def TFD_for_oemols(ref_mol, query_mol):
"""
This is the TFD_for_oemols script.
It makes use of RDKit's TFD calculation and the function rdmol_from_oemol.
TFD_for_oemols takes in two OEMOLs.
It does not matter which mol is the ref mol and which is the querymol.
TFD metric is the same no matter which is the ref and which is the query.
First, OEmols are made RDKit compatible. Then,
TFD is computed and returned using RDKit's TorsionFingerprints
Module. Takes one input reference mol2 and one input query mol2.
Args:
ref_mol (oemol) An oemol that has already been read in.
query_mol (oemol) An oemol that has already been read in.
Returns:
tfd (float) The torsion fingerprint deviation between ref and query.
"""
# converts refmol to one readable by RDKit
rrdmol2 = rdmol_from_oemol(ref_mol)
# converts querymol to one readable by RDKit
qrdmol2 = rdmol_from_oemol(query_mol)
# If there was a mistake in the conversion process, return -1
if (Chem.MolToSmiles(qrdmol2) != Chem.MolToSmiles(rrdmol2)):
tfd = -1
else:
# calculates the TFD
try:
tfd = TorsionFingerprints.GetTFDBetweenMolecules(rrdmol2, qrdmol2)
except IndexError:
tfd = 0
return tfd
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 testTorsionFingerprintsAtomReordering(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')
mol1 = Chem.MolFromPDBFile(refFile)
mol1 = AllChem.AssignBondOrdersFromTemplate(ref, mol1)
refFile = os.path.join(RDConfig.RDCodeDir,'Chem','test_data','1DWD_ligand_reordered.pdb')
mol2 = Chem.MolFromPDBFile(refFile)
mol2 = AllChem.AssignBondOrdersFromTemplate(ref, mol2)
tfd = TorsionFingerprints.GetTFDBetweenMolecules(mol1, mol2)
self.assertEqual(tfd, 0.0)
def calc_tfd(ref_mol, query_mol):
"""
Calculate Torsion Fingerprint Deviation between two molecular structures.
RDKit is required for TFD calculation.
References
----------
Modified from the following code:
https://github.com/MobleyLab/benchmarkff/03_analysis/compare_ffs.py
TFD reference:
https://pubs.acs.org/doi/10.1021/ci2002318
Parameters
----------
ref_mol : RDKit RDMol
query_mol : RDKit RDMol
Returns
-------
tfd : float
Torsion Fingerprint Deviation between ref and query molecules
"""
# check if the molecules are the same
# tfd requires the two molecules must be instances of the same molecule
rsmiles = Chem.MolToSmiles(ref_mol)
qsmiles = Chem.MolToSmiles(query_mol)
if rsmiles != qsmiles:
print(f"- WARNING: The reference mol {ref_mol.GetProp('_Name')} and "
f"query mol {query_mol.GetProp('_Name')} do NOT have the same "
f"SMILES strings as determined by RDKit MolToSmiles. "
f"\n {rsmiles}\n {qsmiles}")
tfd = np.nan
# calculate the TFD
else:
try:
tfd = TorsionFingerprints.GetTFDBetweenMolecules(
ref_mol, query_mol)
# triggered for molecules such as urea
except IndexError:
print(
f"- Error calculating TFD on molecule {ref_mol.GetProp('_Name')}."
" Possibly no non-terminal rotatable bonds found.")
tfd = np.nan
return tfd
def get_tfd(source_1, source_2, file_in, seed):
confab_tfd_uniform = []
confab_tfd_EI = []
confab_tfd_LCB = []
bo_tfd_confab = []
bo_tfd_uniform = []
bo_tfd_EI = []
bo_tfd_LCB = []
bo_check_EI = []
bo_check_LCB = []
confab_check_EI = []
confab_check_LCB = []
bo_target = []
confab_target = []
for i in range(len(file_in)):
print(file_in.iloc[i,0])
if file_in.iloc[i,2] == "Yes":
if "200" in str(file_in.iloc[i,1]):
basenames = file_in.iloc[i,0] + '/' + file_in.iloc[i,1] + '.sdf'
inputs = os.path.join(source_2, basenames)
ref_mol = Chem.SDMolSupplier(inputs)
else:
basenames = file_in.iloc[i,0] +'/' + file_in.iloc[i,1] + '.sdf'
inputs = os.path.join(source_1, basenames)
ref_mol = Chem.SDMolSupplier(inputs)
bo_target.append(file_in.iloc[i,0])
# read EI_bayes
EI_bases = file_in.iloc[i,0] + "/EI_bayes_{}.sdf".format(seed)
EI_input = os.path.join(source_1, EI_bases)
EI_mol = Chem.SDMolSupplier(EI_input)
# read LCB_bayes
LCB_bases = file_in.iloc[i,0] + "/LCB_bayes_{}.sdf".format(seed)
LCB_input = os.path.join(source_1, LCB_bases)
LCB_mol = Chem.SDMolSupplier(LCB_input)
# read uniform
uniform_bases = file_in.iloc[i,0] + "/uniform_{}.sdf".format(seed)
uniform_input = os.path.join(source_1, uniform_bases)
uniform_mol = Chem.SDMolSupplier(uniform_input)
# read confab
confab_bases = file_in.iloc[i,0] + "/confab.sdf"
confab_input = os.path.join(source_1, confab_bases)
confab_mol = Chem.SDMolSupplier(confab_input)
