物理化学学报 >> 1996, Vol. 12 >> Issue (11): 1027-1030.doi: 10.3866/PKU.WHXB19961115

研究简报 上一篇    下一篇

酚类化合物的多元回归分析及神经网络法研究

郭明,许禄   

  1. 中国科学院长春应用化学研究所,长春 130022
  • 收稿日期:1996-05-13 修回日期:1996-07-05 发布日期:1996-11-15
  • 通讯作者: 许禄

Study on Phenol Compounds Using Multiple Regression and Neural Network Methods

Guo Ming,Xu Lu   

  1. Changchun Institute of Applied Chemistry,The Chinese Academy of Sciences,Changchun 130022
  • Received:1996-05-13 Revised:1996-07-05 Published:1996-11-15
  • Contact: Xu Lu

关键词: 拓扑指数, 定量结构-活性/性质相关性, 酚类化合物

Abstract:

In this paper, the molecular connectivity indices and the electronic charge parameters of forty-eight phenol compounds nave been calculated. and applied for studying the relationship between partition coefficients and structure of phenol compounds. The results demonstrate that the properties of compounds can be described better with selective parameters, and the results obtained by neural network are superior to that by multiplle regression.

Key words: Topological indices, Quantitative structure-activity/property relationship, Phenols