def butina_clustering_m(rdkit_mol, difference_matrix='tfd', threshold=0.001):
""" Clustering conformers with RDKit's Butina algorithem """
# calculate difference matrix
if difference_matrix.lower() == 'tfd':
diffmat = TorsionFingerprints.GetTFDMatrix(rdkit_mol)
if difference_matrix.lower() == 'rms':
diffmat = AllChem.GetConformerRMSMatrix(rdkit_mol, prealigned=False)
# cluster conformers
num_confs = rdkit_mol.GetNumConformers()
clt = Butina.ClusterData(diffmat,
num_confs,
threshold,
isDistData=True,
reordering=True)
# new conformers
centroid_idx = [c[0] for c in clt] # centroid indexes.
new_rdkit_mol = copy.deepcopy(rdkit_mol)
new_rdkit_mol.RemoveAllConformers()
for idx in centroid_idx:
centroid_conf = rdkit_mol.GetConformer(idx)
new_rdkit_mol.AddConformer(centroid_conf, assignId=True)
del rdkit_mol # delete old mol, is this nessesary?
return new_rdkit_mol
def testTorsionFingerprints(self):
# we use the xray structure from the paper (JCIM, 52, 1499, 2012): 1DWD
refFile = os.path.join(RDConfig.RDCodeDir, 'Chem', 'test_data', '1DWD_ligand.pdb')
ref = Chem.MolFromSmiles(
'NC(=[NH2+])c1ccc(C[C@@H](NC(=O)CNS(=O)(=O)c2ccc3ccccc3c2)C(=O)N2CCCCC2)cc1')
mol = Chem.MolFromPDBFile(refFile)
mol = AllChem.AssignBondOrdersFromTemplate(ref, mol)
# the torsion lists
tors_list, tors_list_rings = TorsionFingerprints.CalculateTorsionLists(mol)
self.assertEqual(len(tors_list), 11)
self.assertEqual(len(tors_list_rings), 4)
self.assertAlmostEqual(tors_list[-1][1], 180.0, 4)
tors_list, tors_list_rings = TorsionFingerprints.CalculateTorsionLists(mol, maxDev='spec')
self.assertAlmostEqual(tors_list[-1][1], 90.0, 4)
self.assertRaises(ValueError, TorsionFingerprints.CalculateTorsionLists, mol, maxDev='test')
tors_list, tors_list_rings = TorsionFingerprints.CalculateTorsionLists(mol, symmRadius=0)
self.assertEqual(len(tors_list[0][0]), 2)
# the weights
weights = TorsionFingerprints.CalculateTorsionWeights(mol)
self.assertAlmostEqual(weights[4], 1.0)
self.assertEqual(len(weights), len(tors_list + tors_list_rings))
weights = TorsionFingerprints.CalculateTorsionWeights(mol, 15, 14)
self.assertAlmostEqual(weights[3], 1.0)
self.assertRaises(ValueError, TorsionFingerprints.CalculateTorsionWeights, mol, 15, 3)
# the torsion angles
tors_list, tors_list_rings = TorsionFingerprints.CalculateTorsionLists(mol)
torsions = TorsionFingerprints.CalculateTorsionAngles(mol, tors_list, tors_list_rings)
self.assertEqual(len(weights), len(torsions))
self.assertAlmostEqual(torsions[2][0][0], 232.5346, 4)
# the torsion fingerprint deviation
tfd = TorsionFingerprints.CalculateTFD(torsions, torsions)
self.assertAlmostEqual(tfd, 0.0)
refFile = os.path.join(RDConfig.RDCodeDir, 'Chem', 'test_data', '1PPC_ligand.pdb')
mol2 = Chem.MolFromPDBFile(refFile)
mol2 = AllChem.AssignBondOrdersFromTemplate(ref, mol2)
torsions2 = TorsionFingerprints.CalculateTorsionAngles(mol2, tors_list, tors_list_rings)
weights = TorsionFingerprints.CalculateTorsionWeights(mol)
tfd = TorsionFingerprints.CalculateTFD(torsions, torsions2, weights=weights)
self.assertAlmostEqual(tfd, 0.0691, 4)
tfd = TorsionFingerprints.CalculateTFD(torsions, torsions2)
self.assertAlmostEqual(tfd, 0.1115, 4)
# the wrapper functions
tfd = TorsionFingerprints.GetTFDBetweenMolecules(mol, mol2)
self.assertAlmostEqual(tfd, 0.0691, 4)
mol.AddConformer(mol2.GetConformer(), assignId=True)
mol.AddConformer(mol2.GetConformer(), assignId=True)
tfd = TorsionFingerprints.GetTFDBetweenConformers(mol, confIds1=[0], confIds2=[1, 2])
self.assertEqual(len(tfd), 2)
self.assertAlmostEqual(tfd[0], 0.0691, 4)
tfdmat = TorsionFingerprints.GetTFDMatrix(mol)
self.assertEqual(len(tfdmat), 3)
def tfd_matrix(mol: Chem.Mol) -> np.array:
"""Calculates the TFD matrix for all conformers in a molecule.
"""
tfd = TorsionFingerprints.GetTFDMatrix(mol, useWeights=False)
n = int(np.sqrt(len(tfd) * 2)) + 1
idx = np.tril_indices(n, k=-1, m=n)
matrix = np.zeros((n, n))
matrix[idx] = tfd
matrix += np.transpose(matrix)
return matrix
def cluster_conformers(mol, mode="RMSD", threshold=2.0):
if mode == "TFD":
dmat = TorsionFingerprints.GetTFDMatrix(mol)
else:
dmat = AllChem.GetConformerRMSMatrix(mol, prealigned=False)
rms_clusters = Butina.ClusterData(dmat,
mol.GetNumConformers(),
threshold,
isDistData=True,
reordering=True)
return rms_clusters
def rdkit_tfd(mol):
kernel = TorsionFingerprints.GetTFDMatrix(mol)
return kernel
for mol in mols:
if mol != None:
mol = Chem.AddHs(mol)
conf = AllChem.EmbedMultipleConfs(mol,
numConfs=int(N),
pruneRmsThresh=float(RMS),
useExpTorsionAnglePrefs=True,
useBasicKnowledge=True,
numThreads=int(nbthread))
if len(conf) > 0:
Chem.rdMolAlign.AlignMolConformers(mol)
AllChem.UFFOptimizeMoleculeConfs(mol, numThreads=int(nbthread))
## Here new code to discard identical conformers around an axis of symmetry (not supported by pruneRmsThresh in the previous fct)
matrix = TorsionFingerprints.GetTFDMatrix(mol,
useWeights=False,
maxDev='equal',
symmRadius=2,
ignoreColinearBonds=True)
conf_clusters = Butina.ClusterData(matrix, len(conf), cutoff, True)
confnb = 1
for cluster in conf_clusters:
writer = Chem.SDWriter(output_folder + "/" +
mol.GetProp("_Name") + "_conf_" +
str(confnb) + ".sdf")
writer.write(mol, confId=cluster[0]) # output only centroid
writer.close()
confnb += 1
else:
# not able to make conformers
print("Could not generate any conformers for %s" %
(mol.GetProp("_Name")))
