James Zou
speaker
371 appearances
1 recordings
1 series
first heard Dec 2024
last heard Dec 2024
James Zou’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsNo recordings in the last 12 months.Older appearances are listed below; set an alert to hear about the next one.
Appearances
In this case, uh it's still like a human AI collaboration, but the human feedback to those AI agents in the virtual lab is relatively limited.
We don't actually write the code for them, or we don't do the work, and we don't even tell them here's exactly what you have to do, A, B, and C.
So in this case, like we the human researchers would t would tell the virtual lab, okay, so we're interested in designing potentially new therapeutics or new vaccines, right, for the recent variants of SARS-CoV-2, right?
So it's sort of a high level description.
And the agents actually have to decide first like what approach do they want to take and then how do they then try to achieve that goal.
So even in this case, there's even like a high-level question of like, you know, what should we even design nanobodies or antibodies?
Most of the human researchers actually would go for antibodies, which is the more common form.
And nanobodies to the audience are sort of, you can view them so sort of essentially like smaller versions of antibodies.
They're only present in a few animals, like camels, and they're much smaller.
And the agents actually made kind of a surprising decision themselves.
that they want to actually design nanobodies rather than antibodies and it gives some rationales that because nanobodies are smaller, they're easier to predict and more stable and easier to to design.
And that turned out to be actually a quite wise decision, even though a bit unorthodox it's that it ended up being a wise decision, because then we were able to experimentally validate that the nanobody designed by the agents ends up being
we're very promising candidates.
So that's sort of an example of where in the virtual lab, right, the the guidance, interaction with humans tends to be more high level guidance, but really the the directions of how and what project to to tackle and how to solve that problem is really mostly done by the agents.
Yeah, so these agents um so they're they're GPT 40 under the hood, so they are aware of a lot of the popular powerful tools in the literature, right?
So we don't actually tell them you have to use AlphaFold or you have to use DSM.
So they actually had some now through one of these virtual lab meetings, w which I can describe how that works in a bit, but through one of the virtual lab meetings they actually cited that, okay, so here's a list of potential tools.
Maybe they came up initially a list of six or eight different tools.
And then subsequently they decided: okay, so here are the three tools that may be the most relevant, right?
There's ESM, AlphaFold, Multimer, and Rosetta that have complementary.
Showing 41–60 of 371 · page 3 of 19
← Previous
Next →