Efficient peptide-MHC-I binding prediction for alleles with few known binders

MOTIVATION: In silico methods for the prediction of antigenic peptides binding to MHC class I molecules play an increasingly important role in the identification of T-cell epitopes. Statistical and machine learning methods in particular are widely used to score candidate binders based on their similarity with known binders and non-binders. The genes coding for the MHC molecules, however, are highly polymorphic, and statistical methods have difficulties building models for alleles with few known binders. In this context, recent work has demonstrated the utility of leveraging information across alleles to improve the performance of the prediction. RESULTS: We design a support vector machine algorithm that is able to learn peptide-MHC-I binding models for many alleles simultaneously, by sharing binding information across alleles. The sharing of information is controlled by a user-defined measure of similarity between alleles. We show that this similarity can be defined in terms of supertypes, or more directly by comparing key residues known to play a role in the peptide-MHC binding. We illustrate the potential of this approach on various benchmark experiments where it outperforms other state-of-the-art methods. AVAILABILITY: The method is implemented on a web server: http://cbio.ensmp.fr/kiss. All data and codes are freely and publicly available from the authors.     

Evaluation of different generic in silico methods for predicting HLA class I binding peptide vaccine candidates using a reverse approach

Since CD8⁺ T cell response is crucial to combat intracellular infections and cancer, identification of class I HLA binding peptides is of immense clinical value. The experimental identification of such peptides is protracted and laborious. Exploiting in silico tools to discover such peptides is an attractive alternative. However, this approach needs a thorough assessment before its elaborate application. We have adopted a reverse approach to evaluate the reliability of eight different servers (inclusive of 55 predictors) by exploiting experimentally proven data. A comprehensive data set of more than 960 peptides was employed to test the efficacy of the programs. We have validated commonly used strategies to predict peptides that bind to seven most prevalent HLA class I alleles. We conclude that four of the eight servers are more adept in predictions. Although the overall predictions for class I MHC binders were superior to class II MHC binders, individual predictors for different alleles belonging to the same program were highly variable in their efficiencies. We have also addressed whether a consensus approach can yield better prediction efficiency. We observed that combining the results from different in silico programs could not increase the efficiency significantly.     

Methods for prediction of peptide binding to MHC molecules: a comparative study

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.     

A hybrid approach for predicting promiscuous MHC class I restricted T cell epitopes

In the present study, a systematic attempt has been made to develop an accurate method for predicting MHC class I restricted T cell epitopes for a large number of MHC class I alleles. Initially, a quantitative matrix (QM)-based method was developed for 47 MHC class I alleles having at least 15 binders. A secondary artificial neural network (ANN)-based method was developed for 30 out of 47 MHC alleles having a minimum of 40 binders. Combination of these ANN-and QM-based prediction methods for 30 alleles improved the accuracy of prediction by 6% compared to each individual method. Average accuracy of hybrid method for 30 MHC alleles is 92.8%. This method also allows prediction of binders for 20 additional alleles using QM that has been reported in the literature, thus allowing prediction for 67 MHC class I alleles. The performance of the method was evaluated using jack-knife validation test. The performance of the methods was also evaluated on blind or independent data. Comparison of our method with existing MHC binder prediction methods for alleles studied by both methods shows that our method is superior to other existing methods. This method also identifies proteasomal cleavage sites in antigen sequences by implementing the matrices described earlier. Thus, the method that we discover allows the identification of MHC class I binders (peptides binding with many MHC alleles) having proteasomal cleavage site at C-terminus. The user-friendly result display format (HTML-II) can assist in locating the promiscuous MHC binding regions from antigen sequence. The method is available on the web at www.imtech.res.in/raghava/nhlapred and its mirror site is available at http://bioinformatics.uams.edu/mirror/nhlapred/.     

