Reliable B Cell Epitope Predictions: Impacts of Method Development and Improved Benchmarking

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.     

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

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

Percent of highly immunogenic amino acid residues forming B-cell epitopes is higher in homologous proteins encoded by GC-rich genes

We analyzed the dependence of the percent of highly immunogenic amino acid residues included in B-cell epitopes of homologous proteins on the GC-content (G+C) of genes coding for them in twenty-seven lineages of proteins (and subsequent genes), which belong to seven Varicello and five Simplex viruses. We found out that proteins encoded by genes of a high GC-content usually contain more targets for humoral immune response than their homologs encoded by GC-poor genes. This tendency is characteristic not only to the lineages of glycoproteins, which are the main targets for humoral immune response against Simplex and Varicello viruses, but also to the lineages of capsid proteins and even "housekeeping" enzymes. The percent of amino acids included in linear B-cell epitopes has been predicted for 324 proteins by BepiPred algorithm (www.cbs.dtu.dk/services/BepiPred), the percent of highly immunogenic amino acids included in discontinuous B-cell epitopes and the percent of exposed amino acid residues have been predicted by Epitopia algorithm (http://epitopia.tau.ac.il/). Immunological consequences of the directional mutational GC-pressure are mostly due to the decrease in the total usage of highly hydrophobic amino acids and due to the increase in proline and glycine levels of usage in proteins. The weaker the negative selection on amino acid substitutions caused by symmetric mutational pressure, the higher the slope of direct dependence of the percent of highly immunogenic amino acids included in B-cell epitopes on G+C.     

Identification of conformational B-cell Epitopes in an antigen from its primary sequence

Background

One of the major challenges in the field of vaccine design is to predict conformational B-cell epitopes in an antigen. In the past, several methods have been developed for predicting conformational B-cell epitopes in an antigen from its tertiary structure. This is the first attempt in this area to predict conformational B-cell epitope in an antigen from its amino acid sequence.

Results

All Support vector machine (SVM) models were trained and tested on 187 non-redundant protein chains consisting of 2261 antibody interacting residues of B-cell epitopes. Models have been developed using binary profile of pattern (BPP) and physiochemical profile of patterns (PPP) and achieved a maximum MCC of 0.22 and 0.17 respectively. In this study, for the first time SVM model has been developed using composition profile of patterns (CPP) and achieved a maximum MCC of 0.73 with accuracy 86.59%. We compare our CPP based model with existing structure based methods and observed that our sequence based model is as good as structure based methods.

Conclusion

This study demonstrates that prediction of conformational B-cell epitope in an antigen is possible from is primary sequence. This study will be very useful in predicting conformational B-cell epitopes in antigens whose tertiary structures are not available. A web server CBTOPE has been developed for predicting B-cell epitope http://www.imtech.res.in/raghava/cbtope/.     

NetTepi: an integrated method for the prediction of T cell epitopes

Multiple factors determine the ability of a peptide to elicit a cytotoxic T cell lymphocyte response. Binding to a major histocompatibility complex class I (MHC-I) molecule is one of the most essential factors, as no peptide can become a T cell epitope unless presented on the cell surface in complex with an MHC-I molecule. As such, peptide-MHC (pMHC) binding affinity predictors are currently the premier methods for T cell epitope prediction, and these prediction methods have been shown to have high predictive performances in multiple studies. However, not all MHC-I binders are T cell epitopes, and multiple studies have investigated what additional factors are important for determining the immunogenicity of a peptide. A recent study suggested that pMHC stability plays an important role in determining if a peptide can become a T cell epitope. Likewise, a T cell propensity model has been proposed for identifying MHC binding peptides with amino acid compositions favoring T cell receptor interactions. In this study, we investigate if improved accuracy for T cell epitope discovery can be achieved by integrating predictions for pMHC binding affinity, pMHC stability, and T cell propensity. We show that a weighted sum approach allows pMHC stability and T cell propensity predictions to enrich pMHC binding affinity predictions. The integrated model leads to a consistent and significant increase in predictive performance and we demonstrate how this can be utilized to decrease the experimental workload of epitope screens. The final method, NetTepi, is publically available at www.cbs.dtu.dk/services/NetTepi.     

