def graph_from_smiles(smiles):
graph = MolGraph()
mol = MolFromSmiles(smiles)
# mol = MolFromSmiles(smiles, sanitize=False)
# mol.UpdatePropertyCache(strict=False)
# Chem.SanitizeMol(mol, Chem.SanitizeFlags.SANITIZE_FINDRADICALS | Chem.SanitizeFlags.SANITIZE_KEKULIZE | Chem.SanitizeFlags.SANITIZE_SETAROMATICITY | Chem.SanitizeFlags.SANITIZE_SETCONJUGATION | Chem.SanitizeFlags.SANITIZE_SETHYBRIDIZATION | Chem.SanitizeFlags.SANITIZE_SYMMRINGS, catchErrors=True)
if not mol:
raise ValueError("Could not parse SMILES string:", smiles)
atoms_by_rd_idx = {}
for atom in mol.GetAtoms():
new_atom_node = graph.new_node('atom',
features=atom_features(atom),
rdkit_ix=atom.GetIdx())
atoms_by_rd_idx[atom.GetIdx()] = new_atom_node
for bond in mol.GetBonds():
atom1_node = atoms_by_rd_idx[bond.GetBeginAtom().GetIdx()]
atom2_node = atoms_by_rd_idx[bond.GetEndAtom().GetIdx()]
new_bond_node = graph.new_node('bond', features=bond_features(bond))
new_bond_node.add_neighbors((atom1_node, atom2_node))
atom1_node.add_neighbors((atom2_node, ))
mol_node = graph.new_node('molecule')
mol_node.add_neighbors(graph.nodes['atom'])
return graph
def graph_from_smiles(smiles):
graph = MolGraph()
check = np.array(1)
if type(check) is not type(smiles):
str_smiles = smiles._data[0][0]
else:
str_smiles = smiles[0]
mol = MolFromSmiles(str_smiles)
if not mol:
raise ValueError("Could not parse SMILES string:", str_smiles)
atoms_by_rd_idx = {}
for atom in mol.GetAtoms():
new_atom_node = graph.new_node('atom',
features=atom_features(atom),
rdkit_ix=atom.GetIdx())
atoms_by_rd_idx[atom.GetIdx()] = new_atom_node
for bond in mol.GetBonds():
atom1_node = atoms_by_rd_idx[bond.GetBeginAtom().GetIdx()]
atom2_node = atoms_by_rd_idx[bond.GetEndAtom().GetIdx()]
new_bond_node = graph.new_node('bond', features=bond_features(bond))
new_bond_node.add_neighbors((atom1_node, atom2_node))
atom1_node.add_neighbors((atom2_node, ))
mol_node = graph.new_node('molecule')
mol_node.add_neighbors(graph.nodes['atom'])
return graph
def graph_from_smiles(smiles):
graph = MolGraph()
mol = MolFromSmiles(smiles)
if not mol:
raise ValueError("Could not parse SMILES string:", smiles)
atoms_by_rd_idx = {}
for atom in mol.GetAtoms():
new_atom_node = graph.new_node("atom", features=atom_features(atom), rdkit_ix=atom.GetIdx())
atoms_by_rd_idx[atom.GetIdx()] = new_atom_node
for bond in mol.GetBonds():
atom1_node = atoms_by_rd_idx[bond.GetBeginAtom().GetIdx()]
atom2_node = atoms_by_rd_idx[bond.GetEndAtom().GetIdx()]
new_bond_node = graph.new_node("bond", features=bond_features(bond))
new_bond_node.add_neighbors((atom1_node, atom2_node))
atom1_node.add_neighbors((atom2_node,))
mol_node = graph.new_node("molecule")
mol_node.add_neighbors(graph.nodes["atom"])
return graph
def graph_from_amino_acids(sequence):
graph = MolGraph()
mol = MolFromSequence(sequence)
if not mol:
raise ValueError("Could not parse input string:", sequence)
atoms_by_rd_idx = {}
for atom in mol.GetAtoms():
new_atom_node = graph.new_node('atom', features=atom_features(atom), rdkit_ix=atom.GetIdx())
atoms_by_rd_idx[atom.GetIdx()] = new_atom_node
for bond in mol.GetBonds():
atom1_node = atoms_by_rd_idx[bond.GetBeginAtom().GetIdx()]
atom2_node = atoms_by_rd_idx[bond.GetEndAtom().GetIdx()]
new_bond_node = graph.new_node('bond', features=bond_features(bond))
new_bond_node.add_neighbors((atom1_node, atom2_node))
atom1_node.add_neighbors((atom2_node,))
mol_node = graph.new_node('molecule')
mol_node.add_neighbors(graph.nodes['atom'])
return graph
def convertDataToGraph(self, data):
chemData = []
for row in data:
mol = row['mol']
atoms = mol.GetAtoms()
graphList = []
atomsFeatures = np.zeros((len(atoms), self.featureSize))
for atom in atoms:
atomFeature = atom_features(atom)
bondFeature = np.zeros(6)
neighborList = []
bonds = atom.GetBonds()
for bond in bonds:
neighbor = bond.GetBeginAtom()
if (neighbor.GetIdx() == atom.GetIdx()):
neighbor = bond.GetEndAtom()
neighborList += [neighbor.GetIdx()]
bondFeature += bond_features(bond)
features = np.concatenate((atomFeature, bondFeature), axis=0)
atomsFeatures[atom.GetIdx()] = features
graphList += [{'idx': atom.GetIdx(), 'neighbor': np.array(neighborList)}]
chemData += [[float(row['pce']), {'graphList': graphList, 'atomsFeatures': atomsFeatures}]]
chemData = np.array(chemData)
return chemData
def tensorize_smiles_job(smiles, max_degree=5, max_atoms=None):
'''Takes a list of smiles and turns the graphs in tensor representation.
