Benchmarking B cell epitope prediction: underperformance of existing methods

Deep learning of antibody epitopes using positional permutation vectors

Background

The accurate computational prediction of B cell epitopes can vastly reduce the cost and time required for identifying potential epitope candidates for the design of vaccines and immunodiagnostics. However, current computational tools for B cell epitope prediction perform poorly and are not fit-for-purpose, and there remains enormous room for improvement and the need for superior prediction strategies.

Results

Here we propose a novel approach that improves B cell epitope prediction by encoding epitopes as binary positional permutation vectors that represent the position and structural properties of the amino acids within a protein antigen sequence that interact with an antibody. This approach supersedes the traditional method of defining epitopes as scores per amino acid on a protein sequence, where each score reflects each amino acids predicted probability of partaking in a B cell epitope antibody interaction. In addition to defining epitopes as binary positional permutation vectors, the approach also uses the 3D macrostructure features of the unbound protein structures, and in turn uses these features to train another deep learning model on the corresponding antibody-bound protein 3D structures. This enables the algorithm to learn the key structural and physiochemical features of the unbound protein and embedded epitope that initiate the antibody binding process helping to eliminate "induced fit" biases in the training data. We demonstrate that the strategy predicts B cell epitopes with improved accuracy compared to the existing tools. Additionally, we show that this approach reliably identifies the majority of experimentally verified epitopes on the spike protein of SARS-CoV-2 not seen by the model during training and generalizes in a very robust manner on dissimilar data not seen by the model during training.

Conclusions

With the approach described herein, a primary protein sequence and a query positional permutation vector encoding a putative epitope is sufficient to predict B cell epitopes in a reliable manner, potentially advancing the use of computational prediction of B cell epitopes in biomedical research applications.

In Silico Tools for Predicting Novel Epitopes

Identifying antigens within a pathogen is a critical task to develop effective vaccines and diagnostic methods, as well as understanding the evolution and adaptation to host immune responses. Historically, antigenicity was studied with experiments that evaluate the immune response against selected fragments of pathogens. Using this approach, the scientific community has gathered abundant information regarding which pathogenic fragments are immunogenic. The systematic collection of this data has enabled unraveling many of the fundamental rules underlying the properties defining epitopes and immunogenicity, and has resulted in the creation of a large panel of immunologically relevant predictive (in silico) tools. The development and application of such tools have proven to accelerate the identification of novel epitopes within biomedical applications reducing experimental costs. This chapter introduces some basic concepts about MHC presentation, T cell and B cell epitopes, the experimental efforts to determine those, and focuses on state-of-the-art methods for epitope prediction, highlighting their strengths and limitations, and catering instructions for their rational use.

Multi-perspectives and challenges in identifying B-cell epitopes

The identification of B-cell epitopes (BCEs) in antigens is a crucial step in developing recombinant vaccines or immunotherapies for various diseases. Over the past four decades, numerous in silico methods have been developed for predicting BCEs. However, existing reviews have only covered specific aspects, such as the progress in predicting conformational or linear BCEs. Therefore, in this paper, we have undertaken a systematic approach to provide a comprehensive review covering all aspects associated with the identification of BCEs. First, we have covered the experimental techniques developed over the years for identifying linear and conformational epitopes, including the limitations and challenges associated with these techniques. Second, we have briefly described the historical perspectives and resources that maintain experimentally validated information on BCEs. Third, we have extensively reviewed the computational methods developed for predicting conformational BCEs from the structure of the antigen, as well as the methods for predicting conformational epitopes from the sequence. Fourth, we have systematically reviewed the in silico methods developed in the last four decades for predicting linear or continuous BCEs. Finally, we have discussed the overall challenge of identifying continuous or conformational BCEs. In this review, we only listed major computational resources; a complete list with the URL is available from the BCinfo website (https://webs.iiitd.edu.in/raghava/bcinfo/).

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.

Critical review of conformational B-cell epitope prediction methods

Accurate in silico prediction of conformational B-cell epitopes would lead to major improvements in disease diagnostics, drug design and vaccine development. A variety of computational methods, mainly based on machine learning approaches, have been developed in the last decades to tackle this challenging problem. Here, we rigorously benchmarked nine state-of-the-art conformational B-cell epitope prediction webservers, including generic and antibody-specific methods, on a dataset of over 250 antibody-antigen structures. The results of our assessment and statistical analyses show that all the methods achieve very low performances, and some do not perform better than randomly generated patches of surface residues. In addition, we also found that commonly used consensus strategies that combine the results from multiple webservers are at best only marginally better than random. Finally, we applied all the predictors to the SARS-CoV-2 spike protein as an independent case study, and showed that they perform poorly in general, which largely recapitulates our benchmarking conclusions. We hope that these results will lead to greater caution when using these tools until the biases and issues that limit current methods have been addressed, promote the use of state-of-the-art evaluation methodologies in future publications and suggest new strategies to improve the performance of conformational B-cell epitope prediction methods.

In silico study to predict promiscuous peptides for immunodiagnosis of cystic echinococcosis

Background

Cystic echinococcosis (CE), caused by Echinococcus granulosus, is a major zoonotic disease that causes significant human morbidity and mortality. This cosmopolitan disease is difficult to diagnose, treat, and control. So far, crude extracts of hydatid cyst fluid containing antigen B or antigen 5 have been used as the primary antigenic source for its immunodiagnosis. The main issue is that it reacts with sera from people infected with other helminths. There is currently no standard, specific, or sensitive test for disease diagnosis, and no human vaccine has been reported.

Aims and Objectives

Considering the need for efficient immunization and/or immunodiagnosis, six E. granulosus antigens, antigen 5, antigen B, heat shock proteins such as Hsp-8 and Hsp-90, phosphoenolpyruvate carboxykinase, and tetraspanin-1, were chosen.

Materials and Methods

Using various in silico tools, T cell and B cell epitopes (promiscuous peptides) were predicted by targeting antigen 5, antigen B, heat shock proteins such as Hsp-8 and Hsp-90, phosphoenolpyruvate carboxykinase, and tetraspanin-1.

Results

There are twelve promiscuous peptides with overlapping human leukocyte antigen (HLA) class-I, class-II, and conformational B cell epitopes. Such immunodominant peptides could be useful as subunit vaccines. Furthermore, six peptides specific for E. granulosus were also discovered, which may prove to be important markers in the diagnosis of CE, potentially preventing misdiagnosis and mismanagement.

Conclusion

These epitopes may be the most important vaccine targets in E. granulosus because they have the most promiscuous peptides and B cell epitopes, as well as the highest affinity for different alleles, as determined by docking scores. However, additional research using in vitro and in vivo models is undertaken.

