This work deals with the use of predictors to identify useful B-cell linear epitopes to develop immunoassays.
Experimental techniques to meet this goal are quite expensive and time consuming. Therefore, we tested 5 free, online
prediction methods (AAPPred, ABCpred, BcePred, BepiPred and Antigenic) widely used for predicting linear epitopes,
using the primary structure of the protein as the only input. We chose a set of 65 experimentally well documented epitopes
obtained by the most reliable experimental techniques as our true positive set. To compare the quality of the predictor
methods we used their positive predictive value (PPV), i.e. the proportion of the predicted epitopes that are true, experimentally
confirmed epitopes, in relation to all the epitopes predicted. We conclude that AAPPred and ABCpred yield the
best results as compared with the other programs and with a random prediction procedure. Our results also indicate that
considering the consensual epitopes predicted by several programs does not improve the PPV.