Designing small molecules has always been an incredibly complex and uncertain process, more art than science. “Creating carbon-carbon bonds is so difficult,” our co-founder Martin Burke told Chemical & Engineering News. “Chemists use thousands of different reactions and reaction conditions and millions of different starting materials to make small molecules. That’s the current state of the art. And it’s very artisanal.”
This excellent article by Aayushi Pratap takes us on a journey to the molecular heart of Excelsior Sciences’ platform, detailing how our breakthrough blocc-based, modularchemistry is pioneering an entirely novel form of chemistry that machines can do and AI can use.
Aayushi paints a picture of how the bloccs, in the form of “colorful powders” are weighed and analyzed by robots, to be fed into automated synthesizers that ‘snap them’ into a multitude of diverse combinations to produce new molecules and drug compounds. These are then tested for efficacy and pharmaceutical properties on Excelsior’s high-throughput automated biological testing system, and the resulting data fed into AI algorithms used to iteratively refine and develop next-generation molecules.
Generating large amounts of data quickly helps train AI models, which can then suggest molecules that are the best fits for a target protein. And automation is the way to synthesize and test scores of new compounds that serve as data points for training AI algorithms, Foley says.
This article highlights how Excelsior is transforming small-molecule chemistry into “chemistry which machines can do and AI can use”, unleashing the power of automation and AI to significantly accelerate, and reshore, drug discovery and manufacturing.
