SEPPA 3.0-enhanced spatial epitope prediction enabling glycoprotein antigens

Transformer-based deep learning enables improved B-cell epitope prediction in parasitic pathogens: A proof-of-concept study on Fasciola hepatica

BACKGROUND

The identification of B-cell epitopes (BCEs) is fundamental to advancing epitope-based vaccine design, therapeutic antibody development, and diagnostics, such as in neglected tropical diseases caused by parasitic pathogens. However, the structural complexity of parasite antigens and the high cost of experimental validation present certain challenges. Advances in Artificial Intelligence (AI)-driven protein engineering, particularly through machine learning and deep learning, offer efficient solutions to enhance prediction accuracy and reduce experimental costs.

METHODOLOGY/PRINCIPAL FINDINGS

Here, we present deepBCE-Parasite, a Transformer-based deep learning model designed to predict linear BCEs from peptide sequences. By leveraging a state-of-the-art self-attention mechanism, the model achieved remarkable predictive performance, achieving an accuracy of approximately 81% and an AUC of 0.90 in both 10-fold cross-validation and independent testing. Comparative analyses against 12 handcrafted features and four conventional machine learning algorithms (GNB, SVM, RF, and LGBM) highlighted the superior predictive power of the model. As a case study, deepBCE-Parasite predicted eight BCEs from the leucine aminopeptidase (LAP) protein in Fasciola hepatica proteomic data. Dot-blot immunoassays confirmed the specific binding of seven synthetic peptides to positive sera, validating their IgG reactivity and demonstrating the model's efficacy in BCE prediction.

CONCLUSIONS/SIGNIFICANCE

deepBCE-Parasite demonstrates excellent performance in predicting BCEs across diverse parasitic pathogens, offering a valuable tool for advancing the design of epitope-based vaccines, antibodies, and diagnostic applications in parasitology.

Clinical microbiology and artificial intelligence: Different applications, challenges, and future prospects

Conventional clinical microbiological techniques are enhanced by the introduction of artificial intelligence (AI). Comprehensive data processing and analysis enabled the development of curated datasets that has been effectively used in training different AI algorithms. Recently, a number of machine learning (ML) and deep learning (DL) algorithms are developed and evaluated using diverse microbiological datasets. These datasets included spectral analysis (Raman and MALDI-TOF spectroscopy), microscopic images (Gram and acid fast stains), and genomic and protein sequences (whole genome sequencing (WGS) and protein data banks (PDBs)). The primary objective of these algorithms is to minimize the time, effort, and expenses linked to conventional analytical methods. Furthermore, AI algorithms are incorporated with quantitative structure-activity relationship (QSAR) models to predict novel antimicrobial agents that address the continuing surge of antimicrobial resistance. During the COVID-19 pandemic, AI algorithms played a crucial role in vaccine developments and the discovery of new antiviral agents, and introduced potential drug candidates via drug repurposing. However, despite their significant benefits, the implementation of AI encounters various challenges, including ethical considerations, the potential for bias, and errors related to data training. This review seeks to provide an overview of the most recent applications of artificial intelligence in clinical microbiology, with the intention of educating a wider audience of clinical practitioners regarding the current uses of machine learning algorithms and encouraging their implementation. Furthermore, it will discuss the challenges related to the incorporation of AI into clinical microbiology laboratories and examine future opportunities for AI within the realm of infectious disease epidemiology.

Dynamic integration of feature- and template-based methods improves the prediction of conformational B cell epitopes

The accurate prediction of conformational epitopes promotes our understanding of antigen-antibody interactions. All existing algorithms depend on a feature-based strategy, which limits their performance. A template-based strategy can provide complementary information, and the interplay between these two strategies could improve the prediction of epitopes. Here, we present DynaBCE, a dynamic ensemble algorithm to effectively identify conformational B cell epitopes (BCEs). Using novel handcrafted structural descriptors and embeddings from protein language models, we developed machine learning and deep learning modules based on boosting algorithms and geometric graph neural networks, respectively. Furthermore, we built a template module by leveraging known structural template information and transformer-based algorithms to capture binding signatures. Finally, we integrated the three modules using a dynamic weighting approach to maximize the strength of each module for different samples. DynaBCE achieved promising results for both native and predicted structures and outperformed previous methods as demonstrated in various evaluation scenarios.

Engineering a New Generation of Gene Editors: Integrating Synthetic Biology and AI Innovations

CRISPR-Cas technology has revolutionized biology by enabling precise DNA and RNA edits with ease. However, significant challenges remain for translating this technology into clinical applications. Traditional protein engineering methods, such as rational design, mutagenesis screens, and directed evolution, have been used to address issues like low efficacy, specificity, and high immunogenicity. These methods are labor-intensive, time-consuming, and resource-intensive and often require detailed structural knowledge. Recently, computational strategies have emerged as powerful solutions to these limitations. Using artificial intelligence (AI) and machine learning (ML), the discovery and design of novel gene-editing enzymes can be streamlined. AI/ML models predict activity, specificity, and immunogenicity while also enhancing mutagenesis screens and directed evolution. These approaches not only accelerate rational design but also create new opportunities for developing safer and more efficient genome-editing tools, which could eventually be translated into the clinic.

Computationally designed multi-epitope vaccine construct targeting the SARS-CoV-2 spike protein elicits robust immune responses in silico

Our research is driven by the need to design an advanced multi-epitope vaccine construct (MEVC) using the S-protein of SARS-CoV-2 to combat the emergence of new variants. Through rigorous computational screening, we have identified linear and discontinuous B-cell epitopes, CD8 + and CD4 + T-cell epitopes, ensuring extensive MEVC coverage across 90.03% of the global population. The MEVC, featuring four CD4 + and four CD8 + T-cell epitopes connected linearly with two adjuvant proteins on both ends, has been carefully designed to elicit robust immune response. Our in-silico analysis has confirmed the construct's antigenicity, non-allergenicity, and non-toxicity with optimized codon sequences for enhanced expression in E. coli K12. Furthermore, molecular docking and dynamics analyses have demonstrated its strong binding affinity with TLR-3 and TLR 4, and in-silico immune simulation yielded promising results on heightened B-cell and T-cell-mediated immunity. However, wet lab experiments are essential to validate computational findings to revolutionize the development of vaccines against SARS-CoV-2.

Molecular Evolution of the Fusion (F) Genes in Human Parainfluenza Virus Type 2

Human parainfluenza virus type 2 (HPIV2) is a clinically significant respiratory pathogen, which highlights the necessity of studies on its molecular evolution. This study investigated the evolutionary dynamics, phylodynamics, and structural characteristics of the HPIV2 fusion (F) gene using a comprehensive dataset spanning multiple decades and geographic regions. Phylogenetic analyses revealed two distinct clusters of HPIV2 F gene sequences, which were estimated to have diverged from a common ancestor approximately a century ago. Cluster 1 demonstrated a higher evolutionary rate and genetic diversity compared to the more stable cluster 2. Bayesian Skyline Plot analyses indicated a significant increase in the effective population size of the F gene between 2005 and 2015; potentially linked to enhanced diagnostic and surveillance capabilities. Structural modeling identified conserved conformational epitopes predominantly in the apex and stalk regions of the F protein. These findings underscore the evolutionary constraints and antigenic landscape of the HPIV2 F protein.

