Lilly’s TuneLab brings decades of proprietary research data into a first-of-its-kind collaborative AI platform. Seamlessly integrated into LiveDesign, TuneLab empowers discovery teams to effortlessly unite computational predictions with wet-lab validation to help drive faster, smarter, and fully aligned decisions.
Run TuneLab models directly at the point of design, eliminating manual file transfers, data exports, or context-switching.
Combine Schrödinger’s physics-based methods with Lilly’s machine learning predictions to screen and score candidate molecules faster.
Surface predictive insights alongside live experimental data across medicinal chemistry, biologics, and discovery leadership.
TuneLab features small molecule ADMET prediction and antibody developability models, which are trained on decades of proprietary datasets. Rather than evaluating endpoints in isolation, these models jointly analyze assay correlation structures to deliver comprehensive profile predictions.
Generates 30+ ADME/Tox predictions (including solubility, permeability, microsomal stability, and toxicity risk) from SMILES strings to flag liabilities before physical synthesis.
Redicts 15+ antibody developability endpoints (such as thermal stability, aggregation risk, viscosity, and solubility) directly from heavy/light chain sequences to streamline candidate selection.
TuneLab’s federated training is hosted by a third party where companies contribute data in a privacy-preserving manner to enable AI/ML drug discovery and development collaboration. Each member’s data stays within its own environment. As TuneLab member companies contribute federated training data, the models become more generalizable across diverse chemical spaces.
Get started with TuneLab in LiveDesign.
Our team will work with you to scope workflows, configure infrastructure, and onboard your team.
TuneLab is a first-of-its-kind, collaborative AI-powered drug discovery and development platform that gives biotech researchers access to powerful Lilly AI models trained on decades of proprietary research data. These are the same models used by Lilly’s own scientists every day.
Companies with at least one preclinical small molecule or antibody program. Lilly TuneLab supports predictive characterization of antibody developability as well as small molecule ADMET profiles prior to in vitro or in vivo validation, with the aim to progress only the most viable candidates and minimize dead ends in drug development.
TuneLab federated training is hosted by a third party. During a training run, a global AI model is distributed from a central orchestration server to each participating company’s node. Each node then trains this model on its proprietary data, with the raw data remaining in that node. Only model updates, such as mathematical weights and parameters, not the underlying molecular structures, are transmitted back to the central server. The server aggregates these updates from all participating nodes to improve the global model, which is then redistributed for the next training round. This iterative process continues until the model converges to optimal performance. To confirm data quality during this process, TuneLab reviews certain aggregated statistics and analytics derived from the data, together with information about assay conditions and protocols used to generate it. This review is designed not to disclose, and does not require access to, any underlying molecular structures, sequences, or individual data points.
TuneLab currently supports preclinical drug discovery programs, from first synthesis through to in vivo testing, with core models for small molecules and antibodies designed to work across different data sources and in federated environments.