A team of researchers from top institutions has made a groundbreaking discovery in biomolecular sciences, developing an artificial intelligence model that can design and analyze genetic code across all domains of life. The model, called Evo 2, was trained on DNA sequences from over 100,000 species and can identify patterns in gene sequences that were previously difficult to uncover.
Evo 2 is a large language model comparable to the most powerful generative AI models in biology, trained on over 9.3 trillion nucleotides from various organisms, including humans, plants, and bacteria. This expanded dataset enables the model to perform tasks such as predicting disease-causing mutations and designing new genomes.
The development of Evo 2 represents a significant milestone in the emerging field of generative biology, allowing machines to read, write, and think in the language of nucleotides. The researchers are excited about the potential applications of this foundation model, which they believe will inspire further innovation in the research community.
Source: https://engineering.berkeley.edu/news/2025/02/new-ai-breakthrough-can-model-and-design-genetic-code-across-all-domains-of-life