Prediction of antigenic epitopes on protein surfaces by consensus scoring

Computer-aided rational design strategy based on protein surface charge to improve the thermal stability of a novel esterase from Geobacillus jurassicus

OBJECTIVES

Although Geobacillus are significant thermophilic bacteria source, there are no reports of thermostable esterase gene in Geobacillus jurassicus or rational design strategies to increase the thermal stability of esterases.

RESULTS

Gene gju768 showed a highest similarity of 15.20% to esterases from Geobacillus sp. with detail enzymatic properties. Using a combination of Gibbs Unfolding Free Energy (∆∆G) calculator and the distance from the mutation site to the catalytic site (DsCα-Cα) to screen suitable mutation sites with elimination of negative surface charge, the mutants (D24N, E221Q, and E253Q) displayed stable mutants with higher thermal stability than the wild-type (WT). Mutant E253Q exhibited the best thermal stability, with a half-life (T1/2) at 65 °C of 32.4 min, which was 1.8-fold of the WT (17.9 min).

CONCLUSION

Cloning of gene gju768 and rational design based on surface charge engineering contributed to the identification of thermostable esterase from Geobacillus sp. and the exploration of evolutionary strategies for thermal stability.

Effect of lactic acid bacteria fermentation on cow milk allergenicity and antigenicity: A review

Cow milk is a major allergenic food. The potential prevention and treatment effects of lactic acid bacteria (LAB)-fermented dairy products on allergic symptoms have garnered considerable attention. Cow milk allergy (CMA) is mainly attributed to extracellular and/or cell envelope proteolytic enzymes with hydrolysis specificity. Numerous studies have demonstrated that LAB prevents the risk of allergies by modulating the development and regulation of the host immune system. Specifically, LAB and its effectors can enhance intestinal barrier function and affect immune cells by interfering with humoral and cellular immunity. Fermentation hydrolysis of allergenic epitopes is considered the main mechanism of reducing CMA. This article reviews the linear epitopes of allergens in cow milk and the effect of LAB on these allergens and provides insight into the means of predicting allergenic epitopes by conventional laboratory analysis methods combined with molecular simulation. Although LAB can reduce CMA in several ways, the mechanism of action remains partially clarified. Therefore, this review additionally attempts to summarize the main mechanism of LAB fermentation to provide guidance for establishing an effective preventive and treatment method for CMA and serve as a reference for the screening, research, and application of LAB-based intervention.

Riding the wave of innovation: immunoinformatics in fish disease control

The spread of infectious illnesses has been a significant factor restricting aquaculture production. To maximise aquatic animal health, vaccination tactics are very successful and cost-efficient for protecting fish and aquaculture animals against many disease pathogens. However, due to the increasing number of immunological cases and their complexity, it is impossible to manage, analyse, visualise, and interpret such data without the assistance of advanced computational techniques. Hence, the use of immunoinformatics tools is crucial, as they not only facilitate the management of massive amounts of data but also greatly contribute to the creation of fresh hypotheses regarding immune responses. In recent years, advances in biotechnology and immunoinformatics have opened up new research avenues for generating novel vaccines and enhancing existing vaccinations against outbreaks of infectious illnesses, thereby reducing aquaculture losses. This review focuses on understanding in silico epitope-based vaccine design, the creation of multi-epitope vaccines, the molecular interaction of immunogenic vaccines, and the application of immunoinformatics in fish disease based on the frequency of their application and reliable results. It is believed that it can bridge the gap between experimental and computational approaches and reduce the need for experimental research, so that only wet laboratory testing integrated with in silico techniques may yield highly promising results and be useful for the development of vaccines for fish.

Dynamic structural analysis-based epitope prediction of Exendin-4 in aqueous solution

The study of epitopes has a broad range of applications in drug discovery, vaccine design, and immunotherapy. In this study, an epitope prediction method was developed based on the dynamic structure of protein antigens. Solvent accessible surface area, charge, and root mean square fluctuation were introduced as the key residue property parameters. The epitope prediction algorithm was established by constructing a three-parameter complex metrics of seven-peptide groups. The method was applied to predict the epitopes of Exendin-4, an effective antidiabetic drug. The epitopes of both the natural and C-terminal amidated forms of Exendin-4 were predicted and compared in their folded and intermediate states. In the folded state, the epitopes of natural Exendin-4 (His1-Phe6 and Asp9-Val19) were found to be nearly identical to the epitopes of C-terminal aminated Exendin-4 (His1-Thr7 and Asp9-Val19). In the intermediate state, however, the epitopes of natural Exendin-4 (His1-Gly4, Phe6 and Lys12-Arg20) covered fewer amino acids than the epitopes of C-terminal aminated Exendin-4 (His1-Gly4, Phe6, Asp9-Val19 and Trp25-Lys27). The comparison with the results from other prediction tools demonstrates the reliability of our predicted epitopes of Exendin-4.

A double-strain TM (gp45) polypeptide antigen and its application in the serodiagnosis of equine infectious anemia

Lentiviruses, including equine infectious anemia virus (EIAV), are considered viral quasispecies because of their intrinsic genetic, structural and phenotypic variability. Immunoenzymatic tests (ELISA) for EIAV reported in the literature were obtained mainly by using the capsid protein p26, which is derived almost exclusively from a single strain (Wyoming), and do not reflect the great potential epitopic variability of the EIAV quasispecies. In this investigation, the GenBank database was exploited in a systematic approach to design a set of representative protein antigens useful for EIAV serodiagnosis. The main bioinformatic tools used were clustering, molecular modelling, epitope predictions and aggregative/ solubility predictions. This approach led to the design of two antigenic proteins, i.e. a full sequence p26 capsid protein and a doublestrain polypeptide derived from the gp45 transmembrane protein fused to Maltose Binding Protein (MBP) that were expressed by recombinant DNA technology starting from synthetic genes, and analyzed by circular dichroism (CD) spectroscopy. Both proteins were used in an indirect ELISA test that can address some of the high variability of EIAV. The novel addition of the gp45 double-strain antigen contributed to enhance the diagnostic sensitivity and could be also useful for immunoblotting application.

