BioPharma, Artificial Intelligence

Generate Bio adds $370M for big push toward programmable protein medicines

Generate Biomedicines applies artificial intelligence and machine learning to protein analysis, which it uses to program its protein therapies for particular applications. The startup now has $370 million in financing to rapidly scale up operations, with a goal of reaching the clinic within two years.

AI, machine learning


“Programmable medicine” is a phrase popping up in biotech financings lately—usually in the context of genetic medicines. But RNA therapies aren’t the only drugs that can be programmed with features and functions. Artificial intelligence is revealing new protein insights, and Generate Biomedicines claims its suite of proprietary technologies enables the startup to develop programmable protein therapies. The company just raised $370 million to prove it.

So how does Cambridge, Massachusetts-based Generate program its proteins? It has analyzed the universe of known proteins in nature to learn how they’re made and how they function. The protein analysis identifies aspects of a disease that can be addressed with a protein. The technology finds patterns, and using machine-learning techniques, it makes predictions about the targets a protein will bind to as well as the subsequent therapeutic effect.

Generate contends it approach can address targets that were previously deemed undruggable. The company also says the technology speeds up the process of protein drug research. Those protein therapies can come in various forms: peptides, antibodies, enzymes, and cytokines. But Generate also says its technology can go beyond proteins found in nature by generating entirely novel proteins designed for a particular therapeutic need.

“Generate is deploying machine learning at scale to understand the genetic code underlying the function of proteins,” the startup’s CEO Mike Nally said in a prepared statement. “We are pioneering the field of Generative Biology—a revolutionary approach to drug development that allows us to program novel protein therapeutics capable of performing almost any desired biological function.”

Generate is a product of venture capital firm Flagship Pioneering. The protein analysis technologies developed within Flagship for three years before Generate formally launched last year. At the time, the startup’s founders would not say much about particular drugs or drug targets. Generate isn’t disclosing much more about its pipeline now, other than to say it aims to have multiple preclinical programs by the end of this year, and several in clinical testing in 2023.

Sponsored Post

Physician Targeting Using Real-time Data: How PurpleLab’s Alerts Can Help

By leveraging real-time data that offers unprecedented insights into physician behavior and patient outcomes, companies can gain a competitive advantage with prescribers. PurpleLab®, a healthcare analytics platform with one of the largest medical and pharmaceutical claims databases in the United States, recently announced the launch of Alerts which translates complex information into actionable insights, empowering companies to identify the right physicians to target, determine the most effective marketing strategies and ultimately improve patient care.

To execute on its plans, Generate is rapidly scaling up its operations. The company is building two facilities totaling 140,000 square feet. Those sites will house computational biology, machine learning, and data generation, as well as wet lab capabilities. The startup also going on a hiring spree. The company projects that its headcount of about 80 will balloon to an estimated 500 over the next two years.

The financing announced Thursday is a Series B round of funding. Besides Flagship, disclosed investors include a subsidiary of the Abu Dhabi Investment Authority, the Alaska Permanent Fund, Altitude Life Science Ventures, ARCH Venture Partners, Fidelity Management & Research Company, Morningside Ventures, and funds and accounts advised by T. Rowe Price Associates.

Photo: Andrzej Wojcicki, Getty Images