Computational binding assays of antigenic peptides

Summary Computer models can be combined with laboratory experiments for the efficient determination of (i) peptides that bind MHC molecules and (ii) T-cell epitopes. For maximum benefit, the use of computer models must be treated as experiments analogous to standard laboratory procedures. This requires the definition of standards and experimental protocols for model application. We describe the requirements for validation and assessment of computer models. The utility of combining accurate predictions with a limited number of laboratory experiments is illustrated by practical examples. These include the identification of T-cell epitopes from IDDM-, melanoma-and malaria-related antigens by combining computational and conventional laboratory assays. The success rate in determining antigenic peptides, each in the context of a specific HLA molecule, ranged from 27 to 71%, while the natural prevalence of MHC-binding peptides is 0.1–5%.     

Computational binding assays of antigenic peptides

Computer models can be combined with laboratory experiments for the efficient determination of (i) peptides that bind MHC molecules and (ii) T-cell epitopes. For maximum benefit, the use of computer models must be treated as experiments analogous to standard laboratory procedures. This requires the definition of standards and experimental protocols for model application. We describe the requirements for validation and assessment of computer models. The utility of combining accurate predictions with a limited number of laboratory experiments is illustrated by practical examples. These include the identification of T-cell epitopes from IDDM-, melanoma- and malaria-related antigens by combining computational and conventional laboratory assays. The success rate in determining antigenic peptides, each in the context of a specific HLA molecule, ranged from 27 to 71%, while the natural prevalence of MHC-binding peptides is 0.1–5%.     

TEpredict: Software for T-Cell epitope prediction

The program TEpredict was developed for T-cell epitope prediction. The used models for T-cell epitope prediction were constructed by the partial least squares regression method using the data extracted from the IEDB (Immune Epitope Database), the most complete resource of experimental peptide-MHC binding data. TEpredict is also able to predict proteasomal processing of protein antigens and the ability of produced oligopeptides to bind to the transporters associated with antigen processing, to discard the peptides sharing local similarity with human proteins from the set of predicted epitopes, and to estimate the expected population coverage by the selected peptides using the data on HLA allele genotypic frequencies. The main part of the constructed models demonstrated a high prediction sensitivity (0.50–0.80) in combination with a high specificity (0.75–0.99). Comparative testing demonstrated that TEpredict was competitive with or even superior to the programs ProPred1, SVRMHC, SVMHC, and SYFPEITHI. Thus, TEpredict can become an efficient tool for developing polyepitope vaccines, including the vaccines against various human pathogens, such as HIV and the influenza virus. TEpredict and the source code are available at http://tepredict.source- forge.net.     

Enhancement to the RANKPEP resource for the prediction of peptide binding to MHC molecules using profiles

We introduced previously an on-line resource, RANKPEP that uses position specific scoring matrices (PSSMs) or profiles for the prediction of peptide-MHC class I (MHCI) binding as a basis for CD8 T-cell epitope identification. Here, using PSSMs that are structurally consistent with the binding mode of MHC class II (MHCII) ligands, we have extended RANKPEP to prediction of peptide-MHCII binding and anticipation of CD4 T-cell epitopes. Currently, 88 and 50 different MHCI and MHCII molecules, respectively, can be targeted for peptide binding predictions in RANKPEP. Because appropriate processing of antigenic peptides must occur prior to major histocompatibility complex (MHC) binding, cleavage site prediction methods are important adjuncts for T-cell epitope discovery. Given that the C-terminus of most MHCI-restricted epitopes results from proteasomal cleavage, we have modeled the cleavage site from known MHCI-restricted epitopes using statistical language models. The RANKPEP server now determines whether the C-terminus of any predicted MHCI ligand may result from such proteasomal cleavage. Also implemented is a variability masking function. This feature focuses prediction on conserved rather than highly variable protein segments encoded by infectious genomes, thereby offering identification of invariant T-cell epitopes to thwart mutation as an immune evasion mechanism.     