Prediction of Disease Causing Non-Synonymous SNPs by the Artificial Neural Network Predictor NetDiseaseSNP

We have developed a sequence conservation-based artificial neural network predictor called NetDiseaseSNP which classifies nsSNPs as disease-causing or neutral. Our method uses the excellent alignment generation algorithm of SIFT to identify related sequences and a combination of 31 features assessing sequence conservation and the predicted surface accessibility to produce a single score which can be used to rank nsSNPs based on their potential to cause disease. NetDiseaseSNP classifies successfully disease-causing and neutral mutations. In addition, we show that NetDiseaseSNP discriminates cancer driver and passenger mutations satisfactorily. Our method outperforms other state-of-the-art methods on several disease/neutral datasets as well as on cancer driver/passenger mutation datasets and can thus be used to pinpoint and prioritize plausible disease candidates among nsSNPs for further investigation. NetDiseaseSNP is publicly available as an online tool as well as a web service: http://www.cbs.dtu.dk/services/NetDiseaseSNP     

Mining for the antibody-antigen interacting associations that predict the B cell epitopes

Background

Predicting B-cell epitopes is very important for designing vaccines and drugs to fight against the infectious agents. However, due to the high complexity of this problem, previous prediction methods that focus on linear and conformational epitope prediction are both unsatisfactory. In addition, antigen interacting with antibody is context dependent and the coarse binary classification of antigen residues into epitope and non-epitope without the corresponding antibody may not reveal the biological reality. Therefore, we take a novel way to identify epitopes by using associations between antibodies and antigens.

Results

Given a pair of antibody-antigen sequences, the epitope residues can be identified by two types of associations: paratope-epitope interacting biclique and cooccurrent pattern of interacting residue pairs. As the association itself does not include the neighborhood information on the primary sequence, residues' cooperativity and relative composition are then used to enhance our method. Evaluation carried out on a benchmark data set shows that the proposed method produces very good performance in terms of accuracy. After compared with other two structure-based B-cell epitope prediction methods, results show that the proposed method is competitive to, sometimes even better than, the structure-based methods which have much smaller applicability scope.

Conclusions

The proposed method leads to a new way of identifying B-cell epitopes. Besides, this antibody-specified epitope prediction can provide more precise and helpful information for wet-lab experiments.

     

Markov Chain Ontology Analysis (MCOA)

Background

Biomedical ontologies have become an increasingly critical lens through which researchers analyze the genomic, clinical and bibliographic data that fuels scientific research. Of particular relevance are methods, such as enrichment analysis, that quantify the importance of ontology classes relative to a collection of domain data. Current analytical techniques, however, remain limited in their ability to handle many important types of structural complexity encountered in real biological systems including class overlaps, continuously valued data, inter-instance relationships, non-hierarchical relationships between classes, semantic distance and sparse data.

Results

In this paper, we describe a methodology called Markov Chain Ontology Analysis (MCOA) and illustrate its use through a MCOA-based enrichment analysis application based on a generative model of gene activation. MCOA models the classes in an ontology, the instances from an associated dataset and all directional inter-class, class-to-instance and inter-instance relationships as a single finite ergodic Markov chain. The adjusted transition probability matrix for this Markov chain enables the calculation of eigenvector values that quantify the importance of each ontology class relative to other classes and the associated data set members. On both controlled Gene Ontology (GO) data sets created with Escherichia coli, Drosophila melanogaster and Homo sapiens annotations and real gene expression data extracted from the Gene Expression Omnibus (GEO), the MCOA enrichment analysis approach provides the best performance of comparable state-of-the-art methods.

Conclusion

A methodology based on Markov chain models and network analytic metrics can help detect the relevant signal within large, highly interdependent and noisy data sets and, for applications such as enrichment analysis, has been shown to generate superior performance on both real and simulated data relative to existing state-of-the-art approaches.     

Fitting hidden Markov models of protein domains to a target species: application to Plasmodium falciparum

Background

The identification of gene sets that are significantly impacted in a given condition based on microarray data is a crucial step in current life science research. Most gene set analysis methods treat genes equally, regardless how specific they are to a given gene set.

Results

In this work we propose a new gene set analysis method that computes a gene set score as the mean of absolute values of weighted moderated gene t-scores. The gene weights are designed to emphasize the genes appearing in few gene sets, versus genes that appear in many gene sets. We demonstrate the usefulness of the method when analyzing gene sets that correspond to the KEGG pathways, and hence we called our method P athway A nalysis with D own-weighting of O verlapping G enes (PADOG). Unlike most gene set analysis methods which are validated through the analysis of 2-3 data sets followed by a human interpretation of the results, the validation employed here uses 24 different data sets and a completely objective assessment scheme that makes minimal assumptions and eliminates the need for possibly biased human assessments of the analysis results.

Conclusions

PADOG significantly improves gene set ranking and boosts sensitivity of analysis using information already available in the gene expression profiles and the collection of gene sets to be analyzed. The advantages of PADOG over other existing approaches are shown to be stable to changes in the database of gene sets to be analyzed. PADOG was implemented as an R package available at: http://bioinformaticsprb.med.wayne.edu/PADOG/or http://www.bioconductor.org.     

