Summary
Methods for predicting the binding affinity of peptides to the MHC have become more sophisticated in the past 5–10 years. It is possible to use computational quantitative structure-activity methods to build models of peptide affinity that are truly predictive. Two of the most useful methods for building models are Bayesian regularized neural networks for continuous or discrete (categorical) data and support vector machines (SVMs) for discrete data. We illustrate the application of Bayesian regularized neural networks to modeling MHC class II-binding affinity of peptides. Training data comprised sequences and binding data for nonamer (nine amino acid) peptides. Peptides were characterized by mathematical representations of several types. Independent test data comprised sequences and binding data for peptides of length ≤ 25 . We also internally validated the models by using 30% of the data in an internal test set. We obtained robust models, with near-identical statistics for multiple training runs. We determined how predictive our models were using statistical tests and area under the receiver operating characteristic (ROC) graphs (AROC) . Some mathematical representations of the peptides were more efficient than others and were able to generalize to unknown peptides outside of the training space. Bayesian neural networks are robust, efficient ‘‘universal approximators’’ that are well able to tackle the difficult problem of correctly predicting the MHC class II-binding activities of a majority of the test set peptides.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Buus, S. (1999) Description and prediction of peptide-MHC binding: The ‘Human MHC Project’. Curr. Opin. Immunol. 11, 209–213.
Doytchinova, I.A. and Flower, D.R. (2001) Towards 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.
Doytchinova, I.A., Blythe, M.J., and Flower, D.R. (2002) Additive method for the prediction of protein-peptide binding affinity. Application to the MHC class 1 molecule HLA-A * 0201. J. Proteome Res. 1, 263–272.
Logean, A., Sette, A., and Rognen, D. (2000) Customized versus universal scoring functions: application to class I MHC-peptide binding free energy predictions. Bioorg. Med. Chem. Lett. 11, 675–679.
Brusic, V., Bucci, K., Schönbach, C., Petrovsky, N., Zelezvikow, J., and Kazura, J.K. (2001) Efficient discovery of immune response targets by cyclical refinement of QSAR models of peptide binding. J. Mol. Graph. Model. 19, 405–411.
Gulukota, K., Sidney, J., Sette, A., and DeLisi, C. (1997) Two complementary methods for predicting peptides binding major histocompatibility complex molecules. J. Mol. Biol. 267, 1258–1267.
De Hann, E.C., Wauben, M.H.M., Grosfeld-Stulemeyer, M.C., Kruijtzer, J.A.W., Liskamp, R.M.J., and Moret, E.E. (2002) Major histocompatibility complex class II binding characteristics of peptoid-peptide hybrids. Biorg. Med. Chem. 10, 1939–1945.
Bhasin, M. and Raghava, G.P.S. (2004) SVM-based method for predicting HLA-DRB1 * 0401 binding peptides in an antigen sequence. Bioinformatics 20, 421–423.
Polley, M.J., Winkler, D.A., and Burden, F.R. (2004) Broad-based QSAR of farnesyltransferase inhibitors using a Bayesian regularized neural network. J. Med. Chem. 47, 6230–6238.
Winkler, D.A. and Burden, F.R. (2004) Modelling blood brain barrier partitioning using Bayesian neural nets. J. Mol. Graph. Model. 22, 499–508.
Burden, F.R. and Winkler, D.A. (2000) A QSAR model for the acute toxicity of substituted benzenes towards Tetrahymena pyriformis using Bayesian regularized neural networks. Chem. Res. Toxicol. 13, 436–440.
Sorich, M.J., McKinnon, R.A., Winkler, D.A., Burden, F.R., Miners, J.O., and Smith, P.A. (2003) Comparison of linear and nonlinear classification algorithms: Prediction of drug metabolism by UDP-glucuronosyltransferase isoforms. J. Chem. Inf. Comput. Sci. 43, 2019–2024.
Winkler, D.A. and Burden, F.R. (2000) Robust QSAR models from novel descriptors and Bayesian regularized neural networks. Mol. Simul. 24. 243–258.
Burden, F.R. and Winkler, D.A. (1999) Robust QSAR models using Bayesian regularized artificial neural networks. J. Med. Chem. 42, 3183–3187.
Nabney, I.T. (2002). Netlab: Algorithms for Pattern Recognition. Springer-Verlag, London.
Burden, F.R and Winkler, D.A. (2007) Bayesian Regularization of Neural Networks, in ‘‘Applications of Artificial Neural Networks in Chemistry and Biology’’, Livingston, D. (ed.) Humana Press.
Winkler, D.A. and Burden, F.R. (2005) Predictive Bayesian neural network models of MHC class II peptide binding. J. Mol. Graph. Model. 23, 481–489.
Brusic, V., Rudy, G., and Harrison, L.C. (1998) MHCPEP, a database of MHC-binding peptides: update 1997. Nucleic Acids Res. 26, 368–371.
Sandberg, M., Eriksson, L., Jonsson, J., Sjostrom, M., and Wold, S. (1998) New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J. Med. Chem. 41, 2481–2491.
MacKay, D. J. C. (1992) A practical Bayesian framework for backpropagation networks. Neural Comput. 4, 448–472.
Swets, J.A. (1988) Measuring the accuracy of diagnostic systems. Science 240, 1285–1293.
Brusic, V., Rudy, G., Honeyman, M., Hammer, J., Harrison, L. (1998) Prediction of MHC Class II-binding peptides using an evolutionary algorithm and artificial neural network. Bioinformatics 14, 121–130.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Humana Press Inc.
About this protocol
Cite this protocol
Winkler, D.A., Burden, F.R. (2007). Nonlinear Predictive Modeling of MHC Class II-Peptide Binding Using Bayesian Neural Networks. In: Flower, D.R. (eds) Immunoinformatics. Methods in Molecular Biology™, vol 409. Humana Press. https://doi.org/10.1007/978-1-60327-118-9_27
Download citation
DOI: https://doi.org/10.1007/978-1-60327-118-9_27
Publisher Name: Humana Press
Print ISBN: 978-1-58829-699-3
Online ISBN: 978-1-60327-118-9
eBook Packages: Springer Protocols