Search

Mycobacterium avium subspecies paratuberculosis (MAP) is a global concern in modern livestock production worldwide. The available vaccines against paratuberculosis do not offer optimal protection and interfere with the diagnosis of bovine tuberculosis. The aim of this study was to identify immunogenic MAP-specific peptides that do not interfere with the diagnosis of bovine tuberculosis. Initially, 119 peptides were selected by either (1) identifying unique MAP peptides that were predicted to bind to bovine major histocompatibility complex class II (MHC-predicted peptides) or (2) selecting hydrophobic peptides unique to MAP within proteins previously shown to be immunogenic (hydrophobic peptides). Subsequent testing of peptide-specific CD4+ T-cell lines from MAP-infected, adult goats vaccinated with peptides in cationic liposome adjuvant pointed to 23 peptides as being most immunogenic. These peptides were included in a second vaccine trial where three groups of eight healthy goat kids were vaccinated with 14 MHC-predicted peptides, nine hydrophobic peptides, or no peptides in o/w emulsion adjuvant. The majority of the MHC-predicted (93%) and hydrophobic peptides (67%) induced interferon-gamma (IFN-γ) responses in at least one animal. Similarly, 86% of the MHC-predicted and 89% of the hydrophobic peptides induced antibody responses in at least one goat. The immunization of eight healthy heifers with all 119 peptides formulated in emulsion adjuvant identified more peptides as immunogenic, as peptide specific IFN-γ and antibody responses in at least one heifer was found toward 84% and 24% of the peptides, respectively. No peptide-induced reactivity was found with commercial ELISAs for detecting antibodies against Mycobacterium bovis or MAP or when performing tuberculin skin testing for bovine tuberculosis. The vaccinated animals experienced adverse reactions at the injection site; thus, it is recommend that future studies make improvements to the vaccine formulation. In conclusion, immunogenic MAP-specific peptides that appeared promising for use in a vaccine against paratuberculosis without interfering with surveillance and trade tests for bovine tuberculosis were identified by in silico analysis and ex vivo generation of CD4+ T-cell lines and validated by the immunization of goats and cattle. Future studies should test different peptide combinations in challenge trials to determine their protective effect and identify the most MHC-promiscuous vaccine candidates., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Lybeck, Tollefsen, Mikkelsen, Sjurseth, Lundegaard, Aagaard, Olsen and Jungersen.)

Background: IgE is the least abundant immunoglobulin and tightly regulated, and IgE-producing B cells are rare. The cellular origin and evolution of IgE responses are poorly understood., Objective: The cellular and clonal origin of IgE memory responses following mucosal allergen exposure by sublingual immunotherapy (SLIT) were investigated., Methods: In a randomized double-blind, placebo-controlled, time course SLIT study, PBMCs and nasal biopsy samples were collected from 40 adults with seasonal allergic rhinitis at baseline and at 4, 8, 16, 28, and 52 weeks. RNA was extracted from PBMCs, sorted B cells, and nasal biopsy samples for heavy chain variable gene repertoire sequencing. Moreover, mAbs were derived from single B-cell transcriptomes., Results: Combining heavy chain variable gene repertoire sequencing and single-cell transcriptomics yielded direct evidence of a parallel boost of 2 clonally and functionally related B-cell subsets of short-lived IgE + plasmablasts and IgG + memory B cells. Mucosal grass pollen allergen exposure by SLIT resulted in highly diverse IgE and IgG E repertoires. These were extensively mutated and appeared relatively stable as per heavy chain isotype, somatic hypermutations, and clonal composition. Single IgG E + memory B-cell and IgE + preplasmablast transcriptomes encoded antibodies that were specific for major grass pollen allergens and able to elicit basophil activation at very low allergen concentrations., Conclusion: For the first time, we have shown that on mucosal allergen exposure, human IgE memory resides in allergen-specific IgG + memory B cells. These cells rapidly switch isotype, expand into short-lived IgE + plasmablasts, and serve as a potential target for therapeutic intervention., (Crown Copyright © 2019. Published by Elsevier Inc. All rights reserved.)

Background: Ragweed frequently causes seasonal allergies in North America and Europe. In the United States, several related ragweed species with diverse geographical distribution cause allergic symptoms. Cross-reactivity towards related ragweed species of IgE and treatment-induced IgG 4 has been demonstrated previously. However, less is known about the underlying T-cell cross-reactivity., Methods: The allergen content of ragweed extracts was determined by mass spectrometry and related to T-cell epitopes of Amb a allergens (group 1, 3, 4, 5, 8 and 11) in 20 American ragweed allergic patients determined by FluoroSpot and proliferation assays. T-cell responses to 50 frequently recognized Amb a-derived T-cell epitopes and homologous peptides from western ragweed (Amb p), giant ragweed (Amb t) and mugwort (Art v) were investigated in an additional 11 American and 14 Slovakian ragweed allergic donors., Results: Ragweed extracts contained all known allergens and isoallergens thereof. Donor T-cell responses were diverse and directed against all Amb a 1 isoallergens and to most minor allergens investigated. Similar response patterns were seen in American and Slovakia donors. Several epitopes were cross-reactive between isoallergens and ragweed species, some even including mugwort. T-cell cross-reactivity generally correlated with allergen sequence homology., Conclusion: T-cell epitopes of multiple allergens/isoallergens are involved in the diverse T-cell responses in ragweed allergic individuals. T-cell lines were highly cross-reactive to epitopes of related ragweed species without any apparent geographical response bias. These data support that different ragweed species can be considered an allergen homology group with Amb a as the representative species regarding diagnosis as well as allergy immunotherapy., (© 2019 EAACI and John Wiley and Sons A/S. Published by John Wiley and Sons Ltd.)

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.

