Eli Lilly launches TuneLab AI platform to empower biotechs in drug discovery

Eli Lilly and Company has introduced TuneLab, a cutting-edge artificial intelligence and machine learning platform aimed at transforming the landscape of drug discovery. Announced on September 9, 2025, this initiative allows biotechnology firms, particularly smaller ones, to tap into sophisticated AI models developed from Lilly's extensive proprietary research. The platform's core value lies in its foundation of data amassed over years of investment exceeding $1 billion, encompassing insights from hundreds of thousands of unique molecules across areas like drug disposition, safety profiles, and preclinical testing. By making these resources available, Lilly seeks to level the playing field, enabling innovative companies to accelerate the development of novel therapies without the need for massive in-house investments in AI infrastructure.

This move underscores a shift in the pharmaceutical sector toward collaborative innovation, where big players share advanced tools to foster breakthroughs. TuneLab operates on a federated learning framework, which ensures that sensitive data from both Lilly and its partners remains secure and private. This privacy-focused approach means biotechs can refine models using their own datasets while benefiting from Lilly's vast knowledge base, all without direct data sharing. The result is a more efficient pipeline for identifying promising drug candidates, potentially shortening the traditionally lengthy and costly process of bringing new medicines to market.

Technical features and privacy safeguards

At its heart, TuneLab provides access to pre-trained AI models that predict critical aspects of drug behavior, such as absorption, distribution, metabolism, excretion, and toxicity—collectively known as ADMET properties. These models draw from Lilly's decades-long accumulation of high-quality, consistent preclinical data, including in vitro and in vivo measurements from compounds that have progressed through various development stages. The platform's federated learning system, hosted by a third-party provider, allows for collaborative model improvement without compromising intellectual property. Partners contribute anonymized training data in a controlled manner, enhancing the models' accuracy over time while adhering to strict data protection standards.

Daniel Skovronsky, chief scientific officer and president of Lilly Research Laboratories, emphasized the platform's role in inclusivity: "Lilly TuneLab was created to be an equalizer so that smaller companies can access some of the same AI capabilities used every day by Lilly scientists. By opening up access, we hope to accelerate the creation of new medicines for patients who need them." This statement highlights TuneLab's design not just as a tool, but as a catalyst for broader ecosystem growth. Selected biotechs gain free access initially, with opportunities to integrate their data for mutual benefit, creating a virtuous cycle of innovation.

Initial partnerships driving adoption

The TuneLab rollout is bolstered by two significant collaborations that demonstrate its immediate practical applications. Circle Pharma, a clinical-stage biopharmaceutical firm specializing in macrocycle therapeutics for oncology, has agreed to integrate TuneLab into its proprietary MXMO platform. This partnership aims to improve predictions for cell permeability, oral bioavailability, and manufacturing scalability of macrocycles—molecules that target challenging proteins often deemed "undruggable." Circle Pharma's lead candidate, CID-078, an oral cyclin A/B RxL inhibitor currently in Phase 1 trials for advanced solid tumors, stands to benefit directly. Constantine Kreatsoulas, Ph.D., senior vice president and head of discovery technology sciences at Circle Pharma, noted: "We are thrilled to partner with Lilly and gain access to TuneLab. This collaboration will further enhance our MXMO platform... This collaboration comes at an important time of growth at Circle Pharma with our lead program, CID-078, now in clinical development and our preclinical pipeline advancing rapidly to address cyclins and other historically undruggable targets in oncology."

In parallel, insitro, an AI-driven biotech focused on machine learning for therapeutic discovery, is partnering with Lilly to develop specialized models for small molecule drug design. Building on their October 2024 agreement targeting metabolic diseases, this expansion involves training models on Lilly's ADMET datasets to forecast in vivo performance more accurately. Insitro will contribute its expertise in ML model building, with the resulting tools available to both companies and their TuneLab partners. Daphne Koller, Ph.D., founder and CEO of insitro, commented: "The rapid design of safe and effective small molecules has long been a holy grail in drug discovery... That is why we are especially excited to again partner with Lilly in bringing our ML capabilities to their unique dataset." Philip Tagari, insitro's chief scientific officer, added that these models could "elevate the broader ecosystem" by enabling earlier identification of viable candidates, ultimately improving patient outcomes through faster, more targeted therapies.

Broader implications for the pharmaceutical industry

TuneLab's debut aligns with surging momentum in AI adoption across pharmaceuticals, driven by regulatory encouragement and economic pressures. The U.S. Food and Drug Administration (FDA) has been advocating for alternatives to animal testing, with AI simulations offering a promising path to more ethical and efficient safety assessments. Industry analysts project explosive growth in this space: Precedence Research estimates the global AI in drug discovery market at $6.93 billion in 2025, expanding to $16.52 billion by 2034. Similarly, DelveInsight forecasts a 37.67% compound annual growth rate from 2024 to 2030, fueled by advancements in predictive modeling and data integration. MarketsandMarkets anticipates the sector reaching $6.89 billion by 2029 at a 29.9% CAGR, highlighting AI's role in cutting development costs by up to 30% and timelines by years.

This platform also reflects a strategic pivot toward open innovation, contrasting with historically siloed R&D efforts. By democratizing access to high-value AI, Lilly positions itself as a hub for the biotech ecosystem, potentially spurring discoveries in areas like oncology, immunology, and beyond. Challenges remain, including ensuring model generalizability across diverse datasets and navigating ethical concerns around AI bias in healthcare, but early indicators suggest TuneLab could set a new standard for collaborative drug development.

Connection to Lilly's Catalyze360 ecosystem

TuneLab integrates seamlessly into Lilly's Catalyze360 initiative, launched in January 2024 to support early-stage biotechs regardless of therapeutic focus. This holistic program offers multifaceted aid: strategic investments through Lilly Ventures, state-of-the-art laboratory space at Gateway Labs in Boston, and hands-on development support via ExploR&D for process optimization and scaling. By adding TuneLab, Catalyze360 now encompasses AI empowerment, creating a one-stop resource for emerging companies. Participants exchange data contributions for these benefits, fostering a networked community that drives continuous model refinement and shared progress toward patient-centric outcomes.