Artificial intelligence for coordinating vaccine design, antiviral discovery, and real-world monitoring in the era of emerging and endemic viral threats

Abstract

Vaccine development has traditionally been a lengthy and resource-intensive process, often struggling to keep pace with rapidly emerging infectious threats. Recent advances in artificial intelligence (AI) offer new opportunities to transform this landscape by enabling faster, more precise, and data-driven approaches to vaccine design. This review examines how AI is being applied across key stages of vaccine development, including antigen discovery, epitope prediction, structural optimisation, immunogenicity assessment, and safety evaluation. We highlight the use of machine learning and deep learning models to analyse large-scale genomic, proteomic, and immunological datasets, allowing for more targeted identification of promising vaccine candidates. While AI-driven approaches show considerable promise, their successful translation into effective vaccines depends on the quality and representativeness of the data used, as well as close integration with experimental and clinical validation. Current challenges include data bias, limited representation of populations from low- and middle-income countries, and the need for transparent and interpretable models that can support regulatory decision-making. By synthesising recent developments and ongoing challenges, this review underscores the potential of AI to complement traditional vaccine development pipelines. When responsibly implemented, AI-based methods may accelerate vaccine innovation, improve global preparedness, and support more equitable responses to future infectious disease outbreaks.