A probabilistic meta-predictor for the MHC class II binding peptides

Several computational methods for the prediction of major histocompatibility complex (MHC) class II binding peptides embodying different strengths and weaknesses have been developed. To provide reliable prediction, it is important to design a system that enables the integration of outcomes from various predictors. The construction of a meta-predictor of this type based on a probabilistic approach is introduced in this paper. The design permits the easy incorporation of results obtained from any number of individual predictors. It is demonstrated that this integrated method outperforms six state-of-the-art individual predictors based on computational studies using MHC class II peptides from 13 HLA alleles and three mouse MHC alleles obtained from the Immune Epitope Database and Analysis Resource. It is concluded that this integrative approach provides a clearly enhanced reliability of prediction. Moreover, this computational framework can be directly extended to MHC class I binding predictions.     

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.     

Toward more accurate pan-specific MHC-peptide binding prediction: a review of current methods and tools

Binding of short antigenic peptides to major histocompatibility complex (MHC) molecules is a core step in adaptive immune response. Precise identification of MHC-restricted peptides is of great significance for understanding the mechanism of immune response and promoting the discovery of immunogenic epitopes. However, due to the extremely high MHC polymorphism and huge cost of biochemical experiments, there is no experimentally measured binding data for most MHC molecules. To address the problem of predicting peptides binding to these MHC molecules, recently computational approaches, called pan-specific methods, have received keen interest. Pan-specific methods make use of experimentally obtained binding data of multiple alleles, by which binding peptides (binders) of not only these alleles but also those alleles with no known binders can be predicted. To investigate the possibility of further improvement in performance and usability of pan-specific methods, this article extensively reviews existing pan-specific methods and their web servers. We first present a general framework of pan-specific methods. Then, the strategies and performance as well as utilities of web servers are compared. Finally, we discuss the future direction to improve pan-specific methods for MHC-peptide binding prediction.     

In silico tools for predicting peptides binding to HLA-class II molecules: more confusion than conclusion

Identification of promiscuous peptides, which bind to human leukocyte antigen, is indispensable for global vaccination. However, the development of such vaccines is impaired due to the exhaustive polymorphism in human leukocyte antigens. The use of in silico tools for mining such peptides circumvents the expensive and laborious experimental screening methods. Nevertheless, the intrepid use of such tools warrants a rational assessment with respect to experimental findings. Here, we have adopted a 'bottom up' approach, where we have used experimental data to assess the reliability of existing in silico methods. We have used a data set of 179 peptides from diverse antigens and have validated six commonly used in silico methods; ProPred, MHC2PRED, RANKPEP, SVMHC, MHCPred, and MHC-BPS. We observe that the prediction efficiency of the programs is not balanced for all the HLA-DR alleles and there is extremely high level of discrepancy in the prediction efficiency apropos of the nature of the antigen. It has not escaped our notice that the in silico methods studied here are not very proficient in identifying promiscuous peptides. This puts a much constraint on the intrepid use of such programs for human leukocyte antigen class II binding peptides. We conclude from this study that the in silico methods cannot be wholly relied for selecting crucial peptides for development of vaccines.     

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.     

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/.     

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     

Proteome sampling by the HLA class I antigen processing pathway

The peptide repertoire that is presented by the set of HLA class I molecules of an individual is formed by the different players of the antigen processing pathway and the stringent binding environment of the HLA class I molecules. Peptide elution studies have shown that only a subset of the human proteome is sampled by the antigen processing machinery and represented on the cell surface. In our study, we quantified the role of each factor relevant in shaping the HLA class I peptide repertoire by combining peptide elution data, in silico predictions of antigen processing and presentation, and data on gene expression and protein abundance. Our results indicate that gene expression level, protein abundance, and rate of potential binding peptides per protein have a clear impact on sampling probability. Furthermore, once a protein is available for the antigen processing machinery in sufficient amounts, C-terminal processing efficiency and binding affinity to the HLA class I molecule determine the identity of the presented peptides. Having studied the impact of each of these factors separately, we subsequently combined all factors in a logistic regression model in order to quantify their relative impact. This model demonstrated the superiority of protein abundance over gene expression level in predicting sampling probability. Being able to discriminate between sampled and non-sampled proteins to a significant degree, our approach can potentially be used to predict the sampling probability of self proteins and of pathogen-derived proteins, which is of importance for the identification of autoimmune antigens and vaccination targets.     

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.     

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.     

