NVIDIA and Arc Institute Launch Groundbreaking Genomic AI Model Evo 2

NVIDIA has partnered with the Arc Institute and Stanford University to launch Evo 2, a new foundation model designed to understand the genetic code across all domains of life. The collaborative effort has produced what is being touted as the largest publicly available AI model for genomic data, built using the NVIDIA DGX Cloud platform on Amazon Web Services.

Trained on a dataset of nearly 9 trillion nucleotides—the fundamental building blocks of DNA and RNA—Evo 2 offers researchers powerful capabilities for biomolecular applications. The model can predict protein form and function based on genetic sequences, identify novel molecules for healthcare and industrial applications, and evaluate how gene mutations affect functionality.

Researchers worldwide can now access Evo 2 through the NVIDIA BioNeMo platform, including as an NVIDIA NIM microservice, which simplifies deployment while maintaining security. The microservice allows users to generate various biological sequences with adjustable model parameters. For those interested in customization, developers can download the model via the open-source NVIDIA BioNeMo Framework to fine-tune it on proprietary datasets.

"Evo 2 represents a major milestone for generative genomics," said Patrick Hsu, Arc Institute cofounder and core investigator and assistant professor of bioengineering at the University of California, Berkeley. "By advancing our understanding of these fundamental building blocks of life, we can pursue solutions in healthcare and environmental science that are unimaginable today."

Dave Burke, Arc's chief technology officer, offered an evocative comparison: "Deploying a model like Evo 2 is like sending a powerful new telescope out to the farthest reaches of the universe. We know there's immense opportunity for exploration, but we don't yet know what we're going to discover."

The Arc Institute operates with a unique research model, providing scientists with multiyear funding and allowing them to focus on creative research rather than grant writing, enabling them to tackle long-term scientific challenges.

This latest initiative builds on NVIDIA's expanding healthcare portfolio. In 2022, the company launched Clara Holoscan MGX to help medical device organizations develop AI tools that meet regulatory standards. Previous collaborations include partnerships with AstraZeneca and the University of Florida on AI projects for drug discovery, and work with Harvard University on an AI toolkit for DNA analysis.

Earlier this month, the Arc Institute launched the Arc Virtual Cell Atlas, a resource for computation-ready single-cell measurements that currently includes data from more than 300 cells—part of the institute's broader vision to assemble, curate and generate large-scale cellular data for AI-driven biological discovery.

Click here for the original news story