insitro Extends Research Collaboration with Bristol Myers Squibb Leveraging insitro’s ChemML Discovery Platform

Novel ALS target identified preclinically; next phase of collaboration will leverage insitro’s ChemML™ platform to discover molecules with potential as next-generation therapies for ALS

insitro's ChemML™ platform integrates proprietary binding and ADMET data at scale with best-in-class machine learning and compute infrastructure to discover and optimize new small molecule therapeutics

Collaboration extension builds on 5-year agreement announced in 2020

SOUTH SAN FRANCISCO, Calif.--(BUSINESS WIRE)--insitro, a pioneer in machine learning–driven drug discovery and development, and Bristol Myers Squibb (NYSE: BMY), today announced the next phase of their collaboration to discover new molecules with potential as new treatments for amyotrophic lateral sclerosis (ALS).

The collaboration extension will leverage insitro’s AI-enabled ChemML™ platform to design new medicines for a novel ALS target that was identified in the first biological evaluation phase and may provide up to $20 million in new funding for the one-year extension. The successful delivery of a new therapeutic from the collaboration could have an aggregate value of more than $2 billion in discovery, development, regulatory and commercial milestone payments to insitro in addition to royalty payments.

“Our collaboration with Bristol Myers Squibb has uncovered novel targets with potential to address the underlying biology of ALS,” said Daphne Koller, Ph.D., founder and CEO of insitro. “We are now moving into the next phase – turning these discoveries into medicines. With ChemML, our end-to-end drug design platform, we can translate novel targets into advanced small-molecule leads rapidly, leveraging a differentiated set of capabilities that spans AI-driven modeling, medicinal chemistry, and structural biology. While advancing these initial drug candidates, we will continue our efforts to identify additional new targets that have the potential to be disease-modifying. Our aim remains unwavering: to deliver truly transformative treatments that enable people with ALS to live longer.”

Leveraging insitro’s ChemML™ platform to discover and advance novel ALS medicines

insitro's proprietary ChemML™ platform enables end-to-end small molecule discovery and optimization built through internal development and the acquisition of Haystack Sciences. Although significant efforts have been made to apply AI/ML to various aspects of drug discovery, advancing novel therapeutics for complex and challenging targets remains a slow and costly iterative process. ChemML™ seamlessly integrates multiple in silico and laboratory capabilities to rapidly design and optimize new small molecule therapies across different disease areas. These include:

• Data generation at scale: Proprietary Quantitative Adaptive Libraries (QALs) can generate 100s of millions of drug-target binding and selectivity data to inform ML models, and support rapid, ML-driven data generation.
• Predictive pharmacological property modeling: Advanced ML models for absorption, distribution, metabolism, excretion, and toxicity (ADMET, including in vivo PK), powered by large, high-quality datasets from a collaboration with Eli Lilly and Company.
• AI-driven design loop: A proprietary iterative engine that gets smarter at every turn as it drives “design-make-test” cycles, allowing the platform to combine in silico predictions and data from physical experiments to intelligently guide each round of synthesis.
• Robust compute infrastructure: A large compute cluster of 192 H100 GPUs that provides the necessary power for high-end ML modeling and physics-based simulation.

“insitro's proprietary machine learning-enabled discovery engine revealed new biology that allowed us to identify multiple differentiated, high-confidence novel ALS drug targets at record speed,” said Philip Tagari, Chief Scientific Officer, insitro. “These targets are supported by robust evidence, including functional data that demonstrates motor neuron survival and the reversal of multiple downstream markers of ALS pathology. Our holistic ChemML platform has already generated novel chemical compounds that can potentially be optimized using insitro's ML-powered medicinal chemistry to address technically challenging targets.”

ALS is a devastating, progressive neurodegenerative disease characterized by the selective loss of upper and lower motor neurons. The disease leads to muscle weakness, respiratory failure, and ultimately death, with a median survival of 3 to 5 years post-diagnosis.

Since nearly 90% of ALS cases arise sporadically, the initial phase of the collaboration focused on identifying cross-cutting biology – the shared underlying pathology of the disease – to develop therapies capable of helping the largest possible number of patients suffering from familial and sporadic forms of ALS. Both insitro and Bristol Myers Squibb share a deep commitment to moving at pace to bring new therapies to patients and families who are waiting for transformative treatment options.

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.