An empirical method for the prediction of T-cell epitopes

Identification of T-cell epitopes from foreign proteins is the current focus of much research. Methods using simple two or three position motifs have proved useful in epitope prediction for major histocompatibility complex (MHC) class I, but to date not for MHC class II molecules. We utilized data from pool sequence analysis of peptides eluted from two HLA-DR13 alleles to construct a computer algorithm for predicting the probability that a given sequence will be naturally processed and presented on these alleles. We assessed the ability of this method to predict know self-peptides from these DR-13 alleles, DRB1 ^*1301 and *1302, as well as an immunodominant T-cell epitope. We also compared the predictions of this scoring procedure with the measured binding affinities of a panel of overlapping peptides from hepatitis B virus surface antigen. We concluded that this method may have wide application for the prediction of T-cell epitopes for both MHC class I and class II molecules.     

Automated generation and evaluation of specific MHC binding predictive tools: ARB matrix applications

Prediction of which peptides can bind major histocompatibility complex (MHC) molecules is commonly used to assist in the identification of T cell epitopes. However, because of the large numbers of different MHC molecules of interest, each associated with different predictive tools, tool generation and evaluation can be a very resource intensive task. A methodology commonly used to predict MHC binding affinity is the matrix or linear coefficients method. Herein, we described Average Relative Binding (ARB) matrix methods that directly predict IC₅₀ values allowing combination of searches involving different peptide sizes and alleles into a single global prediction. A computer program was developed to automate the generation and evaluation of ARB predictive tools. Using an in-house MHC binding database, we generated a total of 85 and 13 MHC class I and class II matrices, respectively. Results from the automated evaluation of tool efficiency are presented. We anticipate that this automation framework will be generally applicable to the generation and evaluation of large numbers of MHC predictive methods and tools, and will be of value to centralize and rationalize the process of evaluation of MHC predictions. MHC binding predictions based on ARB matrices were made available at web server.     

Definition of supertypes for HLA molecules using clustering of specificity matrices

Major histocompatibility complex (MHC) proteins are encoded by extremely polymorphic genes and play a crucial role in immunity. However, not all genetically different MHC molecules are functionally different. Sette and Sidney (1999) have defined nine HLA class I supertypes and showed that with only nine main functional binding specificities it is possible to cover the binding properties of almost all known HLA class I molecules. Here we present a comprehensive study of the functional relationship between all HLA molecules with known specificities in a uniform and automated way. We have developed a novel method for clustering sequence motifs. We construct hidden Markov models for HLA class I molecules using a Gibbs sampling procedure and use the similarities among these to define clusters of specificities. These clusters are extensions of the previously suggested ones. We suggest splitting some of the alleles in the A1 supertype into a new A26 supertype, and some of the alleles in the B27 supertype into a new B39 supertype. Furthermore the B8 alleles may define their own supertype. We also use the published specificities for a number of HLA-DR types to define clusters with similar specificities. We report that the previously observed specificities of these class II molecules can be clustered into nine classes, which only partly correspond to the serological classification. We show that classification of HLA molecules may be done in a uniform and automated way. The definition of clusters allows for selection of representative HLA molecules that can cover the HLA specificity space better. This makes it possible to target most of the known HLA alleles with known specificities using only a few peptides, and may be used in construction of vaccines. Supplementary material is available at .     

Transporter associated with antigen processing preselection of peptides binding to the MHC: a bioinformatic evaluation

TAP is responsible for the transit of peptides from the cytosol to the lumen of the endoplasmic reticulum. In an immunological context, this event is followed by the binding of peptides to MHC molecules before export to the cell surface and recognition by T cells. Because TAP transport precedes MHC binding, TAP preferences may make a significant contribution to epitope selection. To assess the impact of this preselection, we have developed a scoring function for TAP affinity prediction using the additive method, have used it to analyze and extend the TAP binding motif, and have evaluated how well this model acts as a preselection step in predicting MHC binding peptides. To distinguish between MHC alleles that are exclusively dependent on TAP and those exhibiting only a partial dependence on TAP, two sets of MHC binding peptides were examined: HLA-A*0201 was selected as a representative of partially TAP-dependent HLA alleles, and HLA-A*0301 represented fully TAP-dependent HLA alleles. TAP preselection has a greater impact on TAP-dependent alleles than on TAP-independent alleles. The reduction in the number of nonbinders varied from 10% (TAP-independent) to 33% (TAP-dependent), suggesting that TAP preselection is an important component in the successful in silico prediction of T cell epitopes.     

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.     

Clustering HLA Class I Superfamilies Using Structural Interaction Patterns

Human leukocyte antigen (HLA) class I molecules are critical components of the cell-mediated immune system that bind and present intracellular antigenic peptides to CD8⁺ T cell receptors. To understand the interaction mechanism underlying human leukocyte antigen (HLA) class I specificity in detail, we studied the structural interaction characteristics of 16,393 nonameric peptides binding to 58 HLA-A and -B molecules. Our analysis showed for the first time that HLA-peptide intermolecular bonding patterns vary among different alleles and may be grouped in a superfamily dependent manner. Through the use of these HLA class I ‘fingerprints’, a high resolution HLA class I superfamily classification schema was developed. This classification is capable of separating HLA alleles into well resolved, non-overlapping clusters, which is consistent with known HLA superfamily definitions. Such structural interaction approach serves as an excellent alternative to the traditional methods of HLA superfamily definitions that use peptide binding motifs or receptor information, and will help identify appropriate antigens suitable for broad-based subunit vaccine design.     