The major histocompatibility complex (MHC) genes are the most polymorphic genes found in the vertebrate genome, and they encode proteins that play an essential role in the adaptive immune response. Many songbirds (passerines) have been shown to have a large number of transcribed MHC class I genes compared to most mammals. To elucidate the reason for this large number of genes, we compared 14 MHC class I alleles (α1-α3 domains), from great reed warbler, house sparrow and tree sparrow, via phylogenetic analysis, homology modelling and in silico peptide-binding predictions to investigate their functional and genetic relationships. We found more pronounced clustering of the MHC class I allomorphs (allele specific proteins) in regards to their function (peptide-binding specificities) compared to their genetic relationships (amino acid sequences), indicating that the high number of alleles is of functional significance. The MHC class I allomorphs from house sparrow and tree sparrow, species that diverged 10 million years ago (MYA), had overlapping peptide-binding specificities, and these similarities across species were also confirmed in phylogenetic analyses based on amino acid sequences. Notably, there were also overlapping peptide-binding specificities in the allomorphs from house sparrow and great reed warbler, although these species diverged 30 MYA. This overlap was not found in a tree based on amino acid sequences. Our interpretation is that convergent evolution on the level of the protein function, possibly driven by selection from shared pathogens, has resulted in allomorphs with similar peptide-binding repertoires, although trans-species evolution in combination with gene conversion cannot be ruled out.

Bioinformatics methods for immunology have become increasingly used over the last decade and now form an integrated part of most epitope discovery projects. This wide usage has led to the confusion of defining which of the many methods to use for what problems. In this chapter, an overview is given focusing on the suite of tools developed at the Technical University of Denmark.

The immune epitope database analysis resource (IEDB-AR: http://tools.iedb.org) is a collection of tools for prediction and analysis of molecular targets of T- and B-cell immune responses (i.e. epitopes). Since its last publication in the NAR webserver issue in 2008, a new generation of peptide:MHC binding and T-cell epitope predictive tools have been added. As validated by different labs and in the first international competition for predicting peptide:MHC-I binding, their predictive performances have improved considerably. In addition, a new B-cell epitope prediction tool was added, and the homology mapping tool was updated to enable mapping of discontinuous epitopes onto 3D structures. Furthermore, to serve a wider range of users, the number of ways in which IEDB-AR can be accessed has been expanded. Specifically, the predictive tools can be programmatically accessed using a web interface and can also be downloaded as software packages.

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 www.cbs.dtu.dk/services/NetMHCcons , and allows the user in an automatic manner to obtain the most accurate predictions for any given MHC molecule.

Prediction methods as well as experimental methods for T-cell epitope discovery have developed significantly in recent years. High-throughput experimental methods have made it possible to perform full-length protein scans for epitopes restricted to a limited number of MHC alleles. The high costs and limitations regarding the number of proteins and MHC alleles that are feasibly handled by such experimental methods have made in silico prediction models of high interest. MHC binding prediction methods are today of a very high quality and can predict MHC binding peptides with high accuracy. This is possible for a large range of MHC alleles and relevant length of binding peptides. The predictions can easily be performed for complete proteomes of any size. Prediction methods are still, however, dependent on good experimental methods for validation, and should merely be used as a guide for rational epitope discovery. We expect prediction methods as well as experimental validation methods to continue to develop and that we will soon see clinical trials of products whose development has been guided by prediction methods.

CD4+ T cells orchestrate immunity against viral infections, but their importance in HIV infection remains controversial. Nevertheless, comprehensive studies have associated increase in breadth and functional characteristics of HIV-specific CD4+ T cells with decreased viral load. A major challenge for the identification of HIV-specific CD4+ T cells targeting broadly reactive epitopes in populations with diverse ethnic background stems from the vast genomic variation of HIV and the diversity of the host cellular immune system. Here, we describe a novel epitope selection strategy, PopCover, that aims to resolve this challenge, and identify a set of potential HLA class II-restricted HIV epitopes that in concert will provide optimal viral and host coverage. Using this selection strategy, we identified 64 putative epitopes (peptides) located in the Gag, Nef, Env, Pol and Tat protein regions of HIV. In total, 73% of the predicted peptides were found to induce HIV-specific CD4+ T cell responses. The Gag and Nef peptides induced most responses. The vast majority of the peptides (93%) had predicted restriction to the patient's HLA alleles. Interestingly, the viral load in viremic patients was inversely correlated to the number of targeted Gag peptides. In addition, the predicted Gag peptides were found to induce broader polyfunctional CD4+ T cell responses compared to the commonly used Gag-p55 peptide pool. These results demonstrate the power of the PopCover method for the identification of broadly recognized HLA class II-restricted epitopes. All together, selection strategies, such as PopCover, might with success be used for the evaluation of antigen-specific CD4+ T cell responses and design of future vaccines.

The interaction between antibodies and antigens is one of the most important immune system mechanisms for clearing infectious organisms from the host. Antibodies bind to antigens at sites referred to as B-cell epitopes. Identification of the exact location of B-cell epitopes is essential in several biomedical applications such as; rational vaccine design, development of disease diagnostics and immunotherapeutics. However, experimental mapping of epitopes is resource intensive making in silico methods an appealing complementary approach. To date, the reported performance of methods for in silico mapping of B-cell epitopes has been moderate. Several issues regarding the evaluation data sets may however have led to the performance values being underestimated: Rarely, all potential epitopes have been mapped on an antigen, and antibodies are generally raised against the antigen in a given biological context not against the antigen monomer. Improper dealing with these aspects leads to many artificial false positive predictions and hence to incorrect low performance values. To demonstrate the impact of proper benchmark definitions, we here present an updated version of the DiscoTope method incorporating a novel spatial neighborhood definition and half-sphere exposure as surface measure. Compared to other state-of-the-art prediction methods, Discotope-2.0 displayed improved performance both in cross-validation and in independent evaluations. Using DiscoTope-2.0, we assessed the impact on performance when using proper benchmark definitions. For 13 proteins in the training data set where sufficient biological information was available to make a proper benchmark redefinition, the average AUC performance was improved from 0.791 to 0.824. Similarly, the average AUC performance on an independent evaluation data set improved from 0.712 to 0.727. Our results thus demonstrate that given proper benchmark definitions, B-cell epitope prediction methods achieve highly significant predictive performances suggesting these tools to be a powerful asset in rational epitope discovery. The updated version of DiscoTope is available at www.cbs.dtu.dk/services/DiscoTope-2.0.

