| 酚类化合物的QSAR研究 |
| |
| 引用本文： | 郭明,许禄.酚类化合物的QSAR研究[J].环境科学学报,1998,18(2):122-127. |
| |
| 作者姓名： | 郭明 许禄 |
| |
| 作者单位： | 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.
|
| 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 |
| 收稿时间： | 1996/5/13 0:00:00 |
| 修稿时间： | 1997/2/22 0:00:00 |
QUANTITATIVE STRUCTURE--ACTIVITY RELATIONSHIP FOR TOXICITY OF PHENOLS USING REGRESSION ANALYSIS AND NEURAL NETWORK |
| |
| Guo Ming and Xu Lu.QUANTITATIVE STRUCTURE--ACTIVITY RELATIONSHIP FOR TOXICITY OF PHENOLS USING REGRESSION ANALYSIS AND NEURAL NETWORK[J].Acta Scientiae Circumstantiae,1998,18(2):122-127. |
| |
| Authors: | Guo Ming and Xu Lu |
| |
| Institution: | Changchun Institute of Applied Chemistry, Chinese Academy of Sciences, Changchun 130022 and Changchun Institute of Applied Chemistry, Chinese Academy of Sciences, Changchun 130022 |
| |
| 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. |
| |
| Keywords: | phenols quantitative structure toxicity relationship topological indices partition coefficient Van der Waals volumes |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《环境科学学报》浏览原始摘要信息 |
| 点击此处可从《环境科学学报》下载免费的PDF全文 |
|
