Integrating molecular dynamics simulation with small- and wide-angle X-ray scattering to unravel the flexibility, antigen-blocking, and protease-restoring functions in a hindrance-based pro-antibody.

Spatial hindrance-based pro-antibodies (pro-Abs) are engineered antibodies to reduce monoclonal antibodies' (mAbs) on-target toxicity using universal designed blocking segments that mask mAb antigen-binding sites through spatial hindrance. By linking through protease substrates and linkers, these blocking segments can be removed site-specifically. Although many types of blocking segments have been developed, such as coiled-coil and hinge-based Ab locks, the molecular structure of the pro-Ab, particularly the region showing how the blocking fragment blocks the mAb, has not been elucidated by X-ray crystallography or cryo-EM. To achieve maximal effect, a pro-Ab must have high antigen-blocking and protease-restoring efficiencies, but the unclear structure limits its further optimization. Here, we utilized molecular dynamics (MD) simulations to study the dynamic structures of a hinge-based Ab lock pro-Ab, pro-Nivolumab, and validated the simulated structures with small- and wide-angle X-ray scattering (SWAXS). The MD results were closely consistent with SWAXS data (χ2 best-fit = 1.845, χ2 allMD = 3.080). The further analysis shows a pronounced flexibility of the Ab lock (root-mean-square deviation = 10.90 Å), yet it still masks the important antigen-binding residues by 57.3%-88.4%, explaining its 250-folded antigen-blocking efficiency. The introduced protease accessible surface area method affirmed better protease efficiency for light chain (33.03 Å2) over heavy chain (5.06 Å2), which aligns with the experiments. Overall, we developed MD-SWAXS validation method to study the dynamics of flexible blocking segments and introduced methodologies to estimate their antigen-blocking and protease-restoring efficiencies, which would potentially be advancing the clinical applications of any spatial hindrance-based pro-Ab.

Relationship between protein conformational stability and its immunogenicity when administering antigens to mice using adjuvants-Analysis employed the CH2 domain in human antibodies.

Antigen-presenting cells (APCs) play a crucial role in the immune system by breaking down antigens into peptide fragments that subsequently bind to major histocompatibility complex (MHC) molecules. Previous studies indicate that stable proteins can impede CD4+ T cell stimulation by hindering antigen processing and presentation. Conversely, certain proteins require stabilization in order to activate the immune response. Several factors, including the characteristics of the protein and the utilization of different adjuvants in animal experiments, may contribute to this disparity. In this study, we investigated the impact of adjuvants on antigen administration in mice, specifically focusing on the stability of the CH2 domain. Consequently, the CH2 domain induced a stronger IgG response in comparison to the stabilized one when using Alum and PBS (without adjuvant). On the other hand, animal experiment using Freund's adjuvant showed the opposite results. These findings indicate the significance of considering the intrinsic conformational stability of a protein when eliciting its immunogenicity, particularly within the context of vaccine development.

AttABseq: an attention-based deep learning prediction method for antigen-antibody binding affinity changes based on protein sequences.

The optimization of therapeutic antibodies through traditional techniques, such as candidate screening via hybridoma or phage display, is resource-intensive and time-consuming. In recent years, computational and artificial intelligence-based methods have been actively developed to accelerate and improve the development of therapeutic antibodies. In this study, we developed an end-to-end sequence-based deep learning model, termed AttABseq, for the predictions of the antigen-antibody binding affinity changes connected with antibody mutations. AttABseq is a highly efficient and generic attention-based model by utilizing diverse antigen-antibody complex sequences as the input to predict the binding affinity changes of residue mutations. The assessment on the three benchmark datasets illustrates that AttABseq is 120% more accurate than other sequence-based models in terms of the Pearson correlation coefficient between the predicted and experimental binding affinity changes. Moreover, AttABseq also either outperforms or competes favorably with the structure-based approaches. Furthermore, AttABseq consistently demonstrates robust predictive capabilities across a diverse array of conditions, underscoring its remarkable capacity for generalization across a wide spectrum of antigen-antibody complexes. It imposes no constraints on the quantity of altered residues, rendering it particularly applicable in scenarios where crystallographic structures remain unavailable. The attention-based interpretability analysis indicates that the causal effects of point mutations on antibody-antigen binding affinity changes can be visualized at the residue level, which might assist automated antibody sequence optimization. We believe that AttABseq provides a fiercely competitive answer to therapeutic antibody optimization.

