Pod Insights StarTalk Podcast Curing All Disease with AI with Max Jaderberg About this episode Can AI help us model biology down to the molecular level? Neil deGrasse Tyson, Chuck Nice, and Gary O’Reilly learn about Nobel-prize-winning Alphafold, the protein folding problem, and how solving it could end disease with AI researcher, Max Jaderberg.
Transcript Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.
0:00 Neil deGrasse Tyson? So AI was not satisfied just whooping our ass in chess and in Jeopardy and everything else where it looks like brains mattered. It's now taken over our physiology.
0:10 Gary O'Reilly? Well, no, you pointed it in a good direction, aimed it at a good place and we're getting someone.
0:14 Neil deGrasse Tyson? To solve our diseases.
0:15 Chuck Nice? Yeah, so now it's going to cure us of all disease before it makes us its slaves.
0:22 Gary O'Reilly? Cause we need healthy slaves.
0:24 Neil deGrasse Tyson? All that and more coming up on StarTalk.
0:29 Neil deGrasse Tyson? Welcome to StarTalk, your place in the universe where science and pop culture collide. StarTalk begins right now.
0:42 Neil deGrasse Tyson? This is StarTalk, special edition. Neil deGrasse Tyson, your personal astrophysicist. Special edition means we've got Gary O'Reilly in the house. Gary.
0:52 Gary O'Reilly? Hi Neil.
0:52 Neil deGrasse Tyson? Former soccer pro.
0:53 Gary O'Reilly? Apparently.
0:54 Neil deGrasse Tyson? Yeah, and soccer announcer.
0:55 Gary O'Reilly? Yes, definitely.
0:57 Neil deGrasse Tyson? And you still do that, don't you?
0:58 Gary O'Reilly? I do.
0:59 Neil deGrasse Tyson? Chuck Nice, baby.
1:00 Chuck Nice? Hey, announcing that I know nothing about soccer.
1:04 Gary O'Reilly? You're in my club then.
1:05 Neil deGrasse Tyson? Announcing that you are American.
1:07 Chuck Nice? American dove on a grill football, violence.
1:12 Neil deGrasse Tyson? So we're talking about AI today. It's a favorite topic. We revisit that often.
1:17 Chuck Nice? Only, only the future of the entire world.
1:20 Neil deGrasse Tyson? AI as it matters in biology.
1:23 Chuck Nice? Oh, wow. Now that's a big deal.
1:25 Neil deGrasse Tyson? I know, I know. Cause people thinking about, you know, composing your term paper or winning a chess. But it's got a whole frontier ready to be explored.
1:36 Chuck Nice? Yeah.
1:37 Neil deGrasse Tyson? And so tell me what you and your producers cooked up today.
1:40 Gary O'Reilly? Okay, so we've been on the case to get these guys involved for some time, but they are so busy. So here we go. I'll say it. I'm made of proteins. Yes. You're made of proteins from strings of amino acids that fold into shapes that put all together form us. But there's a fundamental problem in biology. That has implications for all of medicine. How do these proteins fold up?
2:06 Chuck Nice? Oh.
2:07 Gary O'Reilly? For this solution, we looked to AI and a Google DeepMind tool called AlphaFold. The second iteration of AlphaFold 2 won the Nobel Prize in Chemistry last year for answering this very question. Who knew AI was smart, huh?
2:22 Neil deGrasse Tyson? I appreciate AI win all the Nobel prizes.
2:24 Gary O'Reilly? Yeah, just get them now. Just pack them all up.
2:26 Neil deGrasse Tyson? Pack them up.
2:27 Gary O'Reilly? Now, the Isomorphic Labs, together with Google DeepMind, developed and released AlphaFold 3. Yes, we're on the third iteration. And that was last year and applied these new AI models for drug discovery.
2:38 Chuck Nice? Oh, that's great.
2:39 Gary O'Reilly? All right, so think this through. Could our next generations of treatments be computer generated?
2:45 Chuck Nice? Oh, yeah.
2:46 Gary O'Reilly? Oh, by the way, Neil, let's introduce our guest.
2:48 Neil deGrasse Tyson? I will. And we've got Max Yadeberg. Did I pronounce that correctly?
2:53 Speaker 03 Yeah, you got it. You got it right.
2:54 Gary O'Reilly? Let's hear you say it. Let's hear you say it.
2:56 Speaker 03 Me say it.
2:57 Gary O'Reilly? Yeah.
