Nvidia unveils ‘largest artificial intelligence system yet’ for genetic research

Tech giant and AI chipmaker Nvidia has unveiled an AI system for biological research with focus in genetics with its research partners 

In a blog post on 19 February, the company said the AI model known as Evo 2 provides insights into DNA, RNA and proteins across diverse species.

The model is now accessible to scientists everywhere for in-depth understanding of genetics for all domains of life.

Delving into genetic research

Until now, Nvidia was known for its design of chips and games, but that has changed significantly.

The company recently went in big on AI and is now harnessing the technology for biological research. 

According to the blog, the new AI model was built on the NVIDIA DGX Cloud platform led by nonprofit biomedical research organization Arc Institute and Stanford University.

Evo 2 uses a novel model architecture that can process up to 1 million sequences of genetic information. 

With it, scientists can understand the connection between distant parts of an organism’s genetic code and the mechanics of cell function, gene expression and diseases.

Commenting on the model, Patrick Hsu, Arc Institute co- founder and core investigator, and an assistant professor of bioengineering at the University of California, Berkeley said:

“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 model was trained on nearly 9 trillion nucleotides, which is why it has such a wide application in biomolecular research. 

Evo 2 can provide insights into DNA, RNA and proteins having been trained on a wide array of species including plants, animals and bacteria. 

The model can be applied to scientific fields such as healthcare, agricultural biotechnology and materials science.

Nvidia’s diversification

Nvidia has been diversifying its focus recently from gaming and miner design. The company went into AI last year, starting with the building of specialized computers for humanoid robots.

In line with this focus, Nvidia also acquired AI infrastructure Run:ai to streamline its operations in the AI sector, which could be driving the current results.