Prediction of residues in discontinuous B-cell epitopes using protein 3D structures

Discovery of discontinuous B-cell epitopes is a major challenge in vaccine design. Previous epitope prediction methods have mostly been based on protein sequences and are not very effective. Here, we present DiscoTope, a novel method for discontinuous epitope prediction that uses protein three-dimensional structural data. The method is based on amino acid statistics, spatial information, and surface accessibility in a compiled data set of discontinuous epitopes determined by X-ray crystallography of antibody/antigen protein complexes. DiscoTope is the first method to focus explicitly on discontinuous epitopes. We show that the new structure-based method has a better performance for predicting residues of discontinuous epitopes than methods based solely on sequence information, and that it can successfully predict epitope residues that have been identified by different techniques. DiscoTope detects 15.5% of residues located in discontinuous epitopes with a specificity of 95%. At this level of specificity, the conventional Parker hydrophilicity scale for predicting linear B-cell epitopes identifies only 11.0% of residues located in discontinuous epitopes. Predictions by the DiscoTope method can guide experimental epitope mapping in both rational vaccine design and development of diagnostic tools, and may lead to more efficient epitope identification.     

A meta-learning approach for B-cell conformational epitope prediction

Background

One of the major challenges in the field of vaccine design is identifying B-cell epitopes in continuously evolving viruses. Various tools have been developed to predict linear or conformational epitopes, each relying on different physicochemical properties and adopting distinct search strategies. We propose a meta-learning approach for epitope prediction based on stacked and cascade generalizations. Through meta learning, we expect a meta learner to be able integrate multiple prediction models, and outperform the single best-performing model. The objective of this study is twofold: (1) to analyze the complementary predictive strengths in different prediction tools, and (2) to introduce a generic computational model to exploit the synergy among various prediction tools. Our primary goal is not to develop any particular classifier for B-cell epitope prediction, but to advocate the feasibility of meta learning to epitope prediction. With the flexibility of meta learning, the researcher can construct various meta classification hierarchies that are applicable to epitope prediction in different protein domains.

Results

We developed the hierarchical meta-learning architectures based on stacked and cascade generalizations. The bottom level of the hierarchy consisted of four conformational and four linear epitope prediction tools that served as the base learners. To perform consistent and unbiased comparisons, we tested the meta-learning method on an independent set of antigen proteins that were not used previously to train the base epitope prediction tools. In addition, we conducted correlation and ablation studies of the base learners in the meta-learning model. Low correlation among the predictions of the base learners suggested that the eight base learners had complementary predictive capabilities. The ablation analysis indicated that the eight base learners differentially interacted and contributed to the final meta model. The results of the independent test demonstrated that the meta-learning approach markedly outperformed the single best-performing epitope predictor.

Conclusions

Computational B-cell epitope prediction tools exhibit several differences that affect their performances when predicting epitopic regions in protein antigens. The proposed meta-learning approach for epitope prediction combines multiple prediction tools by integrating their complementary predictive strengths. Our experimental results demonstrate the superior performance of the combined approach in comparison with single epitope predictors.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-014-0378-y) contains supplementary material, which is available to authorized users.     

Immunoinformatics analysis of H5N1 proteome for designing an epitope-derived vaccine and predicting the prevalence of pre-existing cellular-mediated immunity toward bird flu virus in Indonesian population

