人工神经网络预测多氯代二苯并呋喃类化合物的正辛醇/水分配系数  

Predicting n-Octanol/Water Partition Coefficients of Polychlorinated Dibenzofurans with Artificial Neural Network

作　　者：俞青芬[1] 

机构地区：[1]青海民族大学化学系,青海西宁810007

出　　处：《广西师范大学学报（自然科学版）》2011年第4期92-98,共7页Journal of Guangxi Normal University:Natural Science Edition

基　　金：国家自然科学基金资助项目(30760195)

摘　　要：采用Chemoffice8.0中的MOPAC-AM1算法对多氯代二苯并呋喃类(PCDFs)化合物的量子化学结构参数进行计算,并将筛选后的量化参数作为PCDFs分子的结构描述符。利用人工神经网络中的反向传播网络和径向基函数网络,建立分子结构与正辛醇/水分配系数间的相关模型并进行预测。将所得结果与多元回归方法的结果进行对比分析,发现反向传播网络和径向基函数网络所得结果均优于多元回归方法。The structure parameters of the quantum chemistry for polychlorinated dibenzofurans （PCD- Fs） compounds were calculated by using the MOPAC-AM1 method in Chemoffice 8. 0. Some parameters are selected as the structure descriptors of PCDFs compounds. The molecular structures and the model of n-octanol/water partition coefficients are constructed and predicted in terms of back-propagation net-work and radial basis function networks in artificial neural network. These results are compared with the results of multiple regression methods. It can be found that the results of back-propagation network and radial basis function networks are better than those of multiple regression methods.

关 键 词：人工神经网络 多氯代二苯并呋喃 正辛醇/水分配系数 

分 类 号：O625.2[理学—有机化学]