STATISTICAL COMPARISON OF ESTABLISHED T-CELL EPITOPE PREDICTORS AGAINST A LARGE DATABASE OF HUMAN AND MURINE ANTIGENS

Identification of T-cell epitopes within a protein antigen is an impor tant tool in vaccine design. The T-cell epitope prediction schemes oft en are exploited by workers but have proved unreliable in comparison w ith experimental techniques. We compared published T-cell epitope pred ictors against two databases of human and murine T-cell epitopes. Each predictor was assessed against random cyclic permutations of epitopes in order to determine significance. Predictor performance was express ed in terms of two parameters, specificity and sensitivity. Specificit y is an expression of the quality of predictions, whereas sensitivity is an expression of the quantity of epitopes predicted. Against the hu man data set, the strip-of-hydrophobic helix algorithm [Stille et al., Molec. Immun. 24, 1021-1027 (1987)] was the only significant predicto r (p < 0.05), whereas against murine data only, the Roth2 pattern [Rot hbard and Taylor, EMBO J. 7, 93-100 (1988)] was significant (p < 0.05) . Not only were the majority of algorithms no better than random again st both data sets, against the murine data two schemes were significan t (p < 0.05) anti-predictors. This report indicates which predictors a re relevant statistically and is the first to describe anti-predictors which can themselves be useful in the identification of T-cell epitop es.