In a significant advancement for genetic research, NVIDIA has unveiled Evo 2, the largest publicly available AI model for genomic data analysis. The revolutionary platform, developed through collaboration between the Arc Institute, Stanford University, and NVIDIA, was announced on February 19, 2025.

Built on NVIDIA’s DGX Cloud platform using Amazon Web Services (AWS), Evo 2 represents a remarkable breakthrough in processing genetic information, having been trained on an unprecedented dataset of nearly 9 trillion nucleotides. This extensive training enables the model to analyze DNA, RNA, and proteins across diverse species, marking a new era in biomolecular sciences.

Patrick Hsu, Arc Institute cofounder and UC Berkeley assistant professor of bioengineering, emphasizes the model’s significance: “Evo 2 represents a major milestone for generative genomics. By advancing our understanding of these fundamental building blocks of life, we can pursue solutions in healthcare and environmental science that are unimaginable today.”

The platform’s innovative architecture allows it to process up to 1 million tokens of genetic information simultaneously, providing researchers with unprecedented insights into complex biological systems. This capability is particularly crucial for analyzing human genes, which typically contain thousands of nucleotides.

Stanford University’s Assistant Professor Brian Hie highlights the platform’s transformative potential: “Designing new biology has traditionally been a laborious, unpredictable and artisanal process. With Evo 2, we make biological design of complex systems more accessible to researchers, enabling the creation of new and beneficial advances in a fraction of the time it would previously have taken.”

The development of Evo 2 was accelerated through access to 2,000 NVIDIA H100 GPUs via NVIDIA DGX Cloud on AWS. The platform is now available to global developers through the NVIDIA BioNeMo platform, including as an NVIDIA NIM microservice for secure AI deployment.

Early testing has shown promising results, particularly in healthcare applications. Researchers from Stanford and the Arc Institute demonstrated that Evo 2 could predict with 90% accuracy whether unrecognized mutations in the BRCA1 gene, associated with breast cancer, would affect gene function.

Beyond healthcare, Evo 2’s applications extend to agricultural biotechnology and materials science. The platform could help develop climate-resilient crops, engineer proteins for breaking down pollutants, and create more sustainable biofuels.

Dave Burke, Arc’s chief technology officer, draws an inspiring parallel: “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.”

This breakthrough represents a significant step forward in democratizing access to advanced genetic research tools, potentially accelerating discoveries in healthcare, agriculture, and environmental science. As researchers worldwide begin to utilize Evo 2, its impact on biomolecular sciences is expected to grow substantially.

News Source: https://blogs.nvidia.com/blog/evo-2-biomolecular-ai/