The current status and future applicability of quantitative structure-activity relationships (QSARs) in predicting toxicity

Abstract

The current status of quantitative structure-activity relationships (QSARs) in predicting toxicity is assessed. Widespread use of these methods to predict toxicity from chemical structure is possible, both by industry to develop new compounds, and also by regulatory agencies. The current use of QSARs is restricted by the lack of suitable toxicity data available for modelling, the unsuitability of simplistic modelling approaches for the prediction of certain endpoints, and the poor definition and utilisation of the applicability domain of models. Suggestions to resolve these issues are made.