def GenerateTopologicalTorsionsFingerprints(Mols):
"""Generate TopologicalTorsions fingerprints."""
MiscUtil.PrintInfo("\nGenerating TopologicalTorsions %s fingerprints..." %
OptionsInfo["SpecifiedFingerprintsType"])
UseChirality = OptionsInfo["FingerprintsParams"]["TopologicalTorsions"][
"UseChirality"]
FPSize = OptionsInfo["FingerprintsParams"]["TopologicalTorsions"]["FPSize"]
BitsPerHash = OptionsInfo["FingerprintsParams"]["TopologicalTorsions"][
"BitsPerHash"]
if re.match("^BitVect$", OptionsInfo["SpecifiedFingerprintsType"], re.I):
# Generate ExplicitBitVect fingerprints...
MiscUtil.PrintInfo("FPSize: %s; BitsPerHash: %s" %
(FPSize, BitsPerHash))
MolsFingerprints = [
rdMolDescriptors.GetHashedTopologicalTorsionFingerprintAsBitVect(
Mol,
includeChirality=UseChirality,
nBits=FPSize,
nBitsPerEntry=BitsPerHash) for Mol in Mols
]
else:
# Generate LongSparseIntVect fingerprint...
MolsFingerprints = [
rdMolDescriptors.GetTopologicalTorsionFingerprint(
Mol, includeChirality=UseChirality) for Mol in Mols
]
return MolsFingerprints
def GenerateTopologicalTorsionsFingerprints(Mols):
"""Generate TopologicalTorsions fingerprints."""
MiscUtil.PrintInfo("\nGenerating TopologicalTorsions fingerprints...")
UseChirality = OptionsInfo["FingerprintsParams"]["TopologicalTorsions"][
"UseChirality"]
if OptionsInfo["GenerateBitVectFingerints"]:
FPSize = 2048
BitsPerHash = 4
MolsFingerprints = [
rdMolDescriptors.GetHashedTopologicalTorsionFingerprintAsBitVect(
Mol,
includeChirality=UseChirality,
nBits=FPSize,
nBitsPerEntry=BitsPerHash) for Mol in Mols
]
else:
# Generate LongSparseIntVect fingerprint...
MolsFingerprints = [
rdMolDescriptors.GetTopologicalTorsionFingerprint(
Mol, includeChirality=UseChirality) for Mol in Mols
]
return MolsFingerprints
def get_topological_torsion(molecule, length=512):
try:
tt = rdMolDescriptors.GetHashedTopologicalTorsionFingerprintAsBitVect(
molecule, nBits=length)
except Exception as e:
print(e)
print("error" + str(molecule))
tt = np.nan
return tt
def featurize(self, x):
if self.input_type == 'smiles':
x_ = x
x = Chem.MolFromSmiles(x)
if x is None:
raise ValueError('can not convert Mol from SMILES %s' % x_)
if self.input_type == 'any':
if not isinstance(x, Chem.rdchem.Mol):
x_ = x
x = Chem.MolFromSmiles(x)
if x is None:
raise ValueError('can not convert Mol from SMILES %s' % x_)
return list(
rdMol.GetHashedTopologicalTorsionFingerprintAsBitVect(
x, nBits=self.n_bits))
def testAtomPairOptions(self):
m1 = Chem.MolFromSmiles('c1ccccc1')
m2 = Chem.MolFromSmiles('c1ccccn1')
fp1 = rdMD.GetAtomPairFingerprint(m1)
fp2 = rdMD.GetAtomPairFingerprint(m2)
self.assertNotEqual(fp1,fp2)
fp1 = rdMD.GetAtomPairFingerprint(m1,atomInvariants=[1]*6)
fp2 = rdMD.GetAtomPairFingerprint(m2,atomInvariants=[1]*6)
self.assertEqual(fp1,fp2)
fp1 = rdMD.GetAtomPairFingerprint(m1,atomInvariants=[1]*6)
fp2 = rdMD.GetAtomPairFingerprint(m2,atomInvariants=[2]*6)
self.assertNotEqual(fp1,fp2)
fp1 = rdMD.GetHashedAtomPairFingerprintAsBitVect(m1)
fp2 = rdMD.GetHashedAtomPairFingerprintAsBitVect(m2)
self.assertNotEqual(fp1,fp2)
fp1 = rdMD.GetHashedAtomPairFingerprintAsBitVect(m1,atomInvariants=[1]*6)
fp2 = rdMD.GetHashedAtomPairFingerprintAsBitVect(m2,atomInvariants=[1]*6)
self.assertEqual(fp1,fp2)
fp1 = rdMD.GetHashedAtomPairFingerprintAsBitVect(m1,atomInvariants=[1]*6)
fp2 = rdMD.GetHashedAtomPairFingerprintAsBitVect(m2,atomInvariants=[2]*6)
self.assertNotEqual(fp1,fp2)