As an essential step of adaptive immune response, the recognition between antigen and antibody triggers a series of self-protection mechanisms. Therefore, the prediction of antibody-binding sites (B-cell epitope) for protein antigens is an important field in immunology research. The performance of current prediction methods is far from satisfying, especially for conformational epitope prediction. Here a multi-perspective analysis was carried on with a comprehensive B-cell conformational epitope dataset, which contains 161 immunoglobulin complex structures collected from PDB, corresponding to 166 unique computationally defined epitopes. These conformational epitopes were described with parameters from different perspectives, including characteristics of epitope itself, comparison to non-epitope surface areas, and interaction pattern with antibody. According to the analysis results, B-cell conformational epitopes were relatively constant both in the number of composing residues and the accessible surface area. Though composed of spatially clustering residues, there were sequentially linear segments exist in these epitopes. Besides, statistical differences were found between epitope and non-epitope surface residues with parameters in residual and structural levels. Compared to non-epitope surface residues, epitope ones were more accessible. Amino acid enrichment and preference for specific types of residue-pair set on epitope areas have also been observed. Several amino acid properties from AAindex have been proven to distinguish epitope residues from non-epitope surface ones. Additionally, epitope residues tended to be less conservative under the environmental pressure. Measured by topological parameters, epitope residues were surrounded with fewer residues but in a more compact way. The occurrences of residue-pair sets between epitope and paratope also showed some patterns. Results indicate that, certain rules do exist in conformational epitopes in terms of size and sequential continuity. Statistical differences have been found between epitope and non-epitope surface residues in residual and structural levels. Such differences indicate the existence of distinctiveness for conformation epitopes. On the other hand, there was no accordant estimation for higher or lower values derived from any parameter for epitope residues compared with non-epitope surface residues. This observation further confirms the complicacy of characteristics for conformational epitope. Under such circumstance, it will be a more effective and accurate approach to combine several parameters to predict the conformation epitope. Finding conformational epitopes and analysing their properties is an important step to identify internal formation mechanism of conformational epitopes and this study will help future development of new prediction tools.     

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/.     

EPSVR and EPMeta: prediction of antigenic epitopes using support vector regression and multiple server results

Background  

Accurate prediction of antigenic epitopes is important for immunologic research and medical applications, but it is still an open problem in bioinformatics. The case for discontinuous epitopes is even worse - currently there are only a few discontinuous epitope prediction servers available, though discontinuous peptides constitute the majority of all B-cell antigenic epitopes. The small number of structures for antigen-antibody complexes limits the development of reliable discontinuous epitope prediction methods and an unbiased benchmark to evaluate developed methods.     

构象性B细胞表位预测的免疫信息学方法及其网络资源

抗原表位预测是免疫信息学研究的重要方向之一,可以给实验提供重要的线索。B细胞表位或抗原决定簇是抗原中可被B细胞受体或抗体特异性识别并结合的部位。实际上,近90%的B细胞表位是构象性的。即使抗原蛋白质三级结构已知,B细胞表位预测仍然是一大挑战。该文结合实例阐述当今主要的构象性B细胞表位预测方法和算法:机器学习预测、非机器学习的计算预测、基于噬菌体展示数据的识别方法,以及一些也可用于构象性B细胞表位预测的通用蛋白质-蛋白质界面预测方法;介绍最新相关预测软件和Web服务资源,说明未来的研究趋势。     

Prediction of continuous B-cell epitopes in an antigen using recurrent neural network

B-cell epitopes play a vital role in the development of peptide vaccines, in diagnosis of diseases, and also for allergy research. Experimental methods used for characterizing epitopes are time consuming and demand large resources. The availability of epitope prediction method(s) can rapidly aid experimenters in simplifying this problem. The standard feed-forward (FNN) and recurrent neural network (RNN) have been used in this study for predicting B-cell epitopes in an antigenic sequence. The networks have been trained and tested on a clean data set, which consists of 700 non-redundant B-cell epitopes obtained from Bcipep database and equal number of non-epitopes obtained randomly from Swiss-Prot database. The networks have been trained and tested at different input window length and hidden units. Maximum accuracy has been obtained using recurrent neural network (Jordan network) with a single hidden layer of 35 hidden units for window length of 16. The final network yields an overall prediction accuracy of 65.93% when tested by fivefold cross-validation. The corresponding sensitivity, specificity, and positive prediction values are 67.14, 64.71, and 65.61%, respectively. It has been observed that RNN (JE) was more successful than FNN in the prediction of B-cell epitopes. The length of the peptide is also important in the prediction of B-cell epitopes from antigenic sequences. The webserver ABCpred is freely available at www.imtech.res.in/raghava/abcpred/.     

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.     