A Promising Tool in Serological Diagnosis: Current Research Progress of Antigenic Epitopes in Infectious Diseases

Infectious diseases, caused by various pathogens in the clinic, threaten the safety of human life, are harmful to physical and mental health, and also increase economic burdens on society. Infections are a complex mechanism of interaction between pathogenic microorganisms and their host. Identification of the causative agent of the infection is vital for the diagnosis and treatment of diseases. Etiological laboratory diagnostic tests are therefore essential to identify pathogens. However, due to its rapidity and automation, the serological diagnostic test is among the methods of great significance for the diagnosis of infections with the basis of detecting antigens or antibodies in body fluids clinically. Epitopes, as a special chemical group that determines the specificity of antigens and the basic unit of inducing immune responses, play an important role in the study of immune responses. Identifying the epitopes of a pathogen may contribute to the development of a vaccine to prevent disease, the diagnosis of the corresponding disease, and the determination of different stages of the disease. Moreover, both the preparation of neutralizing antibodies based on useful epitopes and the assembly of several associated epitopes can be used in the treatment of disease. Epitopes can be divided into B cell epitopes and T cell epitopes; B cell epitopes stimulate the body to produce antibodies and are therefore commonly used as targets for the design of serological diagnostic experiments. Meanwhile, epitopes can fall into two possible categories: linear and conformational. This article reviews the role of B cell epitopes in the clinical diagnosis of infectious diseases.

Prediction of B cell epitopes in proteins using a novel sequence similarity-based method

Prediction of B cell epitopes that can replace the antigen for antibody production and detection is of great interest for research and the biotech industry. Here, we developed a novel BLAST-based method to predict linear B cell epitopes. To that end, we generated a BLAST-formatted database upon a dataset of 62,730 known linear B cell epitope sequences and considered as a B cell epitope any peptide sequence producing ungapped BLAST hits to this database with identity ≥ 80% and length ≥ 8. We examined B cell epitope predictions by this method in tenfold cross-validations in which we considered various types of non-B cell epitopes, including 62,730 peptide sequences with verified negative B cell assays. As a result, we obtained values of accuracy, specificity and sensitivity of 72.54 ± 0.27%, 81.59 ± 0.37% and 63.49 ± 0.43%, respectively. In an independent dataset incorporating 503 B cell epitopes, this method reached accuracy, specificity and sensitivity of 74.85%, 99.20% and 50.50%, respectively, outperforming state-of-the-art methods to predict linear B cell epitopes. We implemented this BLAST-based approach to predict B cell epitopes at http://imath.med.ucm.es/bepiblast.

In vivo study of the immune response to bioengineered spider silk spheres

Bioengineered MS1 silk is derived from major ampullate spidroin 1 (MaSp1) from the spider Nephila clavipes. The MS1 silk was functionalized with the H2.1 peptide to target Her2-overexpressing cancer cells. The immunogenic potential of drug carriers made from MS1-type silks was investigated. The silk spheres were administered to healthy mice, and then (i) the phenotypes of the immune cells that infiltrated the Matrigel plugs containing spheres (implanted subcutaneously), (ii) the presence of silk-specific antibodies (after two intravenous injections of the spheres), (iii) the splenocyte phenotypes and their activity after restimulation ex vivo in terms of proliferation and cytokine secretion (after single intravenous injection of the spheres) were analyzed. Although the immunogenicity of MS1 particles was minor, the H2.1MS1 spheres attracted higher levels of B lymphocytes, induced a higher anti-silk antibody titer, and, after ex vivo restimulation, caused the activation of splenocytes to proliferate and express more IFN-γ and IL-10 compared with the PBS and MS1 groups. Although the H2.1MS1 spheres triggered a certain degree of an immunological response, multiple injections (up to six times) neither hampered the carrier-dependent specific drug delivery nor induced toxicity, as previously indicated in a mouse breast cancer model. Both findings indicate that a drug delivery system based on MS1-type silk has great potential for the treatment of cancer and other conditions.

A framework for predicting variable-length epitopes of human-adapted viruses using machine learning methods

The coronavirus disease 2019 pandemic has alerted people of the threat caused by viruses. Vaccine is the most effective way to prevent the disease from spreading. The interaction between antibodies and antigens will clear the infectious organisms from the host. Identifying B-cell epitopes is critical in vaccine design, development of disease diagnostics and antibody production. However, traditional experimental methods to determine epitopes are time-consuming and expensive, and the predictive performance using the existing in silico methods is not satisfactory. This paper develops a general framework to predict variable-length linear B-cell epitopes specific for human-adapted viruses with machine learning approaches based on Protvec representation of peptides and physicochemical properties of amino acids. QR decomposition is incorporated during the embedding process that enables our models to handle variable-length sequences. Experimental results on large immune epitope datasets validate that our proposed model's performance is superior to the state-of-the-art methods in terms of AUROC (0.827) and AUPR (0.831) on the testing set. Moreover, sequence analysis also provides the results of the viral category for the corresponding predicted epitopes with high precision. Therefore, this framework is shown to reliably identify linear B-cell epitopes of human-adapted viruses given protein sequences and could provide assistance for potential future pandemics and epidemics.

Compilation of parasitic immunogenic proteins from 30 years of published research using machine learning and natural language processing

The World Health Organisation reported in 2020 that six of the top 10 sources of death in low-income countries are parasites. Parasites are microorganisms in a relationship with a larger organism, the host. They acquire all benefits at the host’s expense. A disease develops if the parasitic infection disrupts normal functioning of the host. This disruption can range from mild to severe, including death. Humans and livestock continue to be challenged by established and emerging infectious disease threats. Vaccination is the most efficient tool for preventing current and future threats. Immunogenic proteins sourced from the disease-causing parasite are worthwhile vaccine components (subunits) due to reliable safety and manufacturing capacity. Publications with ‘subunit vaccine’ in their title have accumulated to thousands over the last three decades. However, there are possibly thousands more reporting immunogenicity results without mentioning ‘subunit’ and/or ‘vaccine’. The exact number is unclear given the non-standardised keywords in publications. The study aim is to identify parasite proteins that induce a protective response in an animal model as reported in the scientific literature within the last 30 years using machine learning and natural language processing. Source code to fulfil this aim and the vaccine candidate list obtained is made available.

A combined application of molecular docking technology and indirect ELISA for the serodiagnosis of bovine tuberculosis

BACKGROUND

There is an urgent need to find reliable and rapid bovine tuberculosis (bTB) diagnostics in response to the rising prevalence of bTB worldwide. Toll-like receptor 2 (TLR2) recognizes components of bTB and initiates antigen-presenting cells to mediate humoral immunity. Evaluating the affinity of antigens with TLR2 can form the basis of a new method for the diagnosis of bTB based on humoral immunity.