B-Cell Epitope Predictions Using Computational Methods

Identifying protein antigenic epitopes that are recognizable by antibodies is a key step in immunologic research. This type of research has broad medical applications, such as new immunodiagnostic reagent discovery, vaccine design, and antibody design. However, due to the countless possibilities of potential epitopes, the experimental search through trial and error would be too costly and time-consuming to be practical. To facilitate this process and improve its efficiency, computational methods were developed to predict both linear epitopes and discontinuous antigenic epitopes. For linear B-cell epitope prediction, many methods were developed, including PREDITOP, PEOPLE, BEPITOPE, BepiPred, COBEpro, ABCpred, AAP, BCPred, BayesB, BEOracle/BROracle, BEST, LBEEP, DRREP, iBCE-EL, SVMTriP, etc. For the more challenging yet important task of discontinuous epitope prediction, methods were also developed, including CEP, DiscoTope, PEPITO, ElliPro, SEPPA, EPITOPIA, PEASE, EpiPred, SEPIa, EPCES, EPSVR, etc. In this chapter, we will discuss computational methods for B-cell epitope predictions of both linear and discontinuous epitopes. SVMTriP and EPCES/EPCSVR, the most successful among the methods for each type of the predictions, will be used as model methods to detail the standard protocols. For linear epitope prediction, SVMTriP was reported to achieve a sensitivity of 80.1% and a precision of 55.2% with a fivefold cross-validation based on a large dataset, yielding an AUC of 0.702. For discontinuous or conformational B-cell epitope prediction, EPCES and EPCSVR were both benchmarked by a curated independent test dataset in which all antigens had no complex structures with the antibody. The identified epitopes by these methods were later independently validated by various biochemical experiments. For these three model methods, webservers and all datasets are publicly available at http://sysbio.unl.edu/SVMTriP , http://sysbio.unl.edu/EPCES/ , and http://sysbio.unl.edu/EPSVR/ .

Omicron-included mutation-induced changes in epitopes of SARS-CoV-2 spike protein and effectiveness assessments of current antibodies

The COVID-19 pandemic, caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is spreading globally and continues to rage, posing a serious threat to human health and life quality. Antibody therapy and vaccines both have shown great efficacy in the prevention and treatment of COVID-19, whose development progress and adaptation range have attracted wide attention. However, with the emergence of variant strains of SARS-CoV-2, the neutralization activity of therapeutic or vaccine-induced antibodies may be reduced, requiring long-term virus monitoring and drug upgrade in response to its evolution. In this paper, conformational changes including continuous epitopes (CPs), discontinuous epitopes (DPs) and recognition interfaces of the three representative SARS-CoV-2 spike protein (SP) mutants (i.e., the Delta (B.1.617.2), Mu (B.1.621) and Omicron (B.1.1.529) strains), were analyzed to evaluate the effectiveness of current mainstream antibodies. The results showed that the conformation of SP wild type (WT) and mutants both remained stable, while the local antigenic epitopes underwent significant changes. Sufficient flexibility of SP CPs is critical for effective antibody recognition. The DPs of Delta, Mu and Omicron variants have showed stronger binding to human angiotensin converting enzyme-2 (hACE2) than WT; the possible drug resistance mechanisms of antibodies against three different epitopes (i.e., NTD_DP, RBD1_DP and RBD2_DP) were also proposed, respectively; the RBD2 of Delta, NTD of Mu, NTD and RBD2 of Omicron are deserve more attention in the subsequent design of next-generation vaccines. The simulation results not only revealed structural characteristics of SP antigenic epitopes, but also provided guidance for antibody modification, vaccine design and effectiveness evaluation.

Peptide-Based Vaccines for Tuberculosis

Tuberculosis (TB) is an infectious disease caused by Mycobacterium tuberculosis. As a result of the coronavirus disease 2019 (COVID-19) pandemic, the global TB mortality rate in 2020 is rising, making TB prevention and control more challenging. Vaccination has been considered the best approach to reduce the TB burden. Unfortunately, BCG, the only TB vaccine currently approved for use, offers some protection against childhood TB but is less effective in adults. Therefore, it is urgent to develop new TB vaccines that are more effective than BCG. Accumulating data indicated that peptides or epitopes play essential roles in bridging innate and adaptive immunity and triggering adaptive immunity. Furthermore, innovations in bioinformatics, immunoinformatics, synthetic technologies, new materials, and transgenic animal models have put wings on the research of peptide-based vaccines for TB. Hence, this review seeks to give an overview of current tools that can be used to design a peptide-based vaccine, the research status of peptide-based vaccines for TB, protein-based bacterial vaccine delivery systems, and animal models for the peptide-based vaccines. These explorations will provide approaches and strategies for developing safer and more effective peptide-based vaccines and contribute to achieving the WHO’s End TB Strategy.

epitope3D: a machine learning method for conformational B-cell epitope prediction

The ability to identify antigenic determinants of pathogens, or epitopes, is fundamental to guide rational vaccine development and immunotherapies, which are particularly relevant for rapid pandemic response. A range of computational tools has been developed over the past two decades to assist in epitope prediction; however, they have presented limited performance and generalization, particularly for the identification of conformational B-cell epitopes. Here, we present epitope3D, a novel scalable machine learning method capable of accurately identifying conformational epitopes trained and evaluated on the largest curated epitope data set to date. Our method uses the concept of graph-based signatures to model epitope and non-epitope regions as graphs and extract distance patterns that are used as evidence to train and test predictive models. We show epitope3D outperforms available alternative approaches, achieving Mathew's Correlation Coefficient and F1-scores of 0.55 and 0.57 on cross-validation and 0.45 and 0.36 during independent blind tests, respectively.

Infectious disease mRNA vaccines and a review on epitope prediction for vaccine design

Messenger RNA (mRNA) vaccines have recently emerged as a new type of vaccine technology, showing strong potential to combat the COVID-19 pandemic. In addition to SARS-CoV-2 which caused the pandemic, mRNA vaccines have been developed and tested to prevent infectious diseases caused by other viruses such as Zika virus, the dengue virus, the respiratory syncytial virus, influenza H7N9 and Flavivirus. Interestingly, mRNA vaccines may also be useful for preventing non-infectious diseases such as diabetes and cancer. This review summarises the current progresses of mRNA vaccines designed for a range of diseases including COVID-19. As epitope study is a primary component in the in silico design of mRNA vaccines, we also survey on advanced bioinformatics and machine learning algorithms which have been used for epitope prediction, and review on user-friendly software tools available for this purpose. Finally, we discuss some of the unanswered concerns about mRNA vaccines, such as unknown long-term side effects, and present with our perspectives on future developments in this exciting area.