Structure-based identification of MHC binding peptides: Benchmarking of prediction accuracy

Identification of MHC binding peptides is essential for understanding the molecular mechanism of immune response. However, most of the prediction methods use motifs/profiles derived from experimental peptide binding data for specific MHC alleles, thus limiting their applicability only to those alleles for which such data is available. In this work we have developed a structure-based method which does not require experimental peptide binding data for training. Our method models MHC-peptide complexes using crystal structures of 170 MHC-peptide complexes and evaluates the binding energies using two well known residue based statistical pair potentials, namely Betancourt-Thirumalai (BT) and Miyazawa-Jernigan (MJ) matrices. Extensive benchmarking of prediction accuracy on a data set of 1654 epitopes from class I and class II alleles available in the SYFPEITHI database indicate that BT pair-potential can predict more than 60% of the known binders in case of 14 MHC alleles with AUC values for ROC curves ranging from 0.6 to 0.9. Similar benchmarking on 29,522 class I and class II MHC binding peptides with known IC(50) values in the IEDB database showed AUC values higher than 0.6 for 10 class I alleles and 9 class II alleles in predictions involving classification of a peptide to be binder or non-binder. Comparison with recently available benchmarking studies indicated that, the prediction accuracy of our method for many of the class I and class II MHC alleles was comparable to the sequence based methods, even if it does not use any experimental data for training. It is also encouraging to note that the ranks of true binding peptides could further be improved, when high scoring peptides obtained from pair potential were re-ranked using all atom forcefield and MM/PBSA method.     

Quantitative prediction of mouse class I MHC peptide binding affinity using support vector machine regression (SVR) models

Background  

The binding between peptide epitopes and major histocompatibility complex proteins (MHCs) is an important event in the cellular immune response. Accurate prediction of the binding between short peptides and the MHC molecules has long been a principal challenge for immunoinformatics. Recently, the modeling of MHC-peptide binding has come to emphasize quantitative predictions: instead of categorizing peptides as "binders" or "non-binders" or as "strong binders" and "weak binders", recent methods seek to make predictions about precise binding affinities.     

MHC motif viewer

In vertebrates, the major histocompatibility complex (MHC) presents peptides to the immune system. In humans, MHCs are called human leukocyte antigens (HLAs), and some of the loci encoding them are the most polymorphic in the human genome. Different MHC molecules present different subsets of peptides, and knowledge of their binding specificities is important for understanding the differences in the immune response between individuals. Knowledge of motifs may be used to identify epitopes, to understand the MHC restriction of epitopes, and to compare the specificities of different MHC molecules. Algorithms that predict which peptides MHC molecules bind have recently been developed and cover many different alleles, but the utility of these algorithms is hampered by the lack of tools for browsing and comparing the specificity of these molecules. We have, therefore, developed a web server, MHC motif viewer, that allows the display of the likely binding motif for all human class I proteins of the loci HLA A, B, C, and E and for MHC class I molecules from chimpanzee (Pan troglodytes), rhesus monkey (Macaca mulatta), and mouse (Mus musculus). Furthermore, it covers all HLA-DR protein sequences. A special viewing feature, MHC fight, allows for display of the specificity of two different MHC molecules side by side. We show how the web server can be used to discover and display surprising similarities as well as differences between MHC molecules within and between different species. The MHC motif viewer is available at .     

Accurate approximation method for prediction of class I MHC affinities for peptides of length 8, 10 and 11 using prediction tools trained on 9mers

Several accurate prediction systems have been developed for prediction of class I major histocompatibility complex (MHC):peptide binding. Most of these are trained on binding affinity data of primarily 9mer peptides. Here, we show how prediction methods trained on 9mer data can be used for accurate binding affinity prediction of peptides of length 8, 10 and 11. The method gives the opportunity to predict peptides with a different length than nine for MHC alleles where no such peptides have been measured. As validation, the performance of this approach is compared to predictors trained on peptides of the peptide length in question. In this validation, the approximation method has an accuracy that is comparable to or better than methods trained on a peptide length identical to the predicted peptides. AVAILABILITY: The algorithm has been implemented in the web-accessible servers NetMHC-3.0: http://www.cbs.dtu.dk/services/NetMHC-3.0, and NetMHCpan-1.1: http://www.cbs.dtu.dk/services/NetMHCpan-1.1     

