def ConstructMolecularGraph(molecule):
'''Constructs molecular graph from rdkit's molecule object '''
g = OrderedDict({})
h = OrderedDict({})
molecule = Chem.MolFromSmiles(molecule)
stereo = Chem.FindMolChiralCenters(molecule)
features = rdDesc.GetFeatureInvariants(molecule)
chiral_centers = [0] * molecule.GetNumAtoms()
for i in stereo:
chiral_centers[i[0]] = i[1]
for i in range(0, molecule.GetNumAtoms()):
atom_i = molecule.GetAtomWithIdx(i)
h[i] = torch.FloatTensor(
atom_features(atom_i, chiral_centers[i],
features[i]).astype(np.float64)).to(device)
for j in range(0, molecule.GetNumAtoms()):
e_ij = molecule.GetBondBetweenAtoms(i, j)
if e_ij != None:
e_ij = map(lambda x: 1 if x == True else 0,
bond_features(e_ij).tolist()) # ADDED edge feat
e_ij = torch.FloatTensor(list(e_ij)).to(device)
atom_j = molecule.GetAtomWithIdx(j)
if i not in g:
g[i] = []
g[i].append((e_ij, j))
return g, h
def calculateMol(self, m, smiles, internalParsing=False):
return list(
rd.GetMorganFingerprintAsBitVect(
m,
radius=self.radius,
nBits=self.nbits,
invariants=rd.GetFeatureInvariants(m)))
def calculateMol(self, m, smiles, internalParsing=False):
counts = list(
rd.GetHashedMorganFingerprint(
m,
radius=self.radius,
nBits=self.nbits,
invariants=rd.GetFeatureInvariants(m)))
counts = [clip(x, smiles) for x in counts]
return counts
def get_graph_from_smile(molecule_smile):
"""
Method that constructs a molecular graph with nodes being the atoms
and bonds being the edges.
:param molecule_smile: SMILE sequence
:return: DGL graph object, Node features and Edge features
"""
G = DGLGraph()
molecule = Chem.MolFromSmiles(molecule_smile)
features = rdDesc.GetFeatureInvariants(molecule)
stereo = Chem.FindMolChiralCenters(molecule)
chiral_centers = [0] * molecule.GetNumAtoms()
for i in stereo:
chiral_centers[i[0]] = i[1]
G.add_nodes(molecule.GetNumAtoms())
node_features = []
edge_features = []
for i in range(molecule.GetNumAtoms()):
atom_i = molecule.GetAtomWithIdx(i)
atom_i_features = get_atom_features(atom_i, chiral_centers[i], features[i])
node_features.append(atom_i_features)
for j in range(molecule.GetNumAtoms()):
bond_ij = molecule.GetBondBetweenAtoms(i, j)
if bond_ij is not None:
G.add_edge(i, j)
bond_features_ij = get_bond_features(bond_ij)
edge_features.append(bond_features_ij)
G.ndata['x'] = np.array(node_features)
G.edata['w'] = np.array(edge_features)
return G
def testMorganFingerprints(self):
mol = Chem.MolFromSmiles('CC(F)(Cl)C(F)(Cl)C')
fp = rdMD.GetMorganFingerprint(mol, 0)
self.assertTrue(len(fp.GetNonzeroElements()) == 4)
mol = Chem.MolFromSmiles('CC')
fp = rdMD.GetMorganFingerprint(mol, 0)
self.assertTrue(len(fp.GetNonzeroElements()) == 1)
self.assertTrue(list(fp.GetNonzeroElements().values())[0] == 2)
fp = rdMD.GetMorganFingerprint(mol, 0, useCounts=False)
self.assertTrue(len(fp.GetNonzeroElements()) == 1)
self.assertTrue(list(fp.GetNonzeroElements().values())[0] == 1)
mol = Chem.MolFromSmiles('CC(F)(Cl)C(F)(Cl)C')
fp = rdMD.GetHashedMorganFingerprint(mol, 0)
self.assertTrue(len(fp.GetNonzeroElements()) == 4)
fp = rdMD.GetMorganFingerprint(mol, 1)
self.assertTrue(len(fp.GetNonzeroElements()) == 8)
fp = rdMD.GetHashedMorganFingerprint(mol, 1)
self.assertTrue(len(fp.GetNonzeroElements()) == 8)
fp = rdMD.GetMorganFingerprint(mol, 2)
self.assertTrue(len(fp.GetNonzeroElements()) == 9)
mol = Chem.MolFromSmiles('CC(F)(Cl)[C@](F)(Cl)C')
fp = rdMD.GetMorganFingerprint(mol, 0)
self.assertTrue(len(fp.GetNonzeroElements()) == 4)
fp = rdMD.GetMorganFingerprint(mol, 1)
self.assertTrue(len(fp.GetNonzeroElements()) == 8)
fp = rdMD.GetMorganFingerprint(mol, 2)
self.assertTrue(len(fp.GetNonzeroElements()) == 9)
fp = rdMD.GetMorganFingerprint(mol, 0, useChirality=True)
self.assertTrue(len(fp.GetNonzeroElements()) == 4)
fp = rdMD.GetMorganFingerprint(mol, 1, useChirality=True)
self.assertTrue(len(fp.GetNonzeroElements()) == 9)
fp = rdMD.GetMorganFingerprint(mol, 2, useChirality=True)
self.assertTrue(len(fp.GetNonzeroElements()) == 10)
mol = Chem.MolFromSmiles('CCCCC')
fp = rdMD.GetMorganFingerprint(mol, 0, fromAtoms=(0, ))
self.assertTrue(len(fp.GetNonzeroElements()) == 1)
mol = Chem.MolFromSmiles('CC1CC1')
vs1 = rdMD.GetConnectivityInvariants(mol)
self.assertEqual(len(vs1), mol.GetNumAtoms())
fp1 = rdMD.GetMorganFingerprint(mol, 2, invariants=vs1)
fp2 = rdMD.GetMorganFingerprint(mol, 2)
self.assertEqual(fp1, fp2)
vs2 = rdMD.GetConnectivityInvariants(mol, False)
self.assertEqual(len(vs2), mol.GetNumAtoms())
self.assertNotEqual(vs1, vs2)
fp1 = rdMD.GetMorganFingerprint(mol, 2, invariants=vs2)
self.assertNotEqual(fp1, fp2)
mol = Chem.MolFromSmiles('Cc1ccccc1')
vs1 = rdMD.GetFeatureInvariants(mol)
self.assertEqual(len(vs1), mol.GetNumAtoms())
self.assertEqual(vs1[0], 0)
self.assertNotEqual(vs1[1], 0)
self.assertEqual(vs1[1], vs1[2])
self.assertEqual(vs1[1], vs1[3])
self.assertEqual(vs1[1], vs1[4])
mol = Chem.MolFromSmiles('FCCCl')
vs1 = rdMD.GetFeatureInvariants(mol)
self.assertEqual(len(vs1), mol.GetNumAtoms())
self.assertEqual(vs1[1], 0)
self.assertEqual(vs1[2], 0)
self.assertNotEqual(vs1[0], 0)
self.assertEqual(vs1[0], vs1[3])
fp1 = rdMD.GetMorganFingerprint(mol, 0, invariants=vs1)
fp2 = rdMD.GetMorganFingerprint(mol, 0, useFeatures=True)
self.assertEqual(fp1, fp2)
def calculateMol(self, m, smiles, internalParsing=False):
return clip_sparse(rd.GetHashedMorganFingerprint(
m, radius=self.radius, nBits=self.nbits, invariants=rd.GetFeatureInvariants(m)),
self.nbits)