In this paper, we describe the methodologies behind three different aspects of the NetMHC family for prediction of MHC class I binding, mainly to HLAs. We have updated the prediction servers, NetMHC-3.2, NetMHCpan-2.2, and a new consensus method, NetMHCcons, which, in their previous versions, have been evaluated to be among the very best performing MHC:peptide binding predictors available. Here we describe the background for these methods, and the rationale behind the different optimization steps implemented in the methods. We go through the practical use of the methods, which are publicly available in the form of relatively fast and simple web interfaces. Furthermore, we will review results obtained in actual epitope discovery projects where previous implementations of the described methods have been used in the initial selection of potential epitopes. Selected potential epitopes were all evaluated experimentally using ex vivo assays., (Copyright © 2010 Elsevier B.V. All rights reserved.)

Epitopes from all available full-length sequences of yellow fever virus (YFV) and dengue fever virus (DENV) restricted by Human Leukocyte Antigen class I (HLA-I) alleles covering 12 HLA-I supertypes were predicted using the NetCTL algorithm. A subset of 179 predicted YFV and 158 predicted DENV epitopes were selected using the EpiSelect algorithm to allow for optimal coverage of viral strains. The selected predicted epitopes were synthesized and approximately 75% were found to bind the predicted restricting HLA molecule with an affinity, K(D), stronger than 500 nM. The immunogenicity of 25 HLA-A*02:01, 28 HLA-A*24:02 and 28 HLA-B*07:02 binding peptides was tested in three HLA-transgenic mice models and led to the identification of 17 HLA-A*02:01, 4 HLA-A*2402 and 4 HLA-B*07:02 immunogenic peptides. The immunogenic peptides bound HLA significantly stronger than the non-immunogenic peptides. All except one of the immunogenic peptides had K(D) below 100 nM and the peptides with K(D) below 5 nM were more likely to be immunogenic. In addition, all the immunogenic peptides that were identified as having a high functional avidity had K(D) below 20 nM. A*02:01 transgenic mice were also inoculated twice with the 17DD YFV vaccine strain. Three of the YFV A*02:01 restricted peptides activated T-cells from the infected mice in vitro. All three peptides that elicited responses had an HLA binding affinity of 2 nM or less. The results indicate the importance of the strength of HLA binding in shaping the immune response.

Unlabelled: β-turns are the most common type of non-repetitive structures, and constitute on average 25% of the amino acids in proteins. The formation of β-turns plays an important role in protein folding, protein stability and molecular recognition processes. In this work we present the neural network method NetTurnP, for prediction of two-class β-turns and prediction of the individual β-turn types, by use of evolutionary information and predicted protein sequence features. It has been evaluated against a commonly used dataset BT426, and achieves a Matthews correlation coefficient of 0.50, which is the highest reported performance on a two-class prediction of β-turn and not-β-turn. Furthermore NetTurnP shows improved performance on some of the specific β-turn types. In the present work, neural network methods have been trained to predict β-turn or not and individual β-turn types from the primary amino acid sequence. The individual β-turn types I, I', II, II', VIII, VIa1, VIa2, VIba and IV have been predicted based on classifications by PROMOTIF, and the two-class prediction of β-turn or not is a superset comprised of all β-turn types. The performance is evaluated using a golden set of non-homologous sequences known as BT426. Our two-class prediction method achieves a performance of: MCC=0.50, Qtotal=82.1%, sensitivity=75.6%, PPV=68.8% and AUC=0.864. We have compared our performance to eleven other prediction methods that obtain Matthews correlation coefficients in the range of 0.17-0.47. For the type specific β-turn predictions, only type I and II can be predicted with reasonable Matthews correlation coefficients, where we obtain performance values of 0.36 and 0.31, respectively., Conclusion: The NetTurnP method has been implemented as a webserver, which is freely available at http://www.cbs.dtu.dk/services/NetTurnP/. NetTurnP is the only available webserver that allows submission of multiple sequences.

Background: Binding of peptides to Major Histocompatibility class II (MHC-II) molecules play a central role in governing responses of the adaptive immune system. MHC-II molecules sample peptides from the extracellular space allowing the immune system to detect the presence of foreign microbes from this compartment. Predicting which peptides bind to an MHC-II molecule is therefore of pivotal importance for understanding the immune response and its effect on host-pathogen interactions. The experimental cost associated with characterizing the binding motif of an MHC-II molecule is significant and large efforts have therefore been placed in developing accurate computer methods capable of predicting this binding event. Prediction of peptide binding to MHC-II is complicated by the open binding cleft of the MHC-II molecule, allowing binding of peptides extending out of the binding groove. Moreover, the genes encoding the MHC molecules are immensely diverse leading to a large set of different MHC molecules each potentially binding a unique set of peptides. Characterizing each MHC-II molecule using peptide-screening binding assays is hence not a viable option., Results: Here, we present an MHC-II binding prediction algorithm aiming at dealing with these challenges. The method is a pan-specific version of the earlier published allele-specific NN-align algorithm and does not require any pre-alignment of the input data. This allows the method to benefit also from information from alleles covered by limited binding data. The method is evaluated on a large and diverse set of benchmark data, and is shown to significantly out-perform state-of-the-art MHC-II prediction methods. In particular, the method is found to boost the performance for alleles characterized by limited binding data where conventional allele-specific methods tend to achieve poor prediction accuracy., Conclusions: The method thus shows great potential for efficient boosting the accuracy of MHC-II binding prediction, as accurate predictions can be obtained for novel alleles at highly reduced experimental costs. Pan-specific binding predictions can be obtained for all alleles with know protein sequence and the method can benefit by including data in the training from alleles even where only few binders are known. The method and benchmark data are available at http://www.cbs.dtu.dk/services/NetMHCIIpan-2.0.

