def _parse_atom(self, atom: Chem.Atom) -> None:
if atom.GetSymbol() == '*':
neighbor = atom.GetNeighbors()[0]
n_name = self._get_pdb_atomname(neighbor)
self.CONNECT.append([n_name, len(self.CONNECT) + 1, 'CONNECT'])
else:
d = self._get_atom_descriptors(atom)
self.ATOM.append(d)
def atom_type_CO(atom: Chem.Atom) -> List[bool]:
"""Returns a one-hot list of length 2 for whether `atom` is a carbon or oxygen atom.
"""
anum = atom.GetSymbol()
atom_feats = [
anum == 'C',
anum == 'O',
]
return atom_feats
def atom_features(atom: Chem.Atom):
return np.array(
encoding_onehot_unk(atom.GetSymbol(), [
'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'
]) + encoding_onehot(atom.GetDegree(), [0, 1, 2, 3, 4, 5]) +
encoding_onehot_unk(atom.GetTotalNumHs(), [0, 1, 2, 3, 4]) +
encoding_onehot_unk(atom.GetImplicitValence(), [0, 1, 2, 3, 4, 5]) +
[atom.GetIsAromatic()])
def is_sp2(atom: Chem.Atom) -> bool:
N_neigh = len(atom.GetBonds())
symbol = atom.GetSymbol()
if symbol == 'H':
return False
elif symbol == 'N' and N_neigh < 3:
return True
elif symbol == 'C' and N_neigh < 4:
return True
elif symbol == 'O' and N_neigh < 2:
return True
else:
return False
def get_atom_type(self, atom: Chem.Atom) -> int:
"""
Get the atom type (represented as the index in self.atom_types) of the
given atom `atom`
Args:
atom (Chem.Atom):
The input atom
Returns:
int:
The atom type as int
"""
atom_symbol = atom.GetSymbol()
atom_charge = atom.GetFormalCharge()
atom_hs = atom.GetNumExplicitHs()
return self.atom_types.index((atom_symbol, atom_charge, atom_hs))
def atom_to_feat(self, atm: Chem.Atom, owning_mol: Chem.Mol, idx):
# nb the func GetOwningMol could not be used for mol as would return different object each time
this_atms_idx = atm.GetIdx()
assert idx == this_atms_idx
feat = torch.zeros(len(self), dtype=torch.float32)
# One hot encoding of element
try:
feat[self.atms_to_idx[atm.GetSymbol()]] = 1.
except KeyError as ex:
warnings.warn(f"Ignoring the symbol {atm.GetSymbol()}")
idx_up_to = self.number_atom_options
# Atomic Number
feat[idx_up_to] = float(atm.GetAtomicNum())
idx_up_to += 1
# Acceptor/donor
acceptor_ids, donor_ids = self.get_acceptor_and_donor_ids(owning_mol)
# Acceptor
feat[idx_up_to] = float(this_atms_idx in acceptor_ids)
idx_up_to += 1
# Donor
feat[idx_up_to] = float(this_atms_idx in donor_ids)
idx_up_to += 1
# Hybridization
hyb_idx = self.hybridization(atm.GetHybridization())
if hyb_idx is not None:
feat[idx_up_to + hyb_idx] = 1.
idx_up_to += self.number_hyb_options
# Aromatic
feat[idx_up_to] = float(atm.GetIsAromatic())
idx_up_to += 1
# Number of Hydrogens
feat[idx_up_to] = float(atm.GetNumImplicitHs())
idx_up_to += 1
return feat
def _parse_atom(self, atom: Chem.Atom) -> None:
if atom.GetSymbol() == '*':
neighbor = atom.GetNeighbors()[0]
n_name = self._get_PDBInfo_atomname(neighbor)
if self.is_aminoacid() and neighbor.GetSymbol() == 'N':
# atom_name, index, connect_type, connect_name
self.CONNECT.append([n_name, 1, 'LOWER_CONNECT', 'LOWER'])
elif self.is_aminoacid() and neighbor.GetSymbol() == 'C':
# atom_name, index, connect_type, connect_name
self.CONNECT.append([n_name, 2, 'UPPER_CONNECT', 'UPPER'])
elif self.is_aminoacid():
i = max(3, len(self.CONNECT) + 1)
self.CONNECT.append([n_name, i, 'CONNECT'])
else:
self.CONNECT.append([n_name, len(self.CONNECT) + 1, 'CONNECT'])
else:
d = self._get_atom_descriptors(atom)
self.ATOM.append(d)
def _parse_atom(self, atom: Chem.Atom) -> None:
self.log.debug(
f'Parsing {atom.GetSymbol()} at position {atom.GetIdx()}')
if atom.GetSymbol() == '*':
neighbor = atom.GetNeighbors()[0]
n_name = self._get_PDBInfo_atomname(neighbor)
if self.is_aminoacid() and neighbor.GetSymbol() == 'N':
# atom_name, index, connect_type, connect_name
self.CONNECT.append([n_name, 1, 'LOWER_CONNECT', 'LOWER'])
elif self.is_aminoacid() and neighbor.GetSymbol() == 'C':
# atom_name, index, connect_type, connect_name
self.CONNECT.append([n_name, 2, 'UPPER_CONNECT', 'UPPER'])
elif self.is_aminoacid():
i = max(3, len(self.CONNECT) + 1)
self.CONNECT.append([n_name, i, 'CONNECT'])
else:
self.CONNECT.append([n_name, len(self.CONNECT) + 1, 'CONNECT'])
else:
d = self._get_atom_descriptors(
atom) # dict of 'name', 'rtype': 'mtype', 'partial'
self.ATOM.append(d)
formal = atom.GetFormalCharge()
if formal != 0:
self.CHARGE.append([d['name'], formal])
def has_hybridization(self, atom: Atom):
symbol = atom.GetSymbol()
return symbol in self.ATOMS_WITH_HYBRIDIZATION
def _copy_atom(atom: Chem.Atom) -> Chem.Atom:
new_atom = Chem.Atom(atom.GetSymbol())
new_atom.SetFormalCharge(atom.GetFormalCharge())
new_atom.SetNumRadicalElectrons(atom.GetNumRadicalElectrons())
return new_atom
def is_hydrogen(self, atom: Atom):
return atom.GetSymbol() == "H"
def symbol(atom: Atom) -> str:
"""Atomic symbol (string).
"""
return atom.GetSymbol()