Simulating 500 million years of evolution with a language model
Thomas Hayes, Roshan Rao, Halil Akin, Nicholas Sofroniew, Deniz Oktay, Zeming Lin, Robert Verkuil, Vincent Q. Tran, Jonathan Deaton, Marius Wiggert, Rohil Badkundri, Irhum Shafkat, Jun Gong, Alexander Derry, Raul S. Molina, , Alexander W. Rives
ESM3, a 98-billion-parameter multimodal protein language model tokenized across sequence, structure, and function, designs a bright green fluorescent protein at 58% sequence identity to known fluorescent proteins.
Science · Jan 16, 2025Peer-reviewedSynthetic Biology✦ In-depth digest