fp1 = rdMD.GetTopologicalTorsionFingerprint(m1)
fp2 = rdMD.GetTopologicalTorsionFingerprint(m2)
self.assertNotEqual(fp1,fp2)
fp1 = rdMD.GetTopologicalTorsionFingerprint(m1,atomInvariants=[1]*6)
fp2 = rdMD.GetTopologicalTorsionFingerprint(m2,atomInvariants=[1]*6)
self.assertEqual(fp1,fp2)
fp1 = rdMD.GetTopologicalTorsionFingerprint(m1,atomInvariants=[1]*6)
fp2 = rdMD.GetTopologicalTorsionFingerprint(m2,atomInvariants=[2]*6)
self.assertNotEqual(fp1,fp2)
fp1 = rdMD.GetHashedTopologicalTorsionFingerprintAsBitVect(m1)
fp2 = rdMD.GetHashedTopologicalTorsionFingerprintAsBitVect(m2)
self.assertNotEqual(fp1,fp2)
fp1 = rdMD.GetHashedTopologicalTorsionFingerprintAsBitVect(m1,atomInvariants=[1]*6)
fp2 = rdMD.GetHashedTopologicalTorsionFingerprintAsBitVect(m2,atomInvariants=[1]*6)
self.assertEqual(fp1,fp2)
fp1 = rdMD.GetHashedTopologicalTorsionFingerprintAsBitVect(m1,atomInvariants=[1]*6)
fp2 = rdMD.GetHashedTopologicalTorsionFingerprintAsBitVect(m2,atomInvariants=[2]*6)
self.assertNotEqual(fp1,fp2)
nBits -- the size of the bit vector (only for fpType='bv')
minLength -- the minimum path length for an atom pair
maxLength -- the maxmimum path length for an atom pair
nBitsPerEntry -- the number of bits available for each pair
"""
if fpType not in ['normal', 'hashed', 'bv']: raise ValueError("Unknown Atom pairs fingerprint type")
if atomId < 0:
return apDict[fpType](mol, nBits, minLength, maxLength, nBitsPerEntry, 0)
if atomId >= mol.GetNumAtoms(): raise ValueError("atom index greater than number of atoms")
return apDict[fpType](mol, nBits, minLength, maxLength, nBitsPerEntry, [atomId])
ttDict = {}
ttDict['normal'] = lambda m, bits, ts, bpe, ia: rdMD.GetTopologicalTorsionFingerprint(m, targetSize=ts, ignoreAtoms=ia)
ttDict['hashed'] = lambda m, bits, ts, bpe, ia: rdMD.GetHashedTopologicalTorsionFingerprint(m, nBits=bits, targetSize=ts, ignoreAtoms=ia)
ttDict['bv'] = lambda m, bits, ts, bpe, ia: rdMD.GetHashedTopologicalTorsionFingerprintAsBitVect(m, nBits=bits, targetSize=ts, nBitsPerEntry=bpe, ignoreAtoms=ia)
# usage: lambda m,i: GetTTFingerprint(m, i, fpType, nBits, targetSize)
def GetTTFingerprint(mol, atomId=-1, fpType='normal', nBits=2048, targetSize=4, nBitsPerEntry=4):
"""
Calculates the topological torsion fingerprint with the pairs of atomId removed.
Parameters:
mol -- the molecule of interest
atomId -- the atom to remove the torsions for (if -1, no torsion is removed)
fpType -- the type of TT fingerprint ('normal', 'hashed', 'bv')
nBits -- the size of the bit vector (only for fpType='bv')
minLength -- the minimum path length for an atom pair
maxLength -- the maxmimum path length for an atom pair
nBitsPerEntry -- the number of bits available for each torsion
"""
fpdict["ap"] = lambda m: Pairs.GetAtomPairFingerprint(m)
fpdict["tt"] = lambda m: Torsions.GetTopologicalTorsionFingerprintAsIntVect(m)
fpdict[
"hashap"
] = lambda m: rdMolDescriptors.GetHashedAtomPairFingerprintAsBitVect(
m, nBits=nbits
)
fpdict[
"hashap_cas_length"
] = lambda m: rdMolDescriptors.GetHashedAtomPairFingerprintAsBitVect(
m, nBits=n_cas_bits
)
fpdict[
"hashtt"
] = lambda m: rdMolDescriptors.GetHashedTopologicalTorsionFingerprintAsBitVect(
m, nBits=nbits
)
fpdict[
"hashtt_cas_length"
] = lambda m: rdMolDescriptors.GetHashedTopologicalTorsionFingerprintAsBitVect(
m, nBits=n_cas_bits
)
fpdict["avalon"] = lambda m: fpAvalon.GetAvalonFP(m, nbits)
fpdict["avalon_cas_length"] = lambda m: fpAvalon.GetAvalonFP(m, n_cas_bits)