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.

Summary: Over the last decade, in silico models of the major histocompatibility complex (MHC) class I pathway have developed significantly. Before, peptide binding could only be reliably modelled for a few major human or mouse histocompatibility molecules; now, high-accuracy predictions are available for any human leucocyte antigen (HLA) -A or -B molecule with known protein sequence. Furthermore, peptide binding to MHC molecules from several non-human primates, mouse strains and other mammals can now be predicted. In this review, a number of different prediction methods are briefly explained, highlighting the most useful and historically important. Selected case stories, where these 'reverse immunology' systems have been used in actual epitope discovery, are briefly reviewed. We conclude that this new generation of epitope discovery systems has become a highly efficient tool for epitope discovery, and recommend that the less accurate prediction systems of the past be abandoned, as these are obsolete.

Mice are still the most used model organism in initial phases of vaccine design. Bioinformatics is becoming increasingly more important in vaccine development, both for the design of novel simplified epitope-based vaccines and also in order to understand the specific immune response of selected vaccine formulations. Toxoplasma gondii, an intracellular parasite, causes severe neurologic and ocular disease in congenitally infected and immunocompromised individuals. No protective vaccine exists against human toxoplasmosis. However, studies with mice have revealed immunodominant cytotoxic T lymphocyte epitopes originating from type II strains. These verified epitopes might be useful in human vaccines as the peptide binding repertoire of H-2L(d) MHC and MHCs belonging to the HLA-B07 supertype are very similar. Here, the results obtained using these epitopes in BALB/c as well as transgenic HLA-B*0702 mice are discussed. The stunning results obtained from the use of refined computational methods for the prediction of cytotoxic T lymphocyte epitopes are also discussed. The results highlight some important issues regarding both the use of mice but also the choice of bioinformatics methods in vaccine development.

Summary: Major histocompatibility complex class II (MHC-II) molecules sample peptides from the extracellular space, allowing the immune system to detect the presence of foreign microbes from this compartment. To be able to predict the immune response to given pathogens, a number of methods have been developed to predict peptide-MHC binding. However, few methods other than the pioneering TEPITOPE/ProPred method have been developed for MHC-II. Despite recent progress in method development, the predictive performance for MHC-II remains significantly lower than what can be obtained for MHC-I. One reason for this is that the MHC-II molecule is open at both ends allowing binding of peptides extending out of the groove. The binding core of MHC-II-bound peptides is therefore not known a priori and the binding motif is hence not readily discernible. Recent progress has been obtained by including the flanking residues in the predictions. All attempts to make ab initio predictions based on protein structure have failed to reach predictive performances similar to those that can be obtained by data-driven methods. Thousands of different MHC-II alleles exist in humans. Recently developed pan-specific methods have been able to make reasonably accurate predictions for alleles that were not included in the training data. These methods can be used to define supertypes (clusters) of MHC-II alleles where alleles within each supertype have similar binding specificities. Furthermore, the pan-specific methods have been used to make a graphical atlas such as the MHCMotifviewer, which allows for visual comparison of specificities of different alleles.

CPHmodels-3.0 is a web server predicting protein 3D structure by use of single template homology modeling. The server employs a hybrid of the scoring functions of CPHmodels-2.0 and a novel remote homology-modeling algorithm. A query sequence is first attempted modeled using the fast CPHmodels-2.0 profile-profile scoring function suitable for close homology modeling. The new computational costly remote homology-modeling algorithm is only engaged provided that no suitable PDB template is identified in the initial search. CPHmodels-3.0 was benchmarked in the CASP8 competition and produced models for 94% of the targets (117 out of 128), 74% were predicted as high reliability models (87 out of 117). These achieved an average RMSD of 4.6 A when superimposed to the 3D structure. The remaining 26% low reliably models (30 out of 117) could superimpose to the true 3D structure with an average RMSD of 9.3 A. These performance values place the CPHmodels-3.0 method in the group of high performing 3D prediction tools. Beside its accuracy, one of the important features of the method is its speed. For most queries, the response time of the server is <20 min. The web server is available at http://www.cbs.dtu.dk/services/CPHmodels/.

Reliable predictions of immunogenic peptides are essential in rational vaccine design and can minimize the experimental effort needed to identify epitopes. In this work, we describe a pan-specific major histocompatibility complex (MHC) class I epitope predictor, NetCTLpan. The method integrates predictions of proteasomal cleavage, transporter associated with antigen processing (TAP) transport efficiency, and MHC class I binding affinity into a MHC class I pathway likelihood score and is an improved and extended version of NetCTL. The NetCTLpan method performs predictions for all MHC class I molecules with known protein sequence and allows predictions for 8-, 9-, 10-, and 11-mer peptides. In order to meet the need for a low false positive rate, the method is optimized to achieve high specificity. The method was trained and validated on large datasets of experimentally identified MHC class I ligands and cytotoxic T lymphocyte (CTL) epitopes. It has been reported that MHC molecules are differentially dependent on TAP transport and proteasomal cleavage. Here, we did not find any consistent signs of such MHC dependencies, and the NetCTLpan method is implemented with fixed weights for proteasomal cleavage and TAP transport for all MHC molecules. The predictive performance of the NetCTLpan method was shown to outperform other state-of-the-art CTL epitope prediction methods. Our results further confirm the importance of using full-type human leukocyte antigen restriction information when identifying MHC class I epitopes. Using the NetCTLpan method, the experimental effort to identify 90% of new epitopes can be reduced by 15% and 40%, respectively, when compared to the NetMHCpan and NetCTL methods. The method and benchmark datasets are available at http://www.cbs.dtu.dk/services/NetCTLpan/.

