| Artificial Neural Networks Applied to the Quantitative Structure-Activity Relationship Study of Para-substituted Phenols |
| |
| 作者姓名： | 宋新华 陈茁 俞汝勤 |
| |
| 作者单位： | Department of Chemistry and Chemical Engineering，Hunan University，Changsha 410082，PRC，Department of Chemistry and Chemical Engineering，Hunan University，Changsha 410082，PRC，Department of Chemistry and Chemical Engineering，Hunan University，Changsha 410082，PRC |
| |
| 基金项目： | Project supported by the National Natural Science Foundation of China. |
| |
| 摘 要： | The artificial neural network (ANN) model with back-propagation of error is used to study the quantitative structure-activity relationship of para-substituted phenol derivatives between the biological activity and the physicochemical property parameters. Network parameters are optimized, and an empirical rule for dynamically adjusting the network's learning rate is proposed to improve the network's performance. The results showthat the three-layer ANN model gives satisfactory performance, with f(x)=1/(1+exp(-x)) as the network node's input-output transformation function and the number of hidden nodes 10. The network gives the mean square error (rose) of 0.036 when predicting the biological activity of 26 para-substituted phenol derivatives. This result compares favourably with that obtained by the conventional methods.
|
Artificial Neural Networks Applied to the Quantitative Structure-Activity Relationship Study of Para-substituted Phenols |
| |
| SONG Xin-Hua CHEN Zhuo and YU Ru-Qin.Artificial Neural Networks Applied to the Quantitative Structure-Activity Relationship Study of Para-substituted Phenols[J].Science in China(Chemistry),1993(12). |
| |
| Authors: | SONG Xin-Hua CHEN Zhuo and YU Ru-Qin |
| |
| Abstract: | The artificial neural network (ANN) model with back-propagation of error is used to study the quantitative structure-activity relationship of para-substituted phenol derivatives between the biological activity and the physicochemical property parameters. Network parameters are optimized, and an empirical rule for dynamically adjusting the network's learning rate is proposed to improve the network's performance. The results showthat the three-layer ANN model gives satisfactory performance, with f(x)=1/(1+exp(-x)) as the network node's input-output transformation function and the number of hidden nodes 10. The network gives the mean square error (rose) of 0.036 when predicting the biological activity of 26 para-substituted phenol derivatives. This result compares favourably with that obtained by the conventional methods. |
| |
| Keywords: | artifieial neural network quantitative structure-activity relationship para-substituted phenols |
| 本文献已被 CNKI 等数据库收录！ |
