河北化工2012，Vol.35Issue(9)：28-31,4.
人工神经网络用于氯代芳烃定量结构-活性关系研究
QSAR Study of Chlorinated Aromatic Hydrocarbons Using ANN
摘要
Abstract
The systematic study of the quantitative structure-activity relationship（QSAR） on 37 chlorinated aromatic hydrocarbons was performed by the artificial neural network based on the back propagation algorithm.For the artificial neural network method,when using the quantum chemical parameters about structure as the inputs of the neural network and the acute toxicities as the outputs of the neural network,the correlation coefficient was 0.996 5,the leave one out cross-validation regression coefficient was 0.991 1,the standard error was 0.04,the correlation coefficient of the test set was 0.988 4 and the absolute values of residual were less than 0.18.In order to make contrast,the QSAR model was set up by multiple linear regressions（MLR） method.For the model built by MLR,the correlation coefficient was 0.949 6,the correlation coefficient of the test set was 0.928 8,the standard error was 0.14,the absolute values of residual were less than 0.32 and the correlation coefficient of the test set was 0.950 5.The results showed that the performance of neural network method is better than that of MLR method.关键词
氯代芳烃/定量结构-活性关系/人工神经网络/急性毒性Key words
chlorinated aromatic hydrocarbons/quantitative structure-activity relationship/artificial neural network/acute toxicity分类
化学引用本文复制引用
何琴,李婧..人工神经网络用于氯代芳烃定量结构-活性关系研究[J].河北化工,2012,35(9):28-31,4.基金项目
河南省教育厅自然科学研究计划项目(批准号:2009B150023) （批准号:2009B150023）
