首页 | 本学科首页   官方微博 | 高级检索  
检索        

神经网络方法在5,7,8位取代的喹诺酮类化合物定量构效关系中的应用
引用本文:郭波涛,黄明辉,柏干荣,张彦琦,杨梦苏,易东.神经网络方法在5,7,8位取代的喹诺酮类化合物定量构效关系中的应用[J].华南国防医学杂志,2005,19(1):48-51.
作者姓名:郭波涛  黄明辉  柏干荣  张彦琦  杨梦苏  易东
作者单位:1. 第三军医大学卫生统计学教研室,重庆,400038
2. 香港城市大学基因组科技应用研究中心
基金项目:国家自然科学基金资助项目(60371034)
摘    要:目的探讨神经网络方法应用于5,7,8位取代的喹诺酮类化合物定量构效关系研究的效果。方法利用Matlab软件包构建一个三层的BP神经网络,对数据集进行计算,并将结果与线性回归进行比较。结果神经网络法的误差平方和为0.3042,小于线性回归法,预测的相关系数为0.86。结论神经网络方法获得了比回归模型更精密的拟合。

关 键 词:喹诺酮类化合物  定量构效关系  络方  构效关系研究  BP神经网络  Matlab  神经网络法  线性回归法  方法应用  相关系数  回归模型  软件包  数据集  平方和
修稿时间:2004年11月20

Application of Neural Network to study of Quantitive Structure- Activity Relationship of 5,7,8 - Substituted Quinolones
CUO Bo-tao,HUANG Ming-hui,YANG Meng-su,et al..Application of Neural Network to study of Quantitive Structure- Activity Relationship of 5,7,8 - Substituted Quinolones[J].Military Medical Journal of South China,2005,19(1):48-51.
Authors:CUO Bo-tao  HUANG Ming-hui  YANG Meng-su  
Institution:CUO Bo-tao,HUANG Ming-hui,YANG Meng-su,et al. Department of Medical Statistics,Third Military Medical University,Chongqing 400038,China
Abstract:Objective To explore the effect of neural network( NN) on the study of structure - activity relationship of 5,7,8 - substituted quinolones .Methods A three- layer BP neural network was built by the Matlab software.The data were calculated and analysed.The results of present study were compared with those of the study by linear regression. Results NN'SSE (sum of square errors) was 0.3042, less than that of linear regression. The predicted correlation coefficient was 0.86. Conclusion The fitted performance of NN was better than that of linear regression.
Keywords:BP neural network  quantirve structure- activity relationship  Matlab software
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号