人工神经网络用于1,1-二苯基乙烯衍生物的QSAR研究  

Study on the QSAR of 1,1-diphenylethylene Derivatives Using the Artificial Neural Network

作　　者：杜雨静[1] 范英芳[1] 张佳瑛[1] 

机构地区：[1]山西大学分子科学研究所,山西太原030006

出　　处：《科学之友（中）》2009年第9期93-94,96,共3页Friend of Science Amateurs

基　　金：山西省自然科学基金(2007011025);山西省归国留学基金(2006)

摘　　要：对于19个1,1-二苯基乙烯衍生物,分别采用人工神经网络(网络结构为3-7-1)和线性回归分析方法,建立了其抗雌激素活性/C与扩展的引力指数Go、17号氢原子的净电荷Q和24号氧原子与17号氢原子间库仑力KL之间的QSAR模型,ANN模型的相关系数R=0.9999,标准偏差SD=3.05888E-4;MLR模型的相关系数R=0.9660,标准偏差SD=0.1010。结果表明人工神经网络是一种比较精密的拟合方法,具有良好的预测效果。The anlieslrogen activily of 1,1-Diphenyhhylene derivatives （/C） are highly correlated with the extended gravitational index （Go）, coulombian force between the 24th oxygen and the 17th hydrogen （KL）, and net charge of the 17th hydrogen （Q）. For 19 1,1-Diphenyhhylene derivatives, using these parameters the QSAR models were set up respectively with ANN and MLR methods. The correlation coefficients and the standard deviation for former were R=0.9999 and SD=3.05888E-4, while for later were R=0.9660 and SD=0.1010.The result showed that the fitted performance of neural network method was comparatively precise and it has a preferable predicted effect.

关 键 词：人工神经网络 定量结构活性关系 1 1-二苯基乙烯衍生物 

分 类 号：O641[理学—物理化学]