Design and structural bioinformatic analysis of polypeptide antigens useful for the SRLV serodiagnosis

Due to their intrinsic genetic, structural and phenotypic variability the Lentiviruses, and specifically small ruminant lentiviruses (SRLV), are considered viral quasispecies with a population structure that consists of extremely large numbers of variant genomes, termed mutant spectra or mutant cloud. Immunoenzymatic tests for SRLVs are available but the dynamic heterogeneity of the virus makes the development of a diagnostic "golden standard" extremely difficult. The ELISA reported in the literature have been obtained using proteins derived from a single strain or they are multi-strain based assay that may increase the sensitivity of the serological diagnosis. Hundreds of SRLV protein sequences derived from different viral strains are deposited in GenBank. The aim of this study is to verify if the database can be exploited with the help of bioinformatics in order to have a more systematic approach in the design of a set of representative protein antigens useful in the SRLV serodiagnosis. Clustering, molecular modelling, molecular dynamics, epitope predictions and aggregative/solubility predictions were the main bioinformatic tools used. This approach led to the design of SRLV antigenic proteins that were expressed by recombinant DNA technology using synthetic genes, analyzed by CD spectroscopy, tested by ELISA and preliminarily compared to currently commercially available detection kits.

Immunoinformatics study to search epitopes of spike glycoprotein from SARS-CoV-2 as potential vaccine

The Coronavirus disease named COVID-19 is caused by the virus reported in 2019 first identified in China. The cases of this disease have increased and as of June 1st, 2020 there are more than 216 countries affected. Pharmacological treatments have been proposed based on the resemblance of the HIV virus. With regard to prevention there is no vaccine, thus, we proposed to explore the spike protein due to its presence on the viral surface, and it also contains the putative viral entry receptor as well as the fusion peptide (important in the genome release). In this work we have employed In Silico techniques such as immunoinformatics tools which permit the identification of potential immunogenic regions on the viral surface (spike glycoprotein). From these analyses, we identified four epitopes E332-370, E627-651, E440-464 and E694-715 that accomplish essential features such as promiscuity, conservation grade, exposure and universality, and they also form stable complexes with MHCII molecule. We suggest that these epitopes could generate a specific immune response, and thus, they could be used for future applications such as the design of new epitope vaccines against the SARS-CoV-2.Communicated by Ramaswamy H. Sarma.

Conformational epitope matching and prediction based on protein surface spiral features

Background

A conformational epitope (CE) is composed of neighboring amino acid residues located on an antigenic protein surface structure. CEs bind their complementary paratopes in B-cell receptors and/or antibodies. An effective and efficient prediction tool for CE analysis is critical for the development of immunology-related applications, such as vaccine design and disease diagnosis.

Results

We propose a novel method consisting of two sequential modules: matching and prediction. The matching module includes two main approaches. The first approach is a complete sequence search (CSS) that applies BLAST to align the sequence with all known antigen sequences. Fragments with high epitope sequence identities are identified and the predicted residues are annotated on the query structure. The second approach is a spiral vector search (SVS) that adopts a novel surface spiral feature vector for large-scale surface patch detection when queried against a comprehensive epitope database. The prediction module also contains two proposed subsystems. The first system is based on knowledge-based energy and geometrical neighboring residue contents, and the second system adopts combinatorial features, including amino acid contents and physicochemical characteristics, to formulate corresponding geometric spiral vectors and compare them with all spiral vectors from known CEs. An integrated testing dataset was generated for method evaluation, and our two searching methods effectively identified all epitope regions. The prediction results show that our proposed method outperforms previously published systems in terms of sensitivity, specificity, positive predictive value, and accuracy.

Conclusions

The proposed method significantly improves the performance of traditional epitope prediction. Matching followed by prediction is an efficient and effective approach compared to predicting directly on specific surfaces containing antigenic characteristics.

Current and prospective computational approaches and challenges for developing COVID-19 vaccines

SARS-CoV-2, which causes COVID-19, was first identified in humans in late 2019 and is a coronavirus which is zoonotic in origin. As it spread around the world there has been an unprecedented effort in developing effective vaccines. Computational methods can be used to speed up the long and costly process of vaccine development. Antigen selection, epitope prediction, and toxicity and allergenicity prediction are areas in which computational tools have already been applied as part of reverse vaccinology for SARS-CoV-2 vaccine development. However, there is potential for computational methods to assist further. We review approaches which have been used and highlight additional bioinformatic approaches and PK modelling as in silico methods which may be useful for SARS-CoV-2 vaccine design but remain currently unexplored. As more novel viruses with pandemic potential are expected to arise in future, these techniques are not limited to application to SARS-CoV-2 but also useful to rapidly respond to novel emerging viruses.

iLBE for Computational Identification of Linear B-cell Epitopes by Integrating Sequence and Evolutionary Features

Linear B-cell epitopes are critically important for immunological applications, such as vaccine design, immunodiagnostic test, and antibody production, as well as disease diagnosis and therapy. The accurate identification of linear B-cell epitopes remains challenging despite several decades of research. In this work, we have developed a novel predictor, Identification of Linear B-cell Epitope (iLBE), by integrating evolutionary and sequence-based features. The successive feature vectors were optimized by a Wilcoxon-rank sum test. Then the random forest (RF) algorithm using the optimal consecutive feature vectors was applied to predict linear B-cell epitopes. We combined the RF scores by the logistic regression to enhance the prediction accuracy. iLBE yielded an area under curve score of 0.809 on the training dataset and outperformed other prediction models on a comprehensive independent dataset. iLBE is a powerful computational tool to identify the linear B-cell epitopes and would help to develop penetrating diagnostic tests. A web application with curated datasets for iLBE is freely accessible at http://kurata14.bio.kyutech.ac.jp/iLBE/.

Attenuated Subcomponent Vaccine Design Targeting the SARS-CoV-2 Nucleocapsid Phosphoprotein RNA Binding Domain: In Silico Analysis

The novel coronavirus disease (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has previously never been identified with humans, thereby creating devastation in public health. The need for an effective vaccine to curb this pandemic cannot be overemphasized. In view of this, we designed a subcomponent antigenic peptide vaccine targeting the N-terminal (NT) and C-terminal (CT) RNA binding domains of the nucleocapsid protein that aid in viral replication. Promising antigenic B cell and T cell epitopes were predicted using computational pipelines. The peptides “RIRGGDGKMKDL” and “AFGRRGPEQTQGNFG” were the B cell linear epitopes with good antigenic index and nonallergenic property. Two CD8⁺ and Three CD4⁺ T cell epitopes were also selected considering their safe immunogenic profiling such as allergenicity, antigen level conservancy, antigenicity, peptide toxicity, and putative restrictions to a number of MHC-I and MHC-II alleles. With these selected epitopes, a nonallergenic chimeric peptide vaccine incapable of inducing a type II hypersensitivity reaction was constructed. The molecular interaction between the Toll-like receptor-5 (TLR5) which was triggered by the vaccine was analyzed by molecular docking and scrutinized using dynamics simulation. Finally, in silico cloning was performed to ensure the expression and translation efficiency of the vaccine, utilizing the pET-28a vector. This research, therefore, provides a guide for experimental investigation and validation.