2:57 Speaker 03 Max Yadeberg.
2:58 Gary O'Reilly? Oh, he got it perfect.
2:59 Neil deGrasse Tyson? That's what I got.
3:00 Gary O'Reilly? He copied you.
3:01 Speaker 03 He was practicing. He was practicing.
3:03 Neil deGrasse Tyson? So you studied AI at Oxford?
3:05 Speaker 03 That's right. That's right.
3:06 Chuck Nice? No, I hear that's a, that's a community college?
3:09 Neil deGrasse Tyson? Oxford, Oxford Community College. That's exactly right. In Oxford, England. Yes.
3:15 Neil deGrasse Tyson? So, specializes in deep learning algorithms. I got your little bio here. For understanding images.
3:22 Chuck Nice? Nice.
3:22 Neil deGrasse Tyson? That was a big advance when, when a search can go into an image. I thought, you know, I died and gone to computer heaven where that started.
3:30 Speaker 03 Yeah, yeah. I mean, you know, this, this was 10, 15 years ago, back before AI was cool.
3:35 Neil deGrasse Tyson? Right, right.
3:36 Speaker 03 Where, you know, you talk about AI and it's something from a sci-fi book, but understanding images and videos was like the big thing at that point in time. We couldn't, we couldn't actually do that very well.
3:45 Neil deGrasse Tyson? I searched my 9,000 images on my computer for the word telescope.
3:49 Speaker 03 Yeah.
3:50 Neil deGrasse Tyson? And it found telescope written in Chinese.
3:53 Speaker 03 That's crazy.
3:54 Neil deGrasse Tyson? On a photo taken at an angle in one of my images.
3:58 Chuck Nice? Wow.
3:59 Neil deGrasse Tyson? When I was visiting China.
4:00 Speaker 03 Yeah, this is it. Like during my PhD, we took all of the BBC's back catalog.
4:05 Gary O'Reilly? No.
4:06 Speaker 03 And we ran my algorithm across it and created a search engine. So you could pull up. Footage from decades ago that had this text or these objects. That's seriously some archive.
4:17 Chuck Nice? So here's what I'm interested, when you do that, do you tie? So when AI is looking at an image, it's not seeing the image the way we do. We're not even seeing a whole image. Our brains, we're really just intuiting an image when we see it.
4:31 Speaker 03 Exactly, exactly.
4:32 Chuck Nice? That's how we do it. But the AI actually-
4:34 Speaker 03 It's like a holistic processing.
4:35 Chuck Nice? It's a holistic processing. AI actually sees the image and what it's seeing is pixels.
4:40 Speaker 03 That's right.
4:40 Chuck Nice? And that really all it's doing is just, oh, this pixel, this pixel, this pickle, in this arrangement, that's this image. So do you tie that to language and that's how we search? Or is the search just the AI knows the actual image itself?
4:55 Speaker 03 This was like the big breakthrough back then when I was doing my PhD. And this is what deep learning as well is all about.
5:01 Chuck Nice? Right.
5:01 Speaker 03 You can imagine if you have this pics, this image full of pixels, how do you actually code up how to read text from there?
5:07 Chuck Nice? Right.
5:08 Speaker 03 How do you tie it to the language of the text?
5:09 Chuck Nice? Right.
5:10 Speaker 03 It's unimaginably hard to code that up by hand.
5:13 Chuck Nice? Yes.
5:13 Speaker 03 So instead, what you do is you put these, what they're called neural networks. They look at all of the pixels of the image and you give it lots and lots of examples, images that have somewhere it's got the text in it. And you tell the neural network what the text is.
5:28 Chuck Nice? I see.
5:29 Speaker 03 And the neural network, through lots and lots of training, starts to work out its internal algorithm to extract the information from these pixels, piece it all together and spit out the actual text or spit out what the objects are.
5:41 Chuck Nice? Wow.
5:42 Neil deGrasse Tyson? So you're currently chief AI officer at Isomorphic Labs. This is a biology place.
5:48 Speaker 03 That's right.
5:48 Neil deGrasse Tyson? Do you have any biology in your background? Formal biology?
5:51 Speaker 03 No.
5:52 Neil deGrasse Tyson? No, okay. So they want you for your AI.
5:54 Speaker 03 That's right, that's right. So I was at a place called DeepMind beforehand.
5:57 Neil deGrasse Tyson? Oh, Google.