OBJECTIVES

To develop a reliable and rapid strategy to improve diagnostic tools for bTB.

METHODS

In this study, we expressed and purified the sixteen bTB-specific recombinant proteins in Escherichia coli. The two antigenic proteins, MPT70 and MPT83, which were most valuable for serological diagnosis of bTB were screened. Molecular docking technology was used to analyze the affinity of MPT70, MPT83, dominant epitope peptide of MPT70 (M1), and dominant epitope peptide MPT83 (M2) with TLR2, combined with the detection results of enzyme-linked immunosorbent assay to evaluate the molecular docking effect.

RESULTS

The results showed that interaction surface Cα-atom root mean square deviation of proteins (M1, M2, MPT70, MPT83)-TLR2 protein are less than 2.5 A, showing a high affinity. It is verified by clinical serum samples that MPT70, MPT83, MPT70-MPT83 showed good diagnostic potential for the detection of anti-bTB IgG and M1, M2 can replace the whole protein as the detection antigen.

CONCLUSIONS

Molecular docking to evaluate the affinity of bTB protein and TLR2 combined with ELISA provides new insights for the diagnosis of bTB.

LBCEPred: a machine learning model to predict linear B-cell epitopes

B-cell epitopes have the capability to recognize and attach to the surface of antigen receptors to stimulate the immune system against pathogens. Identification of B-cell epitopes from antigens has a great significance in several biomedical and biotechnological applications, provides support in the development of therapeutics, design and development of an epitope-based vaccine and antibody production. However, the identification of epitopes with experimental mapping approaches is a challenging job and usually requires extensive laboratory efforts. However, considerable efforts have been placed for the identification of epitopes using computational methods in the recent past but deprived of considerable achievements. In this study, we present LBCEPred, a python-based web-tool (http://lbcepred.pythonanywhere.com/), build with random forest classifier and statistical moment-based descriptors to predict the B-cell epitopes from the protein sequences. LBECPred outperforms all sequence-based available models that are currently in use for the B-cell epitopes prediction, with 0.868 accuracy value and 0.934 area under the curve. Moreover, the prediction performance of proposed models compared to other state-of-the-art models is 56.3% higher on average for Mathews Correlation Coefficient. LBCEPred is easy to use tool even for novice users and has also shown the models stability and reliability, thus we believe in its significant contribution to the research community and the area of bioinformatics.

Machine Learning Techniques for the Prediction of B-Cell and T-Cell Epitopes as Potential Vaccine Targets with a Specific Focus on SARS-CoV-2 Pathogen: A Review

The only part of an antigen (a protein molecule found on the surface of a pathogen) that is composed of epitopes specific to T and B cells is recognized by the human immune system (HIS). Identification of epitopes is considered critical for designing an epitope-based peptide vaccine (EBPV). Although there are a number of vaccine types, EBPVs have received less attention thus far. It is important to mention that EBPVs have a great deal of untapped potential for boosting vaccination safety—they are less expensive and take a short time to produce. Thus, in order to quickly contain global pandemics such as the ongoing outbreak of coronavirus disease 2019 (COVID-19) caused by the severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), as well as epidemics and endemics, EBPVs are considered promising vaccine types. The high mutation rate of SARS-CoV-2 has posed a great challenge to public health worldwide because either the composition of existing vaccines has to be changed or a new vaccine has to be developed to protect against its different variants. In such scenarios, time being the critical factor, EBPVs can be a promising alternative. To design an effective and viable EBPV against different strains of a pathogen, it is important to identify the putative T- and B-cell epitopes. Using the wet-lab experimental approach to identify these epitopes is time-consuming and costly because the experimental screening of a vast number of potential epitope candidates is required. Fortunately, various available machine learning (ML)-based prediction methods have reduced the burden related to the epitope mapping process by decreasing the potential epitope candidate list for experimental trials. Moreover, these methods are also cost-effective, scalable, and fast. This paper presents a systematic review of various state-of-the-art and relevant ML-based methods and tools for predicting T- and B-cell epitopes. Special emphasis is placed on highlighting and analyzing various models for predicting epitopes of SARS-CoV-2, the causative agent of COVID-19. Based on the various methods and tools discussed, future research directions for epitope prediction are presented.

Organism-specific training improves performance of linear B-cell epitope prediction

MOTIVATION

In silico identification of linear B-cell epitopes represents an important step in the development of diagnostic tests and vaccine candidates, by providing potential high-probability targets for experimental investigation. Current predictive tools were developed under a generalist approach, training models with heterogeneous datasets to develop predictors that can be deployed for a wide variety of pathogens. However, continuous advances in processing power and the increasing amount of epitope data for a broad range of pathogens indicate that training organism or taxon-specific models may become a feasible alternative, with unexplored potential gains in predictive performance.

RESULTS

This article shows how organism-specific training of epitope prediction models can yield substantial performance gains across several quality metrics when compared to models trained with heterogeneous and hybrid data, and with a variety of widely used predictors from the literature. These results suggest a promising alternative for the development of custom-tailored predictive models with high predictive power, which can be easily implemented and deployed for the investigation of specific pathogens.

AVAILABILITY AND IMPLEMENTATION

The data underlying this article, as well as the full reproducibility scripts, are available at https://github.com/fcampelo/OrgSpec-paper. The R package that implements the organism-specific pipeline functions is available at https://github.com/fcampelo/epitopes.

SUPPLEMENTARY INFORMATION

Supplementary materials are available at Bioinformatics online.

EpitopeVec: Linear Epitope Prediction Using Deep Protein Sequence Embeddings

Motivation

B-cell epitopes (BCEs) play a pivotal role in the development of peptide vaccines, immuno-diagnostic reagents and antibody production, and thus in infectious disease prevention and diagnostics in general. Experimental methods used to determine BCEs are costly and time-consuming. Therefore, it is essential to develop computational methods for the rapid identification of BCEs. Although several computational methods have been developed for this task, generalizability is still a major concern, where cross-testing of the classifiers trained and tested on different datasets has revealed accuracies of 51–53%.

Results

We describe a new method called EpitopeVec, which uses a combination of residue properties, modified antigenicity scales, and protein language model-based representations (protein vectors) as features of peptides for linear BCE predictions. Extensive benchmarking of EpitopeVec and other state-of-the-art methods for linear BCE prediction on several large and small datasets, as well as cross-testing, demonstrated an improvement in the performance of EpitopeVec over other methods in terms of accuracy and area under the curve. As the predictive performance depended on the species origin of the respective antigens (viral, bacterial and eukaryotic), we also trained our method on a large viral dataset to create a dedicated linear viral BCE predictor with improved cross-testing performance.