MHC-BPS: MHC-binder prediction server for identifying peptides of flexible lengths from sequence-derived physicochemical properties

Major histocompatibility complex (MHC)-binding peptides are essential for antigen recognition by T-cell receptors and are being explored for vaccine design. Computational methods have been developed for predicting MHC-binding peptides of fixed lengths, based on the training of relatively few non-binders. It is desirable to introduce methods applicable for peptides of flexible lengths and trained by using more diverse sets of non-binders. MHC-BPS is a web-based MHC-binder prediction server that uses support vector machines for predicting peptide binders of flexible lengths for 18 MHC class I and 12 class II alleles from sequence-derived physicochemical properties, which were trained by using 4,208∼3,252 binders and 234,333∼168,793 non-binders, and evaluated by an independent set of 545∼476 binders and 110,564∼84,430 non-binders. The binder prediction accuracies are 86∼99% for 25 and 70∼80% for five alleles, and the non-binder accuracies are 96∼99% for 30 alleles. A screening of HIV-1 genome identifies 0.01∼5% and 5∼8% of the constituent peptides as binders for 24 and 6 alleles, respectively, including 75∼100% of the known epitopes. This method correctly predicts 73.3% of the 15 newly published epitopes in the last 4 months of 2005. MHC-BPS is available at .Electronic Supplementary Material Supplementary material is available for this article at and is accessible for authorized users.     

Towards the in silico identification of class II restricted T-cell epitopes: a partial least squares iterative self-consistent algorithm for affinity prediction

MOTIVATION: The immunogenicity of peptides depends on their ability to bind to MHC molecules. MHC binding affinity prediction methods can save significant amounts of experimental work. The class II MHC binding site is open at both ends, making epitope prediction difficult because of the multiple binding ability of long peptides. RESULTS: An iterative self-consistent partial least squares (PLS)-based additive method was applied to a set of 66 peptides no longer than 16 amino acids, binding to DRB1*0401. A regression equation containing the quantitative contributions of the amino acids at each of the nine positions was generated. Its predictability was tested using two external test sets which gave r(pred) = 0.593 and r(pred) = 0.655, respectively. Furthermore, it was benchmarked using 25 known T-cell epitopes restricted by DRB1*0401 and we compared our results with four other online predictive methods. The additive method showed the best result finding 24 of the 25 T-cell epitopes. AVAILABILITY: Peptides used in the study are available from http://www.jenner.ac.uk/JenPep. The PLS method is available commercially in the SYBYL molecular modelling software package. The final model for affinity prediction of peptides binding to DRB1*0401 molecule is available at http://www.jenner.ac.uk/MHCPred. Models developed for DRB1*0101 and DRB1*0701 also are available in MHCPred.     

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.     

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.     

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.     

POPI: predicting immunogenicity of MHC class I binding peptides by mining informative physicochemical properties

MOTIVATION: Both modeling of antigen-processing pathway including major histocompatibility complex (MHC) binding and immunogenicity prediction of those MHC-binding peptides are essential to develop a computer-aided system of peptide-based vaccine design that is one goal of immunoinformatics. Numerous studies have dealt with modeling the immunogenic pathway but not the intractable problem of immunogenicity prediction due to complex effects of many intrinsic and extrinsic factors. Moderate affinity of the MHC-peptide complex is essential to induce immune responses, but the relationship between the affinity and peptide immunogenicity is too weak to use for predicting immunogenicity. This study focuses on mining informative physicochemical properties from known experimental immunogenicity data to understand immune responses and predict immunogenicity of MHC-binding peptides accurately. RESULTS: This study proposes a computational method to mine a feature set of informative physicochemical properties from MHC class I binding peptides to design a support vector machine (SVM) based system (named POPI) for the prediction of peptide immunogenicity. High performance of POPI arises mainly from an inheritable bi-objective genetic algorithm, which aims to automatically determine the best number m out of 531 physicochemical properties, identify these m properties and tune SVM parameters simultaneously. The dataset consisting of 428 human MHC class I binding peptides belonging to four classes of immunogenicity was established from MHCPEP, a database of MHC-binding peptides (Brusic et al., 1998). POPI, utilizing the m = 23 selected properties, performs well with the accuracy of 64.72% using leave-one-out cross-validation, compared with two sequence alignment-based prediction methods ALIGN (54.91%) and PSI-BLAST (53.23%). POPI is the first computational system for prediction of peptide immunogenicity based on physicochemical properties. AVAILABILITY: A web server for prediction of peptide immunogenicity (POPI) and the used dataset of MHC class I binding peptides (PEPMHCI) are available at http://iclab.life.nctu.edu.tw/POPI     

