def computeFP(self, typeFP):
from rdkit.Chem.Fingerprints import FingerprintMols
from rdkit.Chem import MACCSkeys
from rdkit.Chem.AtomPairs import Pairs, Torsions
from rdkit.Chem import AllChem
if not "smiclean" in self.__dict__:
self.log = self.log + "No smiles prepared\n"
return 1
else:
self.mol = Chem.MolFromSmiles(self.smiclean)
#print self.smiclean
dFP = {}
if typeFP == "Mol" or typeFP == "All":
dFP["Mol"] = FingerprintMols.FingerprintMol(self.mol)
if typeFP == "MACCS" or typeFP == "All":
dFP["MACCS"] = MACCSkeys.GenMACCSKeys(self.mol)
if typeFP == "pairs" or typeFP == "All":
dFP["pairs"] = Pairs.GetAtomPairFingerprint(self.mol)
if typeFP == "Torsion" or typeFP == "All":
dFP["Torsion"] = Torsions.GetTopologicalTorsionFingerprint(
self.mol)
if typeFP == "Morgan" or typeFP == "All":
dFP["Morgan"] = AllChem.GetMorganFingerprint(self.mol, 2)
self.FP = dFP
return 0
def testGetTopologicalTorsionFingerprintAsIds(self):
mol = Chem.MolFromSmiles('C1CCCCN1')
tt = Torsions.GetTopologicalTorsionFingerprint(mol)
self.assertEqual(tt.GetNonzeroElements(), {4437590049: 2, 8732557345: 2, 4445978657: 2})
tt = Torsions.GetTopologicalTorsionFingerprintAsIds(mol)
self.assertEqual(
sorted(tt), [4437590049, 4437590049, 4445978657, 4445978657, 8732557345, 8732557345])
tt = Torsions.GetTopologicalTorsionFingerprintAsIntVect(mol)
self.assertEqual(tt.GetNonzeroElements(), {4437590049: 2, 8732557345: 2, 4445978657: 2})
def getCountInfo(m, fpType):
# m = Chem.MolFromSmiles(formula)
fp = None
if fpType == 'AtomPair' or fpType.lower() == 'atom':
fp = Pairs.GetAtomPairFingerprint(m)
return fp.GetNonzeroElements()
elif fpType.lower() == 'morgan' or fpType.lower() == 'circular':
fp = AllChem.GetMorganFingerprint(m, 2)
return fp.GetNonzeroElements()
elif fpType == 'Topological' or fpType.lower() == 'topo':
fp = Torsions.GetTopologicalTorsionFingerprint(m)
Dict = fp.GetNonzeroElements()
convertedDict = {}
for elem in Dict:
convertedDict[int(elem)] = Dict[elem]
return convertedDict
def Fingerprints(mols, fingerprint):
# Indigo fingerprints
if fingerprint in indigofps:
return [mol.fingerprint(fingerprint) for mol in mols]
# RDKit fingerprints
if fingerprint in rdkitfps:
if fingerprint == "atompair":
return [Pairs.GetAtomPairFingerprintAsBitVect(mol) for mol in mols]
elif fingerprint == "avalon":
return [pyAvalonTools.GetAvalonFP(mol) for mol in mols]
elif fingerprint == "daylight":
return [Chem.RDKFingerprint(mol, fpSize=2048) for mol in mols]
elif fingerprint == "maccs":
return [MACCSkeys.GenMACCSKeys(mol) for mol in mols]
elif fingerprint == "morgan":
return [(AllChem.GetMorganFingerprintAsBitVect(mol, 2, nBits=1024))
for mol in mols]
elif fingerprint == "pharm2d":
return [
Generate.Gen2DFingerprint(mol, Gobbi_Pharm2D.factory)
for mol in mols
]
elif fingerprint == "topological":
return [FingerprintMols.FingerprintMol(mol) for mol in mols]
# RDKit non-bit (integer or float) fingerprints
if fingerprint in rdkitnonbitfps:
if fingerprint == "sheridan":
return [Sheridan.GetBPFingerprint(mol) for mol in mols]
elif fingerprint == "topotorsion":
return [
Torsions.GetTopologicalTorsionFingerprint(mol) for mol in mols
]
# E-state fingerprints
if fingerprint in rdkitestatefps:
if fingerprint == "estate1":
return [Fingerprinter.FingerprintMol(mol)[0] for mol in mols]
elif fingerprint == "estate2":
return [Fingerprinter.FingerprintMol(mol)[1] for mol in mols]
# unknown fingerprint
return None
def computeFP(self, typeFP):
if not "mol" in self.__dict__:
self.log = self.log + "No smiles prepared\n"
self.err = 1
else:
d_FP = {}
if typeFP == "Mol" or typeFP == "All":
d_FP["Mol"] = FingerprintMols.FingerprintMol(self.mol)
if typeFP == "MACCS" or typeFP == "All":
d_FP["MACCS"] = MACCSkeys.GenMACCSKeys(self.mol)
if typeFP == "pairs" or typeFP == "All":
d_FP["pairs"] = Pairs.GetAtomPairFingerprint(self.mol)
if typeFP == "Torsion" or typeFP == "All":
d_FP["Torsion"] = Torsions.GetTopologicalTorsionFingerprint(self.mol)
if typeFP == "Morgan" or typeFP == "All":
d_FP["Morgan"] = AllChem.GetMorganFingerprint(self.mol, 2)
self.d_FP = d_FP
def CalculateTopologicalTorsionFingerprint(
mol: Chem.Mol,
rtype: str = 'countstring',
bits: int = 2048) -> Tuple[str, dict, Any]:
"""Calculate Topological Torsion fingerprints.