Availability and implementation

The software is available at https://github.com/hzi-bifo/epitope-prediction.

Supplementary information

Supplementary data are available at Bioinformatics online.

The Recombinant Expression Proteins FnBP and ClfA From Staphylococcus aureus in Addition to GapC and Sip From Streptococcus agalactiae Can Protect BALB/c Mice From Bacterial Infection

Dairy cow mastitis is a serious disease that is mainly caused by intramammary infection with Staphylococcus aureus and Streptococcus agalactiae [group B streptococcus (GBS)]. FnBP and ClfA are the virulence factors of S. aureus, while GapC is the respective factor for S. agalactiae. Sip is a highly immunogenic protein, and it is conserved in all GBS serotypes. In this study, we analyzed the abovementioned four genes prepared a FnBP+ClfA chimeric protein (FC), a GapC+Sip chimeric protein (GS), and a FnBP+ClfA+GapC+Sip chimeric protein (FCGS) based on the antigenic sites to evaluate their use in vaccine development. After expression and purification of the recombinant proteins in Escherichia coli, BALB/c mice were immunized with them to examine resistance effects. The total lethal and half lethal doses of S. aureus and S. agalactiae were then measured, and the immunoprotective effects of the fusion proteins were evaluated. The FC and FCGS chimeric proteins could induce mice to produce high levels of antibodies, and bacterial loads were significantly reduced in the spleens and livers after challenge. After immunization with FCGS, the recipients resisted the attacks of both S. aureus and S. agalactiae, indicating the potential of the fusion protein as a mastitis vaccine.

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.

Linear B-Cell Epitope Prediction for In Silico Vaccine Design: A Performance Review of Methods Available via Command-Line Interface

Linear B-cell epitope prediction research has received a steadily growing interest ever since the first method was developed in 1981. B-cell epitope identification with the help of an accurate prediction method can lead to an overall faster and cheaper vaccine design process, a crucial necessity in the COVID-19 era. Consequently, several B-cell epitope prediction methods have been developed over the past few decades, but without significant success. In this study, we review the current performance and methodology of some of the most widely used linear B-cell epitope predictors which are available via a command-line interface, namely, BcePred, BepiPred, ABCpred, COBEpro, SVMTriP, LBtope, and LBEEP. Additionally, we attempted to remedy performance issues of the individual methods by developing a consensus classifier, which combines the separate predictions of these methods into a single output, accelerating the epitope-based vaccine design. While the method comparison was performed with some necessary caveats and individual methods might perform much better for specialized datasets, we hope that this update in performance can aid researchers towards the choice of a predictor, for the development of biomedical applications such as designed vaccines, diagnostic kits, immunotherapeutics, immunodiagnostic tests, antibody production, and disease diagnosis and therapy.

Design of a Peptide-Carrier Vaccine Based on the Highly Immunogenic Fasciola hepatica Leucine Aminopeptidase

Many studies have shown that the degree of organization and repetitiveness of an antigen correlates with its efficiency to induce a B-cell response and production of neutralizing antibodies. Here we describe the design of a chimeric protein based on the hexamer form of the highly immunogenic Fasciola hepatica leucine aminopeptidase as a carrier system of small peptides with potential use as a multiepitope vaccine.

Deimmunization of protein therapeutics - Recent advances in experimental and computational epitope prediction and deletion

Biotherapeutics, and antimicrobial proteins in particular, are of increasing interest for human medicine. An important challenge in the development of such therapeutics is their potential immunogenicity, which can induce production of anti-drug-antibodies, resulting in altered pharmacokinetics, reduced efficacy, and potentially severe anaphylactic or hypersensitivity reactions. For this reason, the development and application of effective deimmunization methods for protein drugs is of utmost importance. Deimmunization may be achieved by unspecific shielding approaches, which include PEGylation, fusion to polypeptides (e.g., XTEN or PAS), reductive methylation, glycosylation, and polysialylation. Alternatively, the identification of epitopes for T cells or B cells and their subsequent deletion through site-directed mutagenesis represent promising deimmunization strategies and can be accomplished through either experimental or computational approaches. This review highlights the most recent advances and current challenges in the deimmunization of protein therapeutics, with a special focus on computational epitope prediction and deletion tools.

Computational Immune Proteomics Approach to Target COVID-19

Progress of the omics platforms widens their application to diverse fields, including immunology. This enables a deeper level of knowledge and the provision of a huge amount of data for which management and fruitful integration with the past evidence requires a steadily growing computational effort. In light of this, immunoinformatics emerges as a new discipline placed in between the traditional lab-based investigations and the computational analysis of the biological data. Immunoinformatics make use of tailored bioinformatics tools and data repositories to facilitate the analysis of data from a plurality of disciplines and help drive novel research hypotheses and in silico screening investigations in a fast, reliable, and cost-effective manner. Such computational immunoproteomics studies may as well prepare and guide lab-based investigations, representing valuable technology for the investigation of novel pathogens, to tentatively evaluate specificity of diagnostic products, to forecast on potential adverse effects of vaccines and to reduce the use of animal models. The present manuscript provides an overview of the COVID-19 pandemic and reviews the state of the art of the omics technologies employed in fighting SARS-CoV-2 infections. A comprehensive description of the immunoinformatics approaches and its potential role in contrasting COVID-19 pandemics is provided.

Sequence analysis of digestion-resistant peptides may be an efficient strategy for studying the linear epitopes of Jug r 1, the major walnut allergen

Jug r 1, the major allergen of walnut, triggers severe allergic reactions through epitopes. Hence, research on the efficient strategy for analyzing the linear epitopes of Jug r 1 are necessary. In this work, bioinformatics analysis was used to predict the linear epitopes of Jug r 1. Overlapping peptide synthesis was used to map linear epitopes. In vitro simulated gastrointestinal digestion and HPLC-MS/MS were used to identify digestion-resistant peptides. The results showed that six predicted linear epitopes were AA28-35, AA42-49, AA55-62, AA65-73, AA97-104, and AA109-121. AA16-30 and AA125-139 were identified by the sera of walnut allergic patients. Five digestion-resistant peptides were AA19-33, AA40-45, AA54-74, AA96-106, and AA117-137. The predicted results only included one of the linear epitopes identified by sera, while the digestion-resistant peptides covered all. Therefore, the digestion-resistant property of food allergens may be a promising direction for studying the linear epitopes of Jug r 1.

Deep learning methods improve linear B-cell epitope prediction

Background

B-cell epitopes play important roles in vaccine design, clinical diagnosis, and antibody production. Although some models have been developed to predict linear or conformational B-cell epitopes, their performance is still unsatisfactory. Hundreds of thousands of linear B-cell epitope data have accumulated in the Immune Epitope Database (IEDB). These data can be explored using the deep learning methods, in order to create better predictive models for linear B-cell epitopes.

