RDKit | 基于随机森林的化合物活性二分类模型

基于随机森林算法的化合物二分类机器学习模型

代码示例

   

    

     

      

     
     

      

       #导入依赖包
      
     
    

     

      

     
     

      

       import pandas as pd
      
     
    

     

      

     
     

      

       import numpy as np
      
     
    

     

      

     
     

      

       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
      
     
    

     

      

     
     

      

       from rdkit.Chem import PandasTools
      
     
    

     

      

     
     

      

       from sklearn.ensemble import RandomForestClassifier
      
     
    

     

      

     
     

      

       from sklearn.utils import shuffle
      
     
    

     

      

     
     

      

       from sklearn import metrics
      
     
    

     

      

     
     

      

       from sklearn import model_selection
      
     
    

     

      

     
     

      

       from sklearn.metrics import roc_curve, auc
      
     
    

     

      

     
     

      

       import matplotlib.pyplot as plt
      
     
   
  

   

    

     

      

     
     

      

       #定义化合物指纹计算函数
      
     
    

     

      

     
     

      

       def get_fps(mol):
      
     
    

     

      

     
     

      

           # 计算指纹 (clogP, PSA, etc etc)
      
     
    

     

      

     
     

      

           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)