Quantitative structure-property relationship modeling of skin sensitization: a quantitative prediction

Abstract

A quantitative structure-property relationship (QSPR) model for predicting the skin sensitization effects of chemical compounds has been developed. An extensive database of test results from three exclusive test procedures was used for QSPR model development. Since the experimental procedure and end-point ranking of data for local lymph node assay (LLNA), guinea pig maximization test (GPMT), and Federal Institute for Health Protection of Consumers and Veterinary Medicine (BgVV) are different, three separate QSPR models were developed. Effective non-linear regression models were used for QSPR model development. The predictive capability of the final QSPR models was further improved by using a combination of literature-recommended and structural descriptors. The resultant QSPR models are capable of predicting skin sensitization of the diverse set of molecules considered with accuracies of 90%, 95%, and 90% for the LLNA, GPMT, and BgVV datasets, respectively.