Results

After data cleaning, we obtained 240,563 peptide samples with experimental evidence from the IEDB database, including 25,884 linear B-cell epitopes and 214,679 non-epitopes. Based on the peptide center, we adapted each peptide to the same length by trimming or extending. A random portion of the data, with the same amount of epitopes and non-epitopes, were set aside as test dataset. Then a same number of epitopes and non-epitopes were randomly selected from the remaining data to build a classifier with the feedforward deep neural network. We built eleven classifiers to form an ensemble prediction model. The model will report a peptide as an epitope if it was classified as epitope by all eleven classifiers. Then we used the test data set to evaluate the performance of the model using the area value under the receiver operating characteristic (ROC) curve (AUC) as an indicator. We established 40 models to predict linear B-cell epitopes of length from 11 to 50 separately, and found that the AUC value increased with the length and tended to be stable when the length was 38. Repeated results showed that the models constructed by this method were robust. Tested on our and two public test datasets, our models outperformed current major models available.

Conclusions

We applied the feedforward deep neural network to the large amount of linear B-cell epitope data with experimental evidence in the IEDB database, and constructed ensemble prediction models with better performance than the current major models available. We named the models as DLBEpitope and provided web services using the models at http://ccb1.bmi.ac.cn:81/dlbepitope/.

Designing a Recombinant Multi-Epitope Antigen of Echinococcus granulosus to Diagnose Human Cystic Echinococcosis

BACKGROUND

Cystic echinococcosis can cause severe disease and probable death in humans. Epitopes of its antigens play a key role in the sensitivity and specificity of immunodiagnostic tests.

METHODS

Epitope prediction software programs predict the most antigenic linear B-cell epitopes of AgB (8 kD), Ag5, and Ag95. Six such epitopes were predicted and connected by "Gly-Ser" linker and synthesized. The purity of the concentrated recombinant multi-epitope protein was assessed by 15% SDS-PAGE. Overall, 186 serum samples were collected from the Loghman Hakim Hospital and different laboratories, Tehran, Iran, from July 2016 to February 2017. Patients infected with hepatic hydatid cysts, patients infected by other parasites and viruses, and healthy individuals were used to detect the anti-CE IgG using recombinant multi-epitope protein.

RESULTS

Forty-one samples out of 43 cases of hydatidosis were diagnosed correctly as positive, and two were negative. In addition, six negative cases of healthy individual group were diagnosed as positive and negative with rMEP-ELISA and the commercial kit, respectively. Therefore, these six samples were considered as false positive using our method. In addition, a diagnostic sensitivity of 95.3% (95% CI, 84.19% to 99.43%) and a specificity of 95.0% (95% CI, 89.43% to 98.14%) were obtained using optimum cutoff value (0.20). The sensitivity and specificity of the commercial kit was 100%.

CONCLUSION

Our findings showed high diagnostic accuracy of the ELISA test using the developed recombinant protein, which encourages the use of this recombinant multi-epitope protein for rapid serological diagnosis of hydatidosis.

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/ .

Benchmarking the PEPOP methods for mimicking discontinuous epitopes

Background

Computational methods provide approaches to identify epitopes in protein Ags to help characterizing potential biomarkers identified by high-throughput genomic or proteomic experiments. PEPOP version 1.0 was developed as an antigenic or immunogenic peptide prediction tool. We have now improved this tool by implementing 32 new methods (PEPOP version 2.0) to guide the choice of peptides that mimic discontinuous epitopes and thus potentially able to replace the cognate protein Ag in its interaction with an Ab. In the present work, we describe these new methods and the benchmarking of their performances.

Results

Benchmarking was carried out by comparing the peptides predicted by the different methods and the corresponding epitopes determined by X-ray crystallography in a dataset of 75 Ag-Ab complexes. The Sensitivity (Se) and Positive Predictive Value (PPV) parameters were used to assess the performance of these methods. The results were compared to that of peptides obtained either by chance or by using the SUPERFICIAL tool, the only available comparable method.

Conclusion

The PEPOP methods were more efficient than, or as much as chance, and 33 of the 34 PEPOP methods performed better than SUPERFICIAL. Overall, “optimized” methods (tools that use the traveling salesman problem approach to design peptides) can predict peptides that best match true epitopes in most cases.

The Immune Epitope Database and Analysis Resource Program 2003-2018: reflections and outlook

The Immune Epitope Database and Analysis Resource (IEDB) contains information related to antibodies and T cells across an expansive scope of research fields (infectious diseases, allergy, autoimmunity, and transplantation). Capture and representation of the data to reflect growing scientific standards and techniques have required continual refinement of our rigorous curation and query and reporting processes beginning with the automated classification of over 28 million PubMed abstracts, and resulting in easily searchable data from over 20,000 published manuscripts. Data related to MHC binding and elution, nonpeptidics, natural processing, receptors, and 3D structure is first captured through manual curation and subsequently maintained through recuration to reflect evolving scientific standards. Upon promotion to the free, public database, users can query and export records of specific relevance via the online web portal which undergoes iterative development to best enable efficient data access. In parallel, the companion Analysis Resource site hosts a variety of tools that assist in the bioinformatic analyses of epitopes and related structures, which can be applied to IEDB-derived and independent datasets alike. Available tools are classified into two categories: analysis and prediction. Analysis tools include epitope clustering, sequence conservancy, and more, while prediction tools cover T and B cell epitope binding, immunogenicity, and TCR/BCR structures. In addition to these tools, benchmarking servers which allow for unbiased performance comparison are also offered. In order to expand and support the user-base of both the database and Analysis Resource, the research team actively engages in community outreach through publication of ongoing work, conference attendance and presentations, hosting of user workshops, and the provision of online help. This review provides a description of the IEDB database infrastructure, curation and recuration processes, query and reporting capabilities, the Analysis Resource, and our Community Outreach efforts, including assessment of the impact of the IEDB across the research community.

Immunoinformatics: In Silico Approaches and Computational Design of a Multi-epitope, Immunogenic Protein

Immunoinformatics is a new critical field with several tools and databases that conduct the eyesight of experimental selection and facilitate analysis of the great amount of immunologic data obtained from experimental researches and helps to design and introducing new hypothesis. Given these visages, immunoinformatics seems to be the way that develop and progress the immunological research. Bioinformatics methods and applications are successfully employed in vaccine informatics to assist different sites of the preclinical, clinical, and post-licensure vaccine enterprises. On the other hand, the progression of molecular biology and immunology caused epitope vaccines have become the focus of research on molecular vaccines. Moreover, reverse vaccinology could improve vaccine production and vaccination protocols by in silico prediction of protein-vaccine candidates from genome sequences. B- and T-cell immune epitopes could be predicted by immunoinformatics algorithms and computational methods to improve the vaccine design, protective immunity analysis, assessment of vaccine safety and efficacy, and immunization modeling. This review aims to discuss the power of computational approaches in vaccine design and their relevance to the development of effective vaccines. Furthermore, the various divisions of this field and available tools in each item are introduced and reviewed.