Prediction of lipoprotein signal peptides in Gram-negative bacteria

A method to predict lipoprotein signal peptides in Gram-negative Eubacteria, LipoP, has been developed. The hidden Markov model (HMM) was able to distinguish between lipoproteins (SPaseII-cleaved proteins), SPaseI-cleaved proteins, cytoplasmic proteins, and transmembrane proteins. This predictor was able to predict 96.8% of the lipoproteins correctly with only 0.3% false positives in a set of SPaseI-cleaved, cytoplasmic, and transmembrane proteins. The results obtained were significantly better than those of previously developed methods. Even though Gram-positive lipoprotein signal peptides differ from Gram-negatives, the HMM was able to identify 92.9% of the lipoproteins included in a Gram-positive test set. A genome search was carried out for 12 Gram-negative genomes and one Gram-positive genome. The results for Escherichia coli K12 were compared with new experimental data, and the predictions by the HMM agree well with the experimentally verified lipoproteins. A neural network-based predictor was developed for comparison, and it gave very similar results. LipoP is available as a Web server at www.cbs.dtu.dk/services/LipoP/.     

PathogenFinder - Distinguishing Friend from Foe Using Bacterial Whole Genome Sequence Data

Although the majority of bacteria are harmless or even beneficial to their host, others are highly virulent and can cause serious diseases, and even death. Due to the constantly decreasing cost of high-throughput sequencing there are now many completely sequenced genomes available from both human pathogenic and innocuous strains. The data can be used to identify gene families that correlate with pathogenicity and to develop tools to predict the pathogenicity of newly sequenced strains, investigations that previously were mainly done by means of more expensive and time consuming experimental approaches. We describe PathogenFinder (http://cge.cbs.dtu.dk/services/PathogenFinder/), a web-server for the prediction of bacterial pathogenicity by analysing the input proteome, genome, or raw reads provided by the user. The method relies on groups of proteins, created without regard to their annotated function or known involvement in pathogenicity. The method has been built to work with all taxonomic groups of bacteria and using the entire training-set, achieved an accuracy of 88.6% on an independent test-set, by correctly classifying 398 out of 449 completely sequenced bacteria. The approach here proposed is not biased on sets of genes known to be associated with pathogenicity, thus the approach could aid the discovery of novel pathogenicity factors. Furthermore the pathogenicity prediction web-server could be used to isolate the potential pathogenic features of both known and unknown strains.     

Predicting linear B-cell epitopes using string kernels

The identification and characterization of B-cell epitopes play an important role in vaccine design, immunodiagnostic tests, and antibody production. Therefore, computational tools for reliably predicting linear B-cell epitopes are highly desirable. We evaluated Support Vector Machine (SVM) classifiers trained utilizing five different kernel methods using fivefold cross-validation on a homology-reduced data set of 701 linear B-cell epitopes, extracted from Bcipep database, and 701 non-epitopes, randomly extracted from SwissProt sequences. Based on the results of our computational experiments, we propose BCPred, a novel method for predicting linear B-cell epitopes using the subsequence kernel. We show that the predictive performance of BCPred (AUC = 0.758) outperforms 11 SVM-based classifiers developed and evaluated in our experiments as well as our implementation of AAP (AUC = 0.7), a recently proposed method for predicting linear B-cell epitopes using amino acid pair antigenicity. Furthermore, we compared BCPred with AAP and ABCPred, a method that uses recurrent neural networks, using two data sets of unique B-cell epitopes that had been previously used to evaluate ABCPred. Analysis of the data sets used and the results of this comparison show that conclusions about the relative performance of different B-cell epitope prediction methods drawn on the basis of experiments using data sets of unique B-cell epitopes are likely to yield overly optimistic estimates of performance of evaluated methods. This argues for the use of carefully homology-reduced data sets in comparing B-cell epitope prediction methods to avoid misleading conclusions about how different methods compare to each other. Our homology-reduced data set and implementations of BCPred as well as the APP method are publicly available through our web-based server, BCPREDS, at: http://ailab.cs.iastate.edu/bcpreds/.     

MHCcluster, a method for functional clustering of MHC molecules

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

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

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

Quantitative prediction of the effect of genetic variation using hidden Markov models

Background

With the development of sequencing technologies, more and more sequence variants are available for investigation. Different classes of variants in the human genome have been identified, including single nucleotide substitutions, insertion and deletion, and large structural variations such as duplications and deletions. Insertion and deletion (indel) variants comprise a major proportion of human genetic variation. However, little is known about their effects on humans. The absence of understanding is largely due to the lack of both biological data and computational resources.

