Current methods for the prediction of T‐cell epitopes

T‐cell epitopes are specific peptide sequences derived from foreign or own proteins that can initiate an immune response and which are recognized by specific T‐cells when displayed on the surface of other cells. The prediction of T‐cell epitopes is of particular interest in vaccine design, disease prevention and the development of immunotherapeutics. There are two principal categories of predictive methods: peptide‐sequence based and peptide‐structure‐based. Sequence‐based methods make use of various approaches to identify likely immunogenic amino acid sequences, such as sequence motifs, decision trees, partial least squares (PLS), quantitative matrices (QM), artificial neural networks (ANN), hidden Markov models (HMM), and support vector machines (SVM). Structure‐based methods are more diverse in nature and involve approaches such as quantitative structure‐activity relationships (QSAR), molecular modelling, molecular docking and molecular dynamics simulations (MD). This review highlights the key features of all of these approaches, provides some key examples of their application, and compares and contrasts the most important methods currently in use.