In the field of environmental toxicology, and especially aquatic toxicology, quantitative structure activity relationships (QSARs) have developed as scientifically-credible tools for predicting the toxicity of chemicals when little or no empirical data are available. A basic and fundamental understanding of toxicological principles has been considered crucial to the continued acceptance and application of these techniques as biologically relevant. As a consequence, there has been an evolution of QSAR development and application from that of a chemical-class perspective to one that is more consistent with assumptions regarding modes of toxic action. The assessment of a compound’s likely mode of toxic action is critical for a correct QSAR selection; incorrect mode of action-based QSAR selections can result in 10- to 1000-fold errors in toxicity predictions. The establishment of toxicologically-credible techniques to assess mode of toxic action from chemical structure requires toxicodynamic knowledge bases that are clearly defined with regard to exposure regimes and biological models/endpoints and based on compounds that adequately span the diversity of chemicals anticipated for future applications. With such knowledge bases classification systems, including rule-based experts systems, have been established for use in predictive aquatic toxicology applications.