多环芳烃及其衍生物致癌性的支持向量机预测模型  

SVM Model for Predicting Carcinogenicity of Polycyclic Aromatic Hydrocarbons and Derivatives

作　　者：祁正兴[1] 印家健[1] 陆敏春[1] 李梦龙[1] 

机构地区：[1]四川大学化学学院

出　　处：《四川大学学报（自然科学版）》2005年第6期1213-1218,共6页Journal of Sichuan University(Natural Science Edition)

基　　金：湖南大学化学生物传感与化学计量学国家重点实验室基金资助

摘　　要：分别用支持向量分类法、Fisher法判别、K最近邻法和反向传播人工神经网络,对353种多环芳烃及其衍生物致癌性构建二分类模型,并采用留一法交叉校验作比较,所构建的支持向量机模型的误报样本数及预报准确率均高于其它3种方法.实验结果表明,支持向量机算法具有较强的稳健性和良好的泛化能力,能够用于多环芳烃及其衍生物致癌性的二分类和预测.In this article, support vector machine （SVM）, fisher discrimination （FD） and K nearest neighbors （K-NN） methods are employed to set up the model of carcinogenic properties of 353 polycyclic aromatic hydrocarbons, the model outputs are cross-validated by the leave-one-out method and compared with each other. The results indicate that SVM is better than the other three methods when the prediction accuracy . is concerned. The experiment indicates that SVM possess better robustness and generalization capability and is the best candidate to classify and predict the carcinogenic properties of polycyclic aromatic hydrocarbons and Derivative.

关 键 词：支持向量机 多环芳烃及其衍生物 双区理论 留一法 

分 类 号：O64[理学—物理化学]