Bioinformatics tools for identifying class I-restricted epitopes

The lack of simple methods to identify relevant T-cell epitopes, the high mutation rate of many pathogens, and restriction of T-cell response to epitopes due to human lymphocyte antigen (HLA) polymorphism have significantly hindered the development of cytotoxic T-lymphocyte (CTL) epitope-based or "epitope-driven" vaccines. Previously, CTL epitopes were mapped using large arrays of overlapping synthetic peptides. The large number of protein sequences available for mapping is now making this method prohibitively expensive and time-consuming. Bioinformatics tools such as EpiMatrix and Conservatrix, which search for unique or multi-HLA-restricted (promiscuous) T-cell epitopes and identify epitopes that are conserved across variant strains of the same pathogen, accelerate epitope mapping. These tools offer a significant advantage over other methods of epitope selection because high-throughput screening can be performed in silico, followed by confirmatory studies in vitro. CTL epitopes discovered using these tools might be used to develop novel vaccines and therapeutics for the prevention and treatment of infectious diseases such as human immunodeficiency virus, hepatitis C, tuberculosis, and some cancers.     

Prediction of promiscuous peptides that bind HLA class I molecules

Promiscuous T-cell epitopes make ideal targets for vaccine development. We report here a computational system, MULTIPRED, for the prediction of peptide binding to the HLA-A2 supertype. It combines a novel representation of peptide/MHC interactions with a hidden Markov model as the prediction algorithm. MULTIPREDis both sensitive and specific, and demonstrates high accuracy of peptide-binding predictions for HLA-A*0201, *0204, and *0205 alleles, good accuracy for *0206 allele, and marginal accuracy for *0203 allele. MULTIPREDreplaces earlier requirements for individual prediction models for each HLA allelic variant and simplifies computational aspects of peptide-binding prediction. Preliminary testing indicates that MULTIPRED can predict peptide binding to HLA-A2 supertype molecules with high accuracy, including those allelic variants for which no experimental binding data are currently available.     

A systematic assessment of MHC class II peptide binding predictions and evaluation of a consensus approach

The identification of MHC class II restricted peptide epitopes is an important goal in immunological research. A number of computational tools have been developed for this purpose, but there is a lack of large-scale systematic evaluation of their performance. Herein, we used a comprehensive dataset consisting of more than 10,000 previously unpublished MHC-peptide binding affinities, 29 peptide/MHC crystal structures, and 664 peptides experimentally tested for CD4+ T cell responses to systematically evaluate the performances of publicly available MHC class II binding prediction tools. While in selected instances the best tools were associated with AUC values up to 0.86, in general, class II predictions did not perform as well as historically noted for class I predictions. It appears that the ability of MHC class II molecules to bind variable length peptides, which requires the correct assignment of peptide binding cores, is a critical factor limiting the performance of existing prediction tools. To improve performance, we implemented a consensus prediction approach that combines methods with top performances. We show that this consensus approach achieved best overall performance. Finally, we make the large datasets used publicly available as a benchmark to facilitate further development of MHC class II binding peptide prediction methods.     

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.     