Prediction of immunogenicity for humanized and full human therapeutic antibodies

Immunogenicity is an important concern for therapeutic antibodies during drug development. By analyzing co-crystal structures of idiotypic antibodies and their antibodies, we found that anti-idiotypic antibodies usually bind the Complementarity Determining Regions (CDR) of idiotypic antibodies. Sequence and structural features were identified for distinguishing immunogenic antibodies from non-immunogenic antibodies. For example, non-immunogenic antibodies have a significantly larger cavity volume at the CDR region and a more hydrophobic CDR-H3 loop than immunogenic antibodies. Antibodies containing no Gly at the turn of CDR-H2 loop are often immunogenic. We integrated these features together with a machine learning platform to Predict Immunogenicity for humanized and full human THerapeutic Antibodies (PITHA). This method achieved an accuracy of 83% in leave-one-out experiment for 29 therapeutic antibodies with available crystal structures. The accuracy decreased to 65% for 23 test antibodies with modeled structures, because their crystal structures were not available, and the prediction was made with modeled structures. The server of this method is accessible at http://mabmedicine.com/PITHA.

Leveraging a Validated in silico Approach to Elucidate Genotype-Specific VP7 Epitopes and Antigenic Relationships of Porcine Rotavirus A

Rotavirus A (RVA) remains one of the most widespread causes of diarrheal disease and mortality in piglets despite decades of research and efforts to boost lactogenic immunity for passive protection. Genetic changes at B cell epitopes (BCEs) may be driving failure of lactogenic immunity, which relies on production of IgA antibodies to passively neutralize RVA within the piglet gut, yet little research has mapped epitopes to swine-specific strains of RVA. Here we describe a bioinformatic approach to predict BCEs on the VP7 outer capsid protein using sequence data alone. We first validated the approach using a previously published dataset of VP7-specific cross-neutralization titers, and found that amino acid changes at predicted BCEs on the VP7 protein allowed for accurate recapitulation of antigenic relationships among the strains. Applying the approach to a dataset of swine RVA sequences identified 9 of the 11 known BCEs previously mapped to swine strains, indicating that epitope prediction can identify sites that are known to drive neutralization escape in vitro. Additional genotype-specific BCEs were also predicted that may be the cause of antigenic differences among strains of RVA on farms and should be targeted for further confirmatory work. The results of this work lay the groundwork for high throughput, immunologically-relevant analysis of swine RVA sequence data, and provide potential sites that can be targeted with vaccines to reduce piglet mortality and support farm health.

Enhancement of conformational B-cell epitope prediction using CluSMOTE

BACKGROUND

A conformational B-cell epitope is one of the main components of vaccine design. It contains separate segments in its sequence, which are spatially close in the antigen chain. The availability of Ag-Ab complex data on the Protein Data Bank allows for the development predictive methods. Several epitope prediction models also have been developed, including learning-based methods. However, the performance of the model is still not optimum. The main problem in learning-based prediction models is class imbalance.

METHODS

This study proposes CluSMOTE, which is a combination of a cluster-based undersampling method and Synthetic Minority Oversampling Technique. The approach is used to generate other sample data to ensure that the dataset of the conformational epitope is balanced. The Hierarchical DBSCAN algorithm is performed to identify the cluster in the majority class. Some of the randomly selected data is taken from each cluster, considering the oversampling degree, and combined with the minority class data. The balance data is utilized as the training dataset to develop a conformational epitope prediction. Furthermore, two binary classification methods, Support Vector Machine and Decision Tree, are separately used to develop model prediction and to evaluate the performance of CluSMOTE in predicting conformational B-cell epitope. The experiment is focused on determining the best parameter for optimal CluSMOTE. Two independent datasets are used to compare the proposed prediction model with state of the art methods. The first and the second datasets represent the general protein and the glycoprotein antigens respectively.

RESULT

The experimental result shows that CluSMOTE Decision Tree outperformed the Support Vector Machine in terms of AUC and Gmean as performance measurements. The mean AUC of CluSMOTE Decision Tree in the Kringelum and the SEPPA 3 test sets are 0.83 and 0.766, respectively. This shows that CluSMOTE Decision Tree is better than other methods in the general protein antigen, though comparable with SEPPA 3 in the glycoprotein antigen.

EPCES and EPSVR: Prediction of B-Cell Antigenic Epitopes on Protein Surfaces with Conformational Information

Accurate prediction of discontinuous antigenic epitopes is important for immunologic research and medical applications, but it is not an easy problem. Currently, there are only a few prediction servers available, though discontinuous epitopes constitute the majority of all B-cell antigenic epitopes. In this chapter, we describe two online servers, EPCES and EPSVR, for discontinuous epitope prediction. All methods were benchmarked by a curated independent test set, in which all antigens had no complex structures with the antibody, and their epitopes were identified by various biochemical experiments. The servers and all datasets are available at http://sysbio.unl.edu/EPCES/ and http://sysbio.unl.edu/EPSVR/ .

Porcine parvovirus VP1/VP2 on a time series epitope mapping: exploring the effects of high hydrostatic pressure on the immune recognition of antigens

Porcine parvovirus (PPV) is a DNA virus that causes reproductive failure in gilts and sows, resulting in embryonic and fetal losses worldwide. Epitope mapping of PPV is important for developing new vaccines. In this study, we used spot synthesis analysis for epitope mapping of the capsid proteins of PPV (NADL-2 strain) and correlated the findings with predictive data from immunoinformatics. The virus was exposed to three conditions prior to inoculation in pigs: native (untreated), high hydrostatic pressure (350 MPa for 1 h) at room temperature and high hydrostatic pressure (350 MPa for 1 h) at − 18 °C, and was compared with a commercial vaccine produced using inactivated PPV. The screening of serum samples detected 44 positive spots corresponding to 20 antigenic sites. Each type of inoculated antigen elicited a distinct epitope set. In silico prediction located linear and discontinuous epitopes in B cells that coincided with several epitopes detected in spot synthesis of sera from pigs that received different preparations of inoculum. The conditions tested elicited antibodies against the VP1/VP2 antigen that differed in relation to the response time and the profile of structurally available regions that were recognized.