Phylogenomic Analyses of the Hemagglutinin-Neuraminidase (HN) Gene in Human Parainfluenza Virus Type 4 Isolates in Japan

To better understand the phylogenomics of the hemagglutinin-neuraminidase (HN) gene and HN protein in human parainfluenza virus type 4 (HPIV4), we performed phylogenomic analyses using various bioinformatics methods. The main bioinformatics analyses included a time-scaled phylogeny, genetic distance assessments, and three-dimensional (3D) structure mapping of the HN protein with conformational epitope and selective pressure analyses. The time-scaled phylogenetic tree indicated that the most recent common ancestor of the HN gene emerged approximately 100 years ago. Additionally, the tree revealed two distinct clusters corresponding to HPIV4a and HPIV4b. The divergence times for the most recent common ancestors of the HN gene in HPIV4a and HPIV4b strains were estimated to be around 1993 and 1986, respectively. The evolutionary rates of the gene varied significantly between clusters, ranging from approximately 1.2 × 10-3 to 8.7 × 10-4 substitutions per site per year. Genetic distances within each cluster were relatively short (less than 0.04). Phylodynamic analyses demonstrated an increase in the genome population size around the year 2000. Structural analyses revealed that the active sites of the HN protein were located at the protein's head. Furthermore, the most conformational epitopes were located in adjacent active sites of the protein. These results suggested that reinfection may be unlikely to occur in the case of most HPIV4. Together, the HN gene and protein of HPIV4 strains isolated in Japan have undergone unique evolutionary changes. In addition, antibodies targeting the conformational epitopes of the HPIV4 HN protein may contribute to protection against the virus.

Compromising the immunogenicity of diphtheria toxin-based immunotoxins through epitope engineering: An in silico approach

Immunotoxins are genetically engineered recombinant proteins consisting of a targeting moiety, such as an antibody, and a cytotoxic toxin moiety of microbial origin. Pseudomonas exotoxin A and diphtheria toxin (DT) have been abundantly used in immunotoxins, with the latter applied as the toxin moiety of the FDA-approved drug Denileukin diftitox (ONTAK®). However, the use of immunotoxins provokes an adverse immune response in the host body against the toxin moiety, limiting their efficacy. In silico approaches have received increasing attention in protein engineering. In this study, the epitopes responsible for immunogenicity were identified through multiple platforms. By subtracting conserved and ligand-binding residues, K33, T111, and E112 were identified as common epitopes across all platforms. Substitution analysis evaluated alternative residues regarding their impact on protein stability, considering 19 different amino acid substitutions. Among the mutants explored, the T111A-E112G mutant exhibited the most destabilizing substitution for DT, thereby reducing immunogenicity. Finally, a 3D model of the mutant was generated and verified. The model was then docked with its native ligand NADH, and the complex's molecular behavior was simulated using molecular dynamics.

Molecular Evolutionary Analyses of the RNA-Dependent RNA Polymerase (RdRp) Region and VP1 Gene in Sapovirus GI.1 and GI.2

Human sapovirus (HuSaV) is a significant cause of gastroenteritis. This study aims to analyze the evolutionary dynamics of the RNA-dependent RNA polymerase (RdRp) and capsid (VP1) genes of the HuSaV GI.1 and GI.2 genotypes between 1976 and 2020. Using bioinformatics tools such as the Bayesian phylogenetics software BEAST 2 package (v.2.7.6), we constructed time-scale evolutionary trees based on the gene sequences. Most of the recent common ancestors (MRCAs) of the RdRp region and VP1 gene in the present HuSaV GI.1 diverged around 1930 and 1933, respectively. The trees of the HuSaV GI.1 RdRp region and VP1 gene were divided into two clusters. Further, the MRCAs of the RdRp region and VP1 gene in HuSaV GI.2 diverged in 1960 and 1943, respectively. The evolutionary rates were higher for VP1 gene in HuSaV GI.1 than that in HuSaV GI.2, furthermore, were higher in GI.1 Cluster B than GI.1 Cluster A. In addition, a steep increase was observed in the time-scaled genome population size of the HuSaV GI.1 Cluster B. These results indicate that the HuSaV GI.1 Cluster B may be evolving more actively than other genotypes. The conformational B-cell epitopes were predicted with a higher probability in RdRp for GI.1 and in VP1 for GI.2, respectively. These results suggest that the RdRp region and VP1 gene in HuSaV GI.1 and GI.2 evolved uniquely. These findings suggest unique evolutionary patterns in the RdRp region and VP1 gene of HuSaV GI.1 and GI.2, emphasizing the need for a 'One Health' approach to better understand and combat this pathogen.

A novel HBc-S230 protein chimeric VLPs induced robust immune responses against SARS-CoV-2

Here, we report that four functional fragments of the Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2) spike protein including receptor binding motif (RBM), fusion peptide (FP), heptad repeat 1 (HR1) and heptad repeat 2 (HR2) were chosen to develop a recombinant S subunit protein vaccine. This recombinant protein consisting of S230 amino acids (aa) (S230) bound specifically to the antibody from COVID-19-patients serum, which showed very strong antigenicity. The S230 was then engineered to present on the surface of Hepatitis B core (HBc) virus-like particles (VLPs) to develop HBc-S230 chimeric VLPs vaccine. Both vaccines induced strong humoral and cellular immune responses in mice, however, HBc-S230 chimeric VLPs elicited significantly higher immunogenicity than the S230. HBc-S230 chimeric VLPs promoted to generate not only dramatically higher levels of S230-specific serum antibodies, but also marked higher CD4+/CD8 + T cells ratio and substantially higher yields of IFN-γ and IL-6. Furthermore, HBc-S230 chimeric VLPs induced serum antibodies that could effectively neutralize the infection with three SARS-CoV-2 pseudoviruses (Wild type, Delta and Omicron). Our results demonstrated that HBc-S230 chimeric VLPs immunization conveyed the humoral immunity, which lasted longer than six months. Clearly, HBc-S230 chimeric VLPs enhanced immunogenicity of the S230, which could provide potent and durable protection against SARS-CoV-2 infection, indicating that HBc-S230 chimeric VLPs possessed great potential for developing highly immunogenic vaccines against SARS-CoV-2.

WUREN: Whole-modal union representation for epitope prediction

B-cell epitope identification plays a vital role in the development of vaccines, therapies, and diagnostic tools. Currently, molecular docking tools in B-cell epitope prediction are heavily influenced by empirical parameters and require significant computational resources, rendering a great challenge to meet large-scale prediction demands. When predicting epitopes from antigen-antibody complex, current artificial intelligence algorithms cannot accurately implement the prediction due to insufficient protein feature representations, indicating novel algorithm is desperately needed for efficient protein information extraction. In this paper, we introduce a multimodal model called WUREN (Whole-modal Union Representation for Epitope predictioN), which effectively combines sequence, graph, and structural features. It achieved AUC-PR scores of 0.213 and 0.193 on the solved structures and AlphaFold-generated structures, respectively, for the independent test proteins selected from DiscoTope3 benchmark. Our findings indicate that WUREN is an efficient feature extraction model for protein complexes, with the generalizable application potential in the development of protein-based drugs. Moreover, the streamlined framework of WUREN could be readily extended to model similar biomolecules, such as nucleic acids, carbohydrates, and lipids.

Construction of a Hybrid Vaccine Based on Der f 35-Derived Peptides with Reduced Allergenicity

INTRODUCTION

House dust mite is the primary trigger of allergic respiratory diseases worldwide, and allergen-specific immunotherapy (AIT) is the only disease-modifying treatment in the clinic. The use of allergen molecules instead of extracts is a promising strategy in AIT. In this study, we constructed a peptide hybrid vaccine against the major mite allergen Der f 35 and verified its hypoallergenicity, making it to be a promising candidate for AIT of mite allergy.

METHODS

The gene encoding Der f 35 was retrieved and synthesized. The hypoallergenic peptide fragments derived from the B-cell epitopes were synthesized based on the predicted profiles of B-cell or T helper-cell epitopes in Der f 35, they were verified by immunoglobulin E (IgE)-reaction test and fused to non-allergenic protein carrier to form the hybrid vaccine. Both the wild-type Der f 35 and the designed vaccine were expressed in Escherichia coli and purified by chromatography; their IgE-binding activity was compared by indirect enzyme-linked immunosorbent assay (ELISA), Western blot, inhibition ELISA, and basophil activation test (BAT). The blocking immunoglobulin G (IgG) against the designed vaccine was raised in rabbits and its ability to inhibit IgE binding of Der f 35 was evaluated by ELISA. The vaccine's effects on peripheral blood mononuclear cells (PBMCs) were investigated.

RESULTS

A total of 29 out of 60 (48.33%) IgE-positive sera against Der f 35 were screened. Five peptide fragments (residue 39-42, 60-67, 73-107, 111-118, 126-143) from Der f 35 were selected as candidates, in which four peptides exhibited almost no IgE reactivity and the fragment 73-107 had weak reactions. Only 5.98-24.02% inhibition rates could be achieved by the peptides when compared with Der f 35 (97.32%). The designed vaccine migrated at approximately 30 kDa by SDS-PAGE. The IgE-ELISA revealed a significant reduction in IgE-binding activity to the vaccine when compared to wild-type Der f 35 (p < 0.0001); the decreased allergenicity was further confirmed by IgE-Western blot, inhibition ELISA, and BAT, respectively. The IgE-reactivity of Der f 35 could be blocked by the vaccine-induced IgG (p < 0.01). The levels of IL-5 and IL-13 from PBMCs were significantly decreased after stimulation by the vaccine than that by Der f 35 (p < 0.05).

CONCLUSION

The designed B-cell epitope vaccine of Der f 35 showed greatly diminished allergenicity and Th2 activity. It could be an effective and safe candidate to prevent allergic adverse reactions during the immunotherapy of mite allergy and merits the further study.

Advances of computational methods enhance the development of multi-epitope vaccines

Vaccine development is one of the most promising fields, and multi-epitope vaccine, which does not need laborious culture processes, is an attractive alternative to classical vaccines with the advantage of safety, and efficiency. The rapid development of algorithms and the accumulation of immune data have facilitated the advancement of computer-aided vaccine design. Here we systemically reviewed the in silico data and algorithms resource, for different steps of computational vaccine design, including immunogen selection, epitope prediction, vaccine construction, optimization, and evaluation. The performance of different available tools on epitope prediction and immunogenicity evaluation was tested and compared on benchmark datasets. Finally, we discuss the future research direction for the construction of a multiepitope vaccine.

B cell epitope prediction by capturing spatial clustering property of the epitopes using graph attention network

Knowledge of B cell epitopes is critical to vaccine design, diagnostics, and therapeutics. As experimental validation for epitopes is time-consuming and costly, many in silico tools have been developed to computationally predict the B cell epitopes. While most methods show poor performance, deep learning methods in recent years have shown promising results. We developed a method called EpiGraph that outperformed previous methods, including those that showed a significant improvement in performance in recent years. Our model's performance can be attributed to the following factors: (1) a combination of structure and sequence feature embeddings obtained from pretrained ESM-IF1 and ESM-2 models could capture the structural and evolutionary features of B cell epitopes, (2) a graph attention network could learn the spatial proximity of B cell epitopes with high graph homophily, and (3) residual connections in the model framework mitigate the over-smoothing problem in the graph neural network. Our model achieved the highest performance on an independent benchmark dataset. The results were also consistent on a different dataset. The datasets and source codes are available at https://github.com/sj584/EpiGraph . A user-friendly web server is freely available at http://epigraph.kaist.ac.kr .

A review on the development of bacterial multi-epitope recombinant protein vaccines via reverse vaccinology

Bacterial vaccines play a crucial role in combating bacterial infectious diseases. Apart from the prevention of disease, bacterial vaccines also help to reduce the mortality rates in infected populations. Advancements in vaccine development technologies have addressed the constraints of traditional vaccine design, providing novel approaches for the development of next-generation vaccines. Advancements in reverse vaccinology, bioinformatics, and comparative proteomics have opened horizons in vaccine development. Specifically, the use of protein structural data in crafting multi-epitope vaccines (MEVs) to target pathogens has become an important research focus in vaccinology. In this review, we focused on describing the methodologies and tools for epitope vaccine development, along with recent progress in this field. Moreover, this article also discusses the challenges in epitope vaccine development, providing insights for the future development of bacterial multi-epitope genetically engineered vaccines.

Computational prediction of multiple antigen epitopes

MOTIVATION

Identifying antigen epitopes is essential in medical applications, such as immunodiagnostic reagent discovery, vaccine design, and drug development. Computational approaches can complement low-throughput, time-consuming, and costly experimental determination of epitopes. Currently available prediction methods, however, have moderate success predicting epitopes, which limits their applicability. Epitope prediction is further complicated by the fact that multiple epitopes may be located on the same antigen and complete experimental data is often unavailable.

RESULTS

Here, we introduce the antigen epitope prediction program ISPIPab that combines information from two feature-based methods and a docking-based method. We demonstrate that ISPIPab outperforms each of its individual classifiers as well as other state-of-the-art methods, including those designed specifically for epitope prediction. By combining the prediction algorithm with hierarchical clustering, we show that we can effectively capture epitopes that align with available experimental data while also revealing additional novel targets for future experimental investigations.

Intranasal Multiepitope PD-L1-siRNA-Based Nanovaccine: The Next-Gen COVID-19 Immunotherapy

The first approved vaccines for human use against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are nanotechnology-based. Although they are modular, rapidly produced, and can reduce disease severity, the currently available vaccines are restricted in preventing infection, stressing the global demand for novel preventive vaccine technologies. Bearing this in mind, we set out to develop a flexible nanovaccine platform for nasal administration to induce mucosal immunity, which is fundamental for optimal protection against respiratory virus infection. The next-generation multiepitope nanovaccines co-deliver immunogenic peptides, selected by an immunoinformatic workflow, along with adjuvants and regulators of the PD-L1 expression. As a case study, we focused on SARS-CoV-2 peptides as relevant antigens to validate the approach. This platform can evoke both local and systemic cellular- and humoral-specific responses against SARS-CoV-2. This led to the secretion of immunoglobulin A (IgA), capable of neutralizing SARS-CoV-2, including variants of concern, following a heterologous immunization strategy. Considering the limitations of the required cold chain distribution for current nanotechnology-based vaccines, it is shown that the lyophilized nanovaccine is stable for long-term at room temperature and retains its in vivo efficacy upon reconstitution. This makes it particularly relevant for developing countries and offers a modular system adaptable to future viral threats.

Allergies to Allergens from Cats and Dogs: A Review and Update on Sources, Pathogenesis, and Strategies

Inhalation allergies caused by cats and dogs can lead to a range of discomforting symptoms, such as rhinitis and asthma, in humans. With the increasing popularity of and care provided to these companion animals, the allergens they produce pose a growing threat to susceptible patients' health. Allergens from cats and dogs have emerged as significant risk factors for triggering asthma and allergic rhinitis worldwide; however, there remains a lack of systematic measures aimed at assisting individuals in recognizing and preventing allergies caused by these animals. This review provides comprehensive insights into the classification of cat and dog allergens, along with their pathogenic mechanisms. This study also discusses implementation strategies for prevention and control measures, including physical methods, gene-editing technology, and immunological approaches, as well as potential strategies for enhancing allergen immunotherapy combined with immunoinformatics. Finally, it presents future prospects for the prevention and treatment of human allergies caused by cats and dogs. This review will improve knowledge regarding allergies to cats and dogs while providing insights into potential targets for the development of next-generation treatments.

Molecular Evolutionary Analyses of Shiga toxin type 2 subunit A Gene in the Enterohemorrhagic Escherichia coli (EHEC)

To better understand the molecular genetics of the Shiga toxin type 2 subunit A gene (stx2A gene), we collected many subtypes of stx2A genes and performed detailed molecular evolutionary analyses of the gene. To achieve the aim of the study, we used several bioinformatics technologies, including time-scaled phylogenetic analyses, phylogenetic distance analyses, phylodynamics analyses, selective pressure analyses, and conformational epitope analyses. A time-scaled phylogeny showed that the common ancestor of the stx2A gene dated back to around 18,600 years ago. After that, the gene diverged into two major lineages (Lineage 1 and 2). Lineage 1 comprised the stx2a-2d subtypes, while Lineage 2 comprised the stx2e, 2g, 2h, and 2o subtypes. The evolutionary rates of the genes were relatively fast. Phylogenetic distances showed that the Lineage 2 strains had a wider genetic divergence than Lineage 1. Phylodynamics also indicated that the population size of the stx2A gene increased after the 1930s and spread globally. Moreover, negative selection sites were identified in the Stx2A proteins, and these sites were diffusely distributed throughout the protein. Two negative selection sites were located adjacent to an active site of the common Stx2A protein. Many conformational epitopes were also estimated in these proteins, while no conformational epitope was found adjacent to the active site. The results suggest that the stx2A gene has uniquely evolved and diverged over an extremely long time, resulting in many subtypes. The dominance of the strains belonging to Lineage 1 suggests that differences in virulence may be involved in the prosperity of the offspring. Furthermore, some subtypes of Stx2A proteins may be able to induce effective neutralizing antibodies against the proteins in humans.

Computational Methods to Predict Conformational B-Cell Epitopes

Accurate computational prediction of B-cell epitopes can greatly enhance biomedical research and rapidly advance efforts to develop therapeutics, monoclonal antibodies, vaccines, and immunodiagnostic reagents. Previous research efforts have primarily focused on the development of computational methods to predict linear epitopes rather than conformational epitopes; however, the latter is much more biologically predominant. Several conformational B-cell epitope prediction methods have recently been published, but their predictive performances are weak. Here, we present a review of the latest computational methods and assess their performances on a diverse test set of 29 non-redundant unbound antigen structures. Our results demonstrate that ISPIPab performs better than most methods and compares favorably with other recent antigen-specific methods. Finally, we suggest new strategies and opportunities to improve computational predictions of conformational B-cell epitopes.

Molecular Evolutionary Analyses of the Fusion Genes in Human Parainfluenza Virus Type 4

The human parainfluenza virus type 4 (HPIV4) can be classified into two distinct subtypes, 4a and 4b. The full lengths of the fusion gene (F gene) of 48 HPIV4 strains collected during the period of 1966-2022 were analyzed. Based on these gene sequences, the time-scaled evolutionary tree was constructed using Bayesian Markov chain Monte Carlo methods. A phylogenetic tree showed that the first division of the two subtypes occurred around 1823, and the most recent common ancestors of each type, 4a and 4b, existed until about 1940 and 1939, respectively. Although the mean genetic distances of all strains were relatively wide, the distances in each subtype were not wide, indicating that this gene was conserved in each subtype. The evolutionary rates of the genes were relatively low (4.41 × 10-4 substitutions/site/year). Moreover, conformational B-cell epitopes were predicted in the apex of the trimer fusion protein. These results suggest that HPIV4 subtypes diverged 200 years ago and the progenies further diverged and evolved.

Computational Prediction of Multiple Antigen Epitopes

Motivation

Identifying antigen epitopes is essential in medical applications, such as immunodiagnostic reagent discovery, vaccine design, and drug development. Computational approaches can complement low-throughput, time-consuming, and costly experimental determination of epitopes. Currently available prediction methods, however, have moderate success predicting epitopes, which limits their applicability. Epitope prediction is further complicated by the fact that multiple epitopes may be located on the same antigen and complete experimental data is often unavailable.

Results

Here, we introduce the antigen epitope prediction program ISPIPab that combines information from two feature-based methods and a docking-based method. We demonstrate that ISPIPab outperforms each of its individual classifiers as well as other state-of-the-art methods, including those designed specifically for epitope prediction. By combining the prediction algorithm with hierarchical clustering, we show that we can effectively capture epitopes that align with available experimental data while also revealing additional novel targets for future experimental investigations.

Contact

raji@yu.edu.

Supplementary information

Supplementary data are available at Bioinformatics online.

SEMA 2.0: web-platform for B-cell conformational epitopes prediction using artificial intelligence

Prediction of conformational B-cell epitopes is a crucial task in vaccine design and development. In this work, we have developed SEMA 2.0, a user-friendly web platform that enables the research community to tackle the B-cell epitopes prediction problem using state-of-the-art protein language models. SEMA 2.0 offers comprehensive research tools for sequence- and structure-based conformational B-cell epitopes prediction, accurate identification of N-glycosylation sites, and a distinctive module for comparing the structures of antigen B-cell epitopes enhancing our ability to analyze and understand its immunogenic properties. SEMA 2.0 website https://sema.airi.net is free and open to all users and there is no login requirement. Source code is available at https://github.com/AIRI-Institute/SEMAi.

Cytomegalovirus UL44 protein induces a potent T-cell immune response in mice

Due to the severity of CMV infection in immunocompromised individuals the development of a vaccine has been declared a priority. However, despite the efforts made there is no yet a vaccine available for clinical use. We designed an approach to identify new CMV antigens able to inducing a broad immune response that could be used in future vaccine formulations. We have used serum samples from 28 kidney transplant recipients, with a previously acquired CMV-specific immune response to identify viral proteins that were recognized by the antibodies present in the patient serum samples by Western blot. A band of approximately 45 kDa, identified as UL44, was detected by most serum samples. UL44 immunogenicity was tested in BALB/c mice that received three doses of the UL44-pcDNA DNA vaccine. UL44 elicited both, a strong antibody response and CMV-specific cellular response. Using bioinformatic analysis we demonstrated that UL44 is a highly conserved protein and contains epitopes that are able to activate CD8 lymphocytes of the most common HLA alleles in the world population. We constructed a UL44 ORF deletion mutant virus that produced no viral progeny, suggesting that UL44 is an essential viral protein. In addition, other authors have demonstrated that UL44 is one of the most abundant viral proteins after infection and have suggested an essential role of UL44 in viral replication. Altogether, our data suggests that UL44 is a potent antigen, and favored by its abundance, it may be a good candidate to include in a vaccine formulation.

Prediction of Paratope-Epitope Pairs Using Convolutional Neural Networks

Antibodies play a central role in the adaptive immune response of vertebrates through the specific recognition of exogenous or endogenous antigens. The rational design of antibodies has a wide range of biotechnological and medical applications, such as in disease diagnosis and treatment. However, there are currently no reliable methods for predicting the antibodies that recognize a specific antigen region (or epitope) and, conversely, epitopes that recognize the binding region of a given antibody (or paratope). To fill this gap, we developed ImaPEp, a machine learning-based tool for predicting the binding probability of paratope-epitope pairs, where the epitope and paratope patches were simplified into interacting two-dimensional patches, which were colored according to the values of selected features, and pixelated. The specific recognition of an epitope image by a paratope image was achieved by using a convolutional neural network-based model, which was trained on a set of two-dimensional paratope-epitope images derived from experimental structures of antibody-antigen complexes. Our method achieves good performances in terms of cross-validation with a balanced accuracy of 0.8. Finally, we showcase examples of application of ImaPep, including extensive screening of large libraries to identify paratope candidates that bind to a selected epitope, and rescoring and refining antibody-antigen docking poses.

Animal-derived food allergen: A review on the available crystal structure and new insights into structural epitope

Immunoglobulin E (IgE)-mediated food allergy is a rapidly growing public health problem. The interaction between allergens and IgE is at the core of the allergic response. One of the best ways to understand this interaction is through structural characterization. This review focuses on animal-derived food allergens, overviews allergen structures determined by X-ray crystallography, presents an update on IgE conformational epitopes, and explores the structural features of these epitopes. The structural determinants of allergenicity and cross-reactivity are also discussed. Animal-derived food allergens are classified into limited protein families according to structural features, with the calcium-binding protein and actin-binding protein families dominating. Progress in epitope characterization has provided useful information on the structural properties of the IgE recognition region. The data reveals that epitopes are located in relatively protruding areas with negative surface electrostatic potential. Ligand binding and disulfide bonds are two intrinsic characteristics that influence protein structure and impact allergenicity. Shared structures, local motifs, and shared epitopes are factors that lead to cross-reactivity. The structural properties of epitope regions and structural determinants of allergenicity and cross-reactivity may provide directions for the prevention, diagnosis, and treatment of food allergies. Experimentally determined structure, especially that of antigen-antibody complexes, remains limited, and the identification of epitopes continues to be a bottleneck in the study of animal-derived food allergens. A combination of traditional immunological techniques and emerging bioinformatics technology will revolutionize how protein interactions are characterized.

Construction by artificial intelligence and immunovalidation of hypoallergenic mite allergen Der f 36 vaccine

Background

The house dust mite (HDM) is widely recognized as the most prevalent allergen in allergic diseases. Allergen-specific immunotherapy (AIT) has been successfully implemented in clinical treatment for HDM. Hypoallergenic B-cell epitope-based vaccine designed by artificial intelligence (AI) represents a significant progression of recombinant hypoallergenic allergen derivatives.

Method

The three-dimensional protein structure of Der f 36 was constructed using Alphafold2. AI-based tools were employed to predict B-cell epitopes, which were subsequently verified through IgE-reaction testing. Hypoallergenic Der f 36 was then synthesized, expressed, and purified. The reduced allergenicity was assessed by enzyme-linked immunosorbent assay (ELISA), immunoblotting, and basophil activation test. T-cell response to hypoallergenic Der f 36 and Der f 36 was evaluated based on cytokine expression in the peripheral blood mononuclear cells (PBMCs) of patients. The immunogenicity was evaluated and compared through rabbit immunization with hypoallergenic Der f 36 and Der f 36, respectively. The inhibitory effect of the blocking IgG antibody on the specific IgE-binding activity and basophil activation of Der f 36 allergen was also examined.

Results

The final selected non-allergic B-cell epitopes were 25-48, 57-67, 107-112, 142-151, and 176-184. Hypoallergenic Der f 36 showed significant reduction in IgE-binding activity. The competitive inhibition of IgE-binding to Der f 36 was investigated using the hypoallergenic Der f 36, and only 20% inhibition could be achieved, which is greatly reduced when compared with inhibition by Der f 36 (98%). The hypoallergenic Der f 36 exhibited a low basophil-stimulating ratio similar to that of the negative control, and it could induce an increasing level of IFN-γ but not Th2 cytokines IL-5 and IL-13 in PBMCs. The vaccine-specific rabbit blocking IgG antibodies could inhibit the patients' IgE binding and basophil stimulation activity of Derf 36.

Conclusion

This study represents the first application of an AI strategy to facilitate the development of a B-cell epitope-based hypoallergenic Der f 36 vaccine, which may become a promising immunotherapy for HDM-allergic patients due to its reduced allergenicity and its high immunogenicity in inducing blocking of IgG.

The CDE region of feline Calicivirus VP1 protein is a potential candidate subunit vaccine

BACKGROUND

Feline calicivirus (FCV) infection causes severe upper respiratory disease in cats, but there are no effective vaccines available for preventing FCV infection. Subunit vaccines have the advantages of safety, low cost and excellent immunogenicity, but no FCV subunit vaccine is currently available. The CDE protein is the dominant neutralizing epitope region of the main antigenic structural protein of FCV, VP1. Therefore, this study evaluated the effectiveness of the CDE region as a truncated FCV VP1 protein in preventing FCV infection to provide a strategy for developing potential FCV subunit vaccines.

RESULTS

Through the prediction of FCV VP1 epitopes, we found that the E region is the dominant neutralizing epitope region. By analysing the spatial structure of VP1 protein, 13 amino acid sites in the CD and E regions were found to form hydrogen bonding interactions. The results show the presence of these interaction forces supports the E region, helping improve the stability and expression level of the soluble E protein. Therefore, we selected the CDE protein as the immunogen for the immunization of felines. After immunization with the CDE protein, we found significant stimulation of IgG, IgA and neutralizing antibody production in serum and swab samples, and the cytokine TNF-α levels and the numbers of CD4+ T lymphocytes were increased. Moreover, a viral challenge trial indicated that the protection generated by the CDE subunit vaccine significantly reduced the incidence of disease in animals.

CONCLUSIONS

For the first time, we studied the efficacy of the CDE protein, which is the dominant neutralizing epitope region of the FCV VP1 protein, in preventing FCV infection. We revealed that the CDE protein can significantly activate humoral, mucosal and cellular immunity, and the resulting protective effect can significantly reduce the incidence of animal disease. The CDE region of the FCV capsid is easy to produce and has high stability and excellent immunogenicity, which makes it a candidate for low-cost vaccines.

A method for predicting linear and conformational B-cell epitopes in an antigen from its primary sequence

B-cell is an essential component of the immune system that plays a vital role in providing the immune response against any pathogenic infection by producing antibodies. Existing methods either predict linear or conformational B-cell epitopes in an antigen. In this study, a single method was developed for predicting both types (linear/conformational) of B-cell epitopes. The dataset used in this study contains 3875 B-cell epitopes and 3996 non-B-cell epitopes, where B-cell epitopes consist of both linear and conformational B-cell epitopes. Our primary analysis indicates that certain residues (like Asp, Glu, Lys, and Asn) are more prominent in B-cell epitopes. We developed machine-learning based methods using different types of sequence composition and achieved the highest AUROC of 0.80 using dipeptide composition. In addition, models were developed on selected features, but no further improvement was observed. Our similarity-based method implemented using BLAST shows a high probability of correct prediction with poor sensitivity. Finally, we developed a hybrid model that combines alignment-free (dipeptide based random forest model) and alignment-based (BLAST-based similarity) models. Our hybrid model attained a maximum AUROC of 0.83 with an MCC of 0.49 on the independent dataset. Our hybrid model performs better than existing methods on an independent dataset used in this study. All models were trained and tested on 80 % of the data using a cross-validation technique, and the final model was evaluated on 20 % of the data, called an independent or validation dataset. A webserver and standalone package named "CLBTope" has been developed for predicting, designing, and scanning B-cell epitopes in an antigen sequence available at (https://webs.iiitd.edu.in/raghava/clbtope/).

DiscoTope-3.0: improved B-cell epitope prediction using inverse folding latent representations

Accurate computational identification of B-cell epitopes is crucial for the development of vaccines, therapies, and diagnostic tools. However, current structure-based prediction methods face limitations due to the dependency on experimentally solved structures. Here, we introduce DiscoTope-3.0, a markedly improved B-cell epitope prediction tool that innovatively employs inverse folding structure representations and a positive-unlabelled learning strategy, and is adapted for both solved and predicted structures. Our tool demonstrates a considerable improvement in performance over existing methods, accurately predicting linear and conformational epitopes across multiple independent datasets. Most notably, DiscoTope-3.0 maintains high predictive performance across solved, relaxed and predicted structures, alleviating the need for experimental structures and extending the general applicability of accurate B-cell epitope prediction by 3 orders of magnitude. DiscoTope-3.0 is made widely accessible on two web servers, processing over 100 structures per submission, and as a downloadable package. In addition, the servers interface with RCSB and AlphaFoldDB, facilitating large-scale prediction across over 200 million cataloged proteins. DiscoTope-3.0 is available at: https://services.healthtech.dtu.dk/service.php?DiscoTope-3.0.

Single-residue linear and conformational B cell epitopes prediction using random and ESM-2 based projections

B cell epitope prediction methods are separated into linear sequence-based predictors and conformational epitope predictions that typically use the measured or predicted protein structure. Most linear predictions rely on the translation of the sequence to biologically based representations and the applications of machine learning on these representations. We here present CALIBER 'Conformational And LInear B cell Epitopes pRediction', and show that a bidirectional long short-term memory with random projection produces a more accurate prediction (test set AUC=0.789) than all current linear methods. The same predictor when combined with an Evolutionary Scale Modeling-2 projection also improves on the state of the art in conformational epitopes (AUC = 0.776). The inclusion of the graph of the 3D distances between residues did not increase the prediction accuracy. However, the long-range sequence information was essential for high accuracy. While the same model structure was applicable for linear and conformational epitopes, separate training was required for each. Combining the two slightly increased the linear accuracy (AUC 0.775 versus 0.768) and reduced the conformational accuracy (AUC = 0.769).

Brewpitopes: a pipeline to refine B-cell epitope predictions during public health emergencies

The application of B-cell epitope identification to develop therapeutic antibodies and vaccine candidates is well established. However, the validation of epitopes is time-consuming and resource-intensive. To alleviate this, in recent years, multiple computational predictors have been developed in the immunoinformatics community. Brewpitopes is a pipeline that curates bioinformatic B-cell epitope predictions obtained by integrating different state-of-the-art tools. We used additional computational predictors to account for subcellular location, glycosylation status, and surface accessibility of the predicted epitopes. The implementation of these sets of rational filters optimizes in vivo antibody recognition properties of the candidate epitopes. To validate Brewpitopes, we performed a proteome-wide analysis of SARS-CoV-2 with a particular focus on S protein and its variants of concern. In the S protein, we obtained a fivefold enrichment in terms of predicted neutralization versus the epitopes identified by individual tools. We analyzed epitope landscape changes caused by mutations in the S protein of new viral variants that were linked to observed immune escape evidence in specific strains. In addition, we identified a set of epitopes with neutralizing potential in four SARS-CoV-2 proteins (R1AB, R1A, AP3A, and ORF9C). These epitopes and antigenic proteins are conserved targets for viral neutralization studies. In summary, Brewpitopes is a powerful pipeline that refines B-cell epitope bioinformatic predictions during public health emergencies in a high-throughput capacity to facilitate the optimization of experimental validation of therapeutic antibodies and candidate vaccines.

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/).

Interaction of SARS-CoV-2 with host cells and antibodies: experiment and simulation

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is the causative agent of the devastating global COVID-19 pandemic announced by WHO in March 2020. Through unprecedented scientific effort, several vaccines, drugs and antibodies have been developed, saving millions of lives, but the fight against COVID-19 continues as immune escape variants of concern such as Delta and Omicron emerge. To develop more effective treatments and to elucidate the side effects caused by vaccines and therapeutic agents, a deeper understanding of the molecular interactions of SARS-CoV-2 with them and human cells is required. With special interest in computational approaches, we will focus on the structure of SARS-CoV-2 and the interaction of its spike protein with human angiotensin-converting enzyme-2 (ACE2) as a prime entry point of the virus into host cells. In addition, other possible viral receptors will be considered. The fusion of viral and human membranes and the interaction of the spike protein with antibodies and nanobodies will be discussed, as well as the effect of SARS-CoV-2 on protein synthesis in host cells.

Molecular Evolutionary Analyses of the Spike Protein Gene and Spike Protein in the SARS-CoV-2 Omicron Subvariants

To better understand the evolution of the SARS-CoV-2 Omicron subvariants, we performed molecular evolutionary analyses of the spike (S) protein gene/S protein using advanced bioinformatics technologies. First, time-scaled phylogenetic analysis estimated that a common ancestor of the Wuhan, Alpha, Beta, Delta variants, and Omicron variants/subvariants diverged in May 2020. After that, a common ancestor of the Omicron variant generated various Omicron subvariants over one year. Furthermore, a chimeric virus between the BM.1.1.1 and BJ.1 subvariants, known as XBB, diverged in July 2021, leading to the emergence of the prevalent subvariants XBB.1.5 and XBB.1.16. Next, similarity plot (SimPlot) data estimated that the recombination point (breakpoint) corresponded to nucleotide position 1373. As a result, XBB.1.5 subvariants had the 5' nucleotide side from the breakpoint as a strain with a BJ.1 sequence and the 3' nucleotide side as a strain with a BM.1.1.1 sequence. Genome network data showed that Omicron subvariants were genetically linked with the common ancestors of the Wuhan and Delta variants, resulting in many amino acid mutations. Selective pressure analysis estimated that the prevalent subvariants, XBB.1.5 and XBB.1.16, had specific amino acid mutations, such as V445P, G446S, N460K, and F486P, located in the RBD when compared with the BA.4 and BA.5 subvariants. Moreover, some representative immunogenicity-associated amino acid mutations, including L452R, F486V, R493Q, and V490S, were also found in these subvariants. These substitutions were involved in the conformational epitopes, implying that these mutations affect immunogenicity and vaccine evasion. Furthermore, these mutations were identified as positive selection sites. These results suggest that the S gene/S protein Omicron subvariants rapidly evolved, and mutations observed in the conformational epitopes may reduce the effectiveness of the current vaccine, including bivalent vaccines such as mRNA vaccines containing the BA.4/BA.5 subvariants.

DL-TCNN: Deep Learning-based Temporal Convolutional Neural Network for prediction of conformational B-cell epitopes

Prediction of conformational B-cell epitopes (CBCE) is an essential phase for vaccine design, drug invention, and accurate disease diagnosis. Many laboratorial and computational approaches have been developed to predict CBCE. However, laboratorial experiments are costly and time consuming, leading to the popularity of Machine Learning (ML)-based computational methods. Although ML methods have succeeded in many domains, achieving higher accuracy in CBCE prediction remains a challenge. To overcome this drawback and consider the limitations of ML methods, this paper proposes a novel DL-based framework for CBCE prediction, leveraging the capabilities of deep learning in the medical domain. The proposed model is named Deep Learning-based Temporal Convolutional Neural Network (DL-TCNN), which hybridizes empirical hyper-tuned 1D-CNN and TCN. TCN is an architecture that employs causal convolutions and dilations, adapting well to sequential input with extensive receptive fields. To train the proposed model, physicochemical features are firstly extracted from antigen sequences. Next, the Synthetic Minority Oversampling Technique (SMOTE) is applied to address the class imbalance problem. Finally, the proposed DL-TCNN is employed for the prediction of CBCE. The model's performance is evaluated and validated on a benchmark antigen-antibody dataset. The DL-TCNN achieves 94.44% accuracy, and 0.989 AUC score for the training dataset, 78.53% accuracy, and 0.661 AUC score for the validation dataset; and 85.10% accuracy, 0.855 AUC score for the testing dataset. The proposed model outperforms all the existing CBCE methods.

Computational Methods in Immunology and Vaccinology: Design and Development of Antibodies and Immunogens

The design of new biomolecules able to harness immune mechanisms for the treatment of diseases is a prime challenge for computational and simulative approaches. For instance, in recent years, antibodies have emerged as an important class of therapeutics against a spectrum of pathologies. In cancer, immune-inspired approaches are witnessing a surge thanks to a better understanding of tumor-associated antigens and the mechanisms of their engagement or evasion from the human immune system. Here, we provide a summary of the main state-of-the-art computational approaches that are used to design antibodies and antigens, and in parallel, we review key methodologies for epitope identification for both B- and T-cell mediated responses. A special focus is devoted to the description of structure- and physics-based models, privileged over purely sequence-based approaches. We discuss the implications of novel methods in engineering biomolecules with tailored immunological properties for possible therapeutic uses. Finally, we highlight the extraordinary challenges and opportunities presented by the possible integration of structure- and physics-based methods with emerging Artificial Intelligence technologies for the prediction and design of novel antigens, epitopes, and antibodies.

Molecular evolutionary analyses of the fusion protein gene in human respirovirus 1

Few evolutionary studies of the human respiratory virus (HRV) have been conducted, but most of them have focused on HRV3. In this study, the full-length fusion (F) genes in HRV1 strains collected from various countries were subjected to time-scaled phylogenetic, genome population size, and selective pressure analyses. Antigenicity analysis was performed on the F protein. The time-scaled phylogenetic tree using the Bayesian Markov Chain Monte Carlo method estimated that the common ancestor of the HRV1 F gene diverged in 1957 and eventually formed three lineages. Phylodynamic analyses showed that the genome population size of the F gene has doubled over approximately 80 years. Phylogenetic distances between the strains were short (< 0.02). No positive selection sites were detected for the F protein, whereas many negative selection sites were identified. Almost all conformational epitopes of the F protein, except one in each monomer, did not correspond to the neutralising antibody (NT-Ab) binding sites. These results suggest that the HRV1 F gene has constantly evolved over many years, infecting humans, while the gene may be relatively conserved. Mismatches between computationally predicted epitopes and NT-Ab binding sites may be partially responsible for HRV1 reinfection and other viruses such as HRV3 and respiratory syncytial virus.

Molecular Evolutionary Analyses of the RNA-Dependent RNA Polymerase (RdRp) Region and VP1 Gene in Human Norovirus Genotypes GII.P6-GII.6 and GII.P7-GII.6

To understand the evolution of GII.P6-GII.6 and GII.P7-GII.6 strains, the prevalent human norovirus genotypes, we analysed both the RdRp region and VP1 gene in globally collected strains using authentic bioinformatics technologies. A common ancestor of the P6- and P7-type RdRp region emerged approximately 50 years ago and a common ancestor of the P6- and P7-type VP1 gene emerged approximately 110 years ago. Subsequently, the RdRp region and VP1 gene evolved. Moreover, the evolutionary rates were significantly faster for the P6-type RdRp region and VP1 gene than for the P7-type RdRp region and VP1 genes. Large genetic divergence was observed in the P7-type RdRp region and VP1 gene compared with the P6-type RdRp region and VP1 gene. The phylodynamics of the RdRp region and VP1 gene fluctuated after the year 2000. Positive selection sites in VP1 proteins were located in the antigenicity-related protruding 2 domain, and these sites overlapped with conformational epitopes. These results suggest that the GII.6 VP1 gene and VP1 proteins evolved uniquely due to recombination between the P6- and P7-type RdRp regions in the HuNoV GII.P6-GII.6 and GII.P7-GII.6 virus strains.

The ClusPro AbEMap web server for the prediction of antibody epitopes

Antibodies play an important role in the immune system by binding to molecules called antigens at their respective epitopes. These interfaces or epitopes are structural entities determined by the interactions between an antibody and an antigen, making them ideal systems to analyze by using docking programs. Since the advent of high-throughput antibody sequencing, the ability to perform epitope mapping using only the sequence of the antibody has become a high priority. ClusPro, a leading protein-protein docking server, together with its template-based modeling version, ClusPro-TBM, have been re-purposed to map epitopes for specific antibody-antigen interactions by using the Antibody Epitope Mapping server (AbEMap). ClusPro-AbEMap offers three different modes for users depending on the information available on the antibody as follows: (i) X-ray structure, (ii) computational/predicted model of the structure or (iii) only the amino acid sequence. The AbEMap server presents a likelihood score for each antigen residue of being part of the epitope. We provide detailed information on the server's capabilities for the three options and discuss how to obtain the best results. In light of the recent introduction of AlphaFold2 (AF2), we also show how one of the modes allows users to use their AF2-generated antibody models as input. The protocol describes the relative advantages of the server compared to other epitope-mapping tools, its limitations and potential areas of improvement. The server may take 45-90 min depending on the size of the proteins.

Fungal Vaccine Development: State of the Art and Perspectives Using Immunoinformatics

Fungal infections represent a serious global health problem, causing damage to health and the economy on the scale of millions. Although vaccines are the most effective therapeutic approach used to combat infectious agents, at the moment, no fungal vaccine has been approved for use in humans. However, the scientific community has been working hard to overcome this challenge. In this sense, we aim to describe here an update on the development of fungal vaccines and the progress of methodological and experimental immunotherapies against fungal infections. In addition, advances in immunoinformatic tools are described as an important aid by which to overcome the difficulty of achieving success in fungal vaccine development. In silico approaches are great options for the most important and difficult questions regarding the attainment of an efficient fungal vaccine. Here, we suggest how bioinformatic tools could contribute, considering the main challenges, to an effective fungal vaccine.

SEPPA-mAb: spatial epitope prediction of protein antigens for mAbs

Identifying the exact epitope positions for a monoclonal antibody (mAb) is of critical importance yet highly challenging to the Ab design of biomedical research. Based on previous versions of SEPPA 3.0, we present SEPPA-mAb for the above purpose with high accuracy and low false positive rate (FPR), suitable for both experimental and modelled structures. In practice, SEPPA-mAb appended a fingerprints-based patch model to SEPPA 3.0, considering the structural and physic-chemical complementarity between a possible epitope patch and the complementarity-determining region of mAb and trained on 860 representative antigen-antibody complexes. On independent testing of 193 antigen-antibody pairs, SEPPA-mAb achieved an accuracy of 0.873 with an FPR of 0.097 in classifying epitope and non-epitope residues under the default threshold, while docking-based methods gave the best AUC of 0.691, and the top epitope prediction tool gave AUC of 0.730 with balanced accuracy of 0.635. A study on 36 independent HIV glycoproteins displayed a high accuracy of 0.918 and a low FPR of 0.058. Further testing illustrated outstanding robustness on new antigens and modelled antibodies. Being the first online tool predicting mAb-specific epitopes, SEPPA-mAb may help to discover new epitopes and design better mAbs for therapeutic and diagnostic purposes. SEPPA-mAb can be accessed at http://www.badd-cao.net/seppa-mab/.

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.

Mapping of antibody epitopes based on docking and homology modeling

Antibodies are key proteins produced by the immune system to target pathogen proteins termed antigens via specific binding to surface regions called epitopes. Given an antigen and the sequence of an antibody the knowledge of the epitope is critical for the discovery and development of antibody based therapeutics. In this work, we present a computational protocol that uses template-based modeling and docking to predict epitope residues. This protocol is implemented in three major steps. First, a template-based modeling approach is used to build the antibody structures. We tested several options, including generation of models using AlphaFold2. Second, each antibody model is docked to the antigen using the fast Fourier transform (FFT) based docking program PIPER. Attention is given to optimally selecting the docking energy parameters depending on the input data. In particular, the van der Waals energy terms are reduced for modeled antibodies relative to x-ray structures. Finally, ranking of antigen surface residues is produced. The ranking relies on the docking results, that is, how often the residue appears in the docking poses' interface, and also on the energy favorability of the docking pose in question. The method, called PIPER-Map, has been tested on a widely used antibody-antigen docking benchmark. The results show that PIPER-Map improves upon the existing epitope prediction methods. An interesting observation is that epitope prediction accuracy starting from antibody sequence alone does not significantly differ from that of starting from unbound (i.e., separately crystallized) antibody structure.

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.

Reducing the Immunogenicity of Pulchellin A-Chain, Ribosome-Inactivating Protein Type 2, by Computational Protein Engineering for Potential New Immunotoxins

Pulchellin is a plant biotoxin categorized as a type 2 ribosome-inactivating protein (RIPs) which potentially kills cells at very low concentrations. Biotoxins serve as targeting immunotoxins (IT), consisting of antibodies conjugated to toxins. ITs have two independent protein components, a human antibody and a toxin with a bacterial or plant source; therefore, they pose unique setbacks in immunogenicity. To overcome this issue, the engineering of epitopes is one of the beneficial methods to elicit an immunological response. Here, we predicted the tertiary structure of the pulchellin A-chain (PAC) using five common powerful servers and adopted the best model after refining. Then, predicted structure using four distinct computational approaches identified conformational B-cell epitopes. This approach identified some amino acids as a potential for lowering immunogenicity by point mutation. All mutations were then applied to generate a model of pulchellin containing all mutations (so-called PAM). Mutants’ immunogenicity was assessed and compared to the wild type as well as other mutant characteristics, including stability and compactness, were computationally examined in addition to immunogenicity. The findings revealed a reduction in immunogenicity in all mutants and significantly in N146V and R149A. Furthermore, all mutants demonstrated remarkable stability and validity in Molecular Dynamic (MD) simulations. During docking and simulations, the most homologous toxin to pulchellin, Abrin-A was applied as a control. In addition, the toxin candidate containing all mutations (PAM) disclosed a high level of stability, making it a potential model for experimental deployment. In conclusion, by eliminating B-cell epitopes, our computational approach provides a potential less immunogenic IT based on PAC.

The effects of the E3 ubiquitin-protein ligase UBR7 of Frankliniella occidentalis on the ability of insects to acquire and transmit TSWV

The interactions between plant viruses and insect vectors are very complex. In recent years, RNA sequencing data have been used to elucidate critical genes of Tomato spotted wilt ortho-tospovirus (TSWV) and Frankliniella occidentalis (F. occidentalis). However, very little is known about the essential genes involved in thrips acquisition and transmission of TSWV. Based on transcriptome data of F. occidentalis infected with TSWV, we verified the complete sequence of the E3 ubiquitin-protein ligase UBR7 gene (UBR7), which is closely related to virus transmission. Additionally, we found that UBR7 belongs to the E3 ubiquitin-protein ligase family that is highly expressed in adulthood in F. occidentalis. UBR7 could interfere with virus replication and thus affect the transmission efficiency of F. occidentalis. With low URB7 expression, TSWV transmission efficiency decreased, while TSWV acquisition efficiency was unaffected. Moreover, the direct interaction between UBR7 and the nucleocapsid (N) protein of TSWV was investigated through surface plasmon resonance and GST pull-down. In conclusion, we found that UBR7 is a crucial protein for TSWV transmission by F. occidentalis, as it directly interacts with TSWV N. This study provides a new direction for developing green pesticides targeting E3 ubiquitin to control TSWV and F. occidentalis.

Prediction of Conformational and Linear B-Cell Epitopes on Envelop Protein of Zika Virus Using Immunoinformatics Approach

The current spread of Zika virus infection in India has become a public health issue due to the virus's possible link to birth abnormalities and neurological disorders. There is a need for enhanced vaccines or drugs as a result of its epidemic outbreak and the lack of potential medication. B-cell mediated adaptive immunity is capable of developing pathogen-specific memory that confers immunological protection. Therefore, in this study, the envelope protein of the Zika virus was retrieved from the NCBI protein database. The ABCpred and BepiPred software were used to discover linear B-cell epitopes on envelope protein. Conformational B-cell epitopes on envelope protein were identified using SEPPA 3.0 and Ellipro tools. Predicted B-cell epitopes were evaluated for allergenicity, toxicity, and antigenicity. Two consensus linear B-cell epitopes, envelope_165-180 (AKVEITPNSPRAEATL) and envelope_224-238 (PWHAGADTGTPHWNN) were identified using ABCpred and BepiPredtools. SEPPA 3.0 and Elliprotools predicted consensus conformational envelope_98-110 (DRGWGNGCGLFGK) and envelope_248-251 (AHAK) epitopes and one residue (⁷⁵PRO) within envelope protein as a component of B-cell epitopes. These predicted linear and conformational B-cell epitopes will help in designing peptide vaccines that will activate the humoral response. However, in-vitro and in-vivo laboratory experimental confirmations are still needed to prove the application's feasibility.

Advances in antibody discovery from human BCR repertoires

Antibodies make up an important and growing class of compounds used for the diagnosis or treatment of disease. While traditional antibody discovery utilized immunization of animals to generate lead compounds, technological innovations have made it possible to search for antibodies targeting a given antigen within the repertoires of B cells in humans. Here we group these innovations into four broad categories: cell sorting allows the collection of cells enriched in specificity to one or more antigens; BCR sequencing can be performed on bulk mRNA, genomic DNA or on paired (heavy-light) mRNA; BCR repertoire analysis generally involves clustering BCRs into specificity groups or more in-depth modeling of antibody-antigen interactions, such as antibody-specific epitope predictions; validation of antibody-antigen interactions requires expression of antibodies, followed by antigen binding assays or epitope mapping. Together with innovations in Deep learning these technologies will contribute to the future discovery of diagnostic and therapeutic antibodies directly from humans.

SEMA: Antigen B-cell conformational epitope prediction using deep transfer learning

One of the primary tasks in vaccine design and development of immunotherapeutic drugs is to predict conformational B-cell epitopes corresponding to primary antibody binding sites within the antigen tertiary structure. To date, multiple approaches have been developed to address this issue. However, for a wide range of antigens their accuracy is limited. In this paper, we applied the transfer learning approach using pretrained deep learning models to develop a model that predicts conformational B-cell epitopes based on the primary antigen sequence and tertiary structure. A pretrained protein language model, ESM-1v, and an inverse folding model, ESM-IF1, were fine-tuned to quantitatively predict antibody-antigen interaction features and distinguish between epitope and non-epitope residues. The resulting model called SEMA demonstrated the best performance on an independent test set with ROC AUC of 0.76 compared to peer-reviewed tools. We show that SEMA can quantitatively rank the immunodominant regions within the SARS-CoV-2 RBD domain. SEMA is available at https://github.com/AIRI-Institute/SEMAi and the web-interface http://sema.airi.net.