Trending 
Nvidia and its research partners have launched Evo 2, an advanced artificial intelligence system designed to revolutionise biological research by accelerating discoveries in genetics and medicine.
The AI system, which Nvidia calls the largest of its kind for biological research, is capable of reading and designing genetic code across all forms of life. Through leveraging massive datasets, Evo 2 is expected to speed up breakthroughs that would otherwise take years to achieve manually.
Evo 2 was trained on nearly nine trillion pieces of genetic information from over 128,000 organisms, including bacteria, plants, and humans. In early testing, it successfully identified 90% of potentially harmful mutations in the BRCA1 gene, which is linked to breast cancer.
Scientists believe this could lead to more precise gene therapies that target specific cells, reducing side effects and improving treatment efficacy.
The model was built using 2,000 Nvidia H100 processors on Amazon’s cloud infrastructure. Developed in collaboration with the Arc Institute and Stanford University, Evo 2 is now freely accessible to scientists worldwide through Nvidia’s BioNeMo research platform.
“Designing new biology has traditionally been a laborious, unpredictable, and artisanal process,” said Brian Hie, assistant professor at Stanford University.
“With Evo 2, we make biological design of complex systems more accessible to researchers.”
While Evo 2 has major implications for healthcare, its potential applications extend beyond medicine. Researchers believe the technology could be used to engineer crops that can withstand climate change and develop new methods to break down pollution.
The project is a collaboration between Nvidia and the Arc Institute, a nonprofit research centre founded in 2021 with $650 million in funding. The institute works closely with Stanford, UC Berkeley, and UC San Francisco to tackle long-term scientific challenges.
