| 基于支持向量机回归的麻醉药毒性的QSPR研究 |
| |
| 引用本文： | 王丽,陆文聪,陆瑾,杨善升.基于支持向量机回归的麻醉药毒性的QSPR研究[J].计算机与应用化学,2007,24(12):1617-1621. |
| |
| 作者姓名： | 王丽 陆文聪 陆瑾 杨善升 |
| |
| 作者单位： | 1. 上海大学理学院化学系,上海,200444
2. 上海大学材料科学与工程学院,上海,20007 |
| |
| 基金项目： | 自然科学基金资助项目。(No．20503015) |
| |
| 摘 要： | 采用支持向量机回归(SVR)方法研究了39个麻醉药毒性的定量构效关系,基于留一法交叉验证的结果,模型的相关系数为0.970。结果表明,所建SVR模型的精度高于逆传播人工神经网络(BPANN)、多元线性回归(MLR)和偏最小二乘法(PLS)所得的结果。
|
| 关 键 词： | 定量结构性质关系 支持向量机 麻醉药毒性 |
| 文章编号： | 1001-4160(2007)12-1617-1621 |
| 修稿时间： | 2007年11月3日 |
Quantitative structure-property relationships based on support vector regression for some narcotics toxicities |
| |
| Wang Li,Lu Wencong,Lu jin,Yang Shansheng.Quantitative structure-property relationships based on support vector regression for some narcotics toxicities[J].Computers and Applied Chemistry,2007,24(12):1617-1621. |
| |
| Authors: | Wang Li Lu Wencong Lu jin Yang Shansheng |
| |
| Abstract: | A quantitative structure-property relationships (QSPR) study based on support vector regression (SVR) for the toxicities (pEC50) of 39 narcotics was performed. SVR method with leave-one-out cross-validation was used for evaluating the regression models. The correlation coefficient obtained by the models was 0.970. The result showed that the prediction accuracy of SVR model was higher than those of back propagation artificial neural network (BP ANN), multiple linear regression (MLR) and partial least squares (PLS) methods. |
| |
| Keywords: | Quantitative structure-property relationships Support vector regression narcotic toxicity |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