Ionic Liquid-Based Immunization Patch for the Transdermal Delivery of Antigens.

Herein, we report a transdermal patch prepared using an ionic liquid-based solid in oil (IL-S/O) nanodispersion and a pressure-sensitive adhesive (PSA) to deliver the macromolecular antigenic protein, ovalbumin (OVA). The IL-S/O nanodispersion and a PSA were first mixed at an equal weight ratio, then coated onto a release liner, and covered with a support film. To evaluate the effect of the PSA, three types of PSAs, DURO-TAK 87-4098, DURO-TAK 87-4287, and DURO-TAK 87-235A, were used to obtain the corresponding IL-S/O patches SP-4098, SP-4287, and SP-235A, respectively. The prepared IL-S/O patches were characterized for surface morphology, viscoelasticity, and moisture content. In vitro skin penetration and in vivo immunization studies of the IL-S/O patches were performed using Yucatan micropig skin and the C57BL/6NJc1 mice model, respectively. The SP-4098 and SP-4287 delivered 5.49-fold and 5.47-fold higher amounts of drug compared with the aqueous formulation. Although both patches delivered a similar amount of drug, SP-4287 was not detached fully from the release liner after 30 days, indicating low stability. Mice immunized with the OVA-containing SP-4098 produced a 10-fold increase in anti-OVA IgG compared with those treated with an aqueous formulation. These findings suggested that the IL-S/O patch may be a good platform for the transdermal delivery of antigen molecules.

Ultrasensitive electrochemical immunosensor for the detection of C-reactive protein antigen.

Cardiovascular disease is one of the leading causes of premature death worldwide, and the determination of C-reactive protein (CRP) from human serum is of vital importance for the diagnosis of the disease. For this study, we have developed an electrochemical immunosensor based on onion-like carbon@polyacrylonitrile (OLC-PAN) for the detection of CRP antigens. This was accomplished by immobilizing CRP antibodies on a modified glassy carbon electrode (GCE). Several electrochemical techniques such as cyclic voltammetry (CV), square wave voltammetry (SWV), and electrochemical impedance spectroscopy (EIS) were employed to evaluate the electrochemical detection of the CRP antigen. This ultrasensitive method for CRP antigen detection exhibited a very good logarithmic plot from -4.52 to -12.05 g mL-1 and a limit of detection (LOD) of 0.9 fg mL-1. The high selectivity, sensitivity, and stability of the developed electrochemical immunosensor would facilitate miniaturization for point-of-care applications and the efficient diagnosis of cardiovascular diseases.

Modulating Whey Proteins Antigenicity with Lactobacillus delbrueckii subsp. bulgaricus DLPU F-36 Metabolites: Insights from Spectroscopic and Molecular Docking Studies.

Numerous studies have highlighted the potential of Lactic acid bacteria (LAB) fermentation of whey proteins for alleviating allergies. Nonetheless, the impact of LAB-derived metabolites on whey proteins antigenicity during fermentation remains uncertain. Our objective was to elucidate the impact of small molecular metabolites on the antigenicity of α-lactalbumin (α-LA) and ß-lactoglobulin (ß-LG). Through metabolomic analysis, we picked 13 bioactive small molecule metabolites from Lactobacillus delbrueckii subsp. bulgaricus DLPU F-36 for coincubation with α-LA and ß-LG, respectively. The outcomes revealed that valine, arginine, benzoic acid, 2-keto butyric acid, and glutaric acid significantly diminished the sensitization potential of α-LA and ß-LG, respectively. Moreover, chromatographic analyses unveiled the varying influence of small molecular metabolites on the structure of α-LA and ß-LG, respectively. Notably, molecular docking underscored that the primary active sites of α-LA and ß-LG involved in protein binding to IgE antibodies aligned with the interaction sites of small molecular metabolites. In essence, LAB-produced metabolites wield a substantial influence on the antigenic properties of whey proteins.