Identification of naturally processed ligands in the C57BL/6 mouse using large-scale mass spectrometric peptide sequencing and bioinformatics prediction

Most major histocompatibility complex (MHC) class I–peptide-binding motifs are currently defined on the basis of quantitative in vitro MHC–peptide-binding assays. This information is used to develop bioinformatics-based tools to predict the binding of peptides to MHC class I molecules. To date few studies have analyzed the performance of these bioinformatics tools to predict the binding of peptides determined by sequencing of naturally processed peptides eluted directly from MHC class I molecules. In this study, we performed large-scale sequencing of endogenous peptides eluted from H2K^b and H2D^b molecules expressed in spleens of C57BL/6 mice. Using sequence data from 281 peptides, we identified novel preferred anchor residues located in H2K^b and H2D^b-associated peptides that refine our knowledge of these H2 class I peptide-binding motifs. The analysis comparing the performance of three bioinformatics methods to predict the binding of these peptides, including artificial neural network, stabilized matrix method, and average relative binding, revealed that 61% to 94% of peptides eluted from H2K^b and H2D^b molecules were correctly classified as binders by the three algorithms. These results suggest that bioinformatics tools are reliable and efficient methods for binding prediction of naturally processed MHC class I ligands. Electronic supplementary material  The online version of this article (doi:) contains supplementary material, which is available to authorized users.     

NetMHCIIpan-3.0, a common pan-specific MHC class II prediction method including all three human MHC class II isotypes, HLA-DR, HLA-DP and HLA-DQ

Major histocompatibility complex class II (MHCII) molecules play an important role in cell-mediated immunity. They present specific peptides derived from endosomal proteins for recognition by T helper cells. The identification of peptides that bind to MHCII molecules is therefore of great importance for understanding the nature of immune responses and identifying T cell epitopes for the design of new vaccines and immunotherapies. Given the large number of MHC variants, and the costly experimental procedures needed to evaluate individual peptide–MHC interactions, computational predictions have become particularly attractive as first-line methods in epitope discovery. However, only a few so-called pan-specific prediction methods capable of predicting binding to any MHC molecule with known protein sequence are currently available, and all of them are limited to HLA-DR. Here, we present the first pan-specific method capable of predicting peptide binding to any HLA class II molecule with a defined protein sequence. The method employs a strategy common for HLA-DR, HLA-DP and HLA-DQ molecules to define the peptide-binding MHC environment in terms of a pseudo sequence. This strategy allows the inclusion of new molecules even from other species. The method was evaluated in several benchmarks and demonstrates a significant improvement over molecule-specific methods as well as the ability to predict peptide binding of previously uncharacterised MHCII molecules. To the best of our knowledge, the NetMHCIIpan-3.0 method is the first pan-specific predictor covering all HLA class II molecules with known sequences including HLA-DR, HLA-DP, and HLA-DQ. The NetMHCpan-3.0 method is available at http://www.cbs.dtu.dk/services/NetMHCIIpan-3.0.     

Prediction of MHC class I binding peptides, using SVMHC

Background  

T-cells are key players in regulating a specific immune response. Activation of cytotoxic T-cells requires recognition of specific peptides bound to Major Histocompatibility Complex (MHC) class I molecules. MHC-peptide complexes are potential tools for diagnosis and treatment of pathogens and cancer, as well as for the development of peptide vaccines. Only one in 100 to 200 potential binders actually binds to a certain MHC molecule, therefore a good prediction method for MHC class I binding peptides can reduce the number of candidate binders that need to be synthesized and tested.     