# Arguments:
smiles: a list (or iterable) of smiles representations
max_atoms: the maximum number of atoms per molecule (to which all
molecules will be padded), use `None` for auto
max_degree: max_atoms: the maximum number of neigbour per atom that each
molecule can have (to which all molecules will be padded), use `None`
for auto
**NOTE**: It is not recommended to set max_degree to `None`/auto when
using `NeuralGraph` layers. Max_degree determines the number of
trainable parameters and is essentially a hyperparameter.
While models can be rebuilt using different `max_atoms`, they cannot
be rebuild for different values of `max_degree`, as the architecture
will be different.
For organic molecules `max_degree=5` is a good value (Duvenaud et. al, 2015)
# Returns:
atoms: np.array, An atom feature np.array of size `(molecules, max_atoms, atom_features)`
bonds: np.array, A bonds np.array of size `(molecules, max_atoms, max_neighbours)`
edges: np.array, A connectivity array of size `(molecules, max_atoms, max_neighbours, bond_features)`
TODO:
* Arguments for sparse vector encoding
'''
# import sizes
n = len(smiles)
n_atom_features = features.num_atom_features()
n_bond_features = features.num_bond_features()
# preallocate atom tensor with 0's and bond tensor with -1 (because of 0 index)
# If max_degree or max_atoms is set to None (auto), initialise dim as small
# as possible (1)
atom_tensor = np.zeros((n, max_atoms or 1, n_atom_features),
dtype=np.float32)
bond_tensor = np.zeros(
(n, max_atoms or 1, max_degree or 1, n_bond_features),
dtype=np.float32)
edge_tensor = -np.ones((n, max_atoms or 1, max_degree or 1), dtype=np.int8)
for mol_ix, s in enumerate(smiles):
#load mol, atoms and bonds
sio = sys.stderr = StringIO()
mol = Chem.MolFromSmiles(s)
assert mol is not None, 'Could not parse smiles {}, error: {}'.format(
s, sio.getvalue())
atoms = mol.GetAtoms()
bonds = mol.GetBonds()
# If max_atoms is exceeded, resize if max_atoms=None (auto), else raise
if len(atoms) > atom_tensor.shape[1]:
assert max_atoms is None, 'too many atoms ({0}) in molecule: {1}'.format(
len(atoms), s)
atom_tensor = padaxis(atom_tensor, len(atoms), axis=1)
bond_tensor = padaxis(bond_tensor, len(atoms), axis=1)
edge_tensor = padaxis(edge_tensor,
len(atoms),
axis=1,
pad_value=-1)
rdkit_ix_lookup = {}
connectivity_mat = {}
for atom_ix, atom in enumerate(atoms):
# write atom features
atom_tensor[mol_ix,
atom_ix, :n_atom_features] = features.atom_features(
atom)
# store entry in idx
rdkit_ix_lookup[atom.GetIdx()] = atom_ix
# preallocate array with neighbour lists (indexed by atom)
connectivity_mat = [[] for _ in atoms]
for bond in bonds:
# lookup atom ids
a1_ix = rdkit_ix_lookup[bond.GetBeginAtom().GetIdx()]
a2_ix = rdkit_ix_lookup[bond.GetEndAtom().GetIdx()]
# lookup how many neighbours are encoded yet
a1_neigh = len(connectivity_mat[a1_ix])
a2_neigh = len(connectivity_mat[a2_ix])
# If max_degree is exceeded, resize if max_degree=None (auto), else raise
new_degree = max(a1_neigh, a2_neigh) + 1
if new_degree > bond_tensor.shape[2]:
assert max_degree is None, 'too many neighours ({0}) in molecule: {1}'.format(
new_degree, s)
bond_tensor = padaxis(bond_tensor, new_degree, axis=2)
edge_tensor = padaxis(edge_tensor,
new_degree,
axis=2,
pad_value=-1)
# store bond features
bond_features = np.array(features.bond_features(bond), dtype=int)
bond_tensor[mol_ix, a1_ix, a1_neigh, :] = bond_features
bond_tensor[mol_ix, a2_ix, a2_neigh, :] = bond_features
#add to connectivity matrix
connectivity_mat[a1_ix].append(a2_ix)
connectivity_mat[a2_ix].append(a1_ix)
#store connectivity matrix
for a1_ix, neighbours in enumerate(connectivity_mat):
degree = len(neighbours)
edge_tensor[mol_ix, a1_ix, :degree] = neighbours
return atom_tensor, bond_tensor, edge_tensor