Clusters versus affinity-based approaches in F. tularensis whole genome search of CTL epitopes

Deciphering the cellular immunome of a bacterial pathogen is challenging due to the enormous number of putative peptidic determinants. State-of-the-art prediction methods developed in recent years enable to significantly reduce the number of peptides to be screened, yet the number of remaining candidates for experimental evaluation is still in the range of ten-thousands, even for a limited coverage of MHC alleles. We have recently established a resource-efficient approach for down selection of candidates and enrichment of true positives, based on selection of predicted MHC binders located in high density "hotspots" of putative epitopes. This cluster-based approach was applied to an unbiased, whole genome search of Francisella tularensis CTL epitopes and was shown to yield a 17-25 fold higher level of responders as compared to randomly selected predicted epitopes tested in Kb/Db C57BL/6 mice. In the present study, we further evaluate the cluster-based approach (down to a lower density range) and compare this approach to the classical affinity-based approach by testing putative CTL epitopes with predicted IC(50) values of <10 nM. We demonstrate that while the percent of responders achieved by both approaches is similar, the profile of responders is different, and the predicted binding affinity of most responders in the cluster-based approach is relatively low (geometric mean of 170 nM), rendering the two approaches complimentary. The cluster-based approach is further validated in BALB/c F. tularensis immunized mice belonging to another allelic restriction (Kd/Dd) group. To date, the cluster-based approach yielded over 200 novel F. tularensis peptides eliciting a cellular response, all were verified as MHC class I binders, thereby substantially increasing the F. tularensis dataset of known CTL epitopes. The generality and power of the high density cluster-based approach suggest that it can be a valuable tool for identification of novel CTLs in proteomes of other bacterial pathogens.     

A combined immuno-informatics and structure-based modeling approach for prediction of T cell epitopes of secretory proteins of Mycobacterium tuberculosis

The role of secretory proteins of Mycobacterium tuberculosis in pathogenesis and stimulation of specific host responses is well documented. They are also shown to activate different cell types, which subsequently present mycobacterial antigens to T cells. Therefore identification of T cell epitopes from this set of proteins may serve to define candidate antigens with vaccine potential. Fifty-two secretory proteins of M. tuberculosis H37Rv were analyzed computationally for the presence of HLA class I binding nonameric peptides. All possible overlapping nonameric peptide sequences from 52 secretory proteins were generated in silico and analyzed for their ability to bind to 33 alleles belonging to A, B and C loci of HLA class I. Fifteen percent of generated peptides are predicted to bind to HLA with halftime of dissociation T(1/2) >or=100 min and 73% of the peptides predicted to bind are mono-allelic in their binding. The structural basis for recognition of no-namers by different HLA molecules was studied employing structural modeling of HLA class I-peptide complexes and there exists a good correlation between structural analysis and binding prediction. Pathogen peptides that could behave as self- or partially self-peptides in the host were eliminated using a comparative study with the human proteome, thus reducing the number of peptides for analysis. The implications of the finding for vaccine development are discussed vis-à-vis the limitations of the use of subunit vaccine and DNA vaccine.     

MHCcluster, a method for functional clustering of MHC molecules

The identification of peptides binding to major histocompatibility complexes (MHC) is a critical step in the understanding of T cell immune responses. The human MHC genomic region (HLA) is extremely polymorphic comprising several thousand alleles, many encoding a distinct molecule. The potentially unique specificities remain experimentally uncharacterized for the vast majority of HLA molecules. Likewise, for nonhuman species, only a minor fraction of the known MHC molecules have been characterized. Here, we describe a tool, MHCcluster, to functionally cluster MHC molecules based on their predicted binding specificity. The method has a flexible web interface that allows the user to include any MHC of interest in the analysis. The output consists of a static heat map and graphical tree-based visualizations of the functional relationship between MHC variants and a dynamic TreeViewer interface where both the functional relationship and the individual binding specificities of MHC molecules are visualized. We demonstrate that conventional sequence-based clustering will fail to identify the functional relationship between molecules, when applied to MHC system, and only through the use of the predicted binding specificity can a correct clustering be found. Clustering of prevalent HLA-A and HLA-B alleles using MHCcluster confirms the presence of 12 major specificity groups (supertypes) some however with highly divergent specificities. Importantly, some HLA molecules are shown not to fit any supertype classification. Also, we use MHCcluster to show that chimpanzee MHC class I molecules have a reduced functional diversity compared to that of HLA class I molecules. MHCcluster is available at www.cbs.dtu.dk/services/MHCcluster-2.0.