Recursion and Google Cloud case study

A recent Case Study from Google Cloud highlights how Recursion is accelerating new treatments using the Recursion OS platform which “supports bursts of computational power that weigh in at trillions of calculations per second.”

Combining a data-driven understanding of biology and chemistry with the latest in machine learning tools, the study notes that Recursion is advancing a pipeline of clinical stage drugs, including REC-4881, a potential first-in-disease treatment for the rare disease Familial Adenomatous Polyposis (FAP) that is one of the most advanced AI drugs in development today.

“Recursion has reached an inflection point — from proving that AI can participate in drug discovery to demonstrating that an AI-native operating system can generate clinical proof and durable value,” notes CEO and President Najat Khan, PhD.

In addition to five drugs advancing through clinical trials in Recursion’s internal pipeline and with partners like Sanofi and Roche and and Genentech, the study notes that Recursion has developed a suite of state-of-the-art machine learning foundation models, and maps of biology both internally and with partners (including the world's first whole-genome Neuromap and Microglia Map) that are uncovering unknown biology in difficult areas like neurological diseases.

Leveraging a hybrid computing approach – training models on Recursion’s supercomputer, BioHive-2, and running inference on Cloud GPUs and TPUs – has allowed Recursion to continue to scale efficiently. "The potential of using Cloud TPU pods to accelerate our research while keeping operational costs and complexity low is a big draw," says CTO Ben Mabey.

Learn more:  https://cloud.google.com/customers/recursion?hl=en&e=48754805