:param rtype: Type of output, may either be:
countstring (default), returns a binary string
rdkit, return the native rdkit DataStructs
dict, for a dict of bits turned on
:param bits: Number of folded bits (ignored if rtype != 'countstring')
"""
res = Torsions.GetTopologicalTorsionFingerprint(mol)
if rtype == 'rdkit':
return res
counts = res.GetNonzeroElements()
if rtype == 'dict':
return {f'TopolTorsions_{k}': v for k, v in counts.items()}
folded = np.zeros(bits)
for k, v in counts.items():
folded[k % bits] += v
return ';'.join(folded.tolist())
def CalculateTopologicalTorsionFingerprint(mol):
"""
#################################################################
Calculate Topological Torsion Fingerprints
Usage:
result=CalculateTopologicalTorsionFingerprint(mol)
Input: mol is a molecule object.
Output: result is a tuple form. The first is the number of
fingerprints. The second is a dict form whose keys are the
position which this molecule has some substructure. The third
is the DataStructs which is used for calculating the similarity.
#################################################################
"""
res = Torsions.GetTopologicalTorsionFingerprint(mol)
return res.GetLength(), res.GetNonzeroElements(), res
def calculate_similarity_vector(smile_pair):
"""
Calculate fingerprints between two smile terms using different fingerprinters,
and use different similarity metrics to calculate the difference between those fingerprints.
"""
# smile1, smile2 = smile_pair.split('_')
smile1, smile2 = smile_pair
mol1 = Chem.MolFromSmiles(smile1)
mol2 = Chem.MolFromSmiles(smile2)
molecule_similarity = list()
# RDK topological fingerprint for a molecule
fp1 = Chem.RDKFingerprint(mol1)
fp2 = Chem.RDKFingerprint(mol2)
molecule_similarity.extend(get_similarity_all(fp1, fp2))
#print 'RDK fingerprint: ', DataStructs.KulczynskiSimilarity(fp1,fp2)
## LayeredFingerprint, a fingerprint using SMARTS patterns
#fp1 = Chem.LayeredFingerprint(mol1)
#fp2 = Chem.LayeredFingerprint(mol2)
#print 'RDK fingerprint: ', DataStructs.TanimotoSimilarity(fp1,fp2)
# PatternFingerprint, a fingerprint using SMARTS patterns
#fp1 = Chem.PatternFingerprint(mol1)
#fp2 = Chem.PatternFingerprint(mol2)
#print 'RDK fingerprint: ', DataStructs.TanimotoSimilarity(fp1,fp2)
###############################################################################
# Topological Fingerprints
# Uses Chem.RDKFingerprint internally, but with different parameters, I guess...
# http://www.rdkit.org/docs/GettingStartedInPython.html#topological-fingerprints
from rdkit.Chem.Fingerprints import FingerprintMols
fp1 = FingerprintMols.FingerprintMol(mol1)
fp2 = FingerprintMols.FingerprintMol(mol2)
molecule_similarity.extend(get_similarity_all(fp1, fp2))
#print 'RDK fingerprint: ', DataStructs.TanimotoSimilarity(fp1,fp2)
###############################################################################
# MACCS Keys
# There is a SMARTS-based implementation of the 166 public MACCS keys.
# http://www.rdkit.org/docs/GettingStartedInPython.html#maccs-keys
from rdkit.Chem import MACCSkeys
fp1 = MACCSkeys.GenMACCSKeys(mol1)
fp2 = MACCSkeys.GenMACCSKeys(mol2)
molecule_similarity.extend(get_similarity_all(fp1, fp2))
#print "RDK fingerprint: ", DataStructs.TanimotoSimilarity(fp1,fp2)
###############################################################################
# Atom Pairs and Topological Torsions
# Atom-pair descriptors [3] are available in several different forms.
# The standard form is as fingerprint including counts for each bit instead of just zeros and ones:
# http://www.rdkit.org/docs/GettingStartedInPython.html#atom-pairs-and-topological-torsions
from rdkit.Chem.AtomPairs import Pairs
fp1 = Pairs.GetAtomPairFingerprintAsBitVect(mol1)
fp2 = Pairs.GetAtomPairFingerprintAsBitVect(mol2)
molecule_similarity.extend(get_similarity_all(fp1, fp2))
#print "RDK fingerprint: ", DataStructs.DiceSimilarity(fp1,fp2)
from rdkit.Chem.AtomPairs import Torsions
fp1 = Torsions.GetTopologicalTorsionFingerprint(mol1)
fp2 = Torsions.GetTopologicalTorsionFingerprint(mol2)
molecule_similarity.extend(get_similarity_subset(fp1, fp2))
#print "RDK fingerprint: ", DataStructs.TanimotoSimilarity(fp1,fp2)
###############################################################################
# Morgan Fingerprints (Circular Fingerprints)
#This family of fingerprints, better known as circular fingerprints [5],
#is built by applying the Morgan algorithm to a set of user-supplied atom invariants.
#When generating Morgan fingerprints, the radius of the fingerprint must also be provided...
# http://www.rdkit.org/docs/GettingStartedInPython.html#morgan-fingerprints-circular-fingerprints
from rdkit.Chem import rdMolDescriptors
fp1 = rdMolDescriptors.GetMorganFingerprint(mol1, 2)
fp2 = rdMolDescriptors.GetMorganFingerprint(mol2, 2)
molecule_similarity.extend(get_similarity_subset(fp1, fp2))
fp1 = rdMolDescriptors.GetMorganFingerprint(mol1, 2, useFeatures=True)
fp2 = rdMolDescriptors.GetMorganFingerprint(mol2, 2, useFeatures=True)
molecule_similarity.extend(get_similarity_subset(fp1, fp2))
#print "RDK fingerprint: ", DataStructs.TanimotoSimilarity(fp1,fp2)
###############################################################################
return molecule_similarity