FLAVIdB: A data mining system for knowledge discovery in flaviviruses with direct applications in immunology and vaccinology

The flavivirus genus is unusually large, comprising more than 70 species, of which more than half are known human pathogens. It includes a set of clinically relevant infectious agents such as dengue, West Nile, yellow fever, and Japanese encephalitis viruses. Although these pathogens have been studied exten-sively, safe and efficient vaccines lack for the majority of the flaviviruses. We have assembled a database that combines antigenic data of flaviviruses, specialized analysis tools, and workflows for automated complex analyses focusing on applications in immunology and vaccinology. FLAVIdB contains 12,858 entries of flavivirus antigen sequences, 184 verified T-cell epitopes, 201 verified B-cell epitopes, and 4 representative molecular structures of the dengue virus envelope protein. FLAVIdB was assembled by collection, annotation, and integration of data from GenBank, GenPept, UniProt, IEDB, and PDB. The data were subject to extensive quality control (redundancy elimination, error detection, and vocabulary consolidation). Further annotation of selected functionally relevant features was performed by organizing information extracted from the literature. The database was incorporated into a web-accessible data mining system, combining specialized data analysis tools for integrated analysis of relevant data categories (protein sequences, macromolecular structures, and immune epitopes). The data mining system includes tools for variability and conservation analysis, T-cell epitope prediction, and characterization of neutralizing components of B-cell epitopes. FLAVIdB is accessible at cvc.dfci.harvard.edu/flavi/ FLAVIdB represents a new generation of databases in which data and tools are integrated into a data min-ing infrastructures specifically designed to aid rational vaccine design by discovery of vaccine targets.     

B-cell epitope prediction for peptide-based vaccine design: towards a paradigm of biological outcomes for global health

Global health must address a rapidly evolving burden of disease, hence the urgent need for versatile generic technologies exemplified by peptide-based vaccines. B-cell epitope prediction is crucial for designing such vaccines; yet this approach has thus far been largely unsuccessful, prompting further inquiry into the underlying reasons for its apparent inadequacy. Two major obstacles to the development of B-cell epitope prediction for peptide-based vaccine design are (1) the prevailing binary classification paradigm, which mandates the problematic dichotomization of continuous outcome variables, and (2) failure to explicitly model biological consequences of immunization that are relevant to practical considerations of safety and efficacy. The first obstacle is eliminated by redefining the predictive task as quantitative estimation of empirically observable biological effects of antibody-antigen binding, such that prediction is benchmarked using measures of correlation between continuous rather than dichotomous variables; but this alternative approach by itself fails to address the second obstacle even if benchmark data are selected to exclusively reflect functionally relevant cross-reactivity of antipeptide antibodies with protein antigens (as evidenced by antibody-modulated protein biological activity), particularly where only antibody-antigen binding is actually predicted as a surrogate for its biological effects. To overcome the second obstacle, the prerequisite is deliberate effort to predict, a priori, biological outcomes that are of immediate practical significance from the perspective of vaccination. This demands a much broader and deeper systems view of immunobiology than has hitherto been invoked for B-cell epitope prediction. Such a view would facilitate comprehension of many crucial yet largely neglected aspects of the vaccine-design problem. Of these, immunodominance among B-cell epitopes is a central unifying theme that subsumes immune phenomena of tolerance, imprinting and refocusing; but it is meaningful for vaccine design only in the light of disease-specific pathophysiology, which for infectious processes is complicated by host-pathogen coevolution. To better support peptide-based vaccine design, B-cell epitope prediction would entail individualized quantitative estimation of biological outcomes relevant to safety and efficacy. Passive-immunization experiments could serve as an important initial proving ground for B-cell epitope prediction en route to vaccine-design applications, by restricting biological complexity to render epitope-prediction problems more computationally tractable.      

Antibody-protein interactions: benchmark datasets and prediction tools evaluation

Background  

The ability to predict antibody binding sites (aka antigenic determinants or B-cell epitopes) for a given protein is a precursor to new vaccine design and diagnostics. Among the various methods of B-cell epitope identification X-ray crystallography is one of the most reliable methods. Using these experimental data computational methods exist for B-cell epitope prediction. As the number of structures of antibody-protein complexes grows, further interest in prediction methods using 3D structure is anticipated. This work aims to establish a benchmark for 3D structure-based epitope prediction methods.     

Recent advances in B-cell epitope prediction methods

Identification of epitopes that invoke strong responses from B-cells is one of the key steps in designing effective vaccines against pathogens. Because experimental determination of epitopes is expensive in terms of cost, time, and effort involved, there is an urgent need for computational methods for reliable identification of B-cell epitopes. Although several computational tools for predicting B-cell epitopes have become available in recent years, the predictive performance of existing tools remains far from ideal. We review recent advances in computational methods for B-cell epitope prediction, identify some gaps in the current state of the art, and outline some promising directions for improving the reliability of such methods.     