Administration sequence- and formation-dependent vaccination using acid-degradable polymeric nanoparticles with high antigen encapsulation capability.

Vaccines aim to efficiently and specifically activate the immune system via a cascade of antigen uptake, processing, and presentation by antigen-presenting cells (APCs) to CD4 and CD8 T cells, which in turn drive humoral and cellular immune responses. The specific formulation of vaccine carriers can not only shield the antigens from premature sequestering before reaching APCs but also favorably promote intracellular antigen presentation and processing. This study compares two different acid-degradable polymeric nanoparticles that are capable of encapsulating a moderately immunogenic antigen, GFP, at nearly full efficacy via electrostatic interactions or molecular affinity between His tag and Ni-NTA-conjugated monomners. This resulted in GFP-encapsulating NPs composed of ketal monomers and crosslinkers (KMX/GFP NPs) and NTA-conjugated ketal monomers and crosslinkers (NKMX/GFP NPs), respectively. Encapsulated GFP was found to be released more rapidly from NKMX/GFP NPs (electrostatic encapsulation) than from KMX/GFP NPs (affinity-driven encapsulation). In vivo vaccination studies demonstrated that while repeated injections of either NP formulation resulted in poorer generation of anti-GFP antibodies than injections of the GFP antigen itself, sequential injections of NPs and GFP as prime and booster vaccines, respectively, restored the humoral response. We proposed that NPs primarily assist APCs in antigen presentation by T cells, and B cells need to be further stimulated by free protein antigens to produce antibodies. The findings of this study suggest that the immune response can be modulated by varying the chemistry of vaccine carriers and the sequences of vaccination with free antigens and antigen-encapsulating NPs.

Toward enhancement of antibody thermostability and affinity by computational design in the absence of antigen.

Over the past two decades, therapeutic antibodies have emerged as a rapidly expanding domain within the field of biologics. In silico tools that can streamline the process of antibody discovery and optimization are critical to support a pipeline that is growing more numerous and complex every year. High-quality structural information remains critical for the antibody optimization process, but antibody-antigen complex structures are often unavailable and in silico antibody docking methods are still unreliable. In this study, DeepAb, a deep learning model for predicting antibody Fv structure directly from sequence, was used in conjunction with single-point experimental deep mutational scanning (DMS) enrichment data to design 200 potentially optimized variants of an anti-hen egg lysozyme (HEL) antibody. We sought to determine whether DeepAb-designed variants containing combinations of beneficial mutations from the DMS exhibit enhanced thermostability and whether this optimization affected their developability profile. The 200 variants were produced through a robust high-throughput method and tested for thermal and colloidal stability (Tonset, Tm, Tagg), affinity (KD) relative to the parental antibody, and for developability parameters (nonspecific binding, aggregation propensity, self-association). Of the designed clones, 91% and 94% exhibited increased thermal and colloidal stability and affinity, respectively. Of these, 10% showed a significantly increased affinity for HEL (5- to 21-fold increase) and thermostability (>2.5C increase in Tm1), with most clones retaining the favorable developability profile of the parental antibody. Additional in silico tests suggest that these methods would enrich for binding affinity even without first collecting experimental DMS measurements. These data open the possibility of in silico antibody optimization without the need to predict the antibody-antigen interface, which is notoriously difficult in the absence of crystal structures.

Induction of antigen-specific immunity by mesoporous silica nanoparticles incorporating antigen peptides.

