00:27:21 · Adam Miller, Josh Meier
[00:27:21] S2: Commercially, one of your big partnerships is with Eli Lilly, and from what I understood a little bit today is that you will sort of discover these drugs and they help try and develop them. Can you talk a little bit more about what that partnership looks like and what the feedback loops also look like when working with them? [00:27:35] S0: It's been fantastic working with the Lilly team, right? They were really impressive in terms of how quickly they adopted this technology and then how rigorously they exported it as well. They ran the right experiments to understand whether the models were working and then started to now adopt it at scale within the organization. So it's a great pleasure to work with one of the biggest pharma companies in the world, right, and that really being a great avenue to just create, massive impact with the models that we are building here, you just look at the number of projects they can now go apply it to. [00:28:02] S2: And in terms of those feedback loops, do you hear from them about the results that they're testing with, and you're able to use that data to reinforce your models?
00:28:02 · Adam Miller, Josh Meier, Sachin
[00:28:02] S2: And in terms of those feedback loops, do you hear from them about the results that they're testing with, and you're able to use that data to reinforce your models? [00:28:10] S0: Yeah. We talk to the team all the time. They're really engaged. They've been great partners to us in that too. We're, at a point in this technology curve where there's still a lot of progress being made, so to be able to have a have a company like Lilly who is stress testing our models at scale, applying it to all these projects, telling us this is what works well, this is what doesn't work well. That is so helpful for setting our own research roadmap, and then ultimately that means that we can be a very customer oriented company with what we do. When you're working on big research moonshots, it's very easy to end up working on the wrong thing. You're not getting feedback, maybe you have like a benchmark that you're pushing, but is it really the right benchmark? So when you have a company like Lilly with such broad scope and how they can use our technology, it really helps us learn about what are the right things to be working on, and I think ultimately that's key to our success. [00:28:54] S1: Josh, we kind of flew here to kind of ask this question about like, when can we expect AI produced or designed drugs to be on the market? [00:29:02] S0: And it feels like that's [00:29:03] S1: kind of still a few years off. But what is the case in which this doesn't work? Is it that scaling laws don't continue and model progress kind of drops [00:29:12] S2: off?
00:29:12 · Adam Miller, Sachin, Josh Meier
[00:29:12] S2: off? [00:29:12] S1: Is that the only case where this doesn't materially improve the world that we all live in? [00:29:17] S0: I mean, crazy thing is we've passed the point already where people are using the models on real projects, and those real projects will start in the lab, they'll go into animals, they'll go into people, they'll go through clinical trials, hopefully they someday get approved. So I think the impact is really being made there, and there's a lot that goes into getting a drug approved, you know, whether the idea was correct, whether the molecule really worked as expected, but I think there's a very good chance that even if we just shut down all the work in the company, the models that we have already achieved will probably have a massive impact, in FOMO, and, it's kinda crazy to take a step back and think about that, but then realize that there's still tremendous progress, from here, that's possibly to be made. [00:30:02] S2: And do you have case studies of specific examples of success stories that you can tell us about that you've worked with customers on?
00:30:09 · Josh Meier
[00:30:09] S0: Yeah. So internally, we do a lot of work as well to validate whether the models are working. We try to be, of course, really sensitive with our customers. We invest a lot in security, and their projects are off the top secret, but we've done over 100, 200 projects internally to really stress test whether the models are working. And by the way, that's like more orders of magnitude more than almost any other biotech company will do, which is very, or that then order to more than most biotech companies will do, which is really exciting. So some of the examples that we've gone after are molecules that are, they're very difficult to engineer. So, for example, we might want to generate a molecule, that binds to, to to two different proteins at the same time. Maybe it needs to bind both to a human protein and to a monkey protein. There was a certain case study we were looking at where a customer had spent, 5 to $10,000,000, on a project and, maybe about a year or two of of research, and they couldn't quite hone in, the, the details they needed on hitting both of these targets. And then with our models, we're able to literally zero shot, a couple of designs that actually fit that criteria. If you just think about the kind of impact that that can make, like, downstream for patients, you know, like, yes, they could have made something just for the monkey or just for the human, that really adds a lot of risk into the process, right? Like, what if it... The the the molecule worked for a monkey? Now I I need a whole different molecule to work for the human target. So being able to get all of this within the same molecule really allows us to accelerate that process and then get molecules, to facials a lot faster than before.
00:31:38 · Sachin, Josh Meier, Adam Miller
[00:31:38] S1: A fun one. If Jack came to came up to you and he said, Josh, we can get a drug all the way through regulatory approval like this. What was the one drug that you'd try one shot right now? [00:31:51] S0: I would do much more research to figure that out, right? There's gonna be a lot of constraints around that, right? What is the one thing? It'd probably be aging, right? If you could actually zero shot something right to approval, can we live forever? But that is a very sci fi idea [00:32:06] S2: of yours. Josh, I'm interested in the market structure of the industry, whereby if your models are significantly better than competitors and they stay above that, does this company then end becoming the monopoly for drug discovery? Why would any other institution use other models if this is always ahead of the curve? Will there be competitors that catch up? What's your hypotheses there? [00:32:28] S0: Yeah, I think that at the end of the day, this is an industry where the value that you can create is massive. [00:32:34] S1: Josh, we've explored this topic in a lot of depth, but let's say you're at the bar with your uncle that understands nothing about what you do and you're trying to explain to him what you actually do and what this means to the world, what is the most simplest way you'd explain this?
00:32:34 · Sachin, Josh Meier, Adam Miller
[00:32:34] S1: Josh, we've explored this topic in a lot of depth, but let's say you're at the bar with your uncle that understands nothing about what you do and you're trying to explain to him what you actually do and what this means to the world, what is the most simplest way you'd explain this? [00:32:49] S0: I think the simplest thing is to show how things that we build on the computer at the atomic level really just recapitulate in the lab, in many cases. I think if you just show, hey, here are like atoms that I see, you know, floating around with these models and we're kind of perturbing that with our product, and then you go in the lab, you shoot electron microscopes at this thing, it actually looks like that, it's pretty convincing to many people, right? And to be able to work in an atomic world when discovering these molecules makes a lot of sense that that's going to have some impact in how we create medicines. [00:33:20] S2: So the big question we have on our minds is when is the everyday person actually going to see the impact of chai in their lives?