Abstract
Background
A variety of methods for prediction of peptide binding to major histocompatibility complex (MHC) have been proposed. These methods are based on binding motifs, binding matrices, hidden Markov models (HMM), or artificial neural networks (ANN). There has been little prior work on the comparative analysis of these methods.
Materials and Methods
We performed a comparison of the performance of six methods applied to the prediction of two human MHC class I molecules, including binding matrices and motifs, ANNs, and HMMs.
Results
The selection of the optimal prediction method depends on the amount of available data (the number of peptides of known binding affinity to the MHC molecule of interest), the biases in the data set and the intended purpose of the prediction (screening of a single protein versus mass screening). When little or no peptide data are available, binding motifs are the most useful alternative to random guessing or use of a complete overlapping set of peptides for selection of candidate binders. As the number of known peptide binders increases, binding matrices and HMM become more useful predictors. ANN and HMM are the predictive methods of choice for MHC alleles with more than 100 known binding peptides.
Conclusion
The ability of bioinformatic methods to reliably predict MHC binding peptides, and thereby potential T-cell epitopes, has major implications for clinical immunology, particularly in the area of vaccine design.
Similar content being viewed by others
References
Rammensee HG, Friede T, Stevanoviic S. (1995) MHC ligands and peptide motifs: 1st listing. Immunogenetics 41: 178–228.
Brusic V, Rudy G, Harrison LC. (1998) MHCPEP—a database of MHC-binding peptides: update 1997. Nucleic Acids Res. 26: 368–371.
Wang RF, Rosenberg SA. (1999) Human tumor antigens for cancer vaccine development. Immunol. Rev. 170: 85–100.
Wang R, Doolan DL, Le TP, et al. (1998) Induction of antigen-specific cytotoxic T lymphocytes in humans by a malaria DNA vaccine. Science 282: 467–480.
Berzofsky JA, Ahlers JD, Derby MA, et al. (1999) Approaches to improve engineered vaccines for human immunodeficiency virus and other viruses that cause chronic infections. Immunol. Rev. 170: 151–172.
Brusic V, Zeleznikow J. (1999) Computational binding assays of antigenic peptides. Letters in Peptide Science 6: 313–324.
Prilliman KR, Jackson KW, Lindsey M, et al. (1999) HLA-B15 peptide ligands are preferentially anchored at their C termini. J. Immunol. 162: 7277–7284.
Parker KC, Bednarek MA, Coligan JE. (1994) Scheme for ranking potential HLA-A2 binding peptides based on independent binding of individual peptide sidechains. J. Immunol. 152: 163–175.
Hammer J, Bono E, Gallazzi F, et al. (1994) Precise prediction of major histocompatibility complex class II-peptide interaction based on peptide side chain scanning. J. Exp. Med. 180: 2353–2358.
Schönbach C, Ibe M, Shiga H, et al. (1995) Fine tuning of peptide binding to HLA-B*3501 molecules by nonanchor residues. J. Immunol. 154: 5951–5958.
Mallios RR. (1999) Class II MHC quantitative binding motifs derived from a large molecular database with a versatile iterative stepwise discriminant analysis meta-algorithm. Bioinformatics 15: 432–439.
Rammensee H, Bachmann J, Emmerich NP, Bachor OA, Stevanovic S. (1999) SYFPEITHI: database for MHC ligands and peptide motifs. Immunogenetics 50: 213–219. Available at URL: https://doi.org/www.uni-tuebingen.de/uni/kxi/.
Brusic V, Rudy G, Harrison LC. (1994) Prediction of MHC binding peptides using artificial neural networks. In Stonier RJ, Yu XS (eds). Complex Systems: Mechanism of Adaptation, Amsterdam/OHMSHA Tokyo: IOS Press; 253–260. Also published in Complexity International 2: 1995.
Adams HP, Koziol JA. (1995) Prediction of binding to MHC class I molecules. J. Immunol. Methods 185: 181–190.
Gulukota K, Sidney J, Sette A, Delisi C. (1997) Two complementary methods for predicting peptides binding major histocompatibility complex molecules. J. Mol. Biol. 267: 1258–1267.
Brusic V, Rudy G, Honeyman M, Hammer J, Harrison LC. (1998) Prediction of MHC class II-binding peptides using an evolutionary algorithm and artificial neural network. Bioinformatics 14: 121–130.
Mamitsuka H. (1998) Predicting peptides that bind to MHC molecules using supervised learning of hidden Markov models. Proteins 33: 460–474.
Lim JS, Kim S, Lee HG, et al. (1996) Selection of peptides that bind to the HLA-A2.1 molecule by molecular modeling. Mol. Immunol. 33: 221–230.
Rognan D, Lauemoller SL, Holm A, Buus S, Tschinke V. (1999) Predicting binding affinities of protein ligands from three-dimensional models: application to peptide binding to class I major histocompatibility proteins. J. Med. Chem. 42: 4650–4658.
Doytchinova IA, Flower DR. (2001) Toward the quantitative prediction of T-cell epitopes: coMFA and coMSIA studies of peptides with affinity for the class I MHC molecule HLA-A*0201. J. Med. Chem. 44: 3572–3581.
Zhang, C., Anderson, A. and DeLisi, C. (1998) Structural principles that govern the peptide-binding motifs of class I MHC molecules. J. Mol. Biol. 281, 929–947.
Davenport MP, Ho Shon IA, Hill AV. (1995) An empirical method for the prediction of T-cell epitopes. Immunogenetics 42: 392–397.
Godkin AJ, Davenport MP, Willis A, et al. (1998) Use of complete eluted peptide sequence data from HLA-DR and -DQ molecules to predict T cell epitopes, and the influence of the nonbinding terminal regions of ligands in epitope selection. J. Immunol. 161: 850–858.
