New artificial intelligence (AI) tools could help identify immune biomarkers used to determine whether a new vaccine candidate works.
Discovering and validating potential immune biomarkers is a highly complex and time-consuming process. These biomarkers can be identified in several ways, including studies of recovery from natural infection, animal immunogenicity studies, and human clinical studies. Scientific literature related to the development of vaccines against a given pathogen can cover decades of research and be highly diverse. AI offers a powerful opportunity for accelerating this process. By rapidly analyzing data, generating hypotheses, and supporting regulatory justifications, AI tools may be able to identify potential Correlates of Protection (CoPs) that could help speed the development of new vaccines. Dr. Bilal Mateen, Chief AI Officer at PATH, notes that while automated search and synthesis of research is not new, large language models have profoundly changed what's possible and the speed of execution. He highlights the exciting potential of these tools to revitalize previously considered but abandoned hypotheses, and even to propose radically new ones due to their generative nature.
PATH is actively testing an "AI co-scientist"—an AI tool designed for hypothesis generation and research tasks—to pinpoint potential immune biomarkers for diseases such as rotavirus and respiratory syncytial virus (RSV). The hypotheses generated by this AI will undergo careful review and testing by experts to verify their scientific validity. Dr. Roberto Amato, Deputy Director of AI4Science at PATH, states, “As co-scientist tools evolve, we’re identifying ways we can enhance and tailor these models for CoP discovery.” Additionally, PATH is exploring methods to improve existing AI tools to better support immune biomarker research, which might involve augmenting current AI co-scientist tools or developing new ones for specific functions like statistical analysis. Dr. Amato emphasizes that the expanding landscape of AI tools allows them to adapt and customize these models for CoP discovery, ultimately unlocking insights that could accelerate the development of new vaccines to address urgent global health challenges.
Beyond identifying potential immune biomarkers, AI co-scientists could also play a role in the vaccine authorization process itself. PATH is assessing the capability of these co-scientist tools and similar technologies to produce clear, evidence-based rationales that would support the use of potential Correlates of Protection (CoPs) in regulatory submissions. The organization aims to establish a robust foundation for AI applications in CoP research, thereby accelerating the efficient development and approval of new vaccines. The ultimate objective is to bring life-saving vaccines to market more quickly. Dr. Amato concludes that "Identifying correlates of protection can shorten the runway from vaccine discovery to delivery,” and PATH is rigorously testing new AI tools to achieve this goal.