5:58 Speaker 03 Google DeepMind, yes, exactly. I was there for a long time. I absolutely love this core AI technology called deep learning. That's what I've been developing my whole career so far. At DeepMind, we were working on some crazy stuff, you know, learning to play chess and Go and beating top professionals at games like StarCraft. Back then, it was about-
6:17 Chuck Nice? It was a big deal.
6:17 Speaker 03 Yeah, and because the world didn't know what AI was, so we were trying to prove that this was even a thing, right? It seems crazy now, but back then it was just proving that this was actually a real thing. But at the core, you know, I love this technology. I want to see it have profound impact on our world. And I was thinking these things.
6:34 Neil deGrasse Tyson? That's where it begins.
6:35 Chuck Nice? Yep.
6:36 Neil deGrasse Tyson? That's where the Terminator starts.
6:38 Chuck Nice? It's always the innocent dreamer. Who says, this can change the world for such good.
6:44 Neil deGrasse Tyson? And it's in my closet now. Would you like to see?
6:46 Chuck Nice? Exactly. And then it's always like some evil businessman who's just like, with my weather machine, I will one day rule the world, you know, so.
6:54 Gary O'Reilly? Apart from that, carry on.
6:55 Speaker 03 Yes. The good thing is, there's some pretty strictly good applications of AI that we can drive. And, um, you know, Demis Hassabis.
7:03 Gary O'Reilly? Yes.
7:03 Speaker 03 Started Isomorphic Labs, spinning that out of Google DeepMind, to really think, how can we apply AI to actually, you know, completely solve all disease?
7:13 Neil deGrasse Tyson? Okay, so it has genetic links back to its origin story.
7:16 Speaker 03 Exactly, exactly.
7:17 Neil deGrasse Tyson? It was in DeepMind. I feel better about that now.
7:19 Gary O'Reilly? Yeah.
7:19 Neil deGrasse Tyson? Okay.
7:20 Gary O'Reilly? You happy?
7:20 Neil deGrasse Tyson? Yeah, I'm happier now. Yes.
7:22 Speaker 03 So I moved over as part of that founding team to head up AI in this space. And, um, you know, it's been about three and a half years now. Been a crazy journey, but it's fascinating. It's so much fun.
7:30 Neil deGrasse Tyson? So you got this AI expertise and Alpha Fold spins off this biological application of it. First, tell me the word isomorphic. What does that mean in biology?
7:41 Speaker 03 Isomorphic is this, is this technical term, which is, you know, a one-to-one mapping of, of, of space, right? And the reason we're called Isomorphic Labs is, is really that we believe that biology is really, really complicated. In, in, in the world of physics, we can write down equations for physics with maths. And maths is that perfect description language for physics. But you can't really just write down equations in maths for biology, for the cell. It's just too complicated.
8:06 Neil deGrasse Tyson? Biology is the most complex expression of chemistry.
8:09 Chuck Nice? Yes.
8:10 Neil deGrasse Tyson? That we know.
8:10 Speaker 03 There's just, there's just so many moving parts.
8:12 Chuck Nice? Oh, did you just make that up?
8:13 Neil deGrasse Tyson? Yeah.
8:14 Gary O'Reilly? That's really good. So we're looking for a Rosetta Stone here for, for the language of biology.
8:18 Speaker 03 Exactly. So, so what could be that perfect description language for biology? We believe AI and machine learning is that.
8:23 Chuck Nice? Right.
8:24 Speaker 03 So that there could exist an isomorphism, a mapping between the biological world and the world of AI machine learning.
8:31 Neil deGrasse Tyson? Hence the name. All right.
8:32 Chuck Nice? Gotcha, gotcha.
8:33 Neil deGrasse Tyson? All right. So, uh, tell us about protein folding. Because, you know, when we learn about chemistry, we learn about chemical reactions. And we're not really taught that the shape of the molecule should have anything to do with anything. It's just what is the chemical symbol?
8:49 Speaker 03 And when you write down the chemical equations, there's no shape in there. There's just what elements and molecules comprise it.
8:58 Chuck Nice? And those equations don't really ever represent the three dimensional nature.
9:05 Speaker 03 Exactly. You don't even know if it has handedness, right? So take us from there. We think about proteins. Proteins are these fundamental building blocks of life.
9:14 Chuck Nice? Yeah.
9:15 Speaker 03 They're inside of everyone. They make up everything we have, basically.
9:18 Chuck Nice? Mm hmm.
