SCOPE AND LIMITATION OF SOME APPROACHES TO PREDICTING CONTACT HYPERSENSITIVITY

Allergic contact dermatitis (ACD) is the endpoint of a complex sequenc e of events. Construction of a predictive computational assay requires a combination of statistical analyses, semi-empirical modelling, chem ical acumen and a good understanding of prohapten activation. Main eve nts on the path to the altered self are chemical and microbial convers ion on and in the stratum corneum (SC), epidermal penetration, non-spe cific binding, and finally hapten-protein conjugation. This report rev iews the principal approaches currently taken in the prediction of ACD , using computer-based SAR, QSAR and expert systems, and also includes the BIOSAR models, which combine statistical analysis with chemical k nowledge. Specifically designed to predict the ACD potential of chemic als in man, the BIOSAR approach of two-value regression analysis achie ved a success rate of 88% when trained on a set of 72 compounds of wid e diversity, with a sensitivity of 83% and specificity of 100%. (C) 19 98 Elsevier Science Lid. All rights reserved.