Role of artificial intelligence in peptide vaccine design against RNA viruses

The Development of a Novel Broad-Spectrum Influenza Polypeptide Vaccine Based on Multi-Epitope Tandem Sequences

BACKGROUND

Polypeptide vaccines have the potential to improve immune responses by targeting conserved and weakly immunogenic regions in antigens. This study aimed to identify and evaluate the efficacy of a novel influenza universal vaccine candidate consisting of multiple polypeptides derived from highly conserved regions of influenza virus proteins hemagglutinin (HA), neuraminidase (NA), and matrix protein 2 (M2).

METHODS

Immunoinformatics tools were used to screen conserved epitopes from different influenza virus subtypes (H1N1, H3N2, H5N1, H7N9, H9N2, and IBV). A polypeptide vaccine, P125-H, was constructed by linking multiple epitopes using Ii-Key technology. The immunogenicity of P125-H was assessed in mice using MF59-adjuvanted P125-H via intraperitoneal injection. Hemagglutination inhibition (HI) and neutralizing antibody responses were measured, along with IFN-γ levels in spleen lymphocytes. Protective efficacy was evaluated using viral challenge with lethal doses of H1N1 and H7N9.

RESULTS

Mice immunized with P125-H generated high levels of HI and neutralizing antibodies against multiple influenza strains. IFN-γ production was significantly elevated in spleen lymphocytes upon stimulation with the vaccine. P125-H protected mice from influenza infection, reducing weight loss and the viral load in the lungs, mitigating lung pathology, and decreasing mortality.

CONCLUSIONS

The P125-H vaccine induced broad cross-protection against multiple influenza strains and elicited robust immune responses. It demonstrates strong potential as a candidate for a universal influenza vaccine.

In silico identification and ex vivo evaluation of Toxoplasma gondii peptides restricted to HLA-A*02, HLA-A*24 and HLA-B*35 alleles in human PBMC from a Colombian population

Toxoplasma gondii infects approximately 30% of the population, and there is currently no approved vaccine. Identifying immunogenic peptides with high affinity to different HLA molecules is a promising vaccine strategy. This study used an in silico approach using artificial neural networks to identify T. gondii peptides restricted to HLA-A*02, HLA-A*24, and HLA-B*35 alleles. Proteomes from seven T. gondii strains and transcriptomic data of overexpressed genes from T. gondii-RH in human PBMC were also used. Parasite protein sequences were analyzed with R 'Epitope Prediction' library. Peptide candidates were evaluated in the artificial neural networks based on the probabilities of output neurons (p > 0.5). The IFN-γ responses in PBMC from T. gondii seronegative and seropositive individuals were evaluated by ELISpot. Peptides with higher IFN-γ induction were evaluated to identify cytotoxic response in CD8+ T cells (CD107a). In silico analysis identified 36 peptides from T. gondii proteins with predicted affinity to HLA-A*02, A*24, and B*35 alleles. Experiments with PBMCs revealed that a peptide restricted to HLA-A02 (P1: FLFAWITYV) induced a significant increase in IFN-γ-producing cells (p = 0.004). For HLA-A24, a peptide (P8: VFAFAFAFFLI) also induced a significant IFN-γ response (p = 0.004), while for the HLA-B*35 allele, the P6 peptide (YPIAPSFAM) induced a response that differed significantly from the control (p = 0.05). These peptides induced also a significant percentage of central memory CD8 + T cells expressing the degranulation marker CD107a (p < 0.05). Finally, we identified three T. gondii peptides that induced IFN-γ response, and a cytotoxic response measured by CD107a expression on CD45RAneg-CD8 cells. These peptides could be considered part of a multi-epitope vaccine against toxoplasmosis in humans.

