Schrödinger announced that it is collaborating with Eli Lilly to integrate the pharmaceutical company’s artificial intelligence–based platform, TuneLab, into Schrödinger’s drug design software, LiveDesign. The collaboration will allow biotechnology companies to access Lilly’s AI-driven drug discovery tools directly through Schrödinger’s platform.
The integration will make TuneLab available within LiveDesign, Schrödinger’s cloud-based software used in drug discovery programs. LiveDesign supports chemists by enabling compound design and predicting characteristics such as absorption and distribution.
These capabilities help researchers evaluate how experimental drugs may behave in the body during development. By adding TuneLab, users will be able to apply AI and machine learning workflows alongside LiveDesign’s existing features.
Schrödinger stated that current LiveDesign customers will have access to TuneLab during the first quarter of this year. The software is expected to become available to new users in the second quarter, according to Karen Akinsanya, Schrödinger’s chief strategy officer.
The collaboration reflects a broader increase in the use of artificial intelligence across drug discovery and safety testing. Drug developers are turning to AI-based approaches to achieve faster and lower-cost research outcomes. This trend aligns with an FDA push to reduce animal testing in the near future by supporting alternative methods in drug development.
Eli Lilly launched TuneLab last year as an artificial intelligence and machine learning platform designed to provide biotechnology companies with access to drug discovery models trained on years of Lilly’s internal research data. The company has already announced multiple partnerships with biotech firms that are using the platform in their drug development efforts.
According to Lilly, broader use of TuneLab contributes to more varied training data for its models and supports faster movement of molecules through the discovery process. Aliza Apple, global head of Lilly TuneLab, said, “More biotechs using the models means more diverse training data… Ultimately, this is about moving molecules through discovery faster for the patients who are waiting.”
Schrödinger described LiveDesign as a priority interface through which participating biotechnology companies will access TuneLab workflows. Pat Lorton, chief technology officer and chief operating officer for software at Schrödinger, said the collaboration reflects demand for a unified informatics platform that provides access to AI models, physics-based calculations, and experimental data across discovery teams.
Karen Akinsanya, who also serves as president of research and development for therapeutics at Schrödinger, said the company has a long history of working with partners to accelerate drug discovery. She noted that Schrödinger has previously used LiveDesign’s physics-based and AI and machine learning methods in both proprietary and collaborative programs and plans to build on that experience through the integration of TuneLab.
Lilly stated that TuneLab was developed using a global network of technology partners, including Schrödinger and other AI and machine learning providers. The platform is hosted by a third party and uses a federated learning approach that allows Lilly and partner companies to use TuneLab while keeping proprietary data separate and private.
TuneLab AI Platform Enhances Drug Discovery Efficiency
The partnership focuses on combining Schrödinger’s computational chemistry expertise with Eli Lilly’s extensive drug discovery capabilities. Researchers can now access a streamlined workflow that allows rapid simulation, analysis, and refinement of potential drug candidates. This integration is expected to improve decision-making, reduce time-to-clinic for promising compounds, and ultimately bring new therapies to patients faster.
By embedding advanced AI tools into LiveDesign, Eli Lilly aims to enhance collaboration between computational chemists and medicinal chemists. The system facilitates rapid hypothesis testing, more informed candidate selection, and efficient iteration cycles. The result is a more agile and data-driven approach to discovering next-generation therapeutics.
Industry experts view this collaboration as a key example of how artificial intelligence can transform traditional drug discovery processes. By combining predictive modeling with experimental design, the integration supports smarter decision-making, better resource allocation, and faster innovation in pharmaceutical research.
