Prediction of the binding affinities of peptides to class II MHC using a regularized thermodynamic model

BackgroundThe binding of peptide fragments of extracellular peptides to class II MHC is a crucial event in the adaptive immune response. Each MHC allotype generally binds a distinct subset of peptides and the enormous number of possible peptide epitopes prevents their complete experimental characterization. Computational methods can utilize the limited experimental data to predict the binding affinities of peptides to class II MHC.ResultsWe have developed the Regularized Thermodynamic Average, or RTA, method for predicting the affinities of peptides binding to class II MHC. RTA accounts for all possible peptide binding conformations using a thermodynamic average and includes a parameter constraint for regularization to improve accuracy on novel data. RTA was shown to achieve higher accuracy, as measured by AUC, than SMM-align on the same data for all 17 MHC allotypes examined. RTA also gave the highest accuracy on all but three allotypes when compared with results from 9 different prediction methods applied to the same data. In addition, the method correctly predicted the peptide binding register of 17 out of 18 peptide-MHC complexes. Finally, we found that suboptimal peptide binding registers, which are often ignored in other prediction methods, made significant contributions of at least 50% of the total binding energy for approximately 20% of the peptides.ConclusionsThe RTA method accurately predicts peptide binding affinities to class II MHC and accounts for multiple peptide binding registers while reducing overfitting through regularization. The method has potential applications in vaccine design and in understanding autoimmune disorders. A web server implementing the RTA prediction method is available at http://bordnerlab.org/RTA/.

[1]  T. Lybrand,et al.  Ovalbumin(323-339) peptide binds to the major histocompatibility complex class II I-A(d) protein using two functionally distinct registers. , 1999, Biochemistry.

[2]  J. Gorski,et al.  Cooperativity of Hydrophobic Anchor Interactions: Evidence for Epitope Selection by MHC Class II as a Folding Process1 , 2007, The Journal of Immunology.

[3]  Ellis L. Reinherz,et al.  Enhancement to the RANKPEP resource for the prediction of peptide binding to MHC molecules using profiles , 2004, Immunogenetics.

[4]  Sneh Lata,et al.  Application of machine learning techniques in predicting MHC binders. , 2007, Methods in molecular biology.

[5]  Morten Nielsen,et al.  Quantitative Predictions of Peptide Binding to Any HLA-DR Molecule of Known Sequence: NetMHCIIpan , 2008, PLoS Comput. Biol..

[6]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[7]  Ji Wan,et al.  SVRMHC prediction server for MHC-binding peptides , 2006, BMC Bioinformatics.

[8]  V. Brusic,et al.  Evaluation of MHC class I peptide binding prediction servers: Applications for vaccine research , 2008, BMC Immunology.

[9]  Bjoern Peters,et al.  Automated generation and evaluation of specific MHC binding predictive tools: ARB matrix applications , 2005, Immunogenetics.

[10]  Steve Wilson,et al.  The Immune Epitope Database and Analysis Resource: From Vision to Blueprint , 2005, PLoS biology.

[11]  Vladimir Brusic,et al.  Evaluation of MHC-II peptide binding prediction servers: applications for vaccine research , 2008, BMC Bioinformatics.

[12]  Z. Nagy,et al.  Precise prediction of major histocompatibility complex class II-peptide interaction based on peptide side chain scanning , 1994, The Journal of experimental medicine.

[13]  Y. Cheng,et al.  Relationship between the inhibition constant (K1) and the concentration of inhibitor which causes 50 per cent inhibition (I50) of an enzymatic reaction. , 1973, Biochemical pharmacology.

[14]  Channa K. Hattotuwagama,et al.  Toward Prediction of Class II Mouse Major Histocompatibility Complex Peptide Binding Affinity: in Silico Bioinformatic Evaluation Using Partial Least Squares, a Robust Multivariate Statistical Technique , 2006, J. Chem. Inf. Model..

[15]  U. Şahin,et al.  Generation of tissue-specific and promiscuous HLA ligand databases using DNA microarrays and virtual HLA class II matrices , 1999, Nature Biotechnology.

