Comparative molecular field analysis (CoMFA), a three-dimensional quantitative structure-activity relationship (3D-QSAR) paradigm, was used to examine androgen receptor-binding affinities of a series of structurally diverse natural, synthetic, and environmental chemicals of interest. The CoMFA/3D-QSAR model successfully illustrates that the overall steric and electrostatic properties of structurally diverse ligands for the androgen receptor are necessary and sufficient to describe the binding affinity. The practical utility of models of this type is demonstrated using parent compounds in the training set and known as well as putative biological metabolites as test set molecules. The ability of the model to accurately predict binding affinity of test set molecules suggests that structure-based 3D-QSAR models may be used to supplement the process of hazard identification. The application of 3D-QSAR models within a toxicological framework is, at present, limited by the quantity and quality of biological data for relevant biomarkers of toxicity.