Advances in In-silico B-cell Epitope Prediction

Identification of B-cell epitopes in target antigens is one of the most crucial steps for epitopebased vaccine development, immunodiagnostic tests, antibody production, and disease diagnosis and therapy. Experimental methods for B-cell epitope mapping are time consuming, costly and labor intensive; in the meantime, various in-silico methods are proposed to predict both linear and conformational B-cell epitopes. The accurate identification of B-cell epitopes presents major challenges for immunoinformaticians. In this paper, we have comprehensively reviewed in-silico methods for B-cell epitope identification. The aim of this review is to stimulate the development of better tools which could improve the identification of B-cell epitopes, and further for the development of therapeutic antibodies and diagnostic tools.

Understanding the Significance and Implications of Antibody Numbering and Antigen-Binding Surface/Residue Definition

Monoclonal antibodies are playing an increasing role in both human and animal health. Different strategies of protein and chemical engineering, including humanization techniques of non-human antibodies were applied successfully to optimize clinical performances of antibodies. Despite the emergence of techniques allowing the development of fully human antibodies such as transgenic Xeno-mice, antibody humanization remains a standard procedure for therapeutic antibodies. An important prerequisite for antibody humanization requires standardized numbering methods to define precisely complementary determining regions (CDR), frameworks and residues from the light and heavy chains that affect the binding affinity and/or specificity of the antibody-antigen interaction. The recently generated deep-sequencing data and the increasing number of solved three-dimensional structures of antibodies from human and non-human origins have led to the emergence of numerous databases. However, these different databases use different numbering conventions and CDR definitions. In addition, the large fluctuation of the variable chain lengths, especially in CDR3 of heavy chains (CDRH3), hardly complicates the comparison and analysis of antibody sequences and the identification of the antigen binding residues. This review compares and discusses the different numbering schemes and "CDR" definition that were established up to date. Furthermore, it summarizes concepts and strategies used for numbering residues of antibodies and CDR residues identification. Finally, it discusses the importance of specific sets of residues in the binding affinity and/or specificity of immunoglobulins.

Isolation and genome analysis of a lytic Pasteurella multocida Bacteriophage PMP-GAD-IND

Currently used alum precipitated and oil adjuvant vaccines against HS caused by Pasteurella multocida B:2, have side effects and short-lived immunity, leading to regular catastrophic outbreaks in bovines in Asian subcontinent. The need for the development of an improved vaccine with longer immunity and the ability to differentiate between vaccinated and infected is essential. Pasteurella phage isolated in present study belongs to family Siphoviridae. PMP-GAD-IND phage exhibited lytic activity against vaccine strain (P52) as well as several field strains of P. multocida (B:2), and fowl cholera agent (P. multocida A:1).The phage has a double stranded DNA (dsDNA) with a genome of 46 335 bp. The complete genome sequence of the Pasteurella multocida phage has been deposited in Gen Bank with accession no: KY203335. PMP-GAD-IND being a lytic phage with broad activity range has a potential to be used in therapy against multidrug resistant P. multocida infections.

SIGNIFICANCE AND IMPACT OF THE STUDY

The present work is a part of research for the development of an improved phage lysate marker vaccine and a companion DIVA assay against haemorhagic septicaemia. This study describes the isolation and genome analysis of PMP-GAD-IND a lytic Pasteurella multocida bacteriophage.

Rational design, preparation and characterization of recombinant Ag85B variants and their glycoconjugates with T-cell antigenic activity against Mycobacterium tuberculosis

Tuberculosis is the deadliest infectious disease in the world. The variable efficacy of the current treatments highlights the need for more effective agents against this disease. In the past few years, we focused on the investigation of antigenic glycoconjugates starting from recombinant Ag85B (rAg85B), a potent protein antigen from Mycobacterium tuberculosis. In this paper, structural modifications were rationally designed in order to obtain a rAg85B variant protein able to maintain its immunogenicity after glycosylation. Lysine residues involved in the main T-epitope sequences (namely, K30 and K282) have been substituted with arginine to prevent their glycosylation by a lysine-specific reactive linker. The effectiveness of the mutation strategy and the detailed structure of resulting neo-glycoconjugates have been studied by intact mass spectrometry, followed by peptide and glycopeptide mapping. The effect of K30R and K282R mutations on the T-cell activity of rAg85B has also been investigated with a preliminary immunological evaluation performed by enzyme-linked immunospotting on the different variant proteins and their glycosylation products. After glycosylation, the two variant proteins with an arginine in position 30 completely retain the original T-cell activity, thus representing adequate antigenic carriers for the development of efficient glycoconjugate vaccines against tuberculosis.

Postgenomic Approaches and Bioinformatics Tools to Advance the Development of Vaccines against Bacteria of the Burkholderia cepacia Complex

Bacteria of the Burkholderia cepacia complex (Bcc) remain an important cause of morbidity and mortality among patients suffering from cystic fibrosis. Eradication of these pathogens by antimicrobial therapy often fails, highlighting the need to develop novel strategies to eradicate infections. Vaccines are attractive since they can confer protection to particularly vulnerable patients, as is the case of cystic fibrosis patients. Several studies have identified specific virulence factors and proteins as potential subunit vaccine candidates. So far, no vaccine is available to protect from Bcc infections. In the present work, we review the most promising postgenomic approaches and selected web tools available to speed up the identification of immunogenic proteins with the potential of conferring protection against Bcc infections.

In Silico Tools and Databases for Designing Peptide-Based Vaccine and Drugs

The prolonged conventional approaches of drug screening and vaccine designing prerequisite patience, vigorous effort, outrageous cost as well as additional manpower. Screening and experimentally validating thousands of molecules for a specific therapeutic property never proved to be an easy task. Similarly, traditional way of vaccination includes administration of either whole or attenuated pathogen, which raises toxicity and safety issues. Emergence of sequencing and recombinant DNA technology led to the epitope-based advanced vaccination concept, i.e., small peptides (epitope) can stimulate specific immune response. Advent of bioinformatics proved to be an adjunct in vaccine and drug designing. Genomic study of pathogens aid to identify and analyze the protective epitope. A number of in silico tools have been developed to design immunotherapy as well as peptide-based drugs in the last two decades. These tools proved to be a catalyst in drug and vaccine designing. This review solicits therapeutic peptide databases as well as in silico tools developed for designing peptide-based vaccine and drugs.