Mapping the molecular characteristics of Brazilian human T-cell lymphotropic virus type 1 Env (gp46) and Pol amino acid sequences for vaccine design

This study was carried out to evaluate the molecular pattern of all available Brazilian human T-cell lymphotropic virus type 1 Env (n = 15) and Pol (n = 43) nucleotide sequences via epitope prediction, physico-chemical analysis, and protein potential sites identification, giving support to the Brazilian AIDS vaccine program. In 12 previously described peptides of the Env sequences we found 12 epitopes, while in 4 peptides of the Pol sequences we found 4 epitopes. The total variation on the amino acid composition was 9 and 17% for human leukocyte antigen (HLA) class I and class II Env epitopes, respectively. After analyzing the Pol sequences, results revealed a total amino acid variation of 0.75% for HLA-I and HLA-II epitopes. In 5 of the 12 Env epitopes the physico-chemical analysis demonstrated that the mutations magnified the antigenicity profile. The potential protein domain analysis of Env sequences showed the loss of a CK-2 phosphorylation site caused by D197N mutation in one epitope, and a N-glycosylation site caused by S246Y and V247I mutations in another epitope. Besides, the analysis of selection pressure have found 8 positive selected sites (w = 9.59) using the codon-based substitution models and maximum-likelihood methods. These studies underscore the importance of this Env region for the virus fitness, for the host immune response and, therefore, for the development of vaccine candidates.     

SNEP: SNP-derived Epitope Prediction program for minor H antigens

The single nucleotide polymorphism (SNP)-derived Epitope Prediction program (SNEP) is now available to the public. It predicts minor histocompatibility antigens (miHAgs), which are T-cell epitopes containing polymorphic spots, from proteins listed in the SWISS-PROT database. SNEP recognizes polymorphisms (termed VARIANT or CONFLICT in SWISS-PROT) and predicts potential T-cell epitopes within a chosen distance around the polymorphic residue. The prediction algorithm is based on the SYFPEITHI T-cell epitope prediction program. SNEP is able to search for proteins according to their accession numbers, sequence stretches or gene names, for example. The predictions are available for several human leucocyte antigen class I and class II allelic products, which allow for a rapid and precise evaluation of potential miHAgs within polymorphic antigens.     

Amino acid biophysical properties in the statistical prediction of peptide-MHC class I binding

Background

Peptides derived from endogenous antigens can bind to MHC class I molecules. Those which bind with high affinity can invoke a CD8⁺ immune response, resulting in the destruction of infected cells. Much work in immunoinformatics has involved the algorithmic prediction of peptide binding affinity to various MHC-I alleles. A number of tools for MHC-I binding prediction have been developed, many of which are available on the web.

Results

We hypothesize that peptides predicted by a number of tools are more likely to bind than those predicted by just one tool, and that the likelihood of a particular peptide being a binder is related to the number of tools that predict it, as well as the accuracy of those tools. To this end, we have built and tested a heuristic-based method of making MHC-binding predictions by combining the results from multiple tools. The predictive performance of each individual tool is first ascertained. These performance data are used to derive weights such that the predictions of tools with better accuracy are given greater credence. The combined tool was evaluated using ten-fold cross-validation and was found to signicantly outperform the individual tools when a high specificity threshold is used. It performs comparably well to the best-performing individual tools at lower specificity thresholds. Finally, it also outperforms the combination of the tools resulting from linear discriminant analysis.

Conclusion

A heuristic-based method of combining the results of the individual tools better facilitates the scanning of large proteomes for potential epitopes, yielding more actual high-affinity binders while reporting very few false positives.     

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.     

Predicting peptides bound to I-Ag7 class II histocompatibility molecules using a novel expectation-maximization alignment algorithm

The useful structural features of class II MHC molecules are rarely integrated into T-cell epitope predictions. We propose an approach that applies a novel expectation-maximization algorithm to align the naturally processed peptides selected by the class II MHC I-A(g7) molecule - focusing on the five MHC-specific anchor positions. Based on the alignment profile, log of odds (LOD) scores supplemented with the Laplace plus-one pseudocounts method are applied to identify the potential T-cell epitopes. In addition, an innovative computational concept of hindering residues using statistical and structural information is developed to refine the prediction. Performance analysis by receiver operating characteristics statistics and the experimental validation of the LOD scores demonstrate the accuracy of our predictive model. Furthermore, our model successfully predicts T-cell epitopes of hen egg-white lysozyme protein antigen. Our study provides a framework for predicting T-cell epitopes in class II MHC molecules.