PEPOP 2.0: new approaches to mimic non-continuous epitopes

BACKGROUND

Bioinformatics methods are helpful to identify new molecules for diagnostic or therapeutic applications. For example, the use of peptides capable of mimicking binding sites has several benefits in replacing a protein which is difficult to produce, or toxic. Using peptides is less expensive. Peptides are easier to manipulate, and can be used as drugs. Continuous epitopes predicted by bioinformatics tools are commonly used and these sequential epitopes are used as is in further experiments. Numerous discontinuous epitope predictors have been developed but only two bioinformatics tools have been proposed so far to predict peptide sequences: Superficial and PEPOP 2.0. PEPOP 2.0 can generate series of peptide sequences that can replace continuous or discontinuous epitopes in their interaction with their cognate antibody.

RESULTS

We have developed an improved version of PEPOP (PEPOP 2.0) dedicated to answer to experimentalists' need for a tool able to handle proteins and to turn them into peptides. The PEPOP 2.0 web site has been reorganized by peptide prediction category and is therefore better formulated to experimental designs. Since the first version of PEPOP, 32 new methods of peptide design were developed. In total, PEPOP 2.0 proposes 35 methods in which 34 deal specifically with discontinuous epitopes, the most represented epitope type in nature.

CONCLUSION

Through the presentation of its user-friendly, well-structured new web site conceived in close proximity to experimentalists, we report original methods that show how PEPOP 2.0 can assist biologists in dealing with discontinuous epitopes.

Vaccination challenges and strategies against long-lived Toxoplasma gondii

Since the discovery of Toxoplasma gondii in 1908, it is estimated that one-third of the global population has been exposed to this ubiquitous intracellular protozoan. The complex life cycle of T. gondii has enabled itself to overcome stress and transmit easily within a broad host range thus achieving a high seroprevalence worldwide. To date, toxoplasmosis remains one of the most prevalent HIV-associated opportunistic central nervous system infections. This review presents a comprehensive overview of different vaccination approaches ranging from traditional inactivated whole-T. gondii vaccines to the popular DNA vaccines. Extensive discussions are made to highlight the challenges in constructing these vaccines, selecting adjuvants as well as delivery methods, immunisation approaches and developing study models. Herein we also deliberate over the latest and promising enhancement strategies that can address the limitations in developing an effective T. gondii prophylactic vaccine.

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.

Requirements for Empirical Immunogenicity Trials, Rather than Structure-Based Design, for Developing an Effective HIV Vaccine

The claim that it is possible to rationally design a structure-based HIV-1 vaccine is based on misconceptions regarding the nature of protein epitopes and of immunological specificity. Attempts to use reverse vaccinology to generate an HIV-1 vaccine on the basis of the structure of viral epitopes bound to monoclonal neutralizing antibodies have failed so far because it was not possible to extrapolate from an observed antigenic structure to the immunogenic structure required in a vaccine. Vaccine immunogenicity depends on numerous extrinsic factors such as the host immunoglobulin gene repertoire, the presence of various cellular and regulatory mechanisms in the immunized host and the process of antibody affinity maturation. All these factors played a role in the appearance of the neutralizing antibody used to select the epitope to be investigated as potential vaccine immunogen, but they cannot be expected to be present in identical form in the host to be vaccinated. It is possible to rationally design and optimize an epitope to fit one particular antibody molecule or to improve the paratope binding efficacy of a monoclonal antibody intended for passive immunotherapy. What is not possible is to rationally design an HIV-1 vaccine immunogen that will elicit a protective polyclonal antibody response of predetermined efficacy. An effective vaccine immunogen can only be discovered by investigating experimentally the immunogenicity of a candidate molecule and demonstrating its ability to induce a protective immune response. It cannot be discovered by determining which epitopes of an engineered antigen molecule are recognized by a neutralizing monoclonal antibody. This means that empirical immunogenicity trials rather than structural analyses of antigens offer the best hope of discovering an HIV-1 vaccine.

Computational B-cell epitope identification and production of neutralizing murine antibodies against Atroxlysin-I

Epitope identification is essential for developing effective antibodies that can detect and neutralize bioactive proteins. Computational prediction is a valuable and time-saving alternative for experimental identification. Current computational methods for epitope prediction are underused and undervalued due to their high false positive rate. In this work, we targeted common properties of linear B-cell epitopes identified in an individual protein class (metalloendopeptidases) and introduced an alternative method to reduce the false positive rate and increase accuracy, proposing to restrict predictive models to a single specific protein class. For this purpose, curated epitope sequences from metalloendopeptidases were transformed into frame-shifted Kmers (3 to 15 amino acid residues long). These Kmers were decomposed into a matrix of biochemical attributes and used to train a decision tree classifier. The resulting prediction model showed a lower false positive rate and greater area under the curve when compared to state-of-the-art methods. Our predictions were used for synthesizing peptides mimicking the predicted epitopes for immunization of mice. A predicted linear epitope that was previously undetected by an experimental immunoassay was able to induce neutralizing-antibody production in mice. Therefore, we present an improved prediction alternative and show that computationally identified epitopes can go undetected during experimental mapping.

In silico-guided sequence modifications of K-ras epitopes improve immunological outcome against G12V and G13D mutant KRAS antigens

Background

Somatic point substitution mutations in the KRAS proto-oncogene primarily affect codons 12/13 where glycine is converted into other amino acids, and are highly prevalent in pancreatic, colorectal, and non-small cell lung cancers. These cohorts are non-responsive to anti-EGFR treatments, and are left with non-specific chemotherapy regimens as their sole treatment options. In the past, the development of peptide vaccines for cancer treatment was reported to have poor AT properties when inducing immune responses. Utilization of bioinformatics tools have since become an interesting approach in improving the design of peptide vaccines based on T- and B-cell epitope predictions.

Methods

In this study, the region spanning exon 2 from the 4th to 18th codon within the peptide sequence of wtKRAS was chosen for sequence manipulation. Mutated G12V and G13D K-ras controls were generated in silico, along with additional single amino acid substitutions flanking the original codon 12/13 mutations. IEDB was used for assessing human and mouse MHC class I/II epitope predictions, as well as linear B-cell epitopes predictions, while RNA secondary structure prediction was performed via CENTROIDFOLD. A scoring and ranking system was established in order to shortlist top mimotopes whereby normalized and reducing weighted scores were assigned to peptide sequences based on seven immunological parameters. Among the top 20 ranked peptide sequences, peptides of three mimotopes were synthesized and subjected to in vitro and in vivo immunoassays. Mice PBMCs were treated in vitro and subjected to cytokine assessment using CBA assay. Thereafter, mice were immunized and sera were subjected to IgG-based ELISA.

