Nvidia, in collaboration with leading research institutions, has introduced Evo 2—the most advanced artificial intelligence system to date for biological research. Designed to revolutionise the study of genetics, Evo 2 is capable of reading and designing genetic codes across all life forms, from bacteria and plants to humans. Scientists anticipate that this technology will significantly accelerate research by identifying patterns in massive datasets, a process traditionally taking years to complete manually.

Unprecedented Learning from Vast Genetic Data

Evo 2 was trained on nearly 9 trillion genetic data points derived from over 128,000 organisms. This extensive dataset enables the AI to analyse complex biological structures with unparalleled precision. By leveraging this massive pool of information, researchers can gain deeper insights into genetic functions, hereditary diseases, and evolutionary biology.

Revolutionising Cancer Research and Treatment

One of Evo 2’s most impressive early achievements is its ability to identify potentially harmful mutations in the BRCA1 gene, which is closely linked to breast cancer. During initial tests, the AI accurately detected 90 per cent of these mutations, paving the way for more targeted gene therapies. By pinpointing harmful mutations with high accuracy, Evo 2 can help scientists develop personalised treatments that only target specific cells, reducing side effects and increasing treatment efficacy.

Powered by Cutting-Edge Computing

The development of Evo 2 required significant computational power. Built using 2,000 Nvidia H100 processors, the AI system runs on Amazon’s cloud infrastructure, ensuring high-speed processing and scalability for researchers worldwide. This advanced hardware allows Evo 2 to analyse genetic sequences at an unprecedented rate, pushing the boundaries of biological discovery.

Accessible to Scientists Worldwide

In a move to democratise biological research, Evo 2 is now freely available through Nvidia’s BioNeMo research platform. Scientists across world can access the AI system to accelerate their studies in genetics, medicine, and beyond. According to Brian Hie, assistant professor at Stanford University, "Designing new biology has traditionally been a laborious, unpredictable, and artisanal process. With Evo 2, we make the biological design of complex systems more accessible to researchers."