| Cytotoxic T lymphocyte are the key mediators of specific immune responses against diseases such as infectious diseases, cancer, and autoimmune diseases. The minimal essential units of information, T-cell epitopes, which are derived from self and nonself proteins can provoke the cellular immune responses when presented to T cell. Thereby, the precision prediction of T cell epitopes, followed by confirmatory studies in vitro, remains a critical step in the development of epitope-driven vaccines.In general, MHC class I molecules present peptides 8-10 amino acids in length that are recognized predominately by CD8+ cytotoxic T lymphocytes. Host- or pathogen-derived intracellular proteins are cleaved by a complex of proteases in the proteasome. Small peptide fragments are then transported into the endoplasmic reticulum (ER), where they form complexes with MHC class I andβ2-microglobulin. The peptide-MHC class I complexes are transported to the cell surface for presentation to the receptors of CD8+ T cells. Several computer algorithms are currently being used for epitope prediction of various MHC class I molecules, based either on the analysis of natural MHC ligands or on the binding properties of synthetic peptides. The rules that govern the binding of peptides to MHC class I molecules are quite well understood and have been used to design computerized prediction tools. The algorithms that are currently available are based on binding motifs, matrices, artificial neural networks (ANNs) or structure. Moreover, the analysis of proteasomal digest of peptides and whole proteins has led to the development of algorithms for the prediction of proteasomal cleavages.Although computer-driven algorithms listed above are now widely used, they do present obvious drawbacks: (1). Most of the algorithms are based on the protein sequences but ignored the fact that the peptide side chain has complicated interactions with the... |