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.