def _get_valence_difference(self, atom: Chem.Atom) -> int:
pt = Chem.GetPeriodicTable()
valence = self._get_atom_valence(atom)
if self._valence_mode == 'max':
maxv = max(pt.GetValenceList(atom.GetAtomicNum()))
return valence - maxv
else:
d = pt.GetDefaultValence(atom.GetAtomicNum())
return valence - d
def from_rdkit(cls, rd_atom: Chem.Atom) -> "Atom":
"""
Build a QUBEKit atom from an rdkit atom instance.
"""
atomic_number = rd_atom.GetAtomicNum()
index = rd_atom.GetIdx()
formal_charge = rd_atom.GetFormalCharge()
aromatic = rd_atom.GetIsAromatic()
bonds = [a.GetIdx() for a in rd_atom.GetNeighbors()]
# check for names in the normal places pdb, mol2 and mol
if rd_atom.HasProp("_Name"):
name = rd_atom.GetProp("_Name")
elif rd_atom.HasProp("_TriposAtomName"):
name = rd_atom.GetProp("_TriposAtomName")
else:
try:
name = rd_atom.GetMonomerInfo().GetName().strip()
except AttributeError:
name = None
# stereochem
if rd_atom.HasProp("_CIPCode"):
stereo_code = rd_atom.GetProp("_CIPCode")
else:
stereo_code = None
return cls(
atomic_number=atomic_number,
atom_index=index,
atom_name=name,
formal_charge=formal_charge,
aromatic=aromatic,
stereochemistry=stereo_code,
bonds=bonds,
)
def assess_atom(atom: Chem.Atom, bt: Chem.BondType) -> Tuple[bool, Chem.BondType]:
if atom.GetAtomicNum() > 8:
return True, bt
elif len(atom.GetNeighbors()) <= 2 and atom.GetIsAromatic():
return True, Chem.BondType.SINGLE
elif len(atom_i.GetNeighbors()) <= 3 and not atom.GetIsAromatic():
return True, bt
else:
return False, bt # too bonded already!
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 _AtomHallKierDeltas(atom: Chem.Atom, skipHs: bool = False) -> List[float]:
"""Calculate Kier & Hall atomic valence delta-values for molecular connectivity.
From Kier L. and Hall L., J. Pharm. Sci. (1983), 72(10),1170-1173.
"""
global periodicTable
res = []
n = atom.GetAtomicNum()
if n > 1:
nV = periodicTable.GetNOuterElecs(n)
nHs = atom.GetTotalNumHs()
if n < 10:
res.append(float(nV - nHs))
else:
res.append(float(nV - nHs) / float(n - nV - 1))
elif not skipHs:
res.append(0.0)
return res
def assess_atom(atom: Chem.Atom, bt: Chem.BondType) -> Tuple[bool, Chem.BondType]:
"""
True means add, False means delete
:param atom:
:param bt:
:return:
"""
n_neigh = sum([self._is_count_valid(neigh) for neigh in atom.GetNeighbors()])
if atom.GetAtomicNum() > 8:
return True, bt
elif atom.HasProp('DELETE'): # if it is to be deleted it should be fine.
return True, bt
elif n_neigh <= 2 and atom.GetIsAromatic():
return True, Chem.BondType.SINGLE
elif n_neigh <= 3 and not atom.GetIsAromatic():
return True, bt
else:
return False, bt # too bonded already!
def atom_feature(atom: Atom) -> Tuple[torch.Tensor, int]:
'''
Extract atom feature vector.
Returns: (feature_vec, feature_dim)
Features:
# item # dim
atomic number 25
exp-valence 7
imp-valence 4
hybridization 7
Hs 5
degree 6
formal charge 6
in ring 1
aromatic 1
mass / 100 1
(sum) 63
'''
index = torch.tensor([
ATOM_MAP[atom.GetAtomicNum()],
atom.GetExplicitValence(),
atom.GetImplicitValence(),
HYBRID_MAP[atom.GetHybridization()],
atom.GetTotalNumHs(),
atom.GetDegree(),
atom.GetFormalCharge() + 2, # -2 ~ 3
int(atom.IsInRing()),
int(atom.GetIsAromatic())
]) + OFFSET
vec = torch.zeros(ATOM_FDIM)
vec[index] = 1.0
vec[-1] = atom.GetMass() / 100
return vec, ATOM_FDIM
def _assess_atom_for_possible_bonding(self, atom: Chem.Atom,
bt: Chem.BondType) -> bool:
"""
Method for add_bond_if_possible
True means add, False means delete
:param atom:
:param bt:
:return:
"""
n_neigh = sum(
[self._is_count_valid(neigh) for neigh in atom.GetNeighbors()])
if atom.GetAtomicNum() > 8:
return True
elif atom.HasProp(
'DELETE'): # if it is to be deleted it should be fine.
return True
elif n_neigh <= 2 and atom.GetIsAromatic():
return True, Chem.BondType.SINGLE
elif n_neigh <= 3 and not atom.GetIsAromatic():
return True
else:
return False # too bonded already!
def atomic_number(atom: Atom) -> int:
"""Atomic number (int).
"""
return atom.GetAtomicNum()