Amgen will partner with Generate Biomedicines to discover and create protein therapeutics for five targets across several therapeutic areas and multiple modalities, through a collaboration that could generate up to $1.9 billion-plus for the Flagship Pioneering spinout, the companies said today.

By combining Amgen’s biologics drug discovery expertise with Generate’s Artificial Intelligence (AI) platform, the companies said, they can further facilitate multi-specific drug design by shortening drug discovery timelines and generating potential lead molecules that demonstrate predictable manufacturability and clinical behavior.

The collaboration reflects the focus of both companies on generative biology, which combines wet lab high throughput automation and dry lab computational biology to develop new treatments.

“We believe Generate Biomedicine’s integrated in silico design and wet lab capabilities combined with Amgen’s strength in protein engineering can accelerate our drug discovery efforts, generating novel protein sequences with optimal therapeutic properties,” David M. Reese, MD, executive vice president of Research and Development at Amgen, said in a statement.

Amgen has centered its generative biology strategy on the development of a Digital Biologics Discovery group, designed to harness the company’s strengths in biology, automation, and protein engineering. Amgen says it has committed to combining its experience and expertise in biologics with emerging sequence-based drug design technologies to deliver complex multi-specific therapies against difficult-to-treat diseases.

Amgen and Generate have not disclosed the therapeutic areas for which they plan to develop protein therapeutics via generative biology. Speaking with GEN Edge in November 2021, Mike Nally, Generate’s CEO, said his company had worked to find targets in oncology, immunology, and infectious disease, but wasn’t limiting its R&D to these areas.

Generate’s approach to generative biology is designed to facilitate testing and learning which proteins work best against which disease targets. The company projects its approach can shave two years off traditional protein-based optimization processes.

Generate’s machine learning algorithms are designed to analyze hundreds of millions of known proteins, looking for statistical patterns linking amino acid sequence, structure and function. The company’s technology platform has been enhanced by closed-loop learning on tens of thousands of computationally generated and broadly experimental characterized novel proteins over the past three years.

Disease agnostic

Generate says that its platform is disease-area agnostic and, combined with its wet lab research, can rapidly generate antibodies, peptides, enzymes, cell therapies, and gene therapies for a variety of therapeutic needs—enabling the company to learn generalizable rules by which a linear amino acid sequence encodes protein structure and function and design therapeutics for previously intractable targets at unprecedented speed and scale.

“With our technology platform, we are able to expand beyond just proteins that are found in nature—creating de novo, purpose-built proteins capable of performing any desired function under timelines that have not been possible through other approaches,” stated Nally, who is also CEO-partner with Flagship Pioneering, the venture capital and business acceleration firm whose best-known spinout is Moderna.

Flagship launched Generate in 2019 by combining a pair of exploratory projects. One was an algorithmic drug discovery platform based on insights from Gevorg Grigoryan, PhD, of Dartmouth College, who with colleagues discovered that protein structure formed according to a “language” enabling the engineering of novel proteins that folded and functioned without physical descriptions.

In the other exploratory project, Molly Gibson, PhD, a principal at Flagship, partnered with general partner Geoffrey von Maltzahn, to test whether advances in machine learning in natural language processing and image processing could be applied to amino-acid sequences of proteins. ​

Amgen agreed to pay Generate Bio $50 million upfront for the initial five programs. For each of those programs, Amgen will pay up to $370 million in future milestones and royalties up to low double digits—bringing the combined value of those programs to up to $1.9 billion plus royalties.

In addition, Amgen will also retain an option to nominate up to five additional Generate programs for development, though how much additional Amgen would pay upon exercise of those options has yet to be disclosed.

The deal appeared to have little impact on Amgen’s stock, which rose 0.3% to $225.82 in early trading as of 11:20 a.m., from yesterday’s close of $225.14.

Amgen also committed to participating in a future financing round for privately-held Generate, which in November 2021 raised $370 million in Series B financing, on top of the $50 million it racked up in its Series A in September 2020.

“We’re proud to partner strategically with Amgen to combine their world-leading expertise in engineering protein-based therapies with our unique machine learning-enabled drug generation platform,” Nally added. “This agreement is a recognition of the transformative power of our generative biology platform.”