RDKit：基于RDKit的溶解度预测的机器学习模型

基于RDKit和Python3的化合物溶解度的机器学习模型小案例。

《仅供参考》

# In[1]:导入依赖包

from rdkit import Chem, DataStructs
from rdkit.Chem import AllChem
from rdkit.ML.Descriptors import MoleculeDescriptors
from rdkit.Chem import Descriptors
from rdkit.Chem.EState import Fingerprinter

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

from sklearn.preprocessing import StandardScaler
from sklearn import cross_validation
from sklearn.metrics import r2_score
from sklearn.ensemble import RandomForestRegressor
from sklearn import gaussian_process
from sklearn.gaussian_process.kernels import Matern, WhiteKernel, ConstantKernel, RBF

# In[2]:定义描述符计算函数

def get_fps(mol):
    calc=MoleculeDescriptors.MolecularDescriptorCalculator([x[0] for x in Descriptors._descList])
    ds = np.asarray(calc.CalcDescr