We trained a genomic language model on all observed evolution, which we are calling Evo 2. The model achieves an unprecedented breadth in capabilities, enabling prediction and design tasks from molecular to genome scale and across all three domains of life.

AI provides a universal framework that leverages data and compute at scale to uncover higher-order patterns Today, Arc Institute in collaboration with NVIDIA releases Evo 2—a fully open source biological foundation model trained on genomes spanning the entire tree of life 🧵

Evo 2 is the kind of project that can only be done at a place like Arc Institute, and with partners like NVIDIA. Without doubt, the most exciting project I have been part of! Learned so much from some of world's greatest engineers and AI scientists.

Announcing Evo 2: The largest publicly available, AI model for biology to date, capable of understanding and designing genetic code across all three domains of life. arcinstitute.org/manuscripts/Ev…

New from Arc Institute: Evo 2, the largest (by training compute) biology ML model ever, and one of the largest-ever open source ML models in any category. Evo 2 is a foundation model trained on 9T DNA base pairs that learns a lot of fundamental details about life. A few examples

Also: you can try Evo 2 yourself! arcinstitute.org/tools/evo/evo-….

Evo 2, a DNA foundation model trained on 9T DNA base pairs, with state-of-the-art performance across a wide variety of biologically relevant tasks:

We made an AI agent go vroom on all of SRA to create scBaseCamp, Arc Institute's ever-expanding and uniformly processed single cell data repo! 230M cells drawn from 21 species, 72 tissues, and counting... arcinstitute.org/manuscripts/sc… x.com/yusufroohani/s…

Spurred by how well things worked with Evo 2, and with the awesome people who helped out, I'm curious if there's interest in a larger Arc Institute software engineering volunteer program. Something like: • Spend 6–12 months working full-time at Arc. • Learn/perform

Joining forces with Babak Alipanahi, Hormozdiari Lab, Aiden M Sababi & Mehran Karimzadeh to bring you Exai-1; a multi-modal cell-free RNA foundation model for blood surveillance and liquid biopsy. Kudos to the broader exai bio team for getting this across the line. biorxiv.org/content/10.110…

Introducing Arc Institute’s first virtual cell model: STATE