QSAR prediction of antagonistic activity of PCBs towards human PXR by using heuristic method and best subset modeling

Polychlorinated biphenyls (PCBs) can antagonize human pregnane X receptor (hPXR) activation. Such chemicals could pose a serious threat to the reproductive and developmental ability of humans. The quantitative structure activity relationship (QSAR) provides a promising method for the estimation of PCBs’ antagonistic activity. In this investigation, a QSAR model was developed by using heuristic method and best subset modeling (r 2 = 0.873, q 2 LOO=0.742). The built model was validated externally by splitting the original data set into training and prediction sets. The results of the model derived are as follows: r 2 = 0.907, q 2 LOO=0.709, r 2 pred=0.676, suggesting developed QSAR model had good robustness and predictive ability. The applicability domain (AD) of the model was assessed by Williams plot. The antagonistic activity (−logK i ) of 108 PCBs, which are unavailable by experiment at present, was predicted within the applicability domain of the model. The critical structural features related to the activity of PCBs were identified.