Injection of Bacteria in An Organoid
Schematic representation of the injection of bacteria into the lumen of an organoid, and a fluorescent microscopy image of such an organoid. Human intestinal organoid (green) filled with labeled bacteria (blue). [Cayetano Pleguezuelos-Manzano, Jens Puschhof, Axel Rosendahl Huber, ©Hubrecht Institute.]

EvolutionaryScale, an AI startup founded by x-Meta researchers, launched this week with its ESM3 platform for novel protein generation. ESM3 generated a new Green Fluorescent Protein (GFP), a process the company says would take 500 million years of evolution to occur naturally. The company also announced a seed round of more than $142 million, led by Nat Friedman and Daniel Gross, and Lux Capital, with participation from Amazon, NVentures (NVIDIA’s venture capital arm) and angel investors.

ESM3 was trained with 1 trillion teraflops—the company says that is more compute than any other known model in biology—on a dataset of 2.78 billion proteins across the Earth’s natural diversity. It is the first generative model for biology that simultaneously reasons over the sequence, structure and function of proteins. This enables scientists to understand and create new proteins, making biology programmable.

“ESM3 takes a step toward a future of biology where AI is a tool to engineer from first principles, the way we engineer structures, machines, and microchips, and write computer programs,” said EvolutionaryScale co-founder and chief scientist, Alexander Rives. “We’ve been working on this for a long time, and we’re excited to share it with the scientific community and see what they do with it.”

The company believes the model has the potential to accelerate discovery across a broad range of applications, ranging from the development of new cancer treatments to creating proteins that could help capture carbon.

Prompted to reason over possible sequences and structures of GFP, ESM3 stepped across 500 million years of evolution to create a new fluorescent protein. GFP is one of the most unique proteins in nature, responsible for the glowing of jellyfish and the fluorescent colors of coral. It is the only protein that emits light, and the biological mechanism for this is unique—it is a protein that transforms itself forming a light emitting chromophore out of its own atoms.GFP has also become an important tool in molecular biology, helping scientists to see molecules inside cells. 

New fluorescent proteins this distant from known ones have only been found through the discovery of new GFPs in the natural world so far. ESM3’s success in generating a new GFP underscores the model’s potential for advancements in biological research and life sciences.

EvolutionaryScale will be opening an API for closed beta, and code and weights are available for a small open version of ESM3 for non-commercial use. EvolutionaryScale is also collaborating with Amazon Web Services (AWS) and NVIDIA to accelerate applications from drug discovery to synthetic biology with AI.

Evolutionary Scale is making the full ESM3 model family accessible to hundreds of thousands of researchers around the world and nine out of the top ten global pharma companies, who already use AWS’s generative AI and health services—Amazon SageMaker, Amazon Bedrock, and AWS HealthOmics. This move should make it easier for researchers to fine-tune the ESM3 models using their own proprietary data securely, and at scale.

Also of Interest