_unk(None,
ATOM_FEATURES['global_chiral_tag'])
return features
def atom_features(atom: Chem.rdchem.Atom,
functional_groups: List[int] = None) \
-> List[Union[bool, int, float]]:
'''
Builds a feature vector for an atom.
:param atom: An RDKit atom.
:param functional_groups: A k-hot vector indicating the functional groups
the atom belongs to.
:return: A list containing the atom features.
'''
features = onek_encoding_unk(atom.GetAtomicNum() - 1,
ATOM_FEATURES['atomic_num']) + \
onek_encoding_unk(atom.GetTotalDegree(),
ATOM_FEATURES['degree']) + \
onek_encoding_unk(atom.GetFormalCharge(),
ATOM_FEATURES['formal_charge']) + \
onek_encoding_unk(int(atom.GetChiralTag()),
ATOM_FEATURES['chiral_tag']) + \
onek_encoding_unk(int(atom.GetTotalNumHs()),
ATOM_FEATURES['num_Hs']) + \
onek_encoding_unk(int(atom.GetHybridization()),
ATOM_FEATURES['hybridization']) + \
[1 if atom.GetIsAromatic() else 0] + \
[atom.GetMass() * 0.01] # scaled to about same range as other features
if functional_groups:
features += functional_groups
return features
def atom_features(
atom: Chem.rdchem.Atom,
functional_groups: List[int] = None) -> List[Union[bool, int, float]]:
"""
Builds a feature vector for an atom.
:param atom: An RDKit atom.
:param functional_groups: A k-hot vector indicating the functional groups the atom belongs to.
:return: A list containing the atom features.
"""
features = (
onek_encoding_unk(atom.GetAtomicNum() - 1, ATOM_FEATURES["atomic_num"])
+ onek_encoding_unk(atom.GetTotalDegree(), ATOM_FEATURES["degree"]) +
onek_encoding_unk(atom.GetFormalCharge(),
ATOM_FEATURES["formal_charge"]) +
onek_encoding_unk(int(atom.GetChiralTag()),
ATOM_FEATURES["chiral_tag"]) +
onek_encoding_unk(int(atom.GetTotalNumHs()), ATOM_FEATURES["num_Hs"]) +
onek_encoding_unk(int(atom.GetHybridization()),
ATOM_FEATURES["hybridization"]) +
[1 if atom.GetIsAromatic() else 0] + [atom.GetMass() * 0.01]
) # scaled to about the same range as other features
if functional_groups is not None:
features += functional_groups
return features
def atom_features(
atom: Chem.rdchem.Atom,
functional_groups: List[int] = None) -> List[Union[bool, int, float]]:
"""
Builds a feature vector for an atom.
:param atom: An RDKit atom.
:param functional_groups: A k-hot vector indicating the functional groups the atom belongs to.
:return: A list containing the atom features.
"""
features = onek_encoding_unk(atom.GetAtomicNum() - 1, ATOM_FEATURES['atomic_num']) + \
onek_encoding_unk(atom.GetTotalDegree(), ATOM_FEATURES['degree']) + \
onek_encoding_unk(int(atom.GetTotalNumHs()), ATOM_FEATURES['num_Hs']) + \
[atom.GetMass() * 0.01] # scaled to about the same range as other features
features += [
atom.IsInRingSize(3),
atom.IsInRingSize(4),
atom.IsInRingSize(5),
atom.IsInRingSize(6),
atom.IsInRingSize(7),
atom.IsInRingSize(8),
atom.IsInRingSize(9),
atom.IsInRingSize(10),
]
if functional_groups is not None:
features += functional_groups
return features
def atom_features(atom: Chem.rdchem.Atom, functional_groups: List[int] = None) -> List[Union[bool, int, float]]:
features = onek_encoding_unk(atom.GetAtomicNum() - 1, ATOM_FEATURES['atomic_num']) + \
onek_encoding_unk(atom.GetTotalDegree(), ATOM_FEATURES['degree']) + \
onek_encoding_unk(atom.GetFormalCharge(), ATOM_FEATURES['formal_charge']) + \
onek_encoding_unk(int(atom.GetChiralTag()), ATOM_FEATURES['chiral_tag']) + \
onek_encoding_unk(int(atom.GetTotalNumHs()), ATOM_FEATURES['num_Hs']) + \
onek_encoding_unk(int(atom.GetHybridization()), ATOM_FEATURES['hybridization']) + \
[1 if atom.GetIsAromatic() else 0] + \
[atom.GetMass() * 0.01] # scaled to about the same range as other features
if functional_groups is not None:
features += functional_groups
return features
def atom_features(atom: Chem.rdchem.Atom) -> List[Union[bool, int, float]]:
"""
Builds a feature vector for an atom.
