""If you look at the history of drug discovery, we've been kind of circling around the same targets for a long time, and we've largely exhausted the drugs for those targets," she says. A "target" is a biological molecule, often a protein, that's causing a disease. But human biology is extraordinarily complex, and many diseases are likely caused by multiple targets.""
""That's why cancer is so hard," says Powell. "Because it's many things going wrong in concert that actually cause cancer and cause different people to respond to cancer differently.""
""[W]e have to do a bunch of really intricate data science work to . . . take this method and apply it to these crazy data domains," Powell says. "We're going from language and words that are just short little sequences to something that's 3 billion [characters] long.""
Bringing a new drug to market typically takes around a decade and costs billions, with many candidates failing in clinical trials. Historical drug discovery focused on a limited set of targets, leaving fewer obvious single-target opportunities. Many diseases involve multiple targets and complex, interacting biological causes, which complicates treatment and contributes to variable patient responses. Nvidia supplies the chips and infrastructure that power large AI models and is customizing hardware and software to handle specialized biological datasets such as DNA and protein structures. The combinatorial space of molecular sequences is vast, requiring adaptation from short language sequences to datasets billions of characters long. Kimberly Powell leads Nvidia's healthcare investment efforts and manages partnerships with major healthcare companies and startups to apply AI to drug discovery.
Read at Fast Company
Unable to calculate read time
Collection
[
|
...
]