9:19 Speaker 03 And they're made up of what's called a sequence of amino acids. Each amino acid is a molecule. There's about 20 different amino acids and you put them together in a long. Ever or just in life? In life, you can have non-natural amino acids as well that you can make as well.
9:34 Chuck Nice? You can make them.
9:35 Speaker 03 You can make them and actually use those for drugs sometimes. You string these amino acids together and that becomes a protein. But they don't exist as these strings. They fold up spontaneously in the cell.
9:46 Chuck Nice? Right.
9:46 Speaker 03 To create these 3D shapes. And why that's important is that these proteins, they're basically molecular machines. They don't just exist by themselves. They actually like create these little pieces of machinery. They interact with other proteins. They interact with other biomolecules like DNA and RNA. Right. That interaction is a shape fitting. Exactly. Exactly. So these proteins. It's a puzzle. It's a 3D puzzle. It's a 3D puzzle.
10:10 Chuck Nice? Exactly.
10:11 Speaker 03 A 3D jigsaw puzzle. And it's not. Which is way harder than a 2D jigsaw puzzle. And these are not static things. It's not just static puzzle pieces coming together. They change shapes. So something comes in contact and that opens up something else on the other side of the protein, which changes the machine and on and on it goes.
10:25 Gary O'Reilly? And that's what I was gonna ask you. What speeds is this folding taking place? Is it continuous? Once it folds, that's it? But you've just told me, no, it just keeps moving through the whole thing.
10:36 Speaker 03 Yeah. These are really, really complex, dynamical systems.
10:39 Chuck Nice? Yeah.
10:40 Speaker 03 You know, composed of thousands, millions, trillions of atoms within our cells. Unfolding over the course of, you know, microseconds and beyond.
10:47 Chuck Nice? And this dinacism that you're talking about.
10:49 Neil deGrasse Tyson? What word is that?
10:51 Chuck Nice? Dinacism?
10:52 Neil deGrasse Tyson? That's a word?
10:52 Chuck Nice? Isn't that a word?
10:53 Neil deGrasse Tyson? Dinacism?
10:54 Chuck Nice? I think I just made it up. Mism. Oh, dinanism.
10:57 Neil deGrasse Tyson? No, dynamism.
10:58 Chuck Nice? Dynamism.
10:59 Neil deGrasse Tyson? Thank you, okay.
11:00 Chuck Nice? I'm correcting grammar. This is a first. This is.
11:04 Chuck Nice? Dynamism.
11:04 Neil deGrasse Tyson? Dynamism. What kind of din- dinosaur? Dynamism?
11:08 Chuck Nice? Not dinosaur. Not dinosaur. Not dinosaur. But the dynamism that you're talking about within the cell, when you look at each one of us, since each one of us is so different, even though there's a general, like, execution and blueprint, we all come out so different. Is that part of the process that you are looking at and mapping?
11:31 Neil deGrasse Tyson? I, I would say, to a jellyfish, we all look identical.
11:35 Chuck Nice? True.
11:35 Neil deGrasse Tyson? Okay? They're not saying, oh, is your skin color slightly different? Or you're slightly taller?
11:40 Chuck Nice? Yes.
11:40 Neil deGrasse Tyson? You're describing functions at a cellular level. Is your job to understand that? Or is your job to figure out extra ways to fold proteins that maybe biology has yet to even figure out?
11:53 Chuck Nice? Ooh.
11:53 Neil deGrasse Tyson? That can then solve problems that we encounter that the natural universe has not. So, ooh, that was a good question.
12:03 Chuck Nice? You're happy with yourself. I'm so happy with myself.
12:06 Neil deGrasse Tyson? I'm so happy with myself today. Yeah.
12:08 Speaker 03 This is really interesting. We, we have these little molecular machines, these proteins, and we care about that 3D structure and how they work for two reasons. One, we want to understand, you know, how our cells work, because if something goes wrong with that, which is the case for disease.
12:24 Chuck Nice? Right.
12:24 Speaker 03 Then we want to understand, okay, where can we, or where do we actually need to go in and start fixing that?
12:28 Chuck Nice? Right. Or how we can stop it from actually going wrong in the first place.
12:31 Speaker 03 Exactly, exactly. So that, that's one thing. And then when we think about, okay, how can we go and fix that? What, what we're actually saying when we're doing drug design, we're saying, can we create another molecule that will come into the cell and actually start modulating these molecular machines? It's going, this, this drug molecule is going to actually attach to this protein over here, and that's going to cause this protein to change shape, for example, and so it won't operate how it normally does. Or, and so we stop that protein working, or we make it work better. These are the sort of things we do in drug.
