Leveraging artificial intelligence and machine learning to accelerate discovery of disease-modifying therapies in type 1 diabetes – published online 19/12/2024

Melanie R. Shapiro, Erin M. Tallon, Matthew E. Brown, Amanda L. Posgai, Mark A. Clements, Todd M. Brusko

Although considerable resources and decades-long research efforts have been directed towards the discovery of disease-modifying therapies for type 1 diabetes, the pace of therapeutic discovery has substantially lagged behind expectations. To accelerate the discovery and translation of therapies that slow progression to clinical onset of disease, there is a pressing need to optimise cohort, therapeutic agent and endpoint selection. In this issue, Shapiro et al (https://doi.org/10.1007/s00125-024-06339-6) review the emerging role of artificial intelligence and machine learning in addressing these imperatives. The authors highlight the potential for using artificial intelligence-enabled analytics to rapidly advance the field of immunogenetics, speed up drug discovery and target prediction efforts, enable in silico testing of personalised therapeutic agents, facilitate drug repurposing efforts and accelerate clinical trials of disease-modifying therapies in type 1 diabetes. They conclude with a discussion of ethical and pragmatic considerations that impact the relevance and interpretation of artificial intelligence-aided discoveries. The figures from this review are available as a downloadable slideset.