insitro, a leader in machine learning for drug discovery and development, has announced a partnership with Eli Lilly and Company (Lilly) to create sophisticated machine learning models that can accurately predict essential pharmacological properties of small molecules, including their in vivo behavior. This initiative aims to tackle persistent challenges in drug development, where determining these properties has historically been time-consuming and expensive through traditional experimental methods. The pharmaceutical industry continues to focus on developing next-generation models for small molecule design that can expedite processes and minimize experimental cycles, often hindered by insufficient data or ineffective models. By merging insitro's computational expertise with Lilly's extensive drug discovery data, the collaboration strives to meet an industry objective and foster innovation through Lilly TuneLab™, a newly introduced drug discovery platform aimed at providing biotechs with access to powerful machine learning models. Daphne Koller, Ph.D., founder and CEO of insitro, remarked: “The rapid design of safe and effective small molecules has long been a holy grail in drug discovery, but has been stymied by the unpredictability of key pharmacological properties, such as a molecule's behavior in vivo. AI can address this challenge, but only with robust, coherent, and consistently collected data on advanced molecules, data that are very rarely found. That is why we are especially excited to again partner with Lilly in bringing our ML capabilities to their unique dataset, so we can build best-in-class predictive models for small molecule properties, and bring the benefits of delivering better drugs faster to the patients who are waiting.” As part of the agreement, insitro will develop advanced machine learning models trained on Lilly’s proprietary preclinical data, leveraging a comprehensive set of in vitro and in vivo measurements from a vast range of compounds with established ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) properties, cultivated from years of Lilly’s drug discovery endeavors. These models will aim to streamline the design of compounds with favorable ADMET/pharmacokinetic profiles, thus reducing both timelines and the necessity for in vivo studies. This collaboration builds upon the existing relationship between insitro and Lilly, initiated in 2024, which centers on Lilly’s siRNA delivery and antibody discovery capabilities to support insitro’s growing pipeline in metabolic diseases. Philip Tagari, Chief Scientific Officer of insitro, stated: “These models have the potential to be a game-changer by giving researchers an elegant and powerful way to zero in on drug-like chemical structures at the earliest stages. Small molecules that reach the right tissue at the optimal concentration for the right duration result in better patient outcomes. ML-informed decision making for molecular design has been a key focus area for insitro, so we are confident these new models will improve the identification of development candidates, delivering not just for members of this collaboration, but also elevating the broader ecosystem.” The models being developed are intended to enhance the efficiency of hit-to-lead and lead optimization efforts by predicting various ADMET properties, including the in vivo behavior of small molecules. While the benefits of small molecules are evident, the vast and diverse chemical space they occupy presents significant challenges during optimization. Additionally, these properties are interconnected, complex, and notoriously difficult to predict without extensive and costly experimentation. Traditional methods for optimizing pharmacokinetics can often span years and incur costs of tens of millions of dollars. The machine learning models created by insitro will be accessible to both insitro and Lilly, as well as their partners, including biotech firms collaborating with Lilly TuneLab, and will be continually updated as the dataset expands. Lilly TuneLab is part of the Lilly Catalyze360 model, which aims to empower early-stage biotechs. The platform operates on a federated learning infrastructure, ensuring that both Lilly’s and its partners’ data remain separate and confidential. These innovative ADMET models will be a vital element of insitro’s comprehensive AI capabilities for small molecule chemistry, which includes machine learning, physics-based in silico screening, affinity machine learning models derived from proprietary DNA-encoded libraries, and an active learning medicinal chemistry engine that collectively form insitro’s leading ChemML platform. About insitro insitro is a machine learning-enabled drug discovery and development company creating a new approach for target and drug discovery. insitro is uncovering genetic targets and new therapeutic hypotheses by integrating multimodal data from human cohorts and cellular models with the power of AI and machine learning to increase the therapeutic probability of success. These insights provide the starting point for discovering new molecules, which are either built with in-house, AI-enabled drug discovery platforms or with partners that extend insitro’s impact. With more than $700 million in capital raised to date, insitro is building a “pipeline through platform” with a focus on metabolic disease and neuroscience. Approaching the clinic, insitro aims to deploy its AI models to run smaller, better powered trials, enrolling the patients who can benefit most. Learn more at insitro.com.