| 支持向量分类算法在5-HT_3受体拮抗剂的构效关系研究中的应用(英文) |
| |
| 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-HT_3受体拮抗剂的构效关系研究中的应用(英文)[J].上海大学学报(英文版),2006(4). |
| |
| 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，Department of Chemistry College of Sciences Shanghai University Shanghai 200444 P.R. China，Department of Chemistry College of Sciences Shanghai University Shanghai 200444 P.R. China，Department of Chemistry College of Sciences Shanghai University Shanghai 200444 P.R. China |
| |
| 基金项目： | Project supported by National Natural Science Foundation ofChina(Grant No .20373040) |
| |
| 摘 要： | 1 Introduction The 5-hydroxytryptamine type 3 (5-HT3) receptorantagonists1-2]are currently used in the treatment ofchemotherapy and radiotherapy induced emesis . Thecompounds are based onthe parent structure showninFig.1 ,the aromatic systems include mono- and bicy-clic rings ,with or without heteroatoms ,and with vari-ous substitution patterns .This range of structural vari-ation makes it difficult to treat the analysis of thesecompounds .Fig .1 Parent structure of 5-HT3antagonists With t…
|
Support vector classification for SAR of 5-HT_3 receptor antagonists |
| |
| YANG Shan-sheng LU Wen-cong JI Xiao-bo CHEN Nian-yi.Support vector classification for SAR of 5-HT_3 receptor antagonists[J].Journal of Shanghai University(English Edition),2006(4). |
| |
| Authors: | YANG Shan-sheng LU Wen-cong JI Xiao-bo CHEN Nian-yi |
| |
| Institution: | YANG Shan-sheng LU Wen-cong JI Xiao-bo CHEN Nian-yi Department of Chemistry,College of Sciences,Shanghai University,Shanghai 200444,P.R. China |
| |
| 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-HT_3) 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. |
| |
| Keywords: | support vector classification structure-activity relationship chemometrics 5-HT_3 receptor antagonists |
| 本文献已被 CNKI 等数据库收录！ |
