Major histocompatibility complex (MHC) molecules bind short peptides from antigens and present them on the surface of a cell for recognition by T Cell Receptors (TCR) (For general information on MHC see [1]). The presented peptide and MHC complexes induce the naive T Cells to proliferate and differentiate into armed effector T cells that help to remove the antigens. As antigen recognition by MHC molecules is the prerequisite of cellular immune response, it is of great immunological importance to have the ability to accurately predict those peptides that bind to specific MHC molecules. The experimental identification of peptide binding affinity is a time-consuming and expensive process. In contrast, computational approaches for MHC peptide binding prediction can help immunologists to select a small set of promising epitope candidates for further investigations. A precise prediction method can thus reduce the cost significantly.

Various computational approaches have been proposed to tackle the MHC peptide binding prediction problem. Since many methods are based on different principles, their prediction results could be quite different. To make full use of cutting edge prediction methods, we resort to ensemble based method to integrate the output of individual predictor for better prediction performance. Ensemble based systems have been widely deployed and obtained great success in many different areas [2]. MetaMHC is also an ensemble based web server for more accurate MHC peptide binding prediction. Here is a brief framework of working principle of ensemble approach. It includes two components, MetaMHCI and MetaMHCII. MetaMHCI is for MHC-I peptide binding prediction, and MetaMHCII is for MHC-II peptide binding prediction. For the details, please browse the following pages directly.

The Framework of MetaMHC Server

Here is the workflow of the MetaMHC server. The base predictors in MetaMHCI include ANN, SMM, NetMHC and NetMHCpan and the meta-predictors are Consensus, PM and AvgTanh. For MetaMHCII, the base predictors of A, B and C include LA Kernal, TEPITOPE and SMM-align, while the meta-predictors are Consensus, PM, AvgTanh and MetaSVMp. For more details, you can check the references in MetaMHCI and MetaMHCII.

the framework of MetaMHC server


  1. Janeway C A, Travers P, Walport M, Shlomchik M. 2001. Immunobiology: the immune system in health and disease. Garland Publishing, New York.
  2. Polikar R. 2006. Ensemble based systems in decision making. IEEE Circuits and Systems Magazine, 6(3):21-45.