Eli Lilly opens AI drug discovery vault to biotech partners through billion-dollar TuneLab platform
Eli Lilly launches TuneLab, an artificial intelligence platform providing biotechnology companies access to drug discovery models trained on over $1 billion worth of proprietary research data. The federated learning system enables smaller companies to utilise Lilly’s AI capabilities whilst preserving data privacy through third-party hosting.
Pharmaceutical giant Eli Lilly has unveiled TuneLab, a groundbreaking artificial intelligence platform that grants biotechnology companies unprecedented access to drug discovery models developed through decades of internal research investment exceeding $1 billion. The initiative represents one of the industry’s most significant data-sharing programmes aimed at accelerating therapeutic development across the biotech ecosystem.
The platform harnesses Lilly’s comprehensive drug disposition, safety, and preclinical datasets encompassing experimental data from hundreds of thousands of unique molecular compounds. This extensive repository forms the foundation for AI models designed to predict drug behaviour and optimise development pathways for partner organisations.
“Lilly has spent decades building comprehensive datasets for drug discovery. Today, we’re sharing the intelligence gained from that investment to help lift the tide of biotechnology research,” said Daniel Skovronsky, chief scientific officer and president of Lilly Research Laboratories and Lilly Immunology. “Lilly TuneLab was created to be an equaliser so that smaller companies can access some of the same AI capabilities used every day by Lilly scientists.”
Federated learning preserves proprietary data integrity
The platform employs federated learning architecture, a privacy-preserving computational approach that enables biotechnology partners to access Lilly’s AI models without directly exposing either party’s proprietary datasets. This technical framework allows for collaborative model improvement whilst maintaining competitive confidentiality requirements essential to pharmaceutical research.
Selected biotech partners contribute training data to the system, creating a continuous improvement cycle that benefits the broader research community. The reciprocal data exchange model ensures ongoing enhancement of pre-
dictive capabilities across multiple therapeutic areas and molecular targets.
TuneLab operates through third-party hosting infrastructure developed in partnership with leading technology providers and AI specialists. Future platform iterations will incorporate in vivo small molecule predictive models exclusively available through the TuneLab ecosystem, expanding analytical capabilities beyond current offerings.
Strategic integration with Catalyze360 initiative
The AI platform represents the latest addition to Lilly’s Catalyze360 programme, which provides comprehensive support for biotechnology partnerships through multiple channels. Existing Catalyze360 components include strategic capital investment via Lilly Ventures, laboratory facilities at Lilly Gateway Labs, and development expertise through Lilly ExploR&D services.
“For many early-stage biotech companies, the promise of AI and machine learning in drug discovery remains just that – a promise,” explained Nisha Nanda, group vice president and head of Lilly Catalyze360. “While the industry buzzes about the power of AI/ML to accelerate innovation, most small biotechs face a fundamental hurdle: they simply don’t have access to the largescale, high-quality data needed to impact decisions and train truly effective models.”
The initiative addresses a critical resource gap in biotechnology research, where smaller organisations often lack the extensive datasets necessary for effective AI model training. By providing access to Lilly’s computational infrastructure and validated datasets, TuneLab enables emerging companies to implement sophisticated analytical approaches typically reserved for major pharmaceutical corporations.
For more information, visit: https://tunelab.lilly.com