Mesoporous silica nanoparticles (MSNs) are physically and chemically stable inorganic nanomaterials that have been attracting much attention as carriers for drug delivery systems in the field of nanomedicine. In the present study, we investigated the potential of MSN vaccines that incorporate antigen peptides for use in cancer immunotherapy. In vitro experiments demonstrated that fluorescently labeled MSNs accumulated in a line of mouse dendritic cells (DC2.4 cells), where the particles localized to the cytosol. These observations could suggest that MSNs have potential for use in delivering the loaded molecules into antigen-presenting cells, thereby stimulating the host acquired immune system. In vivo experiments demonstrated prolonged survival in mice implanted with ovalbumin (OVA)-expressing lymphoma cells (E.G7-OVA cells) following subcutaneous inoculation with MSNs incorporating OVA antigen peptides. Furthermore, OVA-specific immunoglobulin G antibodies and cytotoxic T lymphocytes were detected in the serum and the spleen cells, respectively, of mice inoculated with an MSN-OVA vaccine, indicating the induction of antigen-specific responses in both the humoral and cellular immune systems. These results suggested that the MSN therapies incorporating antigen peptides may serve as novel vaccines for cancer immunotherapy.

Accurate structure prediction of biomolecular interactions with AlphaFold 3.

The introduction of AlphaFold 21 has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design2-6. Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues. The new AlphaFold model demonstrates substantially improved accuracy over many previous specialized tools: far greater accuracy for protein-ligand interactions compared with state-of-the-art docking tools, much higher accuracy for protein-nucleic acid interactions compared with nucleic-acid-specific predictors and substantially higher antibody-antigen prediction accuracy compared with AlphaFold-Multimer v.2.37,8. Together, these results show that high-accuracy modelling across biomolecular space is possible within a single unified deep-learning framework.

Predicting TCR sequences for unseen antigen epitopes using structural and sequence features.

T-cell receptor (TCR) recognition of antigens is fundamental to the adaptive immune response. With the expansion of experimental techniques, a substantial database of matched TCR-antigen pairs has emerged, presenting opportunities for computational prediction models. However, accurately forecasting the binding affinities of unseen antigen-TCR pairs remains a major challenge. Here, we present convolutional-self-attention TCR (CATCR), a novel framework tailored to enhance the prediction of epitope and TCR interactions. Our approach utilizes convolutional neural networks to extract peptide features from residue contact matrices, as generated by OpenFold, and a transformer to encode segment-based coded sequences. We introduce CATCR-D, a discriminator that can assess binding by analyzing the structural and sequence features of epitopes and CDR3-ß regions. Additionally, the framework comprises CATCR-G, a generative module designed for CDR3-ß sequences, which applies the pretrained encoder to deduce epitope characteristics and a transformer decoder for predicting matching CDR3-ß sequences. CATCR-D achieved an AUROC of 0.89 on previously unseen epitope-TCR pairs and outperformed four benchmark models by a margin of 17.4%. CATCR-G has demonstrated high precision, recall and F1 scores, surpassing 95% in bidirectional encoder representations from transformers score assessments. Our results indicate that CATCR is an effective tool for predicting unseen epitope-TCR interactions. Incorporating structural insights enhances our understanding of the general rules governing TCR-epitope recognition significantly. The ability to predict TCRs for novel epitopes using structural and sequence information is promising, and broadening the repository of experimental TCR-epitope data could further improve the precision of epitope-TCR binding predictions.

Engineering high affinity antigen-binders: Beyond conventional antibodies.

For decades, antibodies have remained the archetypal binding proteins that can be rapidly produced with high affinity and specificity against virtually any target. A conventional antibody is still considered the prototype of a binding molecule. It is therefore not surprising that antibodies are routinely used in basic scientific and biomedical research, analytical workflows, molecular diagnostics etc. and represent the fastest growing sector in the field of biotechnology. However, several limitations associated with conventional antibodies, including stringent requirement of animal immunizations, mammalian cells for expression, issues on stability and aggregation, bulkier size and the overall time and cost of production has propelled evolution of concepts along alternative antigen binders. Rapidly evolving protein engineering approaches and high throughput screening platforms have further complemented the development of myriads of classes of non-conventional protein binders including antibody derived as well as non-antibody based molecular scaffolds. These non-canonical binders are finding use across disciplines of which diagnostics and therapeutics are the most noteworthy.

Self-assembled nanonization of fatty acid-conjugated vaccine antigen for enhanced thermal stability.