[16]  Pingping Guan,et al.  MHCPred: a server for quantitative prediction of peptide-MHC binding , 2003, Nucleic Acids Res..

[17]  Gajendra P. S. Raghava,et al.  ProPred: prediction of HLA-DR binding sites , 2001, Bioinform..

[18]  Brian W. Kernighan,et al.  AMPL: A Modeling Language for Mathematical Programming , 1993 .

[19]  Vladimir Brusic,et al.  PREDBALB/c: a system for the prediction of peptide binding to H2d molecules, a haplotype of the BALB/c mouse , 2005, Nucleic Acids Res..

[20]  N. Viner,et al.  Influence of a dominant cryptic epitope on autoimmune T cell tolerance , 2002, Nature Immunology.

[21]  John Sidney,et al.  A Systematic Assessment of MHC Class II Peptide Binding Predictions and Evaluation of a Consensus Approach , 2008, PLoS Comput. Biol..

[22]  Ulrik Brandes,et al.  Network Analysis: Methodological Foundations , 2010 .

[23]  J A Swets,et al.  Measuring the accuracy of diagnostic systems. , 1988, Science.

[24]  Morten Nielsen,et al.  Prediction of MHC class II binding affinity using SMM-align, a novel stabilization matrix alignment method , 2007, BMC Bioinformatics.

[25]  Tongbin Li,et al.  In silico prediction of peptide-MHC binding affinity using SVRMHC. , 2007, Methods in molecular biology.

[26]  William W. Kwok,et al.  The Binding of Antigenic Peptides to HLA-DR Is Influenced by Interactions between Pocket 6 and Pocket 91 , 2009, The Journal of Immunology.

[27]  A Sette,et al.  T cell recognition of flanking residues of murine invariant chain-derived CLIP peptide bound to MHC class II. , 1998, Cellular immunology.

[28]  Søren Brunak,et al.  Improved prediction of MHC class I and class II epitopes using a novel Gibbs sampling approach , 2004, Bioinform..

[29]  H. Rammensee,et al.  SYFPEITHI: database for MHC ligands and peptide motifs , 1999, Immunogenetics.

[30]  M. Fiedler Algebraic connectivity of graphs , 1973 .

[31]  D. Zaller,et al.  Prediction of peptide affinity to HLA DRB1*0401. , 1994, International archives of allergy and immunology.

[32]  N. Kalouptsidis,et al.  Spectral analysis , 1993 .

[33]  Darren R. Flower,et al.  Predicting Class II MHC-Peptide binding: a kernel based approach using similarity scores , 2006, BMC Bioinformatics.

[34]  D. Wraith,et al.  The nature of cryptic epitopes within the self-antigen myelin basic protein. , 1996, International immunology.

[35]  M. Fiedler Laplacian of graphs and algebraic connectivity , 1989 .

[36]  K. Garcia,et al.  Peptide register shifting within the MHC groove: theory becomes reality. , 2004, Molecular immunology.

[37]  Lars Fugger,et al.  MHC class II proteins and disease: a structural perspective , 2006, Nature Reviews Immunology.

[38]  Z. Cao,et al.  MHC-BPS: MHC-binder prediction server for identifying peptides of flexible lengths from sequence-derived physicochemical properties , 2006, Immunogenetics.

[39]  Yang Dai,et al.  Prediction of MHC class II binding peptides based on an iterative learning model , 2005, Immunome research.

[40]  Vasant Honavar,et al.  On Evaluating MHC-II Binding Peptide Prediction Methods , 2008, PloS one.

[41]  Morten Nielsen,et al.  NN-align. An artificial neural network-based alignment algorithm for MHC class II peptide binding prediction , 2009, BMC Bioinformatics.

[42]  A. Rudensky,et al.  A study of complexes of class II invariant chain peptide: Major histocompatibility complex class II molecules using a new complex‐specific monoclonal antibody , 1996, European journal of immunology.

[43]  D. Madden The three-dimensional structure of peptide-MHC complexes. , 1995, Annual review of immunology.