Personalized cancer vaccine design using AI-powered technologies

Immunotherapy has ushered in a new era of cancer treatment, yet cancer remains a leading cause of global mortality. Among various therapeutic strategies, cancer vaccines have shown promise by activating the immune system to specifically target cancer cells. While current cancer vaccines are primarily prophylactic, advancements in targeting tumor-associated antigens (TAAs) and neoantigens have paved the way for therapeutic vaccines. The integration of artificial intelligence (AI) into cancer vaccine development is revolutionizing the field by enhancing various aspect of design and delivery. This review explores how AI facilitates precise epitope design, optimizes mRNA and DNA vaccine instructions, and enables personalized vaccine strategies by predicting patient responses. By utilizing AI technologies, researchers can navigate complex biological datasets and uncover novel therapeutic targets, thereby improving the precision and efficacy of cancer vaccines. Despite the promise of AI-powered cancer vaccines, significant challenges remain, such as tumor heterogeneity and genetic variability, which can limit the effectiveness of neoantigen prediction. Moreover, ethical and regulatory concerns surrounding data privacy and algorithmic bias must be addressed to ensure responsible AI deployment. The future of cancer vaccine development lies in the seamless integration of AI to create personalized immunotherapies that offer targeted and effective cancer treatments. This review underscores the importance of interdisciplinary collaboration and innovation in overcoming these challenges and advancing cancer vaccine development.

VacSol-ML(ESKAPE): Machine learning empowering vaccine antigen prediction for ESKAPE pathogens

The ESKAPE family, comprising Enterococcus faecium, Staphylococcus aureus, Klebsiella pneumoniae, Acinetobacter baumannii, Pseudomonas aeruginosa, and Enterobacter spp., poses a significant global threat due to their heightened virulence and extensive antibiotic resistance. These pathogens contribute largely to the prevalence of nosocomial or hospital-acquired infections, resulting in high morbidity and mortality rates. To tackle this healthcare problem urgent measures are needed, including development of innovative vaccines and therapeutic strategies. Designing vaccines involves a complex and resource-intensive process of identifying protective antigens and potential vaccine candidates (PVCs) from pathogens. Reverse vaccinology (RV), an approach based on genomics, made this process more efficient by leveraging bioinformatics tools to identify potential vaccine candidates. In recent years, artificial intelligence and machine learning (ML) techniques has shown promise in enhancing the accuracy and efficiency of reverse vaccinology. This study introduces a supervised ML classification framework, to predict potential vaccine candidates specifically against ESKAPE pathogens. The model's training utilized biological and physicochemical properties from a dataset containing protective antigens and non-protective proteins of ESKAPE pathogens. Conventional autoencoders based strategy was employed for feature encoding and selection. During the training process, seven machine learning algorithms were trained and subjected to Stratified 5-fold Cross Validation. Random Forest and Logistic Regression exhibited best performance in various metrics including accuracy, precision, recall, WF1 score, and Area under the curve. An ensemble model was developed, to take collective strengths of both the algorithms. To assess efficacy of our final ensemble model, a high-quality benchmark dataset was employed. VacSol-ML(ESKAPE) demonstrated outstanding discrimination between protective vaccine candidates (PVCs) and non-protective antigens. VacSol-ML(ESKAPE), proves to be an invaluable tool in expediting vaccine development for these pathogens. Accessible to the public through both a web server and standalone version, it encourages collaborative research. The web-based and standalone tools are available at http://vacsolml.mgbio.tech/.

Vaccine design and development: Exploring the interface with computational biology and AI

Computational biology involves applying computer science and informatics techniques in biology to understand complex biological data. It allows us to collect, connect, and analyze biological data at a large scale and build predictive models. In the twenty first century, computational resources along with Artificial Intelligence (AI) have been widely used in various fields of biological sciences such as biochemistry, structural biology, immunology, microbiology, and genomics to handle massive data for decision-making, including in applications such as drug design and vaccine development, one of the major areas of focus for human and animal welfare. The knowledge of available computational resources and AI-enabled tools in vaccine design and development can improve our ability to conduct cutting-edge research. Therefore, this review article aims to summarize important computational resources and AI-based tools. Further, the article discusses the various applications and limitations of AI tools in vaccine development.

