insitro, the AI company unlocking causal human biology to systematically generate high-impact therapeutics, today announced that the advanced machine learning models that insitro built with Eli Lilly and Company (Lilly) to predict in vitro and, critically, in vivo properties of small molecules can now be used by certain biotech companies in Lilly TuneLab™. Trained on multi-species preclinical data that Lilly generated over decades of research from hundreds of thousands of unique molecules, the models offer a powerful alternative to today’s industry standard method of extrapolation from in vitro assays, providing an enterprise-grade capability traditionally available only to organizations with the scale to generate such data volumes themselves. The models will be updated as the dataset continues to expand.

Announced in September 2025, the collaboration paired insitro's computational and AI/ML expertise with Lilly's proprietary preclinical dataset of in vitro and in vivo measurements from a wide array of compounds with established ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) properties, derived from decades of Lilly drug discovery, and representing a world-class dataset in quality, consistency and scale. This collaboration demonstrates the power of insitro’s platform by combining insitro’s AI and ML expertise with Lilly’s data to unlock and advance small molecule development.

“Nine in 10 programs that enter the clinic fail, most often when we first test for efficacy. That happens when the mechanism did not drive the disease, but also when the molecule never reaches the tissue at the right concentration for the right duration,” said Daphne Koller, Ph.D., founder and CEO of insitro. “The question of a molecule’s in vivo behavior has been an empirical question, answered experimentally, slowly, one compound at a time. These models make it a computational question first."

The downstream implications extend to patients. Most small molecule candidates fail, often for pharmacokinetic or safety reasons that surface late, after significant time and capital have been committed. Better prediction at the design stage may mean that fewer candidates advance on flawed structures, promising molecules reach the clinic on shorter timelines, and program development becomes more tractable. Improved in silico prediction also supports reduced reliance on animal studies, which aligns with the goals in FDA’s April 2025 Roadmap to Reducing Animal Testing in Preclinical Safety Studies and its March 2026 draft guidance on new approach methodologies.

"These models let us take signals that have historically only been available later in development from conducting in vivo studies and apply them at the virtual screening stage, before a molecule is even synthesized," stated Aliza Apple, Ph.D., Vice President, Catalyze 360 AI/ML and Global Head of Lilly TuneLab. "TuneLab was built on the premise that the learnings accumulated from drug discovery data could be leveraged as a collective, instead of under-utilized behind a single company's walls. That collective now includes some of the most valuable data sets in the industry: decades of multi-species data. For TuneLab member companies, the practical effect of these new models is a shift towards insights that can inform early decision making and where scarce resources should go."

The in vivo PK models are a critical component of insitro's TherML™ platform for small molecule discovery, alongside machine learning and physics-based in silico screening, affinity models powered by proprietary adaptive DNA-encoded libraries (generating data up to 1B compound scale), and an active-learning medicinal chemistry design engine. These models will also be utilized by insitro and its partners to advance discovery of first-in-class medicines.

Lilly TuneLab is part of Lilly Catalyze360, alongside Lilly Ventures, Lilly Gateway Labs, and Lilly ExploR&D, which together support biotech innovation by providing access to strategic capital, lab space and technology, and research and development capabilities. The platform is built on a federated learning infrastructure and hosted by a third-party provider.

About insitro

insitro is the physical AI company unlocking causal human biology to systematically advance high-impact therapeutics to treat grievous illness, founded and led by AI pioneer Daphne Koller. Our thesis: biology remains illegible to frontier AI for lack of the scaled human and cellular data needed to unlock true domain intelligence. Since 2018, we've built the world's largest integrated multi-modal corpus of human and cellular data; the Virtual Human™, a genetically anchored AI engine that reveals how disease begins, progresses, and can be resolved; and our TherML™ platform, which designs medicines against the causal drivers it identifies. Every disease we interrogate makes the model smarter, compounding our lead as the corpus grows.

We're advancing a pipeline of nine first-in-class programs, including programs targeting novel genetic master regulators of liver fat and fibrosis, entering the clinic in early 2027; the first reported genetic regulator of brown fat for metabolic health and longevity; and a proprietary oligonucleotide therapy with disease-modifying potential in 97% of ALS patients. The company is backed by $750M+ in capital from world-class investors including a16z, ARCH, BlackRock, CPP, T. Rowe Price, and Temasek, alongside collaborations with BMS, Lilly, and Gilead. Learn more at insitro.com.

Koller expands on this thesis at https://deepphenotype.substack.com/.

View source version on businesswire.com: https://www.businesswire.com/news/home/20261006068233/en/