<Emphasis Type="Italic">NetMHCcons</Emphasis>: a consensus method for the major histocompatibility complex class I predictions

A key role in cell-mediated immunity is dedicated to the major histocompatibility complex (MHC) molecules that bind peptides for presentation on the cell surface. Several in silico methods capable of predicting peptide binding to MHC class I have been developed. The accuracy of these methods depends on the data available characterizing the binding specificity of the MHC molecules. It has, moreover, been demonstrated that consensus methods defined as combinations of two or more different methods led to improved prediction accuracy. This plethora of methods makes it very difficult for the non-expert user to choose the most suitable method for predicting binding to a given MHC molecule. In this study, we have therefore made an in-depth analysis of combinations of three state-of-the-art MHC–peptide binding prediction methods (NetMHC, NetMHCpan and PickPocket). We demonstrate that a simple combination of NetMHC and NetMHCpan gives the highest performance when the allele in question is included in the training and is characterized by at least 50 data points with at least ten binders. Otherwise, NetMHCpan is the best predictor. When an allele has not been characterized, the performance depends on the distance to the training data. NetMHCpan has the highest performance when close neighbours are present in the training set, while the combination of NetMHCpan and PickPocket outperforms either of the two methods for alleles with more remote neighbours. The final method, NetMHCcons, is publicly available at , and allows the user in an automatic manner to obtain the most accurate predictions for any given MHC molecule.     

MHCBN: a comprehensive database of MHC binding and non-binding peptides

MHCBN is a comprehensive database of Major Histocompatibility Complex (MHC) binding and non-binding peptides compiled from published literature and existing databases. The latest version of the database has 19 777 entries including 17 129 MHC binders and 2648 MHC non-binders for more than 400 MHC molecules. The database has sequence and structure data of (a) source proteins of peptides and (b) MHC molecules. MHCBN has a number of web tools that include: (i) mapping of peptide on query sequence; (ii) search on any field; (iii) creation of data sets; and (iv) online data submission. The database also provides hypertext links to major databases like SWISS-PROT, PDB, IMGT/HLA-DB, GenBank and PUBMED.     

State of the art and challenges in sequence based T-cell epitope prediction

Sequence based T-cell epitope predictions have improved immensely in the last decade. From predictions of peptide binding to major histocompatibility complex molecules with moderate accuracy, limited allele coverage, and no good estimates of the other events in the antigen-processing pathway, the field has evolved significantly. Methods have now been developed that produce highly accurate binding predictions for many alleles and integrate both proteasomal cleavage and transport events. Moreover have so-called pan-specific methods been developed, which allow for prediction of peptide binding to MHC alleles characterized by limited or no peptide binding data. Most of the developed methods are publicly available, and have proven to be very useful as a shortcut in epitope discovery. Here, we will go through some of the history of sequence-based predictions of helper as well as cytotoxic T cell epitopes. We will focus on some of the most accurate methods and their basic background.     

Comparative analysis of epitope predictions: proposed library of putative vaccine candidates for HIV

Designing a vaccine for a disease is one of the crucial tasks that involve millions and billions of dollars, several decades and yet there is no guarantee of successful results. Several pharmaceutical companies are investing their money and time in such activities. Computational biology could be of great help in these activities by proving a library of plausible candidates that might actually show some positive responses. MHC binding peptide prediction is one such area where the immense power of computers could be used to get a breakthrough. In this direction several databases and servers have been developed by many labs to predict the MHC binding peptides. These short peptides on the antigen surface are recognized by the MHC molecule and are presented to the receptors of T-cells for further immune response. Peptides that bind to a given MHC molecule share sequence similarity. Here we present a comparative study of servers that can predict the MHC binding peptides in a given protein sequence of the antigen. Based on this comparative analysis on HIV data, we are able to propose a library of putative vaccine candidates for the env GP-160 protein of HIV-1.     