Manici S, Sturniolo T, Imro MA, et al. (1999) Melanoma cells present a MAGE-3 epitope to CD4(+) cytotoxic T cells in association with histocompatibility leukocyte antigen DR11. J. Exp. Med. 189: 871–876.
Vissers JL, De Vires JJ, Schreurs MW, et al. (1999) The renal cell carcinoma-associated antigen G250 encodes a human leukocyte antigen (HLA)-A2.1-restricted epitopes recognized by cytotoxic T lymphocytes. Cancer Res. 59: 5554–5559.
Zarour HM, Kirkwood JM, Kierstead LS, et al. (2000) Melan-A/MART-1(51–73) represents an immunogenic HLA-DR4-restricted epitope recognized by melanoma-reactive CD4(+) T cells. Proc. Natl. Acad. Sci. U.S.A. 97: 400–405.
Honeyman MC, Brusic V, Stone NL, Harrison LC. (1998) Neural network-based prediction peptides binding major histocompatibility complex molecules. Nat. Biotechnol. 16: 966–969.
Khanna R, Burrows SR, Nicholls J, Poulsen LM. (1998) Identification of cytotoxic T cell epitopes within Epstein-Barr virus (EBV) oncogene latent membrane protein 1 (LMP1): evidence for HLA A2 supertype-restricted immune recognition of EBV-infected cells by LMP1-specific cytotoxic T lymphocytes. Eur. J. Immunol. 28: 451–458.
Jin X, Roberts CG, Nixon DF, et al. (2000) Identification of subdominant cytotoxic T lymphocyte epitopes encoded by autologous HIV type 1 sequences, using dendritic cell stimulation and computer-driven algorithm. AIDS Res. Hum. Retroviruses. 16: 67–76.
De Lalla C, Sturniolo T, Abbruzzese L, et al. (1999) Cutting edge: identification of novel T cell epitopes in Lol p5a by computational prediction. J. Immunol. 163: 1725–1729.
Deavin AJ, Auton TR, Greaney PJ. (1996) Statistical comparison of established T-cell epitope predictors against a large database of human and murine antigens. Mol. Immunol. 33: 145–155.
Borrás-Cuesta F, Golvano J, Garcia-Granero M, et al. (2000) Specific and general HLA-DR binding motifs: comparison of algorithms. Hum. Immunol. 61: 266–278.
Andersen MH, Tan L, Sondergaard I, et al. (2000) Poor correspondence between predicted and experimental binding of peptides to class I MHC molecules. Tissue Antigens, 55: 519–531.
Weiss SM, Kulikowski CA. (1990) Computer Systems that Learn. San Mateo, CA: Morgan Kaufman Publishers.
Beale R, Jackson T. (1990) Neural Computing: An Introduction. Bristol, UK: Adam Hilger.
Miyata Y. (1991) A User’s Guide to Planet Version 5.6. Boulder, CO: Computer Science Department, University of Colorado.
Rumelhart DE, Hinton E, Williams J. (1986) Learning internal representation by error propagation. In Rumelhart D, McClelland J, and the PDP Research Group (eds). Parallel Distributed Processing, Vol. 1. Cambridge, MA: MIT Press; 318–362.
Hughey R, Krogh A. (1996) Hidden Markov models for sequence analysis: extension and analysis of the basic method. Comput. Appl. Biosci. 12: 95–107.
Krogh A, Brown M, Mian IS, et al. (1994) Hidden Markov models in computational biology. Applications to protein modeling. J. Mol. Biol. 235: 1501–1531.
Eddy SR. (1998) HMMer user’s guide (version 2.1.1). Profile hidden Markov models for biological sequence analysis. Available at URL: https://doi.org/http://hmmer.wustl.edu/hmmer-html/.
Brusic V, Bucci K, Schonbach C, et al. (2001) Efficient discovery of immune response targets by cyclical refinement of QSAR models of peptide binding. J. Mol. Graph. Model. 19: 405–411, 467.
Swets JA. (1988) Measuring the accuracy of diagnostic systems. Science 240: 1285–1293.
Kast WM, Brandt RM, Sidney J, et al. (1994) Role of HLA-A motifs in identification of potential CTL epitopes in human papillomavirus type 16 E6 and E7 proteins. J. Immunol. 152: 3904–3912.
Madden DR, Garboczi DN, and Wiley DC. (1993) The antigenic identity of peptide-MHC complexes: a comparison of the conformations of five viral peptides presented by HLA-A2. Cell 75: 693–708.
Schirle M, Keilholz W, Weber B, et al. (2000) Identification of tumor-associated MHC class I ligands by a novel T cell-independent approach. Eur. J. Immunol. 30: 2216–2225.
Altman JD, Moss PA, Goulder PJ, et al. (1996) Phenotypic analysis of antigen-specific T lymphocytes. Science 274: 94–96.
Mathiassen S, Lauemoller SL, Ruhwald M, et al. (2001) Tumor-associated antigens identified by mRNA expression profiling induce protective anti-tumor immunity. Eur. J. Immunol. 31: 1239–1246.
Linnemann T, Tumenjargal S, Gellrich S, et al. (2001) Mimotopes for tumor-specific T lymphocytes in human cancer determined with combinatorial peptide libraries. Eur. J. Immunol. 31: 156–165.
Acknowledgments
N.P. is supported by a grant from the Canberra Hospital Salaried Specialists Private Practice Fund.
Author information
Authors and Affiliations
Additional information
Contributed by R. Bucala.
Rights and permissions
About this article
Cite this article
Yu, K., Petrovsky, N., Schönbach, C. et al. Methods for Prediction of Peptide Binding to MHC Molecules: A Comparative Study. Mol Med 8, 137–148 (2002). https://doi.org/10.1007/BF03402006
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF03402006