13:01 Chuck Nice? That kind of reminds me of messenger RNA.
13:03 Neil deGrasse Tyson? Vaccines that we developed for COVID.
13:06 Speaker 03 Yeah, you know, there's so many different types of molecular mechanisms that we take advantage for for drug design. Wow.
13:23 Speaker 04 I'm Ali Khan Hemraj and I support StarTalk on Patreon. This is StarTalk with Neil deGrasse Tyson.
13:38 Gary O'Reilly? Are the folding proteins generally following a set path in the way that they do fold? And you're able to map them and when they misfold, that's when you're able to flag that up or have I just reinvented something or talked rubbish?
13:52 Speaker 03 That'd be cool. No, no, you're you're you're on to something. So. That'd be great. So, you know, like the, I mean, the amazing thing is that we can actually, turns out, predict how these proteins fold. So they are.
14:04 Gary O'Reilly? So you're modeling that.
14:04 Speaker 03 Yeah, we're modeling that with deep learning, with neural networks. That's what AlphaFold, you know, and all its generations are all about. And that means that we can actually just take in a sequence of amino acids, knowing nothing about this protein before, and then get out the 3D structure. And normally, this would take people months, if not years, to work out this 3D structure.
14:25 Neil deGrasse Tyson? So how is it that AlphaFold knows how a large molecule wants to fold?
14:34 Speaker 03 Again.
14:35 Neil deGrasse Tyson? It's got to know that in some way.
14:37 Speaker 03 It's learnt this from a few hundred thousand examples. So chemists, biochemists, over the last 50 years, they've been working out these protein structures by hand. They've been literally synthesizing protein, crystallizing it, then shooting X-rays at this to like, look at the electron scattering. And from that, you can resolve the protein structure. It's a pretty hard process, but people have been doing that.
15:02 Neil deGrasse Tyson? That's your way to photograph what the shape of the molecule.
15:04 Speaker 03 That's your way to photograph it in reality.
15:06 Neil deGrasse Tyson? With that, with that kind of, it's basically an electron microscope at that level.
15:10 Speaker 03 Yeah, similar. It's like electron scattering. Yeah, exactly. And so people have been doing that for the last 50 years and depositing these structures. And now we've taken all of that data and trained a neural network. To go just from the input of what is this molecule description to try and predict all of that data.
15:29 Chuck Nice? Right.
15:30 Speaker 03 And the amazing thing is, and this is really remarkable, is that you can then train this on the last fifty years of data, that's a couple of hundred thousand protein and biomolecular systems. But you can apply it seemingly to everything we know about in the protein universe, in the proteome.
15:47 Chuck Nice? Well, it has the...
15:48 Speaker 03 Proteome?
15:49 Chuck Nice? The proteome.
15:50 Speaker 03 Oh, we like that. Proteome.
15:52 Chuck Nice? Proteome.
15:53 Gary O'Reilly? So how accurate is AlphaFold, an AlphaFold with on the third iteration with its predictions? Because AI has been around a little while, as you've already said, and you're not the only AI tool that's out there, but how accurate is this particular tool?
16:07 Speaker 03 Yes, so AlphaFold 2 was that big jump where we started to get experimental level accuracy for just proteins, and that's what won the Nobel Prize in Chemistry.
16:19 Gary O'Reilly? So you balanced it off against empirical experimental...
16:21 Speaker 03 The benchmark is doing the real lab work itself. So AlphaFold 2 reached that level. Now AlphaFold 3 expands from just proteins to incorporate other biomolecular types. So proteins with other proteins, proteins with DNA, with RNA, with what's called small molecules, which are the drugs...
16:39 Neil deGrasse Tyson? They go to the neighborhood, they start mixing all that up.
16:40 Gary O'Reilly? Or maybe not the neighborhood, maybe that neighborhood gets a little bit of an upgrade.
16:45 Chuck Nice? No, that's when you make the superhuman. So everybody thinks it's gonna be the Terminator. It's not gonna be the Terminator, it's gonna be the superhuman, and then they're gonna be like us, and they're gonna look down on us and go, you know, why do we need you guys? And that's it. So anyway, you're able to predict these, and have you actually taken any of the modeled predictions and made the proteins?
17:10 Speaker 03 Yeah.
