• 关键词：酚类化合物  定量结构与毒性相关性  拓扑指数  疏水性参数  范德华体积

• 基金项目：国家自然科学基金

• 郭明
• 中国科学院长春应用化学研究所, 长春 130022

• 许禄
• 中国科学院长春应用化学研究所, 长春 130022

• 摘要：直接应用化合物的分子结构式产生的结构描述参量研究了45个酚类化合物的麻醉毒性和分子结构之间的相关性,用多元回归分析和神经网络法建立了相应的数学模型,并用其预测了5个酚类化合物的麻醉毒性。结果表明,所提取的结构参量较好地反映这类化合物的结构特性,而用神经网络法所得结果优于多元回归分析结果。

• Abstract：Quantitative structure toxicity models were developed that link molecular structures of a set of 50 alkylated and/or halogenated phenols with their polar narcosis toxicity, expressed as the negative logarithm of the IDC 50 (50% growth inhibitory concentration) value in milimoles per liter. Regression alalysis and fully connected, feed forward neural networks were used to develop the models. Two neural network training algorithms (back propagation and a quasi Newton method) were employed.The results demonstrated that the property of compounds can be described better by selective parameters of this paper. Superior results have been achieved by quasi Newton neural network to regression analysis.

• Key words：phenols  quantitative structure toxicity relationship  topological indices  partition coefficient  Van der Waals volumes

• 
  摘要点击次数： 1661 全文下载次数： 3003