def computeSimilarityFP(self, c_chem, typeFP, typeMetric):
try:
if typeMetric == 'Tanimoto':
return DataStructs.TanimotoSimilarity(self.d_FP[typeFP], c_chem.d_FP[typeFP])
elif typeMetric == "Dice":
return DataStructs.DiceSimilarity(self.d_FP[typeFP], c_chem.d_FP[typeFP])
elif typeMetric == "Cosine":
return DataStructs.CosineSimilarity(self.d_FP[typeFP], c_chem.d_FP[typeFP])
elif typeMetric == "Sokal":
return DataStructs.SokalSimilarity(self.d_FP[typeFP], c_chem.d_FP[typeFP])
elif typeMetric == "Russel":
return DataStructs.RusselSimilarity(self.d_FP[typeFP], c_chem.d_FP[typeFP])
elif typeMetric == "RogotGoldberg":
return DataStructs.RogotGoldbergSimilarity(self.d_FP[typeFP], c_chem.d_FP[typeFP])
elif typeMetric == "AllBit":
return DataStructs.AllBitSimilarity(self.d_FP[typeFP], c_chem.d_FP[typeFP])
elif typeMetric == "Kulczynski":
return DataStructs.KulczynskiSimilarity(self.d_FP[typeFP], c_chem.d_FP[typeFP])
elif typeMetric == "McConnaughey":
return DataStructs.McConnaugheySimilarity(self.d_FP[typeFP], c_chem.d_FP[typeFP])
elif typeMetric == "Asymmetric":
return DataStructs.AsymmetricSimilarity(self.d_FP[typeFP], c_chem.d_FP[typeFP])
elif typeMetric == "BraunBlanquet":
return DataStructs.BraunBlanquetSimilarity(self.d_FP[typeFP], c_chem.d_FP[typeFP])
except:
print("Combination %s and %s not supported"%(typeFP, typeMetric))
self.log = "%sCombination %s and %s not supported\n"%(self.log, typeFP, typeMetric)
return "NA"
def get_similarity_all(fp1, fp2):
"""
Get similarity score for fingerprints that are supplied always as SparseBitVect
RDKit has the following similarity measures:
Tanimoto, Dice, Cosine, Sokal, Russel, Kulczynski, McConnaughey, and Tversky.
"""
similarity_scores = [
DataStructs.TanimotoSimilarity(fp1, fp2),
DataStructs.DiceSimilarity(fp1, fp2),
DataStructs.CosineSimilarity(fp1, fp2),
# DataStructs.SokalSimilarity(fp1,fp2),
DataStructs.RusselSimilarity(fp1, fp2),
DataStructs.KulczynskiSimilarity(fp1, fp2),
DataStructs.McConnaugheySimilarity(fp1, fp2)
]
return similarity_scores
def compare_structure(smiles1, smiles2, fp_type="Morgan", sim_type="Dice"):
"""
Task: Compare structual similarity of two compound based on fingerprints.
Parameters:
smiles1: str, smiles of the compound 1
smiles2: str, smiles of the compound 2
fp_type: str, type of fingerprints
sim_type: str, method for calculating similarity
"""
if fp_type == "Morgan":
getfp = lambda smi: AllChem.GetMorganFingerprint(
Chem.MolFromSmiles(smi), 2, useFeatures=False)
elif fp_type == "MorganWithFeature":
getfp = lambda smi: AllChem.GetMorganFingerprint(
Chem.MolFromSmiles(smi), 2, useFeatures=True)
elif fp_type == "MACCS":
getfp = lambda smi: Chem.MACCSkeys.GenMACCSKeys(Chem.MolFromSmiles(smi)
)
elif fp_type == "Topological":
getfp = lambda smi: FingerprintMols.FingerprintMol(
Chem.MolFromSmiles(smi))
elif fp_type == "AtomPairs":
getfp = lambda smi: Pairs.GetAtomPairFingerprint(
Chem.MolFromSmiles(smi))
try:
fp1 = getfp(smiles1)
fp2 = getfp(smiles2)
if sim_type == "Dice":
sim_fp = DataStructs.DiceSimilarity(fp1, fp2)
elif sim_type == "Tanimoto":
sim_fp = DataStructs.TanimotoSimilarity(fp1, fp2)
elif sim_type == "Cosine":
sim_fp = DataStructs.CosineSimilarity(fp1, fp2)
elif sim_type == "Sokal":
sim_fp = DataStructs.SokalSimilarity(fp1, fp2)
elif sim_type == "Russel":
sim_fp = DataStructs.RusselSimilarity(fp1, fp2)
except Exception as e:
sim_fp = -1
return sim_fp
def GetSimilarity(rdkmol1, rdkmol2, metric='tanimoto'):
'''
mol1 and mol2 are RDKit fingerprint objects for molecule
'''
valid_metric = ('tanimoto', 'dice', 'cosine', 'sokal', 'russel', 'kulczynski', 'mcconnaughey')
if metric.lower() == 'tanimoto':
return DataStructs.TanimotoSimilarity(rdkmol1, rdkmol2)
elif metric.lower() == 'dice':
return DataStructs.DiceSimilarity(rdkmol1, rdkmol2)
elif metric.lower() == 'cosine':
return DataStructs.CosineSimilarity(rdkmol1, rdkmol2)
elif metric.lower() == 'sokal':
return DataStructs.SokalSimilarity(rdkmol1, rdkmol2)
elif metric.lower() == 'russel':
return DataStructs.RusselSimilarity(rdkmol1, rdkmol2)
elif metric.lower() == 'kulczynski':
return DataStructs.KulczynskiSimilarity(rdkmol1, rdkmol2)
elif metric.lower() == 'mcconnaughey':
return DataStructs.McConnaugheySimilarity(rdkmol1, rdkmol2)
#elif metric.lower() == 'tversky': #Was returning error
# return DataStructs.TverskySimilarity(rdkmol1, rdkmol2)
else:
sys.exit('***ERROR: Unrecognized similarity metric: %s***.\n Use one of %s' % (metric,', '.join(valid_metric)))