B细胞表位预测方法研究进展

B细胞抗原表位预测方法的研究对基础免疫学的研究及实际应用有着重要的意义。本文归纳了理论预测B细胞表位的常用方法,并对目前预测B细胞表位方法存在的问题进行了分析。     

A novel strategy of epitope design in Neisseria gonorrhoeae

In spite of genome sequences of both human and N. gonorrhoeae in hand, vaccine for gonorrhea is yet not available. Due to availability of several host and pathogen genomes and numerous tools for in silico prediction of effective B-cell and T-cell epitopes; recent trend of vaccine designing has been shifted to peptide or epitope based vaccines that are more specific, safe, and easy to produce. In order to design and develop such a peptide vaccine against the pathogen, we adopted a novel computational approache based on sequence, structure, QSAR, and simulation methods along with fold level analysis to predict potential antigenic B-cell epitope derived T-cell epitopes from four vaccine targets of N. gonorrhoeae previously identified by us [Barh and Kumar (2009) In Silico Biology 9, 1-7]. Four epitopes, one from each protein, have been designed in such a way that each epitope is highly likely to bind maximum number of HLA molecules (comprising of both the MHC-I and II) and interacts with most frequent HLA alleles (A*0201, A*0204, B*2705, DRB1*0101, and DRB1*0401) in human population. Therefore our selected epitopes are highly potential to induce both the B-cell and T-cell mediated immune responses. Of course, these selected epitopes require further experimental validation.     

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.

     

Characterization of a partially protective B-cell epitope within the 62 kDa antigen of Schistosoma japonicum

Approximately 200 million people worldwide currently suffer from schistosomiasis, one of the most important human parasitic diseases. Although an established infection can be treated with anthelminthics and praziquantel, vaccination would be the ideal method for integral control of schistosomiasis. Schistosoma mansoni IrV-5, recommended as a vaccine candidate by the World Health Organization/Special Programme for Research and Training in Tropical Diseases, produced high protection in animal models. We therefore focused on its homolog, the Schistosoma japonicum 62 kDa antigen, and analyzed it using B cell/antibody- related databases and analysis tools for the prediction of B-cell epitopes. Epitope B3 was selected for further investigation. Experiments using a murine model indicated that mice immunized with B3 resulted in lymphocytes proliferation and produced high levels of specific immunoglobulin G and GI, but did not produce impressive cytokines. The vaccination showed partial protective immunity, measured by worm burden and anti-fecundity immunity against S. japonicum. These results indicated that the epitope B3 from S. japonicum 62-kDa antigen might act as a candidate immunogen for future epitope vaccine investigation.     

A synthetic peptide analog of in silico-predicted immunogenic epitope unique to dengue virus serotype 2 NS1 antigen specifically binds immunoglobulin G antibodies raised in rabbits

Development of a serotyping-capable dengue detection test is hampered by the absence of an identified unique marker that can detect specific dengue virus (DENV) serotype. In the current commercially available antibody-capture diagnostic methods, immobilized nonstructural 1 (NS1) antigen indiscriminately binds and detects immunoglobulin M or immunoglobulin G against any serotype, thus limiting its capability to distinguish existing serotypes of dengue. Identification of dengue serotype is important because certain serotypes are associated with severe forms of dengue as well as dengue hemorrhagic fever. In this study, we aimed to identify an immunogenic epitope unique to DENV2 NS1 antigen and determine the binding specificity of its synthetic peptide mimotope to antibodies raised in animal models. Selection of a putative B-cell epitope from the reported DENV2 NS1 antigen was done using Kolaskar and Tongaonkar Antigenicity prediction, Emini surface accessibility prediction, and Parker hydrophilicity prediction available at the immune epitope database and analysis resource. Uniqueness of the B-cell epitope to DENV2 was analyzed by BLASTp. Immunogenicity of the synthetic peptide analog of the predicted immunogenic epitope was tested in rabbits. The binding specificity of the antibodies raised in animals and the synthetic peptide mimotope was tested by indirect ELISA. A synthetic peptide analog comprising the unique epitope of DENV2 located at the 170th–183rd position of DENV2 NS1 was found to be immunogenic in animal models. The antipeptide antibody produced in rabbits showed specific binding to the synthetic peptide mimotope of the predicted unique DENV2 NS1 immunogenic epitope.     

