用投影寻踪方法建立准确的定量构性关系模型  

Data Mining for Seeking Accurate Quantitative Relationship Between Molecular Structure and GC Retention Indices of Alkanes by Projection Pursuit

作　　者：杜一平[1] 王文明[1] 张彦芳 

机构地区：[1]山东理工大学,山东淄博255091

出　　处：《山东工程学院学报》2002年第2期25-27,共3页Journal of Shandong Institute of Technology

摘　　要：用投影寻踪的方法搜寻理想的投影方向 ,以便使高维数据降维而发现数据中化合物的分类信息 .并利用这样的分类信息对样本进行分类建模 ,取得了理想的结果 .Primary data mining on alkanes for seeking accurate quantitative relationship between molecular structure and retention indices of gas chromatography is developed in this paper. Based on the results of classification obtained from projection pursuit, a new idea to build structure-property relationship models, which is to model different relationships for different classes of the alkanes, is proposed. The results obtained in this work show that the technique of projection pursuit developed in statistics is a quite promising tool for seeking accurate quantitative structure-activity relationship (QSAR) and/or quantitative structure-property relationship (QSPR) researches.

关 键 词：投影寻踪 定量构性关系 拓扑指数 保留指数预测 分类信息 化合物 量子化学 化学结构 

分 类 号：O641.1[理学—物理化学]