A genomics library for the AI era

Regeneron Genetics Center (RGC) leverages a massive, longitudinal genomic dataset to drive drug discovery and validate therapeutic targets. By sequencing over 3 million individuals—with a goal of reaching 20 million—the center prioritizes data diversity, particularly among non-European populations, to mitigate scientific bias and enhance biological understanding. This rich, multimodal data, combining genetic information with electronic health records, provides a critical foundation for training life sciences-oriented AI models. Collaborations with global academic partners and healthcare systems remain central to this operation, enabling the identification of novel targets for programs like the recently approved hearing loss gene therapy, Otarmeni. Moving forward, RGC aims to scale its data accumulation through innovative tokenization techniques and potential direct-to-consumer partnerships, further embedding its insights into the broader landscape of healthcare and patient-level interventions.