The aim of this study was to evaluate the enhanced thermal stability and physicochemical properties of fattigated vaccine antigens. High molecular weight influenza hemagglutinin (Heg) was used as a model antigen because of low heat stability requiring cold chamber. Heg was conjugated with long-chain oleic acid (C18) and short-chain 3-decenoic acid (C10) to prepare fattigated Heg. Circular dichroism analysis revealed no significant changes in the three-dimensional structure post-conjugation. In the liquid state, the fattigated Heg was self-assembled into nanoparticles (NPs) due to its amphiphilic nature, with sizes of 136.27 ± 12.78 nm for oleic acid-conjugated Heg (HOC) and 88.73 ± 3.27 nm for 3-decenoic acid-conjugated Heg (HDC). Accelerated thermal stability studies at 60 °C for 7 days demonstrated that fattigated Heg exhibited higher thermal stability than Heg in various liquid or solid states. The longer-chained HOC showed better thermal stability than HDC in the liquid state, attributed to increased hydrophobic interactions during self-assembly. In bio-mimicking liquid states at 37 °C, HOC exhibited higher thermal stability than Heg. Furthermore, solid-state HOC with cryoprotectants (trehalose, mannitol, and Tween® 80) had significantly increased thermal stability due to reduced exposure of protein surface area via nanonization behavior. The current fattigation platform could be a promising strategy for developing thermostable nano vaccines of heat-labile vaccine antigens.

Nanocarriers of antigen proteins for vaccine delivery.

Nanoformulations in vaccinology provide antigen stability and enhanced immunogenicity, in addition to providing targeted delivery and controlled release. In the last years, much research has been focused on vaccine development using virus-like particles, liposomes, emulsions, polymeric, lipid, and inorganic nanoparticles. Importantly, nanoparticle interactions with innate and adaptive immune systems must be clearly understood to guide the rational development of nanovaccines. This review provides a recap and updates on different aspects advocating nanoparticles as promising antigen carriers and immune cell activators for vaccination. Moreover, it offers a discussion of how the physicochemical properties of nanoparticles are modified to target specific cells and improve vaccine efficacy.

Planting a chemical flag on antigens.

Next-generation live vaccines are created by autonomous production of nitrated antigens.

The mechanism of epigallocatechin-3-gallate inhibiting the antigenicity of ß-lactoglobulin under pH 6.2, 7.4 and 8.2: Multi-spectroscopy and molecular simulation methods.

The antigenicity of ß-lactoglobulin (ß-LG) can be influenced by pH values and reduced by epigallocatechin-3-gallate (EGCG). However, a detailed mechanism concerning EGCG decreasing the antigenicity of ß-LG at different pH levels lacks clarity. Here, we explore the inhibition mechanism of EGCG on the antigenicity of ß-LG at pH 6.2, 7.4 and 8.2 using enzyme-linked immunosorbent assay, multi-spectroscopy, mass spectrometry and molecular simulations. The results of Fourier transform infrared spectroscopy (FTIR) and circular dichroism (CD) elucidate that the noncovalent binding of EGCG with ß-LG induces variations in the secondary structure and conformations of ß-LG. Moreover, EGCG inhibits the antigenicity of ß-LG the most at pH 7.4 (98.30 %), followed by pH 6.2 (73.18 %) and pH 8.2 (36.24 %). The inhibitory difference is attributed to the disparity in the number of epitopes involved in the interacting regions of EGCG and ß-LG. Our findings suggest that manipulating pH conditions may enhance the effectiveness of antigenic inhibitors, with the potential for further application in the food industry.

Preparation of glycopeptide-modified pH-sensitive liposomes for promoting antigen cross-presentation and induction of antigen-specific cellular immunity.