Results

In silico immunogenicity prediction using IEDB tools shortlisted one G12V mimotope (68-V) and two G13D mimotopes (164-D, 224-D) from a total of 1,680 candidates. Shortlisted mimotopes were predicted to promote high MHC-II and -I affinities with optimized B-cell epitopes. CBA assay indicated that: 224-D induced secretions of IL-4, IL-5, IL-10, IL-12p70, and IL-21; 164-D triggered IL-10 and TNF-α; while 68-V showed no immunological responses. Specific-IgG sera titers against mutated K-ras antigens from 164-D immunized Balb/c mice were also elevated post first and second boosters compared to wild-type and G12/G13 controls.

Discussion

In silico-guided predictions of mutated K-ras T- and B-cell epitopes were successful in identifying two immunogens with high predictive scores, Th-bias cytokine induction and IgG-specific stimulation. Developments of such immunogens are potentially useful for future immunotherapeutic and diagnostic applications against KRAS(+) malignancies, monoclonal antibody production, and various other research and development initiatives.

A novel synthetic peptide microarray assay detects Chlamydia species-specific antibodies in animal and human sera

Serological analysis of Chlamydia (C.) spp. infections is still mainly based on micro-immunofluorescence and ELISA. To overcome the limitations of conventional serology, we have designed a novel microarray carrying 52 synthetic peptides representing B-cell epitopes from immunodominant proteins of all 11 chlamydial species. The new assay has been validated using monospecific mouse hyperimmune sera. Subsequently, serum samples from cattle, sheep and humans with a known history of chlamydial infection were examined. For instance, the specific humoral response of sheep to treatment with a C. abortus vaccine has been visualized against a background of C. pecorum carriership. In samples from humans, dual infection with C. trachomatis and C. pneumoniae could be demonstrated. The experiments revealed that the peptide microarray assay was capable of simultaneously identifying specific antibodies to each Chlamydia spp. The actual assay represents an open platform test that can be complemented through future advances in Chlamydia proteome research. The concept of the highly parallel multi-antigen microarray proven in this study has the potential to enhance our understanding of antibody responses by defining not only a single quantitative response, but also the pattern of this response. The added value of using peptide antigens will consist in unprecedented serodiagnostic specificity.

Proteome-wide mapping of immune features onto Plasmodium protein three-dimensional structures

Humoral immune responses against the malaria parasite are an important component of a protective immune response. Antibodies are often directed towards conformational epitopes, and the native structure of the antigenic region is usually critical for antibody recognition. We examined the structural features of various Plasmodium antigens that may impact on epitope location, by performing a comprehensive analysis of known and modelled structures from P. falciparum. Examining the location of known polymorphisms over all available structures, we observed a strong propensity for polymorphic residues to be exposed on the surface and to occur in particular secondary structure segments such as hydrogen-bonded turns. We also utilised established prediction algorithms for B-cell epitopes and MHC class II binding peptides, examining predicted epitopes in relation to known polymorphic sites within structured regions. Finally, we used the available structures to examine polymorphic hotspots and Tajima's D values using a spatial averaging approach. We identified a region of PfAMA1 involving both domains II and III under a high degree of balancing selection relative to the rest of the protein. In summary, we developed general methods for examining how sequence-based features relate to one another in three-dimensional space and applied these methods to key P. falciparum antigens.

Immunity to CRISPR Cas9 and Cas12a therapeutics

Genome-editing therapeutics are poised to treat human diseases. As we enter clinical trials with the most promising CRISPR-Cas9 and CRISPR-Cas12a (Cpf1) modalities, the risks associated with administering these foreign biomolecules into human patients become increasingly salient. Preclinical discovery with CRISPR-Cas9 and CRISPR-Cas12a systems and foundational gene therapy studies indicate that the host immune system can mount undesired responses against the administered proteins and nucleic acids, the gene-edited cells, and the host itself. These host defenses include inflammation via activation of innate immunity, antibody induction in humoral immunity, and cell death by T-cell-mediated cytotoxicity. If left unchecked, these immunological reactions can curtail therapeutic benefits and potentially lead to mortality. Ways to assay and reduce the immunogenicity of Cas9 and Cas12a proteins are therefore critical for ensuring patient safety and treatment efficacy, and for bringing us closer to realizing the vision of permanent genetic cures. WIREs Syst Biol Med 2018, 10:e1408. doi: 10.1002/wsbm.1408 This article is categorized under: Laboratory Methods and Technologies > Genetic/Genomic Methods Translational, Genomic, and Systems Medicine > Translational Medicine Translational, Genomic, and Systems Medicine > Therapeutic Methods.

An Introduction to Epitope Mapping

Antibodies are protein molecules used routinely for therapeutic, diagnostic, and research purposes due to their exquisite ability to selectively recognize and bind a given antigen. The particular area of the antigen recognized by the antibody is called the epitope, and for proteinaceous antigens the epitope can be of complex nature. Information about the binding epitope of an antibody can provide important mechanistic insights and indicate for what applications an antibody might be useful. Therefore, a variety of epitope mapping techniques have been developed to localize such regions. Although the real picture is even more complex, epitopes in protein antigens are broadly grouped into linear or discontinuous epitopes depending on the positioning of the epitope residues in the antigen sequence and the requirement of structure. Specialized methods for mapping of the two different classes of epitopes, using high-throughput or high-resolution methods, have been developed. While different in their detail, all of the experimental methods rely on assessing the binding of the antibody to the antigen or a set of antigen mimics. Early approaches utilizing sets of truncated proteins, small numbers of synthesized peptides, and structural analyses of antibody-antigen complexes have been significantly refined. Current state-of-the-art methods involve combinations of mutational scanning, protein display, and high-throughput screening in conjunction with bioinformatic analyses of large datasets.

Fundamentals and Methods for T- and B-Cell Epitope Prediction

Adaptive immunity is mediated by T- and B-cells, which are immune cells capable of developing pathogen-specific memory that confers immunological protection. Memory and effector functions of B- and T-cells are predicated on the recognition through specialized receptors of specific targets (antigens) in pathogens. More specifically, B- and T-cells recognize portions within their cognate antigens known as epitopes. There is great interest in identifying epitopes in antigens for a number of practical reasons, including understanding disease etiology, immune monitoring, developing diagnosis assays, and designing epitope-based vaccines. Epitope identification is costly and time-consuming as it requires experimental screening of large arrays of potential epitope candidates. Fortunately, researchers have developed in silico prediction methods that dramatically reduce the burden associated with epitope mapping by decreasing the list of potential epitope candidates for experimental testing. Here, we analyze aspects of antigen recognition by T- and B-cells that are relevant for epitope prediction. Subsequently, we provide a systematic and inclusive review of the most relevant B- and T-cell epitope prediction methods and tools, paying particular attention to their foundations.