The effect of in silico targeting Pseudomonas aeruginosa patatin-like protein D, for immunogenic administration

The vaccine candidates that have been introduced for immunization against Pseudomonas aeruginosa (P. aeruginosa) strains are quite diverse. In fact, there has been no proper antigen to act as an effective immunogenic substance against this ubiquitous pathogen in the market as yet. The complications caused by this bacterium due to the rapid development of multiple drug resistant strains have led to clinical problems worldwide. P. aeruginosa encodes many specific virulence elements that could be used as appropriate vaccine candidates. Type Vd secretion system, also known as patatin-like protein D, is a novel P. aeruginosa auto-transporter system. It is known that cellular or humoral immune responses could be elevated by chimeric proteins carrying epitopes. It has been recognized that in silico tools are essential for the evaluation of new chimeric antigens. In this study, we have considered the patatin-like protein D (PlpD) molecule from P. aeruginosa and predicted some immunogenic properties of this strong cytotoxic phospholipase A2 with the use of in-depth computational and immunoinformatics assessment methods The novelty of our in silico study is the modeling and assessment of both humoral and cellular immune potential against the PlpD molecule. The molecule was considered by multiple sequence alignment and homology valuation. The extremely conserved regions in the PlpD were predicted. The allergenic and physicochemical property predictions on the PlpD state that the molecule is a non-allergic and stable molecule. High-resolution secondary and tertiary conformations were created. Indeed, the B-cell and T-cell epitope mapping on the chimeric target protein confirmed that the engineered protein contained a tremendous number of both B-cell and T-cell corresponding epitopes. This investigation magnificently attained the chimeric molecule as being a potent lipolytic enzyme composed of numerous B-cell and T-cell restricted epitopes and could induce both humoral and cellular immune responses. The results indicated that this molecule has therapeutic potential against several potent pathogenic P. aeruginosa strains.

Longitudinal Surveillance of Porcine Rotavirus B Strains from the United States and Canada and In Silico Identification of Antigenically Important Sites

Rotavirus B (RVB) is an important swine pathogen, but control and prevention strategies are limited without an available vaccine. To develop a subunit RVB vaccine with maximal effect, we characterized the amino acid sequence variability and predicted antigenicity of RVB viral protein 7 (VP7), a major neutralizing antibody target, from clinically infected pigs in the United States and Canada. We identified genotype-specific antigenic sites that may be antibody neutralization targets. While some antigenic sites had high amino acid functional group diversity, nine antigenic sites were completely conserved. Analysis of nucleotide substitution rates at amino acid sites (dN/dS) suggested that negative selection appeared to be playing a larger role in the evolution of the identified antigenic sites when compared to positive selection, and was identified in six of the nine conserved antigenic sites. These results identified important characteristics of RVB VP7 variability and evolution and suggest antigenic residues on RVB VP7 that are negatively selected and highly conserved may be good candidate regions to include in a subunit vaccine design due to their tendency to remain stable.

Glycosylation of Recombinant Antigenic Proteins from Mycobacterium tuberculosis: In Silico Prediction of Protein Epitopes and Ex Vivo Biological Evaluation of New Semi-Synthetic Glycoconjugates

Tuberculosis is still one of the most deadly infectious diseases worldwide, and the use of conjugated antigens, obtained by combining antigenic oligosaccharides, such as the lipoarabinomannane (LAM), with antigenic proteins from Mycobacterium tuberculosis (MTB), has been proposed as a new strategy for developing efficient vaccines. In this work, we investigated the effect of the chemical glycosylation on two recombinant MTB proteins produced in E. coli with an additional seven-amino acid tag (recombinant Ag85B and TB10.4). Different semi-synthetic glycoconjugated derivatives were prepared, starting from mannose and two disaccharide analogs. The glycans were activated at the anomeric position with a thiocyanomethyl group, as required for protein glycosylation by selective reaction with lysines. The glycosylation sites and the ex vivo evaluation of the immunogenic activity of the different neo-glycoproteins were investigated. Glycosylation does not modify the immunological activity of the TB10.4 protein. Similarly, Ag85B maintains its B-cell activity after glycosylation while showing a significant reduction in the T-cell response. The results were correlated with the putative B- and T-cell epitopes, predicted using a combination of in silico systems. In the recombinant TB10.4, the unique lysine is not included in any T-cell epitope. Lys30 of Ag85B, identified as the main glycosylation site, proved to be the most important site involved in the formation of T-cell epitopes, reasonably explaining why its glycosylation strongly influenced the T-cell activity. Furthermore, additional lysines included in different epitopes (Lys103, -123 and -282) are also glycosylated. In contrast, B-cell epitopic lysines of Ag85B were found to be poorly glycosylated and, thus, the antibody interaction of Ag85B was only marginally affected after coupling with mono- or disaccharides.

Staged heterogeneity learning to identify conformational B-cell epitopes from antigen sequences

Background

The broad heterogeneity of antigen-antibody interactions brings tremendous challenges to the design of a widely applicable learning algorithm to identify conformational B-cell epitopes. Besides the intrinsic heterogeneity introduced by diverse species, extra heterogeneity can also be introduced by various data sources, adding another layer of complexity and further confounding the research.

Results

This work proposed a staged heterogeneity learning method, which learns both characteristics and heterogeneity of data in a phased manner. The method was applied to identify antigenic residues of heterogenous conformational B-cell epitopes based on antigen sequences. In the first stage, the model learns the general epitope patterns of each kind of propensity from a large data set containing computationally defined epitopes. In the second stage, the model learns the heterogenous complementarity of these propensities from a relatively small guided data set containing experimentally determined epitopes. Moreover, we designed an algorithm to cluster the predicted individual antigenic residues into conformational B-cell epitopes so as to provide strong potential for real-world applications, such as vaccine development. With heterogeneity well learnt, the transferability of the prediction model was remarkably improved to handle new data with a high level of heterogeneity. The model has been tested on two data sets with experimentally determined epitopes, and on a data set with computationally defined epitopes. This proposed sequence-based method achieved outstanding performance - about twice that of existing methods, including the sequence-based predictor CBTOPE and three other structure-based predictors.

