Neural Network Method for Predicting Peptides that Bind Major Histocompatibility Complex Molecules

Peptides that bind major histocompatibility complex (MHC) products exhibit allele-specific sequence motifs. The motifs, however, are neither necessary nor sufficient for binding. In particular, about 66% of the peptides that exhibit motifs do not bind the corresponding MHC molecule. This chapter describes a neural network based method for identifying MHC-binding peptides. The neural net is superior to simple motif searches in eliminating false positives; its behavior can be coarsely tuned to the strength of binding desired, and its applicability is easily extendable to any desired MHC allele.