基于支持向量机的乙酰胆碱酯酶抑制剂的构效关系研究

QSAR study of AchEI by using support vector regression

基于最大相关性-最小冗余性方法(mRMR),对27个乙酰胆碱酯酶(AchE)抑制剂进行了特征变量筛选,获得了14个变量。然后,采用支持向量机回归(SVR)方法研究了这27个化合物的定量构效关系。通过留一法交叉验证进行评估,其平均相对误差MRE=2.72%,均方根误差RMSE=0.273,q^2=0.936。最后,通过敏感性分析发现,特征变量logP与药物活性呈负相关,refractivity和water accessible surface area与药物活性呈正相关。

In this work, support vector regression （SVR）, an effective machine learning method, proposed by Vapnik was applied to establish QSAR model for a series of AchEI. Fourteen descriptors were selected for constructing the SVR mode by using mRMR-Forward feature selection method. The parameters （e, C） were adjusted by leave-one-out cross validation （LOOCV） method which was used to judge the predictive power of different models. After optimization, one optimal SVR-QSAR model was attained, and the mean relative errors （MRE） of LOOCV by using SVR is 2.72 %. As a result, logP negatively affected the activity, refractivity and water accessible surface area positively affected the activity.