Modeling alternative binding registers of a minimal immunogenic peptide on two class II major histocompatibility complex (MHC II) molecules predicts polarized T-cell receptor (TCR) contact positions.

Several major histocompatibility complex class II (MHC II) complexes with known minimal immunogenic peptides have now been solved by X-ray crystallography. Specificity pockets within the MHC II binding groove provide distinct peptide contacts that influence peptide conformation and define the binding register within different allelic MHC II molecules. Altering peptide ligands with respect to the residues that contact the T-cell receptor (TCR) can drastically change the nature of the ensuing immune response. Here, we provide an example of how MHC II (I-A) molecules may indirectly effect TCR contacts with a peptide and drive functionally distinct immune responses. We modeled the same immunogenic 12-amino acid peptide into the binding grooves of two allelic MHC II molecules linked to distinct cytokine responses against the peptide. Surprisingly, the favored conformation of the peptide in each molecule was distinct with respect to the exposure of the N- or C-terminus of the peptide above the MHC II binding groove. T-cell clones derived from each allelic MHC II genotype were found to be allele-restricted with respect to the recognition of these N- vs. C-terminal residues on the bound peptide. Taken together, these data suggest that MHC II alleles may influence T-cell functions by restricting TCR access to specific residues of the I-A-bound peptide. Thus, these data are of significance to diseases that display genetic linkage to specific MHC II alleles, e.g. type 1 diabetes and rheumatoid arthritis.     

NetMHCpan,a method for MHC class I binding prediction beyond humans

Binding of peptides to major histocompatibility complex (MHC) molecules is the single most selective step in the recognition of pathogens by the cellular immune system. The human MHC genomic region (called HLA) is extremely polymorphic comprising several thousand alleles, each encoding a distinct MHC molecule. The potentially unique specificity of the majority of HLA alleles that have been identified to date remains uncharacterized. Likewise, only a limited number of chimpanzee and rhesus macaque MHC class I molecules have been characterized experimentally. Here, we present NetMHCpan-2.0, a method that generates quantitative predictions of the affinity of any peptide–MHC class I interaction. NetMHCpan-2.0 has been trained on the hitherto largest set of quantitative MHC binding data available, covering HLA-A and HLA-B, as well as chimpanzee, rhesus macaque, gorilla, and mouse MHC class I molecules. We show that the NetMHCpan-2.0 method can accurately predict binding to uncharacterized HLA molecules, including HLA-C and HLA-G. Moreover, NetMHCpan-2.0 is demonstrated to accurately predict peptide binding to chimpanzee and macaque MHC class I molecules. The power of NetMHCpan-2.0 to guide immunologists in interpreting cellular immune responses in large out-bred populations is demonstrated. Further, we used NetMHCpan-2.0 to predict potential binding peptides for the pig MHC class I molecule SLA-1*0401. Ninety-three percent of the predicted peptides were demonstrated to bind stronger than 500 nM. The high performance of NetMHCpan-2.0 for non-human primates documents the method’s ability to provide broad allelic coverage also beyond human MHC molecules. The method is available at . Electronic supplementary material  The online version of this article (doi:) contains supplementary material, which is available to authorized users.     

Quantitative predictions of peptide binding to any HLA-DR molecule of known sequence: NetMHCIIpan