Background: Estimation of the reliability of specific real value predictions is nontrivial and the efficacy of this is often questionable. It is important to know if you can trust a given prediction and therefore the best methods associate a prediction with a reliability score or index. For discrete qualitative predictions, the reliability is conventionally estimated as the difference between output scores of selected classes. Such an approach is not feasible for methods that predict a biological feature as a single real value rather than a classification. As a solution to this challenge, we have implemented a method that predicts the relative surface accessibility of an amino acid and simultaneously predicts the reliability for each prediction, in the form of a Z-score., Results: An ensemble of artificial neural networks has been trained on a set of experimentally solved protein structures to predict the relative exposure of the amino acids. The method assigns a reliability score to each surface accessibility prediction as an inherent part of the training process. This is in contrast to the most commonly used procedures where reliabilities are obtained by post-processing the output., Conclusion: The performance of the neural networks was evaluated on a commonly used set of sequences known as the CB513 set. An overall Pearson's correlation coefficient of 0.72 was obtained, which is comparable to the performance of the currently best public available method, Real-SPINE. Both methods associate a reliability score with the individual predictions. However, our implementation of reliability scores in the form of a Z-score is shown to be the more informative measure for discriminating good predictions from bad ones in the entire range from completely buried to fully exposed amino acids. This is evident when comparing the Pearson's correlation coefficient for the upper 20% of predictions sorted according to reliability. For this subset, values of 0.79 and 0.74 are obtained using our and the compared method, respectively. This tendency is true for any selected subset.

Motivation: MHC:peptide binding plays a central role in activating the immune surveillance. Computational approaches to determine T-cell epitopes restricted to any given major histocompatibility complex (MHC) molecule are of special practical value in the development of for instance vaccines with broad population coverage against emerging pathogens. Methods have recently been published that are able to predict peptide binding to any human MHC class I molecule. In contrast to conventional allele-specific methods, these methods do allow for extrapolation to uncharacterized MHC molecules. These pan-specific human lymphocyte antigen (HLA) predictors have not previously been compared using independent evaluation sets., Result: A diverse set of quantitative peptide binding affinity measurements was collected from Immune Epitope database (IEDB), together with a large set of HLA class I ligands from the SYFPEITHI database. Based on these datasets, three different pan-specific HLA web-accessible predictors NetMHCpan, adaptive double threading (ADT) and kernel-based inter-allele peptide binding prediction system (KISS) were evaluated. The performance of the pan-specific predictors was also compared with a well performing allele-specific MHC class I predictor, NetMHC, as well as a consensus approach integrating the predictions from the NetMHC and NetMHCpan methods., Conclusions: The benchmark demonstrated that pan-specific methods do provide accurate predictions also for previously uncharacterized MHC molecules. The NetMHCpan method trained to predict actual binding affinities was consistently top ranking both on quantitative (affinity) and binary (ligand) data. However, the KISS method trained to predict binary data was one of the best performing methods when benchmarked on binary data. Finally, a consensus method integrating predictions from the two best performing methods was shown to improve the prediction accuracy.

Human leukocyte antigen class I (HLA-I) molecules are highly polymorphic peptide receptors, which select and present endogenously derived peptide epitopes to CD8+ cytotoxic T cells (CTL). The specificity of the HLA-I system is an important component of the overall specificity of the CTL immune system. Unfortunately, the large and rapidly increasing number of known HLA-I molecules seriously complicates a comprehensive analysis of the specificities of the entire HLA-I system (as of June 2008, the international HLA registry holds >1,650 unique HLA-I protein entries). In an attempt to reduce this complexity, it has been suggested to cluster the different HLA-I molecules into "supertypes" of largely overlapping peptide-binding specificities. Obviously, the HLA supertype concept is only valuable if membership can be assigned with reasonable accuracy. The supertype assignment of HLA-A*3001, a common HLA haplotype in populations of African descent, has variously been assigned to the A1, A3, or A24 supertypes. Using a biochemical HLA-A*3001 binding assay, and a large panel of nonamer peptides and peptide libraries, we here demonstrate that the specificity of HLA-A*3001 most closely resembles that of the HLA-A3 supertype. We discuss approaches to supertype assignment and underscore the importance of experimental verification.

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.

NetMHC-3.0 is trained on a large number of quantitative peptide data using both affinity data from the Immune Epitope Database and Analysis Resource (IEDB) and elution data from SYFPEITHI. The method generates high-accuracy predictions of major histocompatibility complex (MHC): peptide binding. The predictions are based on artificial neural networks trained on data from 55 MHC alleles (43 Human and 12 non-human), and position-specific scoring matrices (PSSMs) for additional 67 HLA alleles. As only the MHC class I prediction server is available, predictions are possible for peptides of length 8-11 for all 122 alleles. artificial neural network predictions are given as actual IC(50) values whereas PSSM predictions are given as a log-odds likelihood scores. The output is optionally available as download for easy post-processing. The training method underlying the server is the best available, and has been used to predict possible MHC-binding peptides in a series of pathogen viral proteomes including SARS, Influenza and HIV, resulting in an average of 75-80% confirmed MHC binders. Here, the performance is further validated and benchmarked using a large set of newly published affinity data, non-redundant to the training set. The server is free of use and available at: http://www.cbs.dtu.dk/services/NetMHC.