Transforming Aquaculture through Vaccination: A Review on Recent Developments and Milestones

Aquaculture has rapidly emerged as one of the fastest growing industries, expanding both on global and on national fronts. With the ever-increasing demand for proteins with a high biological value, the aquaculture industry has established itself as one of the most efficient forms of animal production, proving to be a vital component of global food production by supplying nearly half of aquatic food products intended for human consumption. As in classic animal production, the prevention of diseases constitutes an enduring challenge associated with severe economic and environmental repercussions. Nevertheless, remarkable strides in the development of aquaculture vaccines have been recently witnessed, offering sustainable solutions to persistent health-related issues challenging resilient aquaculture production. These advancements are characterized by breakthroughs in increased species-specific precision, improved vaccine-delivery systems, and innovations in vaccine development, following the recent advent of nanotechnology, biotechnology, and artificial intelligence in the -omics era. The objective of this paper was to assess recent developments and milestones revolving around aquaculture vaccinology and provide an updated overview of strengths, weaknesses, opportunities, and threats of the sector, by incorporating and comparatively discussing various diffuse advances that span across a wide range of topics, including emerging vaccine technologies, innovative delivery methods, insights on novel adjuvants, and parasite vaccine development for the aquaculture sector.

The Applications of Artificial Intelligence (AI)-Driven Tools in Virus-Like Particles (VLPs) Research

Viral-like particles (VLPs) represent versatile nanoscale structures mimicking the morphology and antigenic characteristics of viruses, devoid of genetic material, making them promising candidates for various biomedical applications. The integration of artificial intelligence (AI) into VLP research has catalyzed significant advancements in understanding, production, and therapeutic applications of these nanostructures. This comprehensive review explores the collaborative utilization of AI tools, computational methodologies, and state-of-the-art technologies within the VLP domain. AI's involvement in bioinformatics facilitates sequencing and structure prediction, unraveling genetic intricacies and three-dimensional configurations of VLPs. Furthermore, AI-enabled drug discovery enables virtual screening, demonstrating promise in identifying compounds to inhibit VLP activity. In VLP production, AI optimizes processes by providing strategies for culture conditions, nutrient concentrations, and growth kinetics. AI's utilization in image analysis and electron microscopy expedites VLP recognition and quantification. Moreover, network analysis of protein-protein interactions through AI tools offers an understanding of VLP interactions. The integration of multi-omics data via AI analytics provides a comprehensive view of VLP behavior. Predictive modeling utilizing machine learning algorithms aids in forecasting VLP stability, guiding optimization efforts. Literature mining facilitated by text mining algorithms assists in summarizing information from the VLP knowledge corpus. Additionally, AI's role in laboratory automation enhances experimental efficiency. Addressing data security concerns, AI ensures the protection of sensitive information in the digital era of VLP research. This review serves as a roadmap, providing insights into AI's current and future applications in VLP research, thereby guiding innovative directions in medicine and beyond.

Discovering conserved epitopes of Monkeypox: Novel immunoinformatic and machine learning approaches

The Monkeypox virus, an Orthopoxvirus with zoonotic origins, has been responsible for a growing number of human infections reminiscent of smallpox since May 2022, as reported by the World Health Organization. As of now, there are no established medical treatments for managing Monkeypox infections. In this study, we used machine learning to select conserved epitopes. Proteins were determined using Reverse Vaccinology and Gene Ontology subcellular localization, and their epitopes were predicted. NextClade was used to calculate the number of mutations in each amino acid position using 2433 Monkeypox sequences. The Unsupervised Nearest Neighbor machine learning algorithm and ideal matrix [0 0] were used to calculate the conservancy score of epitopes. Six proteins were determined for epitope prediction. Finally, 47 MHC-I epitopes, 5 MHC-II epitopes, and 10 Linear B cell epitopes were discovered. Our method can select epitopes for vaccine design to prevent viruses with accelerated evolution and high mutation rate.