CD4 positive T helper cells control many aspects of specific immunity. These cells are specific for peptides derived from protein antigens and presented by molecules of the extremely polymorphic major histocompatibility complex (MHC) class II system. The identification of peptides that bind to MHC class II molecules is therefore of pivotal importance for rational discovery of immune epitopes. HLA-DR is a prominent example of a human MHC class II. Here, we present a method, NetMHCIIpan, that allows for pan-specific predictions of peptide binding to any HLA-DR molecule of known sequence. The method is derived from a large compilation of quantitative HLA-DR binding events covering 14 of the more than 500 known HLA-DR alleles. Taking both peptide and HLA sequence information into account, the method can generalize and predict peptide binding also for HLA-DR molecules where experimental data is absent. Validation of the method includes identification of endogenously derived HLA class II ligands, cross-validation, leave-one-molecule-out, and binding motif identification for hitherto uncharacterized HLA-DR molecules. The validation shows that the method can successfully predict binding for HLA-DR molecules-even in the absence of specific data for the particular molecule in question. Moreover, when compared to TEPITOPE, currently the only other publicly available prediction method aiming at providing broad HLA-DR allelic coverage, NetMHCIIpan performs equivalently for alleles included in the training of TEPITOPE while outperforming TEPITOPE on novel alleles. We propose that the method can be used to identify those hitherto uncharacterized alleles, which should be addressed experimentally in future updates of the method to cover the polymorphism of HLA-DR most efficiently. We thus conclude that the presented method meets the challenge of keeping up with the MHC polymorphism discovery rate and that it can be used to sample the MHC "space," enabling a highly efficient iterative process for improving MHC class II binding predictions.     

Molecular and immunological significance of chimpanzee major histocompatibility complex haplotypes for hepatitis C virus immune response and vaccination studies

The chimpanzee is a critical animal model for studying cellular immune responses to infectious pathogens such as hepatitis B and C viruses, human immunodeficiency virus, and malaria. Several candidate vaccines and immunotherapies for these infections aim at the induction or enhancement of cellular immune responses against viral epitopes presented by common human major histocompatibility complex (MHC) alleles. To identify and characterize chimpanzee MHC class I molecules that are functionally related to human alleles, we sequenced 18 different Pan troglodytes (Patr) alleles of 14 chimpanzees, 2 of them previously unknown and 3 with only partially reported sequences. Comparative analysis of Patr binding pockets and binding assays with biotinylated peptides demonstrated a molecular homology between the binding grooves of individual Patr alleles and the common human alleles HLA-A1, -A2, -A3, and -B7. Using cytotoxic T cells isolated from the blood of hepatitis C virus (HCV)-infected chimpanzees, we then mapped the Patr restriction of these HCV peptides and demonstrated functional homology between the Patr-HLA orthologues in cytotoxicity and gamma interferon (IFN-gamma) release assays. Based on these results, 21 HCV epitopes were selected to characterize the chimpanzees' cellular immune response to HCV. In each case, IFN-gamma-producing T cells were detectable in the blood after but not prior to HCV infection and were specifically targeted against those HCV peptides predicted by Patr-HLA homology. This study demonstrates a close functional homology between individual Patr and HLA alleles and shows that HCV infection generates HCV peptides that are recognized by both chimpanzees and humans with Patr and HLA orthologues. These results are relevant for the design and evaluation of vaccines in chimpanzees that can now be selected according to the most frequent human MHC haplotypes.     

Prediction of HLA-DQ3.2beta ligands: evidence of multiple registers in class II binding peptides

MOTIVATION: While processing of MHC class II antigens for presentation to helper T-cells is essential for normal immune response, it is also implicated in the pathogenesis of autoimmune disorders and hypersensitivity reactions. Sequence-based computational techniques for predicting HLA-DQ binding peptides have encountered limited success, with few prediction techniques developed using three-dimensional models. METHODS: We describe a structure-based prediction model for modeling peptide-DQ3.2beta complexes. We have developed a rapid and accurate protocol for docking candidate peptides into the DQ3.2beta receptor and a scoring function to discriminate binders from the background. The scoring function was rigorously trained, tested and validated using experimentally verified DQ3.2beta binding and non-binding peptides obtained from biochemical and functional studies. RESULTS: Our model predicts DQ3.2beta binding peptides with high accuracy [area under the receiver operating characteristic (ROC) curve A(ROC) > 0.90], compared with experimental data. We investigated the binding patterns of DQ3.2beta peptides and illustrate that several registers exist within a candidate binding peptide. Further analysis reveals that peptides with multiple registers occur predominantly for high-affinity binders.