We present a new release of the immune epitope database analysis resource (IEDB-AR, http://tools.immuneepitope.org), a repository of web-based tools for the prediction and analysis of immune epitopes. New functionalities have been added to most of the previously implemented tools, and a total of eight new tools were added, including two B-cell epitope prediction tools, four T-cell epitope prediction tools and two analysis tools.

Unlabelled: 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

Motivation: Immunological bioinformatics methods are applicable to a broad range of scientific areas. The specifics of how and where they might be implemented have recently been reviewed in the literature. However, the background and concerns for selecting between the different available methods have so far not been adequately covered., Summary: Before using predictions systems, it is necessary to not only understand how the methods are constructed but also their strength and limitations. The prediction systems in humoral epitope discovery are still in their infancy, but have reached a reasonable level of predictive strength. In cellular immunology, MHC class I binding predictions are now very strong and cover most of the known HLA specificities. These systems work well for epitope discovery, and predictions of the MHC class I pathway have been further improved by integration with state-of-the-art prediction tools for proteasomal cleavage and TAP binding. By comparison, class II MHC binding predictions have not developed to a comparable accuracy level, but new tools have emerged that deliver significantly improved predictions not only in terms of accuracy, but also in MHC specificity coverage. Simulation systems and mathematical modeling are also now beginning to reach a level where these methods will be able to answer more complex immunological questions.

Background: Reliable predictions of Cytotoxic T lymphocyte (CTL) epitopes are essential for rational vaccine design. Most importantly, they can minimize the experimental effort needed to identify epitopes. NetCTL is a web-based tool designed for predicting human CTL epitopes in any given protein. It does so by integrating predictions of proteasomal cleavage, TAP transport efficiency, and MHC class I affinity. At least four other methods have been developed recently that likewise attempt to predict CTL epitopes: EpiJen, MAPPP, MHC-pathway, and WAPP. In order to compare the performance of prediction methods, objective benchmarks and standardized performance measures are needed. Here, we develop such large-scale benchmark and corresponding performance measures and report the performance of an updated version 1.2 of NetCTL in comparison with the four other methods., Results: We define a number of performance measures that can handle the different types of output data from the five methods. We use two evaluation datasets consisting of known HIV CTL epitopes and their source proteins. The source proteins are split into all possible 9 mers and except for annotated epitopes; all other 9 mers are considered non-epitopes. In the RANK measure, we compare two methods at a time and count how often each of the methods rank the epitope highest. In another measure, we find the specificity of the methods at three predefined sensitivity values. Lastly, for each method, we calculate the percentage of known epitopes that rank within the 5% peptides with the highest predicted score., Conclusion: NetCTL-1.2 is demonstrated to have a higher predictive performance than EpiJen, MAPPP, MHC-pathway, and WAPP on all performance measures. The higher performance of NetCTL-1.2 as compared to EpiJen and MHC-pathway is, however, not statistically significant on all measures. In the large-scale benchmark calculation consisting of 216 known HIV epitopes covering all 12 recognized HLA supertypes, the NetCTL-1.2 method was shown to have a sensitivity among the 5% top-scoring peptides above 0.72. On this dataset, the best of the other methods achieved a sensitivity of 0.64. The NetCTL-1.2 method is available at http://www.cbs.dtu.dk/services/NetCTL. All used datasets are available at http://www.cbs.dtu.dk/suppl/immunology/CTL-1.2.php.

Background: 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 class I system (HLA-I) is extremely polymorphic. The number of registered HLA-I molecules has now surpassed 1500. Characterizing the specificity of each separately would be a major undertaking., Principal Findings: Here, we have drawn on a large database of known peptide-HLA-I interactions to develop a bioinformatics method, which takes both peptide and HLA sequence information into account, and generates quantitative predictions of the affinity of any peptide-HLA-I interaction. Prospective experimental validation of peptides predicted to bind to previously untested HLA-I molecules, cross-validation, and retrospective prediction of known HIV immune epitopes and endogenous presented peptides, all successfully validate this method. We further demonstrate that the method can be applied to perform a clustering analysis of MHC specificities and suggest using this clustering to select particularly informative novel MHC molecules for future biochemical and functional analysis., Conclusions: Encompassing all HLA molecules, this high-throughput computational method lends itself to epitope searches that are not only genome- and pathogen-wide, but also HLA-wide. Thus, it offers a truly global analysis of immune responses supporting rational development of vaccines and immunotherapy. It also promises to provide new basic insights into HLA structure-function relationships. The method is available at http://www.cbs.dtu.dk/services/NetMHCpan.

Background: Antigen presenting cells (APCs) sample the extra cellular space and present peptides from here to T helper cells, which can be activated if the peptides are of foreign origin. The peptides are presented on the surface of the cells in complex with major histocompatibility class II (MHC II) molecules. Identification of peptides that bind MHC II molecules is thus a key step in rational vaccine design and developing methods for accurate prediction of the peptide:MHC interactions play a central role in epitope discovery. The MHC class II binding groove is open at both ends making the correct alignment of a peptide in the binding groove a crucial part of identifying the core of an MHC class II binding motif. Here, we present a novel stabilization matrix alignment method, SMM-align, that allows for direct prediction of peptide:MHC binding affinities. The predictive performance of the method is validated on a large MHC class II benchmark data set covering 14 HLA-DR (human MHC) and three mouse H2-IA alleles., Results: The predictive performance of the SMM-align method was demonstrated to be superior to that of the Gibbs sampler, TEPITOPE, SVRMHC, and MHCpred methods. Cross validation between peptide data set obtained from different sources demonstrated that direct incorporation of peptide length potentially results in over-fitting of the binding prediction method. Focusing on amino terminal peptide flanking residues (PFR), we demonstrate a consistent gain in predictive performance by favoring binding registers with a minimum PFR length of two amino acids. Visualizing the binding motif as obtained by the SMM-align and TEPITOPE methods highlights a series of fundamental discrepancies between the two predicted motifs. For the DRB1*1302 allele for instance, the TEPITOPE method favors basic amino acids at most anchor positions, whereas the SMM-align method identifies a preference for hydrophobic or neutral amino acids at the anchors., Conclusion: The SMM-align method was shown to outperform other state of the art MHC class II prediction methods. The method predicts quantitative peptide:MHC binding affinity values, making it ideally suited for rational epitope discovery. The method has been trained and evaluated on the, to our knowledge, largest benchmark data set publicly available and covers the nine HLA-DR supertypes suggested as well as three mouse H2-IA allele. Both the peptide benchmark data set, and SMM-align prediction method (NetMHCII) are made publicly available.