Results

This paper presents a new indel functional prediction method HMMvar based on HMM profiles, which capture the conservation information in sequences. The results demonstrate that a scoring strategy based on HMM profiles can achieve good performance in identifying deleterious or neutral variants for different data sets, and can predict the protein functional effects of both single and multiple mutations.

Conclusions

This paper proposed a quantitative prediction method, HMMvar, to predict the effect of genetic variation using hidden Markov models. The HMM based pipeline program implementing the method HMMvar is freely available at https://bioinformatics.cs.vt.edu/zhanglab/hmm.     

Bayesian estimation of genomic copy number with single nucleotide polymorphism genotyping arrays

Background

The identification of copy number aberration in the human genome is an important area in cancer research. We develop a model for determining genomic copy numbers using high-density single nucleotide polymorphism genotyping microarrays. The method is based on a Bayesian spatial normal mixture model with an unknown number of components corresponding to true copy numbers. A reversible jump Markov chain Monte Carlo algorithm is used to implement the model and perform posterior inference.

Results

The performance of the algorithm is examined on both simulated and real cancer data, and it is compared with the popular CNAG algorithm for copy number detection.

Conclusions

We demonstrate that our Bayesian mixture model performs at least as well as the hidden Markov model based CNAG algorithm and in certain cases does better. One of the added advantages of our method is the flexibility of modeling normal cell contamination in tumor samples.     

MultiRTA: A simple yet reliable method for predicting peptide binding affinities for multiple class II MHC allotypes

Background

The binding of peptide fragments of antigens to class II MHC is a crucial step in initiating a helper T cell immune response. The identification of such peptide epitopes has potential applications in vaccine design and in better understanding autoimmune diseases and allergies. However, comprehensive experimental determination of peptide-MHC binding affinities is infeasible due to MHC diversity and the large number of possible peptide sequences. Computational methods trained on the limited experimental binding data can address this challenge. We present the MultiRTA method, an extension of our previous single-type RTA prediction method, which allows the prediction of peptide binding affinities for multiple MHC allotypes not used to train the model. Thus predictions can be made for many MHC allotypes for which experimental binding data is unavailable.

Results

We fit MultiRTA models for both HLA-DR and HLA-DP using large experimental binding data sets. The performance in predicting binding affinities for novel MHC allotypes, not in the training set, was tested in two different ways. First, we performed leave-one-allele-out cross-validation, in which predictions are made for one allotype using a model fit to binding data for the remaining MHC allotypes. Comparison of the HLA-DR results with those of two other prediction methods applied to the same data sets showed that MultiRTA achieved performance comparable to NetMHCIIpan and better than the earlier TEPITOPE method. We also directly tested model transferability by making leave-one-allele-out predictions for additional experimentally characterized sets of overlapping peptide epitopes binding to multiple MHC allotypes. In addition, we determined the applicability of prediction methods like MultiRTA to other MHC allotypes by examining the degree of MHC variation accounted for in the training set. An examination of predictions for the promiscuous binding CLIP peptide revealed variations in binding affinity among alleles as well as potentially distinct binding registers for HLA-DR and HLA-DP. Finally, we analyzed the optimal MultiRTA parameters to discover the most important peptide residues for promiscuous and allele-specific binding to HLA-DR and HLA-DP allotypes.

Conclusions

The MultiRTA method yields competitive performance but with a significantly simpler and physically interpretable model compared with previous prediction methods. A MultiRTA prediction webserver is available at http://bordnerlab.org/MultiRTA.

     

SVMTriP: A Method to Predict Antigenic Epitopes Using Support Vector Machine to Integrate Tri-Peptide Similarity and Propensity

Identifying protein surface regions preferentially recognizable by antibodies (antigenic epitopes) is at the heart of new immuno-diagnostic reagent discovery and vaccine design, and computational methods for antigenic epitope prediction provide crucial means to serve this purpose. Many linear B-cell epitope prediction methods were developed, such as BepiPred, ABCPred, AAP, BCPred, BayesB, BEOracle/BROracle, and BEST, towards this goal. However, effective immunological research demands more robust performance of the prediction method than what the current algorithms could provide. In this work, a new method to predict linear antigenic epitopes is developed; Support Vector Machine has been utilized by combining the Tri-peptide similarity and Propensity scores (SVMTriP). Applied to non-redundant B-cell linear epitopes extracted from IEDB, SVMTriP achieves a sensitivity of 80.1% and a precision of 55.2% with a five-fold cross-validation. The AUC value is 0.702. The combination of similarity and propensity of tri-peptide subsequences can improve the prediction performance for linear B-cell epitopes. Moreover, SVMTriP is capable of recognizing viral peptides from a human protein sequence background. A web server based on our method is constructed for public use. The server and all datasets used in the current study are available at http://sysbio.unl.edu/SVMTriP.