Development of an expert system rulebase for the prospective identification of photoallergens

Relationships between the structure and properties of chemicals can be prog rammed into knowledge-based systems such as DEREK (an acronym for 'Deductiv e Estimation of Risk from Existing Knowledge'). The DEREK knowledge-based c omputer system contains a sub-set of over 50 rules describing chemical subs tructures (toxophores) responsible for skin sensitization, This rulebase, b ased originally on Unilever historical in-house guinea pig maximisation tes t data, is largely complete and is undergoing refinement as the next stage of its development. As part of an ongoing program of validation and testing , the predictive ability of the sensitization rule set was assessed by proc essing the structures of over 100 chemical substances in the list of contac t allergens identified by the BgVV (German Federal Institute for Health Pro tection of Consumers). The exercise highlighted areas of chemistry where fu rther development of the rulebase was required, either by extension of the scope of existing rules or by generation of new rules where a sound mechani stic rationale for the biological activity could be established. several ch emicals likely to be acting as photoallergens were identified and rules for photoallergenicity were written covering three classes of chemicals. This paper describes work to extend the DEREK rules for photoallergenicity as pa rt of the European Phototox Project. (C) 2000 Elsevier Science B.V. All rig hts reserved.