The purpose of the present study is to perform a global screening for new immunogenic HLA class I (HLA-I) restricted cytotoxic T cell (CTL) epitopes of potential utility as candidates of influenza A-virus diagnostics and vaccines. We used predictions of antigen processing and presentation, the latter encompassing 12 different HLA class I supertypes with >99% population coverage, and searched for conserved epitopes from available influenza A viral protein sequences. Peptides corresponding to 167 predicted peptide-HLA-I interactions were synthesized, tested for peptide-HLA-I interactions in a biochemical assay and for influenza-specific, HLA-I-restricted CTL responses in an IFN-gamma ELISPOT assay. Eighty-nine peptides could be confirmed as HLA-I binders, and 13 could be confirmed as CTL targets. The 13 epitopes, are highly conserved among human influenza A pathogens, and all of these epitopes are present in the emerging bird flu isolates. Our study demonstrates that present technology enables a fast global screening for T cell immune epitopes of potential diagnostics and vaccine interest. This technology includes immuno-bioinformatics predictors with the capacity to perform fast genome-, pathogen-, and HLA-wide searches for immune targets. To exploit this new potential, a coordinated international effort to analyze the precious source of information represented by rare patients, such as the current victims of bird flu, would be essential.

High-performing MHC class I binding predictions have been available for more than a decade; however, their value in terms of actual epitope finding has only now been estimated in a large-scale investigation undertaken by the group of Sette. This work underlines the importance of bioinformatics as a resource-saving tool in the field of epitope discovery. In addition, the data can be used to benchmark the performance of other new or existing CTL epitope-prediction tools.

Over the past decade a number of bioinformatics tools have been developed that use genomic sequences as input to predict to which parts of a microbe the immune system will react, the so-called epitopes. Many predicted epitopes have later been verified experimentally, demonstrating the usefulness of such predictions. At the same time, simulation models have been developed that describe the dynamics of different immune cell populations and their interactions with microbes. These models have been used to explain experimental findings where timing is of importance, such as the time between administration of a vaccine and infection with the microbe that the vaccine is intended to protect against. In this paper, we outline a framework for integration of these two approaches. As an example, we develop a model in which HIV dynamics are correlated with genomics data. For the first time, the fitness of wild type and mutated virus are assessed by means of a sequence-dependent scoring matrix, derived from a BLOSUM matrix, that links protein sequences to growth rates of the virus in the mathematical model. A combined bioinformatics and systems biology approach can lead to a better understanding of immune system-related diseases where both timing and genomic information are of importance.

Recognition of peptides bound to major histocompatibility complex (MHC) class I molecules by T lymphocytes is an essential part of immune surveillance. Each MHC allele has a characteristic peptide binding preference, which can be captured in prediction algorithms, allowing for the rapid scan of entire pathogen proteomes for peptide likely to bind MHC. Here we make public a large set of 48,828 quantitative peptide-binding affinity measurements relating to 48 different mouse, human, macaque, and chimpanzee MHC class I alleles. We use this data to establish a set of benchmark predictions with one neural network method and two matrix-based prediction methods extensively utilized in our groups. In general, the neural network outperforms the matrix-based predictions mainly due to its ability to generalize even on a small amount of data. We also retrieved predictions from tools publicly available on the internet. While differences in the data used to generate these predictions hamper direct comparisons, we do conclude that tools based on combinatorial peptide libraries perform remarkably well. The transparent prediction evaluation on this dataset provides tool developers with a benchmark for comparison of newly developed prediction methods. In addition, to generate and evaluate our own prediction methods, we have established an easily extensible web-based prediction framework that allows automated side-by-side comparisons of prediction methods implemented by experts. This is an advance over the current practice of tool developers having to generate reference predictions themselves, which can lead to underestimating the performance of prediction methods they are not as familiar with as their own. The overall goal of this effort is to provide a transparent prediction evaluation allowing bioinformaticians to identify promising features of prediction methods and providing guidance to immunologists regarding the reliability of prediction tools.

Reverse immunogenetic approaches attempt to optimize the selection of candidate epitopes, and thus minimize the experimental effort needed to identify new epitopes. When predicting cytotoxic T cell epitopes, the main focus has been on the highly specific MHC class I binding event. Methods have also been developed for predicting the antigen-processing steps preceding MHC class I binding, including proteasomal cleavage and transporter associated with antigen processing (TAP) transport efficiency. Here, we use a dataset obtained from the SYFPEITHI database to show that a method integrating predictions of MHC class I binding affinity, TAP transport efficiency, and C-terminal proteasomal cleavage outperforms any of the individual methods. Using an independent evaluation dataset of HIV epitopes from the Los Alamos database, the validity of the integrated method is confirmed. The performance of the integrated method is found to be significantly higher than that of the two publicly available prediction methods BIMAS and SYFPEITHI. To identify 85% of the epitopes in the HIV dataset, 9% and 10% of all possible nonamers in the HIV proteins must be tested when using the BIMAS and SYFPEITHI methods, respectively, for the selection of candidate epitopes. This number is reduced to 7% when using the integrated method. In practical terms, this means that the experimental effort needed to identify an epitope in a hypothetical protein with 85% probability is reduced by 20-30% when using the integrated method. The method is available at http://www.cbs.dtu.dk/services/NetCTL. Supplementary material is available at http://www.cbs.dtu.dk/suppl/immunology/CTL.php.

