Eli Lilly launched “TuneLab,” an AI/ML platform that gives selected biotechs access to drug-discovery models trained on years of Lilly research data. Initial public partners include Circle Pharma and insitro. Lilly says the first release reflects more than $1B worth of internal data investment.
Lilly says biotechs run its models locally on their own infrastructure in a federated setup. The program uses Rhino Federated Computing’s platform, which deploys NVIDIA FLARE for federated learning, so partners can fine-tune models and share only model updates, not raw data, back to improve the system.
According to Lilly’s program lead cited by BioPharma Dive, about a dozen startups have joined so far, including Firefly Bio and Superluminal Medicines. Rhino says there are 16 ready-to-use models spanning discovery and preclinical workflows, including predictive ADMET, with partner updates used to improve performance over time.
Among its partner base, Circle Pharma will use TuneLab to bolster AI/ML for cancer programs. Insitro said it will build new ML models for small-molecule property prediction to be used within TuneLab.
Separately, Superluminal Medicines signed a deal with Lilly on Aug. 14, 2025, worth up to $1.3B in cardiometabolic/obesity drug discovery; that agreement is separate from its TuneLab access.
The launch aligns with the FDA’s April 2025 roadmap to reduce preclinical animal testing using “new approach methodologies” (NAMs), which include AI-based models. Analysts at Jefferies estimate AI-related R&D spend could reach $30–40B by 2040.
Per BioPharma Dive, TuneLab sits within Catalyze360. Lilly’s website explicitly lists the program alongside Lilly Ventures, Gateway Labs and ExploR&D.
Filed Under: Biotech, Drug Discovery
