Rdkit实现分子指纹

importrdkit
fromrdkit import Chem
from rdkit.Chemimport Draw
from rdkit.Chem.Draw import IPythonConsole
from rdkit import DataStructs
from rdkit.Chem.Fingerprintsimport FingerprintMols
#构建三个分子，CCOC，CCO，以及COC
 ms = [Chem.MolFromSmiles('CCOC'), Chem.MolFromSmiles('CCO'),Chem.MolFromSmiles('COC')]

fps0=FingerprintMols.FingerprintMol(ms[0])
#查看分子指纹的字节
fps[0].ToBitString()
#产生分子指纹
fps =[FingerprintMols.FingerprintMol(x) for x in ms]
#产生所有分子指纹的字节
fpsstr=[x.ToBitString()for x in fps]
#比较两个分子相似度， Tanimoto similarity.
DataStructs.FingerprintSimilarity(fps[0],fps[1])
#结果
0.6

There is a SMARTS-based implementation of the 166public MACCS keys.
#导入包
from rdkit.Chem import MACCSkeys
#获取MACCS指纹
fps =[MACCSkeys.GenMACCSKeys(x) for x in ms]
#进行计算查看相似度
DataStructs.FingerprintSimilarity(fps[0],fps[1])
0.5

#原子对指纹，Atom Pairs
from rdkit.Chem.AtomPairs import Pairs
ms = [Chem.MolFromSmiles('C1CCC1OCC'),Chem.MolFromSmiles('CC(COCC'),Chem.MolFromSmiles('CCOCC')]
pairFps = [Pairs.GetAtomPairFingerprint(x)for x in ms]
 

from rdkit.Chem import AllChem
#读取分子1
m1 = Chem.MolFromSmiles('Cc1ccccc1')
#获取指纹
fp1 = AllChem.GetMorganFingerprint(m1,2)
#读取分子2
m2 = Chem.MolFromSmiles('Cc1ncccc1')
#获取指纹
fp2 = AllChem.GetMorganFingerprint(m2,2)
DataStructs.DiceSimilarity(fp1,fp2)