Cross-presentation, exogenous antigen presentation onto major histocompatibility complex class I molecules on antigen presenting cells, is crucially important for inducing antigen-specific cellular immune responses for cancer immunotherapy and for the treatment of infectious diseases. One strategy to induce cross-presentation is cytosolic delivery of an exogenous antigen using fusogenic or endosomolytic molecule-introduced nanocarriers. Earlier, we reported liposomes modified with pH-responsive polymers to achieve cytosolic delivery of an antigen. Polyglycidol-based or polysaccharide-based pH-responsive polymers can provide liposomes with delivery performance of antigenic proteins into cytosol via membrane fusion with endosomes responding to acidic pH, leading to induction of cross-presentation. Mannose residue was introduced to pH-responsive polysaccharides to increase uptake selectivity to antigen presenting cells and to improve cross-presentation efficiency. However, direct introduction of mannose residue into pH-responsive polysaccharides suppressed cytoplasmic delivery performance of liposomes. To avoid such interference, for this study, mannose-containing glycans were incorporated separately into pH-responsive polysaccharide-modified liposomes. Soybean agglutinin-derived glycopeptide was used as a ligand for lectins on antigen presenting cells. Incorporation of glycopeptide significantly increased the cellular uptake of liposomes by dendritic cell lines and increased cross-presentation efficiency. Liposomes incorporated both glycopeptide and pH-responsive polysaccharides exhibited strong adjuvant effects in vitro and induced the increase of dendritic cells, M1 macrophages, and effector T cells in the spleen. Subcutaneous administration of these liposomes induced antigen-specific cellular immunity, resulting in strong therapeutic effects in tumor-bearing mice. These results suggest that separate incorporation of glycopeptides and pH-responsive polysaccharides into antigen-loaded liposomes is an effective strategy to produce liposome-based nanovaccines to achieve antigen cross-presentation and induction of cellular immunity towards cancer immunotherapy.

Supervised and unsupervised machine learning approaches for monitoring subvisible particles within an aluminum-salt adjuvanted vaccine formulation.

Suspensions of protein antigens adsorbed to aluminum-salt adjuvants are used in many vaccines and require mixing during vial filling operations to prevent sedimentation. However, the mixing of vaccine formulations may generate undesirable particles that are difficult to detect against the background of suspended adjuvant particles. We simulated the mixing of a suspension containing a protein antigen adsorbed to an aluminum-salt adjuvant using a recirculating peristaltic pump and used flow imaging microscopy to record images of particles within the pumped suspensions. Supervised convolutional neural networks (CNNs) were used to analyze the images and create "fingerprints" of particle morphology distributions, allowing detection of new particles generated during pumping. These results were compared to those obtained from an unsupervised machine learning algorithm relying on variational autoencoders (VAEs) that were also used to detect new particles generated during pumping. Analyses of images conducted by applying both supervised CNNs and VAEs found that rates of generation of new particles were higher in aluminum-salt adjuvant suspensions containing protein antigen than placebo suspensions containing only adjuvant. Finally, front-face fluorescence measurements of the vaccine suspensions indicated changes in solvent exposure of tryptophan residues in the protein that occurred concomitantly with new particle generation during pumping.

pH and ROS Responsiveness of Polymersome Nanovaccines for Antigen and Adjuvant Codelivery: An In Vitro and In Vivo Comparison.

The antitumor immunity can be enhanced through the synchronized codelivery of antigens and immunostimulatory adjuvants to antigen-presenting cells, particularly dendritic cells (DCs), using nanovaccines (NVs). To study the influence of intracellular vaccine cargo release kinetics on the T cell activating capacities of DCs, we compared stimuli-responsive to nonresponsive polymersome NVs. To do so, we employed "AND gate" multiresponsive (MR) amphiphilic block copolymers that decompose only in response to the combination of chemical cues present in the environment of the intracellular compartments in antigen cross-presenting DCs: low pH and high reactive oxygen species (ROS) levels. After being unmasked by ROS, pH-responsive side chains are exposed and can undergo a charge shift within a relevant pH window of the intracellular compartments in antigen cross-presenting DCs. NVs containing the model antigen Ovalbumin (OVA) and the iNKT cell activating adjuvant α-Galactosylceramide (α-Galcer) were fabricated using microfluidics self-assembly. The MR NVs outperformed the nonresponsive NV in vitro, inducing enhanced classical- and cross-presentation of the OVA by DCs, effectively activating CD8+, CD4+ T cells, and iNKT cells. Interestingly, in vivo, the nonresponsive NVs outperformed the responsive vaccines. These differences in polymersome vaccine performance are likely linked to the kinetics of cargo release, highlighting the crucial chemical requirements for successful cancer nanovaccines.

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/).