bo_tfd_EI.append(TFP.GetTFDBetweenMolecules(EI_mol[0], ref_mol[0]))
bo_tfd_LCB.append(TFP.GetTFDBetweenMolecules(LCB_mol[0], ref_mol[0]))
bo_tfd_confab.append(TFP.GetTFDBetweenMolecules(confab_mol[0], ref_mol[0]))
bo_tfd_uniform.append(TFP.GetTFDBetweenMolecules(uniform_mol[0], ref_mol[0]))
else:
basenames = file_in.iloc[i,0] + '/confab.sdf'
inputs = os.path.join(source_1, basenames)
ref_mol = Chem.SDMolSupplier(inputs)
confab_target.append(file_in.iloc[i,0])
# read EI_bayes
EI_bases = file_in.iloc[i,0] + "/EI_bayes_{}.sdf".format(seed)
EI_input = os.path.join(source_1, EI_bases)
EI_mol = Chem.SDMolSupplier(EI_input)
# read LCB_bayes
LCB_bases = file_in.iloc[i,0] + "/LCB_bayes_{}.sdf".format(seed)
LCB_input = os.path.join(source_1, LCB_bases)
LCB_mol = Chem.SDMolSupplier(LCB_input)
# read uniform
uniform_bases = file_in.iloc[i,0] + "/uniform_{}.sdf".format(seed)
uniform_input = os.path.join(source_1, uniform_bases)
uniform_mol = Chem.SDMolSupplier(uniform_input)
confab_tfd_EI.append(TFP.GetTFDBetweenMolecules(EI_mol[0], ref_mol[0]))
confab_tfd_LCB.append(TFP.GetTFDBetweenMolecules(LCB_mol[0], ref_mol[0]))
confab_tfd_uniform.append(TFP.GetTFDBetweenMolecules(uniform_mol[0], ref_mol[0]))
bo_data = pd.DataFrame({"target": bo_target, "Uniform": bo_tfd_uniform, "EI": bo_tfd_EI, "LCB": bo_tfd_LCB, "Confab": bo_tfd_confab, "N_rot": 5}, columns = ["target", "Uniform", "EI", "LCB", "Confab", "N_rot"])
confab_data = pd.DataFrame({'target': confab_target, "Uniform": confab_tfd_uniform, "EI": confab_tfd_EI, "LCB": confab_tfd_LCB, "N_rot":5}, columns = ["target","Uniform","EI","LCB", "N_rot"])
return confab_data, bo_data
def calc_tfd(ref_mol, query_mol, conf_id_tag):
"""
Calculate Torsion Fingerprint Deviation between two molecular structures.
RDKit is required for TFD calculation.
References
----------
Modified from the following code:
https://github.com/MobleyLab/off-ffcompare
TFD reference:
https://pubs.acs.org/doi/10.1021/ci2002318
Parameters
----------
ref_mol : OEMol
query_mol : OEMol
conf_id_tag : string
label of the SD tag that should be the same for matching conformers
in different files
Returns
-------
tfd : float
Torsion Fingerprint Deviation between ref and query molecules
"""
# convert refmol to one readable by RDKit
ref_rdmol = reader.rdmol_from_oemol(ref_mol)
# convert querymol to one readable by RDKit
que_rdmol = reader.rdmol_from_oemol(query_mol)
# check if the molecules are the same
# tfd requires the two molecules must be instances of the same molecule
rsmiles = Chem.MolToSmiles(ref_rdmol)
qsmiles = Chem.MolToSmiles(que_rdmol)
if rsmiles != qsmiles:
print(f"- WARNING: The reference mol \'{ref_mol.GetTitle()}\' and "
f"query mol \'{query_mol.GetTitle()}\' do NOT have the same "
"SMILES strings as determined by RDKit MolToSmiles. It is "
"possible that they did not have matching SMILES even before "
"conversion from OEMol to RDKit mol. Listing in order the "
"QCArchive SMILES string, RDKit SMILES for ref mol, and "
"RDKit SMILES for query mol:"
f"\n {oechem.OEGetSDData(ref_mol, conf_id_tag)}"
f"\n {rsmiles}\n {qsmiles}")
tfd = np.nan
# calculate the TFD
else:
try:
tfd = TorsionFingerprints.GetTFDBetweenMolecules(
ref_rdmol, que_rdmol)
# triggered for molecules such as urea
except IndexError:
print(
f"- Error calculating TFD on molecule '{ref_mol.GetTitle()}'."
" Possibly no non-terminal rotatable bonds found.")
tfd = np.nan
return tfd
if pred is None: # in case of failure
entry2RMSD[refEntry] = ''
entry2TFD[refEntry] = ''
continue
predEntry = pred.GetProp('_Name')
assert(refEntry == predEntry)
try:
rmsd = AllChem.GetBestRMS(ref, pred)
except:
rmsd = ''
try:
m = Chem.MolFromSmiles(Chem.MolToSmiles(ref))
ref = AllChem.AssignBondOrdersFromTemplate(m, ref)
pred = AllChem.AssignBondOrdersFromTemplate(m, pred)
tfd = TorsionFingerprints.GetTFDBetweenMolecules(ref, pred)
except:
tfd = ''
entry2RMSD[refEntry] = rmsd
entry2TFD[refEntry] = tfd
# See https://baoilleach.blogspot.com/2010/11/automorphisms-isomorphisms-symmetry.html
print("Entry,SMILES,RMSD,Bond error,Angle error,Torsion error,TFD,Stereo correct")
for ref, pred in zip(pybel.readfile("sdf", refFileName),
pybel.readfile("sdf", predFileName)):
refMol = ref.OBMol
predMol = pred.OBMol
refEntry = refMol.GetTitle()
predEntry = predMol.GetTitle()
assert refEntry == predEntry