A group of researchers successfully simulated the DNA structure of a brand new type of protein -- one that could have an impact on future medicines.
As exciting as that may sound, the real story to me is the way they got to this discovery. Using AI they were able to create a sequence of DNA “letters” that was unique and resulted in the type of protein they were hoping to create: a green-glowing molecule similar to what makes jellyfish glow in the water.
This sequencing, without AI, would have required “a total of 96 different genetic mutations to evolve. These changes would have taken more than 500 million years to evolve naturally.”
So there you have it, folks. AI just saved us 500 million years. Really, who has that kind of time to wait around anyway?
Cover image credit: EvolutionaryScale
"The same way a person can fill in the blanks in the soliloquy "to _ or not to _, that is the _," we can train a language model to fill in the blanks in proteins," Rives said. "Our research has shown that by solving this simple task, information about the deep structure of protein biology emerges in the network."
