QSAR Studies on PCDD/Fs by Kernel PLS  

作　　者：TANG Kai-lin LI Tong-hua CHEN Kai 

机构地区：[1]Department of Chemistry, Tongji University, Shanghai 200092, P. R. China

出　　处：《Chemical Research in Chinese Universities》2008年第5期541-545,共5页高等学校化学研究（英文版）

基　　金：the National Natural Science Foundation of China(No.20275026).

摘　　要：QSPR models of PCDD/Fs were generated by means of kernel partial least squares. The molecular distance-edge vector method was used as descriptors to get model I for predicting PCDD/Fs retention behavior. The chlorinated positions were also used and model II was obtained. In studied cases, the predictive ability of the KPLS model is comparable or superior to those of PLS and ANN. The results indicate that KPLS can be used as an alternative powerful modeling tool for QSPR studies.QSPR models of PCDD/Fs were generated by means of kernel partial least squares. The molecular distance-edge vector method was used as descriptors to get model I for predicting PCDD/Fs retention behavior. The chlorinated positions were also used and model II was obtained. In studied cases, the predictive ability of the KPLS model is comparable or superior to those of PLS and ANN. The results indicate that KPLS can be used as an alternative powerful modeling tool for QSPR studies.

关 键 词：QSPR modeling Kernel partial least squares PCDD/FS 

分 类 号：TG142[一般工业技术—材料科学与工程]