Sequence modeling and design from molecular to genome scale with Evo

• 成果类型: Article
• 署名作者: Nguyen, Eric; Poli, Michael; Durrant, Matthew G.; Kang, Brian; Katrekar, Dhruva; Li, David B.; Bartie, Liam J.; Thomas, Armin W.; King, Samuel H.; Brixi, Garyk; Sullivan, Jeremy; Ng, Madelena Y.; Lewis, Ashley; Lou, Aaron; Ermon, Stefano; Baccus, Stephen A.; Hernandez-Boussard, Tina; Re, Christopher; Hsu, Patrick D.; Hie, Brian L.
• 署名单位: Stanford University; Stanford University; Stanford University; Stanford University; Stanford University; Stanford University; University of California System; University of California Berkeley; University of California System; University of California Berkeley; Stanford University
• 刊物名称: SCIENCE
• ISSN/ISSBN: 0036-9763
• DOI: 10.1126/science.ado9336
• 发表日期: 2024-11-15
• 关键词: protein; bacterial; identification; determinants; EVOLUTION; expansion; database; SYSTEM; IMPACT

摘要

The genome is a sequence that encodes the DNA, RNA, and proteins that orchestrate an organism's function. We present Evo, a long-context genomic foundation model with a frontier architecture trained on millions of prokaryotic and phage genomes, and report scaling laws on DNA to complement observations in language and vision. Evo generalizes across DNA, RNA, and proteins, enabling zero-shot function prediction competitive with domain-specific language models and the generation of functional CRISPR-Cas and transposon systems, representing the first examples of protein-RNA and protein-DNA codesign with a language model. Evo also learns how small mutations affect whole-organism fitness and generates megabase-scale sequences with plausible genomic architecture. These prediction and generation capabilities span molecular to genomic scales of complexity, advancing our understanding and control of biology.