摘要
通过计算获得了39个4-芳基-4氢-苯并吡喃化合物的11个结构特征参数,应用逐步线性回归方法对参数进行筛选.并用支持向量回归(SVR)算法,对4-芳基-4氢-苯并吡喃化合物与其凋亡诱导活性进行定量构效关系(QSAR)研究.通过核函数参数的优化,建立了预测模型,训练集和预测集的实验值与计算值的平方相关系数R2分别为0.997和0.893.研究结果表明,支持向量回归算法可用于小样本数的药物分子设计研究,以合成具有更高生物活性的新药物.
Support vector machines algorithm was applied to study the quantitative structure-activity relationship of 39 apoptosis-inducing 4-aryl-4H-chromenes. The eleven kinds of molecular characteristic parameters were calculated and optimized by stepwise multiple regression. A more predictive model was set up through optimizing kernel function parameters. The squared correlation coefficient （R2） values between experimental versus calculated values for 30 molecules in the training set and 9 molecules in the test set are 0.997 and 0. 893, respectively. The satisfactory results showed that support vector regression algorithm would be well used for drug molecules design.
出处
《分子科学学报》
CAS
CSCD
北大核心
2009年第4期241-246,共6页
Journal of Molecular Science
基金
辽宁省科技厅资助项目(2008S104)
关键词
支持向量机
定量构效关系
逐步线性回归
4-芳基-4氢-苯并吡喃
support vector machines
quantitative structure-activity relationship
stepwise multiple regression
4-aryl- 4H-chromenes