17:11 Neil deGrasse Tyson? Or tell us where you expect these to lead to new and innovative drugs, because otherwise it's just a puzzle exercise.
17:19 Chuck Nice? Yeah, it's a great Lego set.
17:21 Gary O'Reilly? We want the guests to enjoy this.
17:26 Chuck Nice? It's like, oh my god, how much that Lego set costs? Only ten billion dollars.
17:37 Chuck Nice? Sorry, go ahead.
17:38 Speaker 03 Yeah, yeah, so if you take a particular disease and we think that we can actually, you know, solve this disease by modulating a particular protein.
17:48 Chuck Nice? Mm hmm.
17:49 Speaker 03 The question is how we do that. So we design a drug molecule and we want it to fit to this protein in a certain way.
17:55 Chuck Nice? Oh.
17:56 Speaker 03 And so this is where traditionally you would have to actually either just guess.
18:00 Chuck Nice? Right.
18:00 Speaker 03 Or go into the lab.
18:02 Chuck Nice? And create, crystallize each one of those combinations and then photograph them and see if it worked. But now you can model it and the AI can do a thousand of those in like a minute.
18:14 Gary O'Reilly? Isn't this what you call the target proteins?
18:16 Chuck Nice? Wow.
18:17 Gary O'Reilly? So if you know you've got a certain target protein, do you not then run that against a list of drugs and think, yeah, this one, drug A works better with this, or maybe it's drug D, or whichever letter of the alphabet you're on. And now we become the sort of detective and has this Alpha Fold 3 produced how many clues and how many answers? Or are we still grappling with?
18:39 Chuck Nice? Yeah, instead of trying to figure out the drug, the AI actually figures out the drug for you.
18:43 Gary O'Reilly? Drug discovery.
18:45 Speaker 03 Well, exactly. You know, if you let the guy speak, we both hear the two of you.
18:49 Chuck Nice? Okay, we're figuring out this whole industry ourselves, Gary.
18:52 Gary O'Reilly? Yes.
18:53 Speaker 03 Yeah, you know, this is exactly where it's going. So
18:57 Gary O'Reilly? Right.
18:57 Speaker 03 we can start actually rationally designing these drugs.
19:02 Gary O'Reilly? Right.
19:02 Speaker 03 Traditionally, you would take, you know, a million random molecules and you would just throw them at these proteins and see what sticks. And that's how so many drugs have been created historically. You go back further and you're sifting through mud to find these sort of molecules.
19:17 Gary O'Reilly? Is this why there's been such a low percentage of success rates with the sort of drugs for whatever the problem is?
19:25 Speaker 03 That's part of it because, you know, we don't necessarily understand how these molecules are working. But with something like Alpha Fold 3, you can, you know, put the molecule, put the target protein into the system, into the neural network, and you get out the 3D structure. And as a chemist, you can start to understand, okay, how is this small molecule drug modulating this protein? Now, still, the problem is, well, how do you find that small molecule in the first place that's going to be good for this protein? You know, it's estimated there's like 10 to the power of 60 possible drug-like molecules out there. That's, you know, 10 with 60 zeros. So even if
20:02 Neil deGrasse Tyson? People know what ten to the sixty is.
20:04 Speaker 03 Yeah, yeah, yeah. So.
20:06 Gary O'Reilly? Don't be rude.
20:09 Speaker 03 Even if you had the perfect AlphaFold, you'd have to run that across ten to the power sixty molecules, which is just computationally impossible. It's unfeasible.
20:19 Gary O'Reilly? Right.
20:19 Neil deGrasse Tyson? Until quantum computing.
20:20 Speaker 03 Until, yeah. And so then what we need is something that we call a generative model, or an agent, which is able to actually search through that space, understand that entire molecular space, and come up with molecule designs for you.
20:35 Neil deGrasse Tyson? Oh, because the ten to the sixty is if you just did it randomly.
20:38 Speaker 03 Right, right.
20:38 Neil deGrasse Tyson? Exactly. Right, right. That's just throwing it at anything. Right, right. If you don't do it randomly, then you can.
20:43 Speaker 03 But randomly is the state of the art method. That's how people do it.
20:48 Neil deGrasse Tyson? It's how people currently do it.
20:49 Speaker 03 It's how people currently do it.
20:50 Gary O'Reilly? Oh, cool.
20:51 Neil deGrasse Tyson? Well, he called it state of the art. You're the state of the art. Right, thank you. Let's use the word properly here.
