What if evolution could be simulated in a lab? At the intersection of artificial intelligence, biology, and evolutionary science, researchers have unveiled a tool that might just rewrite the rules of protein engineering.

Leveraging the power of large language models, evolutionary biologists have successfully simulated 500 million years of evolution. Called the EvolutionaryScale Model 3, or ESM3, this multimodal generative AI model created a green fluorescent protein that’s 58 percent similar to its closest, real-world cousin.

It’s been trained on 771 billion unique tokens – the AI term for a unit of data – taken from databases of natural protein sequences and structures, as well as some generated synthetic sequences. In total, this data contained 3.15 billion protein sequences, 236 million protein structures, and 539 million proteins with function annotations.

Researchers used an AI to simulate over 500 million years of evolution and created an entirely new protein we've never seen before.

An artificial intelligence model has created a new protein that researchers say would have taken 500 million years to evolve in nature — if nature were capable of producing such a thing.