Evo 2 DNA Foundation Model Published in Nature, Trained on 100,000+ Species

Summary

Evo 2, a DNA foundation model developed by the Arc Institute, has been published in the journal Nature. The model was trained on the DNA sequences of over 100,000 species spanning all domains of life — bacteria, archaea, and eukaryotes — making it one of the most comprehensive biological sequence models to date. Evo 2 can identify patterns in gene sequences across disparate organisms that would take experimental researchers years to uncover through traditional methods. The model represents a si