20:56 Gary O'Reilly? So what if the protein turns left when you've mapped it to turn right? Is that when we have issues that even AlphaFold 3 has a problem with?
21:06 Speaker 03 Exactly. These are not perfect models. At the end of the day, they're very, very accurate, but they will make some mistakes. So you still do currently need to go into the lab occasionally, but the amount of lab work you have to do is so much less.
21:20 Gary O'Reilly? Right.
21:20 Speaker 03 And often you can find the area of molecular space where these models work really, really well. And we then go out to the lab later down the line. We crystallize these things and we see, yeah, like this is a perfect mapping of what the model predicted.
21:35 Neil deGrasse Tyson? So back to an earlier point.
21:37 Gary O'Reilly? Yeah.
21:37 Neil deGrasse Tyson? In the old days, like last month, you, the pharmaceutical companies, Big Pharma, would spend millions, maybe not quite a billion, hundreds of millions of dollars developing a drug. We think that, holding aside what might be abuses of pricing, the fact that there's some truth to this first pill.
22:04 Neil deGrasse Tyson? Costs fifty million dollars. The second pill costs ten cents.
22:08 Gary O'Reilly? Hmm.
22:08 Neil deGrasse Tyson? Because they had to research to get the formula for that first pill. If you have narrowed the search space, then the cost of developing that first pill can be manifold smaller.
22:21 Speaker 03 It costs, on average, three billion dollars to create a new drug.
22:25 Chuck Nice? Wow.
22:25 Speaker 03 That's, that's, that's, that's on average.
22:27 Gary O'Reilly? Yeah.
22:28 Speaker 03 So, yeah, there's a
22:28 Neil deGrasse Tyson? That was low, when I said a hundred million dollars.
22:30 Speaker 03 You were lowballing.
22:31 Neil deGrasse Tyson? Lowballing, okay.
22:32 Speaker 03 Um, so this is a massive opportunity to like, completely change just like the cost, the speed.
22:37 Neil deGrasse Tyson? The business model.
22:38 Speaker 03 The efficacy, and the business model as we do that.
22:39 Chuck Nice? But is it proprietary? So here's my real, because here's where you would revolutionize. So if I come up with it and I'm, I'm company A, right? It's mine and I get to determine everything. If you're an AI company and you're just doing this, okay, so that you can sell it, then it's yours. Which one will be, will make prices lower for the consumer?
23:01 Speaker 03 Our goal is to, is to like really redefine this, this way you do drug design. So it becomes so much cheaper. We have so much more abundance of potential drugs and chemical matter that it really does change the business model. It changes the economics of the space.
23:16 Chuck Nice? So you, you can actually revolutionize the, the cost of making drugs?
23:21 Speaker 03 Yeah, yeah, that's, that's where we're going.
23:23 Chuck Nice? Okay, all right. I'm satisfied.
23:25 Gary O'Reilly? Is one of the next steps with AlphaFold, whichever it's through, or maybe the next iteration or so, going to investigate why and what drives the misfolding of a protein? So as you can kind of get ahead of even the story of that happening?
23:40 Chuck Nice? Wow.
23:41 Speaker 03 So, so actually, the misfolding of a protein is another thing. That, that's what causes some types of disease.
23:48 Gary O'Reilly? Yeah.
23:48 Speaker 03 Where you'll have a genetic mutation, a mutation in your DNA which will change a particular amino acid in that protein. And so it doesn't fold the normal way it should fold.
23:57 Gary O'Reilly? Right.
23:57 Speaker 03 And so it doesn't function as, as it normally should as a molecular machine. And so things like AlphaFold can help us understand what are those mutations that cause misfolding? And they're called misense mutations.
24:11 Gary O'Reilly? Right.
24:11 Speaker 03 And then, you know, these could be potential drug targets. So we could, you know, think about molecules that could mitigate against that.
24:17 Neil deGrasse Tyson? If I understand correctly, if you look at the, the PDR is this thick. And
24:22 Gary O'Reilly? What's P D R?
24:22 Neil deGrasse Tyson? The Physician's Desk Reference.
24:24 Gary O'Reilly? Thank you.
24:24 Neil deGrasse Tyson? Uh, it's this thick. So it's the size of an old style Manhattan phone book. Okay, it's very thick, multiple inches across. And it's chock full of existing medicines available to the doctor to prescribe. Is it true that 100% of those medicines are interacting with the patient chemically rather than through protein folding? So that if that's the case, does that mean that where proteins misfold, we can't combat it with any kind of folding algorithm? We just prescribe chemistry for your body to handle the impact of that? Is that, did I say any of that right?