:param atom: An RDKit atom.
:return: A list containing the atom features.
"""
features = onek_encoding_unk(atom.GetSymbol(), ATOM_FEATURES['atomic_num']) + \
[1 if atom.GetIsAromatic() else 0] + \
onek_encoding_unk(atom.GetTotalDegree(), ATOM_FEATURES['degree']) + \
onek_encoding_unk(atom.GetFormalCharge(), ATOM_FEATURES['formal_charge']) + \
onek_encoding_unk(int(atom.GetTotalNumHs()), ATOM_FEATURES['num_Hs']) + \
[atom.GetMass() * 0.01] # scaled to about the same range as other features
return features
def get_atom_features(atom:Chem.rdchem.Atom) -> np.ndarray:
"Concats all atom features together and returns numpy array of bools"
# elements from Duvenaud's original code. Note the absense of H(optional)
potential_atoms_list = ['C', 'N', 'O', 'S', 'F', 'Si', 'P', 'Cl', 'Br',
'Mg', 'Na', 'Ca', 'Fe', 'As', 'Al', 'I', 'B', 'V',
'K', 'Tl', 'Yb', 'Sb', 'Sn', 'Ag', 'Pd', 'Co', 'Se',
'Ti', 'Zn', 'H', 'Li', 'Ge', 'Cu', 'Au', 'Ni', 'Cd',
'In', 'Mn', 'Zr', 'Cr', 'Pt', 'Hg', 'Pb', 'Unknown']
encoded_element_list = one_of_k(atom.GetSymbol(), potential_atoms_list)
encoded_degree_list = one_of_k(atom.GetDegree(), [0, 1, 2, 3, 4, 5])
encoded_num_hs_list = one_of_k(atom.GetTotalNumHs(), [0, 1, 2, 3, 4])
encoded_fc_list = one_of_k(atom.GetFormalCharge(), [-1,-2,1,2,0])
encoded_implicit_valence_list = one_of_k(atom.GetImplicitValence(),
[0, 1, 2, 3, 4, 5])
feature_vector = np.array(encoded_element_list + encoded_degree_list +
encoded_num_hs_list + encoded_implicit_valence_list +
encoded_fc_list + [atom.GetIsAromatic()])
return feature_vector
def get_atom_features(atom: Chem.rdchem.Atom, hydrogen_acceptor_match,
hydrogen_donor_match, acidic_match, basic_match,
ring_info) -> List[Union[bool, int, float]]:
features = []
features += one_hot_vector(atom.GetAtomicNum() - 1,
[i for i in range(100)],
extra_category=True)
features += one_hot_vector(atom.GetTotalDegree(), [0, 1, 2, 3, 4, 5],
extra_category=True)
features += one_hot_vector(atom.GetFormalCharge(), [-1, -2, 1, 2, 0],
extra_category=True)
features += one_hot_vector(int(atom.GetChiralTag()), [0, 1, 2, 3],
extra_category=True)
features += one_hot_vector(int(atom.GetTotalNumHs()), [0, 1, 2, 3, 4],
extra_category=True)
features += one_hot_vector(int(atom.GetHybridization()), [2, 3, 4, 5, 6],
extra_category=True)
features += [1 if atom.GetIsAromatic() else 0]
features += [atom.GetMass() * 0.01]
features += one_hot_vector(atom.GetImplicitValence(),
[0, 1, 2, 3, 4, 5, 6],
extra_category=True)
atom_idx = atom.GetIdx()
features += [atom_idx in hydrogen_acceptor_match]
features += [atom_idx in hydrogen_donor_match]
features += [atom_idx in acidic_match]
features += [atom_idx in basic_match]
features += [
ring_info.IsAtomInRingOfSize(atom_idx, 3),
ring_info.IsAtomInRingOfSize(atom_idx, 4),
ring_info.IsAtomInRingOfSize(atom_idx, 5),
ring_info.IsAtomInRingOfSize(atom_idx, 6),
ring_info.IsAtomInRingOfSize(atom_idx, 7),
ring_info.IsAtomInRingOfSize(atom_idx, 8)
]
return features