Conclusions

The proposed method uses only antigen sequence information, and thus has much broader applications.

SEPIa, a knowledge-driven algorithm for predicting conformational B-cell epitopes from the amino acid sequence

BACKGROUND

The identification of immunogenic regions on the surface of antigens, which are able to be recognized by antibodies and to trigger an immune response, is a major challenge for the design of new and effective vaccines. The prediction of such regions through computational immunology techniques is a challenging goal, which will ultimately lead to a drastic limitation of the experimental tests required to validate their efficiency. However, current methods are far from being sufficiently reliable and/or applicable on a large scale.

RESULTS

We developed SEPIa, a B-cell epitope predictor from the protein sequence, which is sufficiently fast to be applicable on a large scale. The originality of SEPIa lies in the combination of two classifiers, a naïve Bayesian and a random forest classifier, through a voting algorithm that exploits the advantages of both. It is based on 13 sequence-based features, whose values in a 9-residue sequence window are compiled to predict the epitope/non-epitope state of the central residue. The features are related to the type of amino acid, its conservation in homologous proteins, and its tendency of being exposed to the solvent, soluble, flexible, and disordered. The highest signal is obtained from statistical amino acid preferences, but all 13 features contribute non-negligibly in the predictor. SEPIa's average prediction accuracy is limited, with an AUC score (area under the receiver operating characteristic curve) that reaches 0.65 both in 10-fold cross-validation and on an independent test set. It is nevertheless slightly higher than that of other methods evaluated on the same test set.

CONCLUSIONS

SEPIa was applied to a test protein whose epitopes are known, human β2 adrenergic G-protein-coupled receptor, with promising results. Although the actual AUC score is rather low, many of the predicted epitopes cluster together and overlap the experimental epitope region. The reasons underlying the limitations of SEPIa and of all other B-cell epitope predictors are discussed.

Bioengineering a bacterial pathogen to assemble its own particulate vaccine capable of inducing cellular immunity

Many bacterial pathogens naturally form cellular inclusions. Here the immunogenicity of polyhydroxyalkanoate (PHA) inclusions and their use as particulate vaccines delivering a range of host derived antigens was assessed. Our study showed that PHA inclusions of pathogenic Pseudomonas aeruginosa are immunogenic mediating a specific cell-mediated immune response. Protein engineering of the PHA inclusion forming enzyme by translational fusion of epitopes from vaccine candidates outer membrane proteins OprI, OprF, and AlgE mediated self-assembly of PHA inclusions coated by these selected antigens. Mice vaccinated with isolated PHA inclusions produced a Th1 type immune response characterized by antigen-specific production of IFN-γ and IgG2c isotype antibodies. This cell-mediated immune response was found to be associated with the production of functional antibodies reacting with cells of various P. aeruginosa strains as well as facilitating opsonophagocytic killing. This study showed that cellular inclusions of pathogenic bacteria are immunogenic and can be engineered to display selected antigens suitable to serve as particulate subunit vaccines against infectious diseases.

An Overview of Bioinformatics Tools and Resources in Allergy

The rapidly increasing number of characterized allergens has created huge demands for advanced information storage, retrieval, and analysis. Bioinformatics and machine learning approaches provide useful tools for the study of allergens and epitopes prediction, which greatly complement traditional laboratory techniques. The specific applications mainly include identification of B- and T-cell epitopes, and assessment of allergenicity and cross-reactivity. In order to facilitate the work of clinical and basic researchers who are not familiar with bioinformatics, we review in this chapter the most important databases, bioinformatic tools, and methods with relevance to the study of allergens.

Computer-Aided Antibody Design: An Overview

The use of monoclonal antibody as the next generation protein therapeutics with remarkable success has surged the development of antibody engineering to design molecules for optimizing affinity, better efficacy, greater safety and therapeutic function. Therefore, computational methods have become increasingly important to generate hypotheses, interpret and guide experimental works. In this chapter, we discussed the overall antibody design by computational approches.

Progress and challenges in predicting protein interfaces

The majority of biological processes are mediated via protein-protein interactions. Determination of residues participating in such interactions improves our understanding of molecular mechanisms and facilitates the development of therapeutics. Experimental approaches to identifying interacting residues, such as mutagenesis, are costly and time-consuming and thus, computational methods for this purpose could streamline conventional pipelines. Here we review the field of computational protein interface prediction. We make a distinction between methods which address proteins in general and those targeted at antibodies, owing to the radically different binding mechanism of antibodies. We organize the multitude of currently available methods hierarchically based on required input and prediction principles to provide an overview of the field.

The Relationship between B-cell Epitope and Mimotope Sequences

B-cell epitope is a group of residues which is on the surface of an antigen. It invokes humoral responses. Locating B-cell epitope is important for effective vaccine design, and the development of diagnostic reagents. Mimotope-based B-cell epitope prediction method is a kind of conformational B-cell epitope prediction, and the core idea of the method is mapping the mimotope sequences which are obtained from a random phage display library. However, current mimotope-based B-cell epitope prediction methods cannot maintain a high degree of satisfaction in the circumstances of employing only mimotope sequences. In this study, we did a multi-perspective analysis on parameters for conformational B-cell epitopes and characteristics between epitope and mimotope on a benchmark datasets which contains 67 mimotope sets, corresponding to 40 unique complex structures. In these 67 cases, there are 25 antigen-antibody complexes and 42 protein-protein interactions. We analyzed the two parts separately. The results showed the mimotope sequences do have some epitope features, but there are also some epitope properties that mimotope sequences do not contain. In addition, the numbers of epitope segments with different lengths were obviously different between the antigen-antibody complexes and the protein-protein interactions. This study reflects how similar do mimotope sequence and genuine epitopes have; and evaluates existing mimotope-based B-cell epitope prediction methods from a novel viewpoint.

Design and Antigenic Epitopes Prediction of a New Trial Recombinant Multiepitopic Rotaviral Vaccine: In Silico Analyses

Rotavirus is the major etiologic factor of severe diarrheal disease. Natural infection provides protection against subsequent rotavirus infection and diarrhea. This research presents a new vaccine designed based on computational models. In this study, three types of epitopes are considered-linear, conformational, and combinational-in a proposed model protein. Several studies on rotavirus vaccines have shown that VP6 and VP4 proteins are good candidates for vaccine production. In the present study, a fusion protein was designed as a new generation of rotavirus vaccines by bioinformatics analyses. This model-based study using ABCpred, BCPREDS, Bcepred, and Ellipro web servers showed that the peptide presented in this article has the necessary properties to act as a vaccine. Prediction of linear B-cell epitopes of peptides is helpful to investigate whether these peptides are able to activate humoral immunity.