BCIgEPRED—a Dual-Layer Approach for Predicting Linear IgE Epitopes

Allergy is a common health problem worldwide, especially food allergy. Since B cell epitopes that are recognized by the IgE antibodies act as antigenic determinants for allergy, they play a vital role in diagnostics. Hence, knowledge of an IgE binding epitope in a protein is of particular interest for identifying allergenic proteins. Though IgE epitopes may be conformational or linear, identification of the later is useful especially in food allergens that undergo processing or digestion. Very few computational tools are available for the prediction of linear IgE epitopes. Here we report a prediction system that predicts the exact linear IgE epitope. Since our earlier study on linear B-cell epitope prediction demonstrated the effectiveness of using an exact epitope dataset (in contrast to epitope containing region datasets), the dataset in this study uses only experimentally verified exact IgE, IgG, IgM and IgA epitopes. Models for Support Vector Machine (SVM) and Random Forest (RF) were constructed adopting Dipeptide Deviation from the Expected mean (DDE) feature vector. Extensive validation procedures including five-fold cross validation and two different independent dataset tests have been performed to validate the proposed method, which achieved a balanced accuracy ranging from 74 to 78% with area under receiver operator curve greater than 0.8. Performance of the proposed method was observed to be better (accuracy difference of 16–28%) in comparison to the existing available method. The proposed method is developed as a standalone tool that could be used for predicting IgE epitopes as well as to be incorporated into any allergen prediction toolhttps://github.com/brsaran/BCIgePred.     

Comparison of full-length genomics sequences between dengue virus serotype 3, parental strain,and its derivatives,and B-cell epitopes prediction from envelope region

Biological markers are normally used to evaluate the candidate of live-attenuated dengue vaccines. D3V 16562 Vero 23 and D3V 16562 Vero 33 which were derivatives of D3V 16562, parental strain, showed the similar biological data. We used molecular techniques and computational tools to evaluate these derivatives. The nucleotide and amino acid sequences of the derivatives were compared to their parent. The secondary structures of untranslated regions and B-cell epitopes were predicted. The results showed that nucleotide substitutions mostly occurred in NS5 and NS5 of V2 was unusual because of amino acid change at 3349 (tryptophan →stop codon). The nucleotide substitutions in 5''UTR, prM, E, NS1, NS2A, NS3, and 3''UTR were 4, 1, 2, 2, 1, 3, and 2, respectively. The secondary structure of 5''UTR of V2 was different from P and V1. The secondary structure of 3''UTR of V2 was similar to P and certainly distinct from V1. Furthermore, B-cell epitopes prediction revealed that there were 21 epitopes of envelope and the interesting epitope was at position 297-309 because it was in domain III in which the neutralizing antibody is induced. For this study, the attenuation of derivatives was caused by the nucleotide substitutions in 5''UTR, 3''UTR, and NS5 regions. The genotypic data and B-cell epitope make the derivatives attractive for the chimeric and peptide DENV vaccine development.     

Improved method for predicting linear B-cell epitopes

Background

B-cell epitopes are the sites of molecules that are recognized by antibodies of the immune system. Knowledge of B-cell epitopes may be used in the design of vaccines and diagnostics tests. It is therefore of interest to develop improved methods for predicting B-cell epitopes. In this paper, we describe an improved method for predicting linear B-cell epitopes.

Results

In order to do this, three data sets of linear B-cell epitope annotated proteins were constructed. A data set was collected from the literature, another data set was extracted from the AntiJen database and a data sets of epitopes in the proteins of HIV was collected from the Los Alamos HIV database. An unbiased validation of the methods was made by testing on data sets on which they were neither trained nor optimized on. We have measured the performance in a non-parametric way by constructing ROC-curves.

Conclusion

The best single method for predicting linear B-cell epitopes is the hidden Markov model. Combining the hidden Markov model with one of the best propensity scale methods, we obtained the BepiPred method. When tested on the validation data set this method performs significantly better than any of the other methods tested. The server and data sets are publicly available at http://www.cbs.dtu.dk/services/BepiPred.