Cytotoxic T cells (CTLs) perceive the world through small peptides that are eight to ten amino acids long. These peptides (epitopes) are initially generated by the proteasome, a multi-subunit protease that is responsible for the majority of intra-cellular protein degradation. The proteasome generates the exact C-terminal of CTL epitopes, and the N-terminal with a possible extension. CTL responses may diminish if the epitopes are destroyed by the proteasomes. Therefore, the prediction of the proteasome cleavage sites is important to identify potential immunogenic regions in the proteomes of pathogenic microorganisms (or humans). We have recently shown that NetChop, a neural network-based prediction method, is the best method available at the moment to do such predictions; however, its performance is still lower than desired. Here, we use novel sequence encoding methods and show that the new version of NetChop predicts approximately 10% more of the cleavage sites correctly while lowering the number of false positives with close to 15%. With this more reliable prediction tool, we study two important questions concerning the function of the proteasome. First, we estimate the N-terminal extension of epitopes after proteasomal cleavage and find that the average extension is relatively short. However, more than 30% of the peptides have N-terminal extensions of three amino acids or more, and thus, N-terminal trimming might play an important role in the presentation of a substantial fraction of the epitopes. Second, we show that good TAP ligands have an increased chance of being cleaved by the proteasome, i.e., the specificity of TAP has evolved to fit the specificity of the proteasome. This evolutionary relationship allows for a more efficient antigen presentation.

Motivation: Prediction of which peptides will bind a specific major histocompatibility complex (MHC) constitutes an important step in identifying potential T-cell epitopes suitable as vaccine candidates. MHC class II binding peptides have a broad length distribution complicating such predictions. Thus, identifying the correct alignment is a crucial part of identifying the core of an MHC class II binding motif. In this context, we wish to describe a novel Gibbs motif sampler method ideally suited for recognizing such weak sequence motifs. The method is based on the Gibbs sampling method, and it incorporates novel features optimized for the task of recognizing the binding motif of MHC classes I and II. The method locates the binding motif in a set of sequences and characterizes the motif in terms of a weight-matrix. Subsequently, the weight-matrix can be applied to identifying effectively potential MHC binding peptides and to guiding the process of rational vaccine design., Results: We apply the motif sampler method to the complex problem of MHC class II binding. The input to the method is amino acid peptide sequences extracted from the public databases of SYFPEITHI and MHCPEP and known to bind to the MHC class II complex HLA-DR4(B1*0401). Prior identification of information-rich (anchor) positions in the binding motif is shown to improve the predictive performance of the Gibbs sampler. Similarly, a consensus solution obtained from an ensemble average over suboptimal solutions is shown to outperform the use of a single optimal solution. In a large-scale benchmark calculation, the performance is quantified using relative operating characteristics curve (ROC) plots and we make a detailed comparison of the performance with that of both the TEPITOPE method and a weight-matrix derived using the conventional alignment algorithm of ClustalW. The calculation demonstrates that the predictive performance of the Gibbs sampler is higher than that of ClustalW and in most cases also higher than that of the TEPITOPE method.

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 http://www.cbs.dtu.dk/researchgroups/immunology/supertypes.html.

Strategies for selecting informative data points for training prediction algorithms are important, particularly when data points are difficult and costly to obtain. A Query by Committee (QBC) training strategy for selecting new data points uses the disagreement between a committee of different algorithms to suggest new data points, which most rationally complement existing data, that is, they are the most informative data points. In order to evaluate this QBC approach on a real-world problem, we compared strategies for selecting new data points. We trained neural network algorithms to obtain methods to predict the binding affinity of peptides binding to the MHC class I molecule, HLA-A2. We show that the QBC strategy leads to a higher performance than a baseline strategy where new data points are selected at random from a pool of available data. Most peptides bind HLA-A2 with a low affinity, and as expected using a strategy of selecting peptides that are predicted to have high binding affinities also lead to more accurate predictors than the base line strategy. The QBC value is shown to correlate with the measured binding affinity. This demonstrates that the different predictors can easily learn if a peptide will fail to bind, but often conflict in predicting if a peptide binds. Using a carefully constructed computational setup, we demonstrate that selecting peptides with a high QBC performs better than low QBC peptides independently from binding affinity. When predictors are trained on a very limited set of data they cannot be expected to disagree in a meaningful way and we find a data limit below which the QBC strategy fails. Finally, it should be noted that data selection strategies similar to those used here might be of use in other settings in which generation of more data is a costly process.

In this paper we describe an improved neural network method to predict T-cell class I epitopes. A novel input representation has been developed consisting of a combination of sparse encoding, Blosum encoding, and input derived from hidden Markov models. We demonstrate that the combination of several neural networks derived using different sequence-encoding schemes has a performance superior to neural networks derived using a single sequence-encoding scheme. The new method is shown to have a performance that is substantially higher than that of other methods. By use of mutual information calculations we show that peptides that bind to the HLA A*0204 complex display signal of higher order sequence correlations. Neural networks are ideally suited to integrate such higher order correlations when predicting the binding affinity. It is this feature combined with the use of several neural networks derived from different and novel sequence-encoding schemes and the ability of the neural network to be trained on data consisting of continuous binding affinities that gives the new method an improved performance. The difference in predictive performance between the neural network methods and that of the matrix-driven methods is found to be most significant for peptides that bind strongly to the HLA molecule, confirming that the signal of higher order sequence correlation is most strongly present in high-binding peptides. Finally, we use the method to predict T-cell epitopes for the genome of hepatitis C virus and discuss possible applications of the prediction method to guide the process of rational vaccine design.