Development and use of machine learning algorithms in vaccine target selection

Computer-aided discovery of vaccine targets has become a cornerstone of rational vaccine design. In this article, I discuss how Machine Learning (ML) can inform and guide key computational steps in rational vaccine design concerned with the identification of B and T cell epitopes and correlates of protection. I provide examples of ML models, as well as types of data and predictions for which they are built. I argue that interpretable ML has the potential to improve the identification of immunogens also as a tool for scientific discovery, by helping elucidate the molecular processes underlying vaccine-induced immune responses. I outline the limitations and challenges in terms of data availability and method development that need to be addressed to bridge the gap between advances in ML predictions and their translational application to vaccine design.

Future Prospects, Approaches, and the Government's Role in the Development of a Hepatitis C Virus Vaccine

Developing a safe and effective vaccine against the hepatitis C virus (HCV) remains a top priority for global health. Despite recent advances in antiviral therapies, the high cost and limited accessibility of these treatments impede their widespread application, particularly in resource-limited settings. Therefore, the development of the HCV vaccine remains a necessity. This review article analyzes the current technologies, future prospects, strategies, HCV genomic targets, and the governmental role in HCV vaccine development. We discuss the current epidemiological landscape of HCV infection and the potential of HCV structural and non-structural protein antigens as vaccine targets. In addition, the involvement of government agencies and policymakers in supporting and facilitating the development of HCV vaccines is emphasized. We explore how vaccine development regulatory channels and frameworks affect research goals, funding, and public health policy. The significance of international and public-private partnerships in accelerating the development of an HCV vaccine is examined. Finally, the future directions for developing an HCV vaccine are discussed. In conclusion, the review highlights the urgent need for a preventive vaccine to fight the global HCV disease and the significance of collaborative efforts between scientists, politicians, and public health organizations to reach this important public health goal.

Identification and evaluation in-vitro of conserved peptides with high affinity to MHC-I as potential protective epitopes for Newcastle disease virus vaccines

BACKGROUND

Newcastle disease (ND) is a major threat to the poultry industry, leading to significant economic losses. The current ND vaccines, usually based on active or attenuated strains, are only partially effective and can cause adverse effects post-vaccination. Therefore, the development of safer and more efficient vaccines is necessary. Epitopes represent the antigenic portion of the pathogen and their identification and use for immunization could lead to safer and more effective vaccines. However, the prediction of protective epitopes for a pathogen is a major challenge, especially taking into account the immune system of the target species.

RESULTS

In this study, we utilized an artificial intelligence algorithm to predict ND virus (NDV) peptides that exhibit high affinity to the chicken MHC-I complex. We selected the peptides that are conserved across different NDV genotypes and absent in the chicken proteome. From the filtered peptides, we synthesized the five peptides with the highest affinities for the L, HN, and F proteins of NDV. We evaluated these peptides in-vitro for their ability to elicit cell-mediated immunity, which was measured by the lymphocyte proliferation in spleen cells of chickens previously immunized with NDV.

CONCLUSIONS

Our study identified five peptides with high affinity to MHC-I that have the potential to serve as protective epitopes and could be utilized for the development of multi-epitope NDV vaccines. This approach can provide a safer and more efficient method for NDV immunization.

Innovative Ecosystem Model of Vaccine Lifecycle Management

The COVID-19 pandemic has severely tested humanity, revealing the need to develop and improve the medical, economic, managerial, and IT components of vaccine management systems. The vaccine lifecycle includes vaccine research and development, production, distribution, and vaccination of the population. To manage this cycle effectively the proper organizational and IT support model of the interaction of vaccine lifecycle management stakeholders is needed—which are an innovation ecosystem and an appropriate virtual platform. A literature review has revealed the lack of methodological basis for the vaccine innovation ecosystem and virtual platform. This article is devoted to the development of a complex approach for the development of an innovation ecosystem based on vaccine lifecycle management and a virtual platform which provides the data exchange environment and IT support for the ecosystem stakeholders. The methodological foundation of the solution, developed in the article, is an enterprise architecture approach, CALS technologies, supply chain management and an open innovation philosophy. The results, presented in the article, are supposed to be a reference set of models for the creation of a vaccine innovation ecosystem, both during pandemics and periods of stable viral load.