Re:Accelerating scientific breakthroughs with an AI co-scien...
by kridsdale1 on Wednesday February 19, 2025 @03:24PM
(#43107141)
That’s similar to how Google won in distributed systems. They used cheap PCs in shipping containers when everyone else was buying huge expensive SUN etc servers.
[ Parent
| on HN ]
Re:Accelerating scientific breakthroughs with an AI co-scien...
by dekhn on Wednesday February 19, 2025 @04:44PM
(#43108132)
yes, and that's the reason I went to work at google: to get access to their distributed systems and use ML to scale up biology. I never was able to join Google Research and do the work I wanted (but DeepMind went ahead and solved protein structure prediction, so, the job got done anyway).
Re:Accelerating scientific breakthroughs with an AI co-scien...
by shpongled on Wednesday February 19, 2025 @05:45PM
(#43108735)
They really didn't solve it. AF works great for proteins that have a homologous protein with a crystal structure. It is absolutely useless for proteins with no published structure to use as a template - e.g. many of the undrugged cancer targets in existence.