| 拮抗药化合物活性的支持向量机研究 |
| |
| 引用本文： | 张向东,毕韶丹,关宏宇.拮抗药化合物活性的支持向量机研究[J].辽宁大学学报(自然科学版),2005,32(3):229-233. |
| |
| 作者姓名： | 张向东 毕韶丹 关宏宇 |
| |
| 作者单位： | 1. 辽宁大学,化学系,辽宁,沈阳,110036
2. 辽宁大学,化学系,辽宁,沈阳,110036;沈阳理工大学,化工分院,辽宁,沈阳,110168 |
| |
| 摘 要： | 支持向量机（SVM）算法是一种适用于有限的已知样本训练建模，进而预报未知样本属性的模式识别新方法，应用该方法对拮抗药化合物的生物活性进行了预报，讨论了化合物结构参数、计算核函数及参数的选择和优化问题，建立了药物活性预测的数学模型．研究表明，支持向量机（SVM）算法在小样本情况下，可获得令人满意的结果．
|
| 关 键 词： | 支持向量机算法 QSAR 核函数 |
| 文章编号： | 1000-5846（2005）03-0229-05 |
| 收稿时间： | 2004-10-10 |
| 修稿时间： | 2004-10-10 |
Study on Activity of Antagonists by the Study of Support Vector Machines |
| |
| ZHANG Xiang-dong,BI Shao-dan,GUAN Hong-yu.Study on Activity of Antagonists by the Study of Support Vector Machines[J].Journal of Liaoning University(Natural Sciences Edition),2005,32(3):229-233. |
| |
| Authors: | ZHANG Xiang-dong BI Shao-dan GUAN Hong-yu |
| |
| Abstract: | Support vector machine proposed by Vapnik is a newly developed technique for data mining. It is suitable for the data processing based on finite number of training samples, with special technique to restrict overfitting. In this work, the method is applied to predict the activity of antagonists . The mathematic models are set up by dealing with data. The satisfactory result of practical application indicates that the algorithm of SVM overcomes the problem of overfitting excellently. |
| |
| Keywords: | support vector machine QSAR kernel function |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