25:08 Speaker 03 I think that, that, that is the majority of drugs. They are, yeah, they are chemicals that we take. We are the, we, we, you know.
25:14 Neil deGrasse Tyson? The chemical's not gonna fix the fold. It's gonna treat the symptoms of the, of the misfolding that happens.
25:19 Speaker 03 We're not, we're not changing the mutations of the proteins. That, that could be something like gene therapy.
25:23 Neil deGrasse Tyson? Mm hmm.
25:24 Speaker 03 Um, but these are, these are chemicals that come in and will attach themselves to these proteins and somehow mitigate the, you know, something like a misfold or it'll change an interface, change how these molecular machines work.
25:36 Gary O'Reilly? Hmm, that's wild. Is there a particular disease isomorphic labs are focusing upon right now? Or is this a more of a broad spectrum? Let's do, let's, let's go for proteins and cherry pick out certain things or we'll be really looking at one particular?
25:50 Speaker 03 The technology we're creating, it's really, really general. We wanna be able to apply this drug design engine
25:55 Gary O'Reilly? Alright.
25:55 Speaker 03 on any protein, any target, any disease area that comes our way. Now, saying that, you know, practically as a company and, and you wanna focus on a particular area, we're focusing at the moment on, you know, a lot on cancer and a lot on immunology.
26:10 Gary O'Reilly? Alright.
26:11 Neil deGrasse Tyson? Two biggies.
26:12 Chuck Nice? Two biggies.
26:13 Neil deGrasse Tyson? Yeah, yeah.
26:13 Chuck Nice? And the two that probably lend themselves best to what you're trying to accomplish, actually.
26:17 Gary O'Reilly? Okay, the question everyone's gonna want me to ask right now that's watching this and listening to this is, how are you getting on?
26:25 Speaker 03 Would, I mean, i- i- it's going really well, to be honest. We're seeing these algorithms actually, you know, change the way that we're able to do drug design. We're able to discover, you know, completely novel chemical matter. Again, some of these targets that, you know, people have been working on for, you know, even over a decade. It's really, really hard stuff, making amazing progress. You know, still, still really early in the company, but it's super exciting.
26:48 Chuck Nice? And have you sent anything to be photographed yet?
26:52 Speaker 03 We, we, we, we, we sent some things for, for molecular photographs, yeah.
26:55 Chuck Nice? Okay. Yeah, yeah. I know you're not allowed to talk about it. I know. I get it.
26:59 Speaker 03 But we're all very happy.
27:00 Chuck Nice? Okay. There you go. Listen, I'm, I'm with you. I'm picking up what you're putting down. That's cool.
27:05 Neil deGrasse Tyson? Yeah, but so if you, if you, I see this work as fundamental research so that you publish a result, you publish the image. As they published the image of the DNA molecule to know that it was a double helix.
27:18 Chuck Nice? Exactly.
27:18 Neil deGrasse Tyson? That becomes public knowledge at that point. So someone with tools, access to AlphaFold 3, would any company have access to this once you have published the blueprint for it?
27:29 Speaker 03 In, in drug design, often these blueprints come out in the patents. So when, when you're, when you're going to go into clinical trial, you need to patent these molecules. And in those patents, you'll have a lot of data around the molecules, the formula, how they work.
27:41 Chuck Nice? That's what I was talking about earlier.
27:42 Neil deGrasse Tyson? Yeah, yeah, yeah. Okay.
27:43 Chuck Nice? Yeah.
27:44 Neil deGrasse Tyson? All right. So the immune system, the, the cancer, these are leading causes of maladies in this world. What of the genetic disorders that affect one in a hundred thousand people?
28:02 Chuck Nice? Wow.
28:02 Neil deGrasse Tyson? You, you bring them together, there's enough of them, you know, they'll fill a stadium in the world, but that's so uncommon as to not really trigger anybody's interest.
28:13 Chuck Nice? It's also not profitable.
28:16 Neil deGrasse Tyson? Well, yeah.
28:16 Chuck Nice? Because you don't have, you don't have enough of a market there to sell the drug.
28:19 Neil deGrasse Tyson? Right.
28:19 Speaker 03 I mean, you know, it's exactly that, that point, Chuck. It's, um, traditionally, it might not be that attractive commercially to go after...
28:28 Speaker 03 You know, very small