RDKit：基于RDKit的溶解度预测的机器学习模型

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/u012325865/article/details/82318276

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.CalcDescriptors(mol))
    
    arr=Fingerprinter.FingerprintMol(mol)[0]
    
    return np.append(arr,ds)

# In[3]:

#读入数据
data = pd.read_table('smi_sol.dat', sep=' ')
 
#增加结构和描述符属性
data['Mol'] = data['smiles'].apply(Chem.MolFromSmiles)
data['Descriptors'] = data['Mol'].apply(get_fps)

# In[4]:查看前5行数据

data.head(5)

# In[5]:

#转换为numpy数组
X = np.array(list(data['Descriptors']))
y = data['solubility'].values
 
st = StandardScaler()
X = st.fit_transform(X)
 
#划分训练集和测试集
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.25, random_state=42)

# In[7]:高斯过程回归

kernel=1.0 * RBF(length_scale=1) + WhiteKernel(noise_level=1)

gp = gaussian_process.GaussianProcessRegressor(kernel=kernel,n_restarts_optimizer=0,normalize_y=True)
gp.fit(X_train, y_train)

# In[8]:

y_pred, sigma = gp.predict(X_test, return_std=True)
rms = (np.mean((y_test - y_pred)**2))**0.5
#s = np.std(y_test -y_pred)
print ("GP RMS", rms)

# out[8]:

GP RMS 0.5984083408596741

# In[9]:

print ("GP r^2 score",r2_score(y_test,y_pred))

# out[8]:

GP r^2 score 0.9141780584554846

# In[10]:结果绘图

plt.scatter(y_train,gp.predict(X_train), label = 'Train', c='blue')
plt.title('GP Predictor')
plt.xlabel('Measured Solubility')
plt.ylabel('Predicted Solubility')
plt.scatter(y_test,gp.predict(X_test),c='lightgreen', label='Test', alpha = 0.8)
plt.legend(loc=4)
plt.savefig('GP Predictor.png', dpi=300)
plt.show()

# In[11]:随机森林模型

rf = RandomForestRegressor(n_estimators=100, oob_score=True, max_features='auto')
rf.fit(X_train, y_train)

# In[12]:

y_pred = rf.predict(X_test)
rms = (np.mean((y_test - y_pred)**2))**0.5
print ("RF RMS", rms)

# out[12]:
RF RMS 0.6057144333891424

# In[13]:

print ("RF r^2 score",r2_score(y_test,y_pred))

# out[13]:
RF r^2 score 0.9120696293757707

# In[14]:结果绘图

plt.scatter(y_train,rf.predict(X_train), label = 'Train', c='blue')
plt.title('RF Predictor')
plt.xlabel('Measured Solubility')
plt.ylabel('Predicted Solubility')
plt.scatter(y_test,rf.predict(X_test),c='lightgreen', label='Test', alpha = 0.8)
plt.legend(loc=4)
plt.savefig('RF Predictor.png', dpi=300)
plt.show()

---