高等学校化学学报

高等学校化学学报

• 研究论文 • 上一篇    下一篇

Multi-KNN-SVR组合预测在含氟化合物QSAR研究中的应用

谭显胜1,2, 袁哲明1, 周铁军2, 王春娟1, 熊洁仪1   

    1. 湖南农业大学生物安全科学技术学院,
    2. 理学院, 长沙 410128
  • 收稿日期:2007-03-19 修回日期:1900-01-01 出版日期:2008-01-10 发布日期:2008-01-10
  • 通讯作者: 袁哲明

Multi-KNN-SVR Combinatorial Forecast and Its Application to QSAR of Fluorine-Containing Compounds

TAN Xian-Sheng1,2, YUAN Zhe-Ming1*, ZHOU Tie-Jun2, WANG Chun-Juan1, XIONG Jie-Yi1   

    1. College of Bio-safety Science and Technology,
    2. College of Science, Hunan Agricultural University, Changsha 410128, China
  • Received:2007-03-19 Revised:1900-01-01 Online:2008-01-10 Published:2008-01-10
  • Contact: YUAN Zhe-Ming

PDF (PC)

摘要： 为深入认识含氟农药生物活性与其结构之间的关系, 建立了理想的QSAR模型, 从化合物油水分配系数等7个分子结构描述符出发, 基于支持向量回归(SVR)和MSE最小原则, 经自动寻找最优核函数和非线性筛选描述符, 构建了多个K-最近邻(KNN)预测子模型. 再经非线性筛选获得保留子模型, 以保留子模型实施组合预测(Multi-KNN-SVR). 33种含氟化合物对5种不同病害生物活性的留一法组合预测结果表明, 采用非线性筛选描述符和KNN子模型能有效地提高预测精度, 基于多个KNN子模型的非线性组合能进一步提高预测性能. Multi-KNN-SVR组合预测在QSAR以及其它相关预测研究中具有广泛应用前景.

关键词: 含氟化合物, 支持向量回归, 定量构效关系, K-最近邻, 组合预测

Abstract: To further understand the quantitative structure-activity relationship (QSAR) of fluorine-containing pesticide and improve the prediction precision of QSAR models, a novel nonlinear combinatorial forecast me-thod named Multi-KNN-SVR, multi-K-nearest neighbor based on support vector regression, was proposed. The novel method includes the following key steps: firstly, seeking the best kernel automatically based on the minimum mean square error (MSE); secondly, screening descriptors nonlinearly by F-test; finally, carrying out the combinatorial forecast with multiple KNN sub-models. Multi-KNN-SVR was applied to the QSAR for the antibacterial bioactivities of 33 fluorine-containing pesticides against 5 different plant diseases. The results of leave-one-out test show that screening descriptors and sub-models were essential, and the combinatorial forecast after screening sub-models could get a better precision than single KNN model. The predicte results also indicated that Multi-KNN-SVR had the advantages of high prediction precision (MSE=0.005—0.015, MAPE=2.136—3.164), high stability, strong generalization ability, structural risk minimization, non-linear characteristics and avoiding the over-fit in all reference models. Multi-KNN-SVR, therefore, can be widely used in QSAR and other related fields.

Key words: Fluorine-containing compound, Support vector regression, Quantitative stucture-activity relationship(QSAR), K-nearest neighbor, Combinatorial forecast

中图分类号: 

TrendMD: