Tertiary structure-based prediction of conformational B-cell epitopes through B factors

Leveraging artificial intelligence in vaccine development: A narrative review

Vaccine development stands as a cornerstone of public health efforts, pivotal in curbing infectious diseases and reducing global morbidity and mortality. However, traditional vaccine development methods are often time-consuming, costly, and inefficient. The advent of artificial intelligence (AI) has ushered in a new era in vaccine design, offering unprecedented opportunities to expedite the process. This narrative review explores the role of AI in vaccine development, focusing on antigen selection, epitope prediction, adjuvant identification, and optimization strategies. AI algorithms, including machine learning and deep learning, leverage genomic data, protein structures, and immune system interactions to predict antigenic epitopes, assess immunogenicity, and prioritize antigens for experimentation. Furthermore, AI-driven approaches facilitate the rational design of immunogens and the identification of novel adjuvant candidates with optimal safety and efficacy profiles. Challenges such as data heterogeneity, model interpretability, and regulatory considerations must be addressed to realize the full potential of AI in vaccine development. Integrating emerging technologies, such as single-cell omics and synthetic biology, promises to enhance vaccine design precision and scalability. This review underscores the transformative impact of AI on vaccine development and highlights the need for interdisciplinary collaborations and regulatory harmonization to accelerate the delivery of safe and effective vaccines against infectious diseases.

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.

Deimmunization of flagellin adjuvant for clinical application

Flagellin is the cognate ligand for host pattern recognition receptors, toll-like receptor 5 (TLR5) in the cell surface, and NAIP5/NLRC4 inflammasome in the cytosol. TLR5-binding domain is located in D1 domain, where crucial amino acid sequences are conserved among diverse bacteria. The highly conserved C-terminal 35 amino acids of flagellin were proved to be responsible for the inflammasome activation by binding to NAIP5. D2/D3 domains, located in the central region and exposed to the outside surface of flagellar filament, are heterogeneous across bacterial species and highly immunogenic. Taking advantage of TLR5- and NLRC4-stimulating activities, flagellin has been actively developed as a vaccine adjuvant and immunotherapeutic. Because of its immunogenicity, there exist worries concerning diminished efficacy and possible reactogenicity after repeated administration. Deimmunization of flagellin derivatives while preserving the TLR5/NLRC4-mediated immunomodulatory activity should be the most reasonable option for clinical application. This review describes strategies and current achievements in flagellin deimmunization.

The applications of machine learning in HIV neutralizing antibodies research-A systematic review

Machine learning algorithms play an essential role in bioinformatics and allow exploring the vast and noisy biological data in unrivaled ways. This paper is a systematic review of the applications of machine learning in the study of HIV neutralizing antibodies. This significant and vast research domain can pave the way to novel treatments and to a vaccine. We selected the relevant papers by investigating the available literature from the Web of Science and PubMed databases in the last decade. The computational methods are applied in neutralization potency prediction, neutralization span prediction against multiple viral strains, antibody-virus binding sites detection, enhanced antibodies design, and the study of the antibody-induced immune response. These methods are viewed from multiple angles spanning data processing, model description, feature selection, evaluation, and sometimes paper comparisons. The algorithms are diverse and include supervised, unsupervised, and generative types. Both classical machine learning and modern deep learning were taken into account. The review ends with our ideas regarding future research directions and challenges.

Prediction of HIV sensitivity to monoclonal antibodies using aminoacid sequences and deep learning

MOTIVATION

Knowing the sensitivity of a viral strain versus a monoclonal antibody is of interest for HIV vaccine development and therapy. The HIV strains vary in their resistance to antibodies, and the accurate prediction of virus-antibody sensitivity can be used to find potent antibody combinations that broadly neutralize multiple and diverse HIV strains. Sensitivity prediction can be combined with other methods such as generative algorithms to design novel antibodies in silico or with feature selection to uncover the sites of interest in the sequence. However, these tools are limited in the absence of in silico accurate prediction methods.

RESULTS

Our method leverages the CATNAP dataset, probably the most comprehensive collection of HIV-antibodies assays, and predicts the antibody-virus sensitivity in the form of binary classification. The methods proposed by others focus primarily on analyzing the virus sequences. However, our article demonstrates the advantages gained by modeling the antibody-virus sensitivity as a function of both virus and antibody sequences. The input is formed by the virus envelope and the antibody variable region aminoacid sequences. No structural features are required, which makes our system very practical, given that sequence data is more common than structures. We compare with two other state-of-the-art methods that leverage the same dataset and use sequence data only. Our approach, based on neuronal networks and transfer learning, measures increased predictive performance as measured on a set of 31 specific broadly neutralizing antibodies.

AVAILABILITY AND IMPLEMENTATION

https://github.com/vlad-danaila/deep_hiv_ab_pred/tree/fc-att-fix.

A Structure-Based B-cell Epitope Prediction Model Through Combing Local and Global Features

B-cell epitopes (BCEs) are a set of specific sites on the surface of an antigen that binds to an antibody produced by B-cell. The recognition of BCEs is a major challenge for drug design and vaccines development. Compared with experimental methods, computational approaches have strong potential for BCEs prediction at much lower cost. Moreover, most of the currently methods focus on using local information around target residue without taking the global information of the whole antigen sequence into consideration. We propose a novel deep leaning method through combing local features and global features for BCEs prediction. In our model, two parallel modules are built to extract local and global features from the antigen separately. For local features, we use Graph Convolutional Networks (GCNs) to capture information of spatial neighbors of a target residue. For global features, Attention-Based Bidirectional Long Short-Term Memory (Att-BLSTM) networks are applied to extract information from the whole antigen sequence. Then the local and global features are combined to predict BCEs. The experiments show that the proposed method achieves superior performance over the state-of-the-art BCEs prediction methods on benchmark datasets. Also, we compare the performance differences between data with or without global features. The experimental results show that global features play an important role in BCEs prediction. Our detailed case study on the BCEs prediction for SARS-Cov-2 receptor binding domain confirms that our method is effective for predicting and clustering true BCEs.

Deimmunization of flagellin for repeated administration as a vaccine adjuvant

Flagellin, a protein-based Toll-like receptor agonist, is a versatile adjuvant applicable to wide spectrum of vaccines and immunotherapies. Given reiterated treatments of immunogenic biopharmaceuticals should lead to antibody responses precluding repeated administration, the development of flagellin not inducing specific antibodies would greatly expand the chances of clinical applications. Here we computationally identified immunogenic regions in Vibrio vulnificus flagellin B and deimmunized by simply removing a B cell epitope region. The recombinant deimmunized FlaB (dFlaB) maintains stable TLR5-stimulating activity. Multiple immunization of dFlaB does not induce FlaB-specific B cell responses in mice. Intranasally co-administered dFlaB with influenza vaccine enhanced strong Ag-specific immune responses in both systemic and mucosal compartments devoid of FlaB-specific Ab production. Notably, dFlaB showed better protective immune responses against lethal viral challenge compared with wild type FlaB. The deimmunizing B cell epitope deletion did not compromise stability and adjuvanticity, while suppressing unwanted antibody responses that may negatively affected vaccine antigen-directed immune responses in repeated vaccinations. We explain the underlying mechanism of deimmunization by employing molecular dynamics analysis.

Conformational epitope matching and prediction based on protein surface spiral features

Background

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

Results

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

Conclusions

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

Epitopes of Protein Binders Are Related to the Structural Flexibility of a Target Protein Surface

Protein binders including antibodies are known not to bind to random sites of target proteins, and their functional effectiveness mainly depends on the binding region, called the epitope. For the development of protein binders with desired functions, it is thus critical to understand which surface region protein binders prefer (or do not prefer) to bind. The current methods for epitope prediction focus on static indicators such as structural geometry or amino acid propensity, whereas protein binding events are in fact a consequence of dynamic interactions. Here, we demonstrate that the preference for a binding site by protein binders is strongly related to the structural flexibility of a target protein surface. Molecular dynamics simulations on unbound forms of antigen structures revealed that the antigen surface in direct contact with antibodies is less flexible than the rest of the surface. This tendency was shown to be similar in other non-antibody protein binders such as affibody, DARPin, monobody, and repebody. We also found that the relatedness of epitopes to the structural flexibility of a target protein surface is dependent on the secondary structure elements of paratopes. Monobody and repebody, whose binding sites are composed of β-strands, distinctively prefer to bind to a relatively more rigid region of a target protein. These observations enabled us to develop a simple epitope prediction method which shows a comparable performance to the commonly used ones.

Enhancement of conformational B-cell epitope prediction using CluSMOTE

BACKGROUND

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

METHODS

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

RESULT

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

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.

Determination of immunodominant scaffolds of Com1 and OmpH antigens of Coxiella burnetii

Today, there is an increasing emphasis on recombinant vaccines to eliminate the side effects of conventional vaccines such as whole-cell bacteria. Query fever is an emerging disease that causes irreparable complications for both humans and domestic animals. The cause of this disease is Coxiella burnetii, a gram-negative intracellular bacteria. In order to determine the most immunodominant epitopes of Com1 and OmpH antigens of C. burnetii, the most reliable bioinformatics tools with high rates of citation in predicting B cell and T cell epitopes were used. Finally, by comparing the results of all servers, the best overlapped epitopes with the highest antigenicity among different servers were selected. In this regard, epitopes in 18-27and 67-82 amino acids residues were introduced for MHCI and MHCII of T cell, respectively, whereas epitope in 16-25 amino acids residues was introduced for B cell of OmpH antigen. The epitopes in the range of 193-202, 100-108 and 215-223 amino acid residues were preferred for MHCI class of T cell, MHCII class of T cell and B cell of Com1 antigen, respectively. For each antigen, some empirical common epitopic regions were introduced, which included both T and B cells epitopes, 53-65 and 102-111 amino acid residues of OmpH antigen as well as 38-54 range of the amino acid of Com1 antigen. All the predicted epitopes were selected based on their high antigenicity scores and number of non-digestive enzymes. To optimize the application of reported epitopes, various orders of epitopes were arranged in three categories of B cell, T cell and common T and B cells epitopes for each antigen. Then, the best immunodominant scaffolds for each antigen were proposed in these categories. The results demonstrated that the scaffold arranged based on B cell epitopes had the highest antigenicity in both antigens.

Differences in antigenic sites and other functional regions between genotype A and G mumps virus surface proteins

The surface proteins of the mumps virus, the fusion protein (F) and haemagglutinin-neuraminidase (HN), are key factors in mumps pathogenesis and are important targets for the immune response during mumps virus infection. We compared the predicted amino acid sequences of the F and HN genes from Dutch mumps virus samples from the pre-vaccine era (1957-1982) with mumps virus genotype G strains (from 2004 onwards). Genotype G is the most frequently detected mumps genotype in recent outbreaks in vaccinated communities, especially in Western Europe, the USA and Japan. Amino acid differences between the Jeryl Lynn vaccine strains (genotype A) and genotype G strains were predominantly located in known B-cell epitopes and in N-linked glycosylation sites on the HN protein. There were eight variable amino acid positions specific to genotype A or genotype G sequences in five known B-cell epitopes of the HN protein. These differences may account for the reported antigenic differences between Jeryl Lynn and genotype G strains. We also found amino acid differences in and near sites on the HN protein that have been reported to play a role in mumps virus pathogenesis. These differences may contribute to the occurrence of genotype G outbreaks in vaccinated communities.

A survey on chimeric UreB229-561-HpaA protein targeting Helicobacter pylori: Computational and in vitro urease activity valuation

Helicobacter pylori (H. pylori) as microaerophilic, Gram-negative bacterium colonize the human gastric milieu, where it impetuses chronic disorders. Vaccination is a complementary plan, along with antibiotic therapy, for clearance of H. pylori. Today, Computer based tools are essential for the evaluation, design, and experiment for novel chimeric targets for immunological administration. The purpose of this experiment was immunoinformatic analysis of UreB and HpaA molecules in a fusion arrangement and also, construction and expression of recombinant protein containing chimeric sequences. The targets sequences were screened by using of standard in silico tools and immunoinformatic web servers. The high-resolution 3D models of the protein were created and were validated; indeed, the B-and T-cell restricted epitopes were mapped on the chimeric protein. The recombinant protein in frame of the expression vector pET28a were expressed and purified successfully. The urease activity and immunoblotting were performed in vitro condition. This study confirmed that the engineered protein as a highly conserved, hydrophilic, non-allergenic contained remarkable B-cell and T-cell epitopes. It was magnificently attained; chimeric UreB_229-561-HpaA could provoke both humoral and cellular immunity. The immunoblotting was shown that the chimeric protein could be detected by serum of immunized animal and H.pylori positive patients. In this study, several antigenic patches from UreB and HpaA were identified that could be an efficient immune system activator. The in vitro analysis of our chimeric molecule confirmed its urease activity. It also confirmed that the chimeric protein could be detected by serum of immunized animal and H.pylori positive patients.

Analysis of Conserved, Computationally Predicted Epitope Regions for VP5 and VP7 Across three Orbiviruses

Orbiviruses are double-stranded RNA viruses that have profound economic and veterinary significance, 3 of the most important being African horse sickness virus (AHSV), bluetongue virus (BTV), and epizootic hemorrhagic disease virus (EHDV). Currently, vaccination and vector control are used as preventative measures; however, there are several problems with the current vaccines. Comparing viral amino acid sequences, we obtained an AHSV-BTV-EHDV consensus sequence for VP5 (viral protein 5) and for VP7 (viral protein 7) and generated homology models for these proteins. The structures and sequences were analyzed for amino acid sequence conservation, entropy, surface accessibility, and epitope propensity, to computationally determine whether consensus sequences still possess potential epitope regions. In total, 5 potential linear epitope regions on VP5 and 11 on VP7, as well as potential discontinuous B-cell epitopes, were identified and mapped onto the homology models created. Regions identified for VP5 and VP7 could be important in vaccine design against orbiviruses.

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.

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

Background

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

Results

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

Conclusions

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

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

BACKGROUND

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

RESULTS

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

CONCLUSIONS

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

Antibody H3 Structure Prediction

Antibodies are proteins of the immune system that are able to bind to a huge variety of different substances, making them attractive candidates for therapeutic applications. Antibody structures have the potential to be useful during drug development, allowing the implementation of rational design procedures. The most challenging part of the antibody structure to experimentally determine or model is the H3 loop, which in addition is often the most important region in an antibody's binding site. This review summarises the approaches used so far in the pursuit of accurate computational H3 structure prediction.

Prediction of B Cell Epitopes Among Hantavirus Strains Causing Hemorragic Fever With Renal Syndrome

Hantavirus infections are now recognized to be a global problem. The hantaviruses include several genotypic variants of the virus with different distributions in varying geographical regions. The virus genotypes seem to segregate in association with certain manifestations specific for each syndrome. They primarily include HFRS, HCPS, febrile illness with or without mild involvement of renal diseases. In the course of our study on hantavirus etiology of febrile illnesses, we recovered a hantavirus strain identified by nPCR. This has been sequenced to be Hantaan-like virus (partial S segment). The current manuscript is focused on understanding the N protein coded by S segment in terms of variation of amino acid sequences of the virus genotypes associated with HFRS. The diagnosis of this infection is achieved by PCR testing of serum/plasma or demonstration of IgM/IgG in serum. The limitations of PCR are temporal often not positive after 7 days of onset of infection. IgM detection is possible around this period and up to 21 days. IgG detection is less definitive in acute infections. Here, we report characterization of the sequence diversity of HFRS strains, 3D structure of Hantaan N protein, and B-cell epitopes on this molecule. We predicted a 20 amino acid sequence length peptide by using BepiPred online server in IEDB analysis resource program. We suggest this peptide may be used for development of geographic region-specific immunoassays like EIAs for antibody detection, monoclonal antibody development, and immunoblots (line immunoassay). J. Cell. Biochem. 118: 1182-1188, 2017. © 2016 Wiley Periodicals, Inc.

GlycoMinestruct: a new bioinformatics tool for highly accurate mapping of the human N-linked and O-linked glycoproteomes by incorporating structural features

Glycosylation plays an important role in cell-cell adhesion, ligand-binding and subcellular recognition. Current approaches for predicting protein glycosylation are primarily based on sequence-derived features, while little work has been done to systematically assess the importance of structural features to glycosylation prediction. Here, we propose a novel bioinformatics method called GlycoMine^struct(http://glycomine.erc.monash.edu/Lab/GlycoMine_Struct/) for improved prediction of human N- and O-linked glycosylation sites by combining sequence and structural features in an integrated computational framework with a two-step feature-selection strategy. Experiments indicated that GlycoMine^struct outperformed NGlycPred, the only predictor that incorporated both sequence and structure features, achieving AUC values of 0.941 and 0.922 for N- and O-linked glycosylation, respectively, on an independent test dataset. We applied GlycoMine^struct to screen the human structural proteome and obtained high-confidence predictions for N- and O-linked glycosylation sites. GlycoMine^struct can be used as a powerful tool to expedite the discovery of glycosylation events and substrates to facilitate hypothesis-driven experimental studies.

Positive-unlabeled learning for the prediction of conformational B-cell epitopes

Background

The incomplete ground truth of training data of B-cell epitopes is a demanding issue in computational epitope prediction. The challenge is that only a small fraction of the surface residues of an antigen are confirmed as antigenic residues (positive training data); the remaining residues are unlabeled. As some of these uncertain residues can possibly be grouped to form novel but currently unknown epitopes, it is misguided to unanimously classify all the unlabeled residues as negative training data following the traditional supervised learning scheme.

Results

We propose a positive-unlabeled learning algorithm to address this problem. The key idea is to distinguish between epitope-likely residues and reliable negative residues in unlabeled data. The method has two steps: (1) identify reliable negative residues using a weighted SVM with a high recall; and (2) construct a classification model on the positive residues and the reliable negative residues. Complex-based 10-fold cross-validation was conducted to show that this method outperforms those commonly used predictors DiscoTope 2.0, ElliPro and SEPPA 2.0 in every aspect. We conducted four case studies, in which the approach was tested on antigens of West Nile virus, dihydrofolate reductase, beta-lactamase, and two Ebola antigens whose epitopes are currently unknown. All the results were assessed on a newly-established data set of antigen structures not bound by antibodies, instead of on antibody-bound antigen structures. These bound structures may contain unfair binding information such as bound-state B-factors and protrusion index which could exaggerate the epitope prediction performance. Source codes are available on request.

Broad spectrum assessment of the epitope fluctuation--Immunogenicity hypothesis

Prediction of immunogenicity is a substantial barrier in vaccine design. Here, a molecular dynamics approach to assessing the immunogenicity of nanoparticles based on structure is presented. Molecular properties of epitopes on nonenveloped viral particles are quantified via a set of metrics. One such metric, epitope fluctuation (and implied flexibility), is shown to be inversely correlated with immunogenicity for each of a broad spectrum of nonenveloped viruses. The molecular metrics and experimentally determined immunogenicities for these viruses are archived in the open-source vaccine computer-aided design database. Results indicate the promise of computer-aided vaccine design to bring greater efficiency to traditional lab-based vaccine discovery approaches.

A conformation-based phage-display panning to screen neutralizing anti-VEGF VHHs with VEGFR2 mimicry behavior

The potency of VEGF-based anti-angiogenic strategies in cancer therapy and the brilliant characteristics of VHHs motivated us to directly block VEGF binding to its receptor with neutralizing single domain antibodies, thereby fading away the VEGF signaling pathway. Considering with high resolution crystal structure of VEGF-RBD/VEGFR2 complex, we could adopt a combinatorial screening strategy: stringent panning and competition ELISA, to direct the panning procedure to dominantly screen the favorable binders that bind and block the key functional regions of VEGF. Based on competition assay, the majority of the screened clones (82%) showed the VEGFR2 mimicry behavior for binding to VEGF molecule. The phage pool gets enriched in favor of sequences that bind the receptor binding sites of VEGF. Different immunoassays and molecular docking simulation verified that all selected VHHs could bind and cover the receptor binding sites of VEGF. Consequently, some modifications in panning procedure with considering the structural features and detailed information of functional regions of a protein antigen, led us to successfully trap the high-affinity specific binders against its hot functional regions. Since the selected VHHs could cover the receptor binding site of VEGF and block VEGF binding to the receptor, they might be promising candidates for anti-angiogenic therapies.

Influenza A HA's conserved epitopes and broadly neutralizing antibodies: a prediction method

A conserved epitope is an epitope retained by multiple strains of influenza as the key target of a broadly neutralizing antibody. Identification of conserved epitopes is of strong interest to help design broad-spectrum vaccines against influenza. Conservation score measures the evolutionary conservation of an amino acid position in a protein based on the phylogenetic relationships observed amongst homologous sequences. Here, Average Amino Acid Conservation Score (AAACS) is proposed as a method to identify HA's conserved epitopes. Our analysis shows that there is a clear distinction between conserved epitopes and nonconserved epitopes in terms of AAACS. This method also provides an excellent classification performance on an independent dataset. In contrast, alignment-based comparison methods do not work well for this problem, because conserved epitopes to the same broadly neutralizing antibody are usually not identical or similar. Location-based methods are not successful either, because conserved epitopes are located at both the less-conserved globular head (HA1) and the more-conserved stem (HA2). As a case study, two conserved epitopes on HA are predicted for the influenza A virus H7N9: One should match the broadly neutralizing antibodies CR9114 or FI6v3, while the other is new and requires validation by wet-lab experiments.