The use of databases, data mining and immunoinformatics in vaccinology: where are we?

INTRODUCTION

Vaccinology has evolved from a sub-discipline focussed on simplistic vaccine development based on antibody-mediated protection to a separate discipline involving epidemiology, host and pathogen biology, immunology, genomics, proteomics, structure biology, protein engineering, chemical biology, and delivery systems. Data mining in combination with bioinformatics has provided a scaffold linking all these disciplines to the design of vaccines and vaccine adjuvants. Areas covered: This review provides background knowledge on immunological aspects which have been exploited with informatics for the in silico analysis of immune responses and the design of vaccine antigens. Furthermore, the article presents various databases and bioinformatics tools, and discusses B and T cell epitope predictions, antigen design, adjuvant research and systems immunology, highlighting some important examples, and challenges for the future. Expert opinion: Informatics and data mining have not only reduced the time required for experimental immunology, but also contributed to the identification and design of novel vaccine candidates and the determination of biomarkers and pathways of vaccine response. However, more experimental data is required for benchmarking immunoinformatic tools. Nevertheless, developments in immunoinformatics and reverse vaccinology, which are nascent fields, are likely to hasten vaccine discovery, although the path to regulatory approval is likely to remain a necessary impediment.

DRREP: deep ridge regressed epitope predictor

INTRODUCTION

The ability to predict epitopes plays an enormous role in vaccine development in terms of our ability to zero in on where to do a more thorough in-vivo analysis of the protein in question. Though for the past decade there have been numerous advancements and improvements in epitope prediction, on average the best benchmark prediction accuracies are still only around 60%. New machine learning algorithms have arisen within the domain of deep learning, text mining, and convolutional networks. This paper presents a novel analytically trained and string kernel using deep neural network, which is tailored for continuous epitope prediction, called: Deep Ridge Regressed Epitope Predictor (DRREP).

RESULTS

DRREP was tested on long protein sequences from the following datasets: SARS, Pellequer, HIV, AntiJen, and SEQ194. DRREP was compared to numerous state of the art epitope predictors, including the most recently published predictors called LBtope and DMNLBE. Using area under ROC curve (AUC), DRREP achieved a performance improvement over the best performing predictors on SARS (13.7%), HIV (8.9%), Pellequer (1.5%), and SEQ194 (3.1%), with its performance being matched only on the AntiJen dataset, by the LBtope predictor, where both DRREP and LBtope achieved an AUC of 0.702.

CONCLUSION

DRREP is an analytically trained deep neural network, thus capable of learning in a single step through regression. By combining the features of deep learning, string kernels, and convolutional networks, the system is able to perform residue-by-residue prediction of continues epitopes with higher accuracy than the current state of the art predictors.

Computer-Aided Design of an Epitope-Based Vaccine against Epstein-Barr Virus

Epstein-Barr virus is a very common human virus that infects 90% of human adults. EBV replicates in epithelial and B cells and causes infectious mononucleosis. EBV infection is also linked to various cancers, including Burkitt's lymphoma and nasopharyngeal carcinomas, and autoimmune diseases such as multiple sclerosis. Currently, there are no effective drugs or vaccines to treat or prevent EBV infection. Herein, we applied a computer-aided strategy to design a prophylactic epitope vaccine ensemble from experimentally defined T and B cell epitopes. Such strategy relies on identifying conserved epitopes in conjunction with predictions of HLA presentation for T cell epitope selection and calculations of accessibility and flexibility for B cell epitope selection. The T cell component includes 14 CD8 T cell epitopes from early antigens and 4 CD4 T cell epitopes, targeted during the course of a natural infection and providing a population protection coverage of over 95% and 81.8%, respectively. The B cell component consists of 3 experimentally defined B cell epitopes from gp350 plus 4 predicted B cell epitopes from other EBV envelope glycoproteins, all mapping in flexible and solvent accessible regions. We discuss the rationale for the formulation and possible deployment of this epitope vaccine ensemble.

Usefulness of the ElliPro epitope predictor program in defining the repertoire of HLA-ABC eplets

HLA matching at the epitope level offers new opportunities to identify suitable donors for transplant patients. The International HLA Epitope Registry (www.Epregistry.com.br) describes for the various HLA loci, repertoires of eplets including those that correspond to epitopes experimentally verified with specific antibodies. There are also many eplets which have remained as theoretical entities because no informative antibodies have been found. Which of them have immunogenic potential or conversely, might be considered as non-epitopes that cannot elicit specific antibody responses? This question is important for the application of epitope-based HLA matching in clinical transplantation. Correct predictions of B-cell epitopes on antigenic proteins are essential to the effective design of microbial vaccines and the development of specific antibodies used in immunotherapy and immunodiagnostics but prediction programs based on structural and physiochemical properties of amino acid residues are generally ineffective. Recent prediction programs based on three-dimensional structures of antigen-antibody complexes are more promising. One such program is called ElliPro developed by Ponomarenko. This report describes studies demonstrating that ElliPro can predict alloantibody responses to HLA-ABC eplets. Antibody-verified eplets have amino acid residues with much higher ElliPro scores than eplets for which no specific antibodies have been found. The latter group includes residues with very low ElliPro scores; they appear to represent eplets that might be classified as non-epitopes. In conclusion, ElliPro offers a new approach to characterize epitope repertoires that are clinically relevant in HLA matching.

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.

Proteomic peptide scan of porphyromonas gingivalis fima type ii for searching potential b-cell epitopes

PURPOSE

To identify potential antigenic targets for Porphyromonas gingivalis vaccine development.

MATERIALS AND METHODS

In the present study, we analyzed the Porphyromonas gingivalis, fimA type II primary amino acid sequence and characterized the similarity to the human proteome at the pentapeptide level.

RESULTS

We found that exact peptide-peptide profiling of the fimbrial antigen versus the human proteome shows that only 19 out of 344 fimA type II pentapeptides are uniquely owned by the bacterial protein.

CONCLUSIONS

The concept that protein immunogenicity is allocated in rare peptide sequences and the search the Porphyromonas gingivalis fimA type II sequence for peptides unique to the bacterial protein and absent in the human host, might be used in new therapeutical approaches as a significant adjunct to current periodontal therapies.