Abstract
Circular RNA (circRNA) vaccines have emerged as a groundbreaking innovation in infectious disease prevention and cancer immunotherapy, offering superior stability and reduced immunogenicity compared to conventional linear messenger RNA (mRNA) vaccines. While linear mRNA vaccines are prone to degradation and can trigger strong innate immune responses, covalently closed circRNA vaccines leverage their unique circular structure to enhance molecular stability and minimize innate immune activation, positioning them as a next-generation platform for vaccine development. Artificial intelligence (AI) is revolutionizing circRNA vaccine design and optimization. Deep learning models, such as convolutional neural networks (CNNs) and Transformers, integrate multi-omics data to refine antigen prediction, RNA secondary structure modeling, and lipid nanoparticle delivery system formulation, surpassing traditional bioinformatics approaches in both accuracy and efficiency. While AI-driven bioinformatics enhances antigen screening and delivery system modeling, generative AI accelerates literature synthesis and experimental planning-though the risk of fabricated references and limited biological interpretability hinders its reliability. Despite these advancements, challenges such as the "black-box" nature of AI algorithms, unreliable literature retrieval, and insufficient integration of biological mechanisms underscore the necessity for a hybrid "AI-traditional-experimental" paradigm. This approach integrates explainable AI frameworks, multi-omics validation, and ethical oversight to ensure clinical translatability. Future research should prioritize mechanism-driven AI models, real-time experimental feedback, and rigorous ethical standards to fully unlock the potential of circRNA vaccines in precision oncology and global health.