Garyk Brixia b c, Matthew G. Durranta b, Jerome Kua b, Mohsen Naghipourfara b d, Michael Polib c e, Gwanggyu Suna b, Greg Brockmanb f g, Daniel Changa b c, Alison Fantona b,
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
All of life encodes information with DNA. Although tools for genome sequencing, synthesis and editing have transformed biological research, we still lack sufficient understanding of the immense complexity encoded by genomes to predict the effects of many classes of genomic changes or to intelligently compose new biological systems. Artificial intelligence models that learn information from genomic sequences across diverse organisms have increasingly advanced prediction and design capabilities1,2. Here we introduce Evo 2, a biological foundation model trained on 9 trillion DNA base pairs from a highly curated genomic atlas spanning all domains of life to have a 1 million token context window with single-nucleotide resolution. Evo 2 learns to accurately predict the functional impacts of genetic variation—from noncoding pathogenic mutations to clinically significant BRCA1 variants—without task-specific fine-tuning. Mechanistic interpretability analyses reveal that Evo 2 learns representations associated with biological features, including exon–intron boundaries, transcription factor binding sites, protein structural elements and prophage genomic regions. The generative abilities of Evo 2 produce mitochondrial, prokaryotic and eukaryotic sequences at genome scale with greater naturalness and coherence than previous methods. Evo 2 also generates experimentally validated chromatin accessibility patterns when guided by predictive models3,4 and inference-time search. We have made Evo 2 fully open, including model parameters, training code5, inference code and the OpenGenome2 dataset, to accelerate the exploration and design of biological complexity. Evo 2 is an artificial intelligence-based biological foundation model trained on 9 trillion DNA base pairs spanning all domains of life that predicts functional properties from genomic sequences and provides a rich generative model for researchers in biology.
TL;DREvo 2 is introduced, a biological foundation model trained on 9 trillion DNA base pairs from a highly curated genomic atlas spanning all domains of life to have a 1 million token context window with single-nucleotide resolution and learns to accurately predict the functional impacts of genetic variation without task-specific fine-tuning. (Semantic Scholar)
