A comparative QSAR study on the estrogenic activities of persistent organic pollutants by PLS and SVM

Quantitative structure-activity relationships (QSARs) were determined using partial least square (PLS) and support vector machine (SVM). The predicted values by the final QSAR models were in good agreement with the corresponding experimental values. Chemical estrogenic activities are related to atomic properties (atomic Sanderson electronegativities, van der Waals volumes and polarizabilities). Comparison of the results obtained from two models, the SVM method exhibited better overall performances. Besides, three PLS models were constructed for some specific families based on their chemical structures. These predictive models should be useful to rapidly identify potential estrogenic endocrine disrupting chemicals.