fpdict["laval"] = lambda m: fpAvalon.GetAvalonFP(m, longbits)
fpdict["rdk5"] = lambda m: Chem.RDKFingerprint(
m, maxPath=5, fpSize=nbits, nBitsPerHash=2
)
fpdict["rdk6"] = lambda m: Chem.RDKFingerprint(
m, maxPath=6, fpSize=nbits, nBitsPerHash=2
)
def torsion_fingerprinter(mol):
fp = rdMolDescriptors.GetHashedTopologicalTorsionFingerprintAsBitVect(
mol, nBits=fpSize, targetSize=targetSize)
return _fp_to_bytes(fp)
# dictionary
fpFunc_dict = {}
fpFunc_dict['ecfp0'] = lambda m: AllChem.GetMorganFingerprintAsBitVect(m, 0, nBits=nbits)
fpFunc_dict['ecfp2'] = lambda m: AllChem.GetMorganFingerprintAsBitVect(m, 1, nBits=nbits)
fpFunc_dict['ecfp4'] = lambda m: AllChem.GetMorganFingerprintAsBitVect(m, 2, nBits=nbits)
fpFunc_dict['ecfp6'] = lambda m: AllChem.GetMorganFingerprintAsBitVect(m, 3, nBits=nbits)
fpFunc_dict['fcfp2'] = lambda m: AllChem.GetMorganFingerprintAsBitVect(m, 1, useFeatures=True, nBits=nbits)
fpFunc_dict['fcfp4'] = lambda m: AllChem.GetMorganFingerprintAsBitVect(m, 2, useFeatures=True, nBits=nbits)
fpFunc_dict['fcfp6'] = lambda m: AllChem.GetMorganFingerprintAsBitVect(m, 3, useFeatures=True, nBits=nbits)
fpFunc_dict['lecfp4'] = lambda m: AllChem.GetMorganFingerprintAsBitVect(m, 2, nBits=longbits)
fpFunc_dict['lecfp6'] = lambda m: AllChem.GetMorganFingerprintAsBitVect(m, 3, nBits=longbits)
fpFunc_dict['lfcfp4'] = lambda m: AllChem.GetMorganFingerprintAsBitVect(m, 2, useFeatures=True, nBits=longbits)
fpFunc_dict['lfcfp6'] = lambda m: AllChem.GetMorganFingerprintAsBitVect(m, 3, useFeatures=True, nBits=longbits)
fpFunc_dict['maccs'] = lambda m: MACCSkeys.GenMACCSKeys(m)
fpFunc_dict['hashap'] = lambda m: rdMolDescriptors.GetHashedAtomPairFingerprintAsBitVect(m, nBits=nbits)
fpFunc_dict['hashtt'] = lambda m: rdMolDescriptors.GetHashedTopologicalTorsionFingerprintAsBitVect(m, nBits=nbits)
fpFunc_dict['avalon'] = lambda m: fpAvalon.GetAvalonFP(m, nbits)
fpFunc_dict['laval'] = lambda m: fpAvalon.GetAvalonFP(m, longbits)
fpFunc_dict['rdk5'] = lambda m: Chem.RDKFingerprint(m, maxPath=5, fpSize=nbits, nBitsPerHash=2)
fpFunc_dict['rdk6'] = lambda m: Chem.RDKFingerprint(m, maxPath=6, fpSize=nbits, nBitsPerHash=2)
fpFunc_dict['rdk7'] = lambda m: Chem.RDKFingerprint(m, maxPath=7, fpSize=nbits, nBitsPerHash=2)
fpFunc_dict['tpatf'] = lambda m: get_tpatf(m)
fpFunc_dict['rdkDes'] = lambda m: calc.CalcDescriptors(m)
long_fps = {'laval', 'lecfp4', 'lecfp6', 'lfcfp4', 'lfcfp6'}
fps_to_generate = ['fcfp4', 'rdkDes', 'tpatf', 'rdk5', 'hashap', 'avalon', 'laval', 'rdk7']
ModFileName_LoadedModel_dict = {}
1,
useFeatures=True,
nBits=nbits)
fpdict['fcfp4'] = AllChem.GetMorganFingerprintAsBitVect(smiles,
2,
useFeatures=True,
nBits=nbits)
fpdict['fcfp6'] = AllChem.GetMorganFingerprintAsBitVect(smiles,
3,
useFeatures=True,
nBits=nbits)
fpdict['maccs'] = MACCSkeys.GenMACCSKeys(smiles)
fpdict['ap'] = rdMolDescriptors.GetHashedAtomPairFingerprintAsBitVect(
smiles, nBits=nbits)
fpdict[
'tt'] = rdMolDescriptors.GetHashedTopologicalTorsionFingerprintAsBitVect(
smiles, nBits=nbits)
fpdict['rdk5'] = Chem.RDKFingerprint(smiles,
maxPath=5,
fpSize=nbits,
nBitsPerHash=2)
fpdict['rdk6'] = Chem.RDKFingerprint(smiles,
maxPath=6,
fpSize=nbits,
nBitsPerHash=2)
fpdict['rdk7'] = Chem.RDKFingerprint(smiles,
maxPath=7,
fpSize=nbits,
nBitsPerHash=2)
#fpdict['avalon'] = fpAvalon.GetAvalonFP(smiles, nbits)
#Convert to hex for space save, to go back to bin use "bin(int(x, 16))[2:]