Specificity, polyspecificity, and heterospecificity of antibody-antigen recognition

The concept of antibody specificity is analyzed and shown to reside in the ability of an antibody to discriminate between two antigens. Initially, antibody specificity was attributed to sequence differences in complementarity determining regions (CDRs), but as increasing numbers of crystallographic antibody-antigen complexes were elucidated, specificity was analyzed in terms of six antigen-binding regions (ABRs) that only roughly correspond to CDRs. It was found that each ABR differs significantly in its amino acid composition and tends to bind different types of amino acids at the surface of proteins. In spite of these differences, the combined preference of the six ABRs does not allow epitopes to be distinguished from the rest of the protein surface. These findings explain the poor success of past and newly proposed methods for predicting protein epitopes. Antibody polyspecificity refers to the ability of one antibody to bind a large variety of epitopes in different antigens, and this property explains how the immune system develops an antibody repertoire that is able to recognize every antigen the system is likely to encounter. Antibody heterospecificity arises when an antibody reacts better with another antigen than with the one used to raise the antibody. As a result, an antibody may sometimes appear to have been elicited by an antigen with which it is unable to react. The implications of antibody polyspecificity and heterospecificity in vaccine development are pointed out.

Functional Exposed Amino Acids of BauA as Potential Immunogen Against Acinetobacter baumannii

Multidrug-resistant Acinetobacter baumannii is recognized to be among the most difficult antimicrobial-resistant gram negative bacilli to control and treat. One of the major challenges that the pathogenic bacteria face in their host is the scarcity of freely available iron. To survive under such conditions, bacteria express new proteins on their outer membrane and also secrete iron chelators called siderophores. Antibodies directed against these proteins associated with iron uptake exert a bacteriostatic or bactericidal effect against A. baumanii in vitro, by blocking siderophore mediated iron uptake pathways. Attempts should be made to discover peptides that could mimic protein epitopes and possess the same immunogenicity as the whole protein. Subsequently, theoretical methods for epitope prediction have been developed leading to synthesis of such peptides that are important for development of immunodiagnostic tests and vaccines. The present study was designed to in silico resolving the major obstacles in the control or in prevention of the diseases caused by A. baumannii. We exploited bioinformatic tools to better understand and characterize the Baumannii acinetobactin utilization structure of A. baumannii and select appropriate regions as effective B cell epitopes. In conclusion, amino acids 26-191 of cork domain and 321-635 of part of the barrel domain including L4-L9, were selected as vaccine candidates. These two regions contain functional exposed amino acids with higher score of B cell epitopes properties. Majority of amino acids are hydrophilic, flexible, accessible, and favorable for B cells from secondary structure point of view.

Conformational B-cell epitope prediction method based on antigen preprocessing and mimotopes analysis

Identification of epitopes which invokes strong humoral responses is an essential issue in the field of immunology. Various computational methods that have been developed based on the antigen structures and the mimotopes these years narrow the search for experimental validation. These methods can be divided into two categories: antigen structure-based methods and mimotope-based methods. Though new methods of the two kinds have been proposed in these years, they cannot maintain a high degree of satisfaction in various circumstances. In this paper, we proposed a new conformational B-cell epitope prediction method based on antigen preprocessing and mimotopes analysis. The method classifies the antigen surface residues into “epitopes” and “nonepitopes” by six epitope propensity scales, removing the “nonepitopes” and using the preprocessed antigen for epitope prediction based on mimotope sequences. The proposed method gives out the mean F score of 0.42 on the testing dataset. When compared with other publicly available servers by using the testing dataset, the new method yields better performance. The results demonstrate the proposed method is competent for the conformational B-cell epitope prediction.

Structural and antigenic features of the synthetic SF23 peptide corresponding to the receptor binding fragment of diphtheria toxin

The SF23 peptide corresponding to the receptor binding fragment of diphtheria toxin (residues 508-530) has been synthesized. This fragment forming a protruding beta hairpin has been chosen because it is the less mutable B-cell epitope. Affine chromatography and ELISA show that antibodies from the sera of persons infected by toxigenic Corynebacterium diphtheriae and those immunized by diphtheria toxoid are able to bind the synthetic SF23 peptide. There are antibodies recognizing the SF23 peptide in the serum of horses hyperimmunized with diphtheria toxoid. Analysis of circular dichroism spectra show formation of beta hairpin by the peptide. Taken together, the results showed that the structure of the less mutable epitope of C. diphtheriae toxin was reproduced by the short SF23 peptide. Since antibodies against that epitope should block its interactions with cellular receptor (heparin-binding epidermal growth factor), the SF23 peptide can be considered as a promising candidate for synthetic vaccine development. Fluorescence quenching studies showed the existence of chloride and phosphate binding sites on the SF23 molecule. Phosphate containing adjuvants (aluminum hydroxyphosphate or aluminum hydroxyphosphate sulfate) are recommended to increase the SF23 immunogenic properties.

Conformational B-cell epitopes prediction from sequences using cost-sensitive ensemble classifiers and spatial clustering

B-cell epitopes are regions of the antigen surface which can be recognized by certain antibodies and elicit the immune response. Identification of epitopes for a given antigen chain finds vital applications in vaccine and drug research. Experimental prediction of B-cell epitopes is time-consuming and resource intensive, which may benefit from the computational approaches to identify B-cell epitopes. In this paper, a novel cost-sensitive ensemble algorithm is proposed for predicting the antigenic determinant residues and then a spatial clustering algorithm is adopted to identify the potential epitopes. Firstly, we explore various discriminative features from primary sequences. Secondly, cost-sensitive ensemble scheme is introduced to deal with imbalanced learning problem. Thirdly, we adopt spatial algorithm to tell which residues may potentially form the epitopes. Based on the strategies mentioned above, a new predictor, called CBEP (conformational B-cell epitopes prediction), is proposed in this study. CBEP achieves good prediction performance with the mean AUC scores (AUCs) of 0.721 and 0.703 on two benchmark datasets (bound and unbound) using the leave-one-out cross-validation (LOOCV). When compared with previous prediction tools, CBEP produces higher sensitivity and comparable specificity values. A web server named CBEP which implements the proposed method is available for academic use.