| 支持向量分类算法在5-HT3受体拮抗剂的构效关系研究中的应用 |
| |
| 引用本文： | 杨善升,陆文聪,纪晓波,陈念贻. 支持向量分类算法在5-HT3受体拮抗剂的构效关系研究中的应用[J]. 上海大学学报(英文版), 2006, 10(4): 366-370. DOI: 10.1007/s11741-006-0016-7 |
| |
| 作者姓名： | 杨善升 陆文聪 纪晓波 陈念贻 |
| |
| 作者单位： | Department of Chemistry, College of Sciences, Shanghai University, Shanghai 200444, P.R. China |
| |
| 摘 要： | In this work, support vector classification （SVC） algorithm was used to build structure-activity relationship （SAR） model of the 5-hydroxytryptamine type 3 （5-HT3 ） receptor antagonists with 26 compounds. In a benchmark test, SVC was compared with several techniques of machine learning currently used in the field. The prediction performance of the model was discussed on the basis of the leave-one-out cross-validation. The results show that the accuracy of prediction of SVC model was higher than those of back propagation artificial neural network （BP ANN）, K-nearest neighbor （KNN） and Fisher methods.
|
| 关 键 词： | 支持向量分类 结构-活性关系 化学计量学 5-HT3受体拮抗体 |
| 文章编号： | 1007-6417（2006）04-0366-05 |
| 收稿时间： | 2004-09-28 |
| 修稿时间： | 2005-04-12 |
Support vector classification for SAR of 5-HT3 receptor antagonists |
| |
| Shan-sheng Yang Ph. D. Candidate,Wen-cong Lu,Xiao-bo Ji,Nian-yi Chen. Support vector classification for SAR of 5-HT3 receptor antagonists[J]. Journal of Shanghai University(English Edition), 2006, 10(4): 366-370. DOI: 10.1007/s11741-006-0016-7 |
| |
| Authors: | Shan-sheng Yang Ph. D. Candidate Wen-cong Lu Xiao-bo Ji Nian-yi Chen |
| |
| Abstract: | In this work, support vector classification (SVC) algorithm was used to build structure-activity relationship (SAR) model of the 5-hydroxytryptamine type 3 (5-HT3) receptor antagonists with 26 compounds. In a benchmark test, SVC was compared with several techniques of machine learning currently used in the field. The prediction performance of the model was discussed on the basis of the leave-one-out cross-validation. The results show that the accuracy of prediction of SVC model was higher than those of back propagation artificial neural network (BP ANN), K-nearest neighbor (KNN) and Fisher methods. Project supported by National Natural Science Foundation of China(Grant No. 20373040) |
| |
| Keywords: | support vector classification structure-activity relationship chemometrics 5-HT3 receptor antagonists |
| 本文献已被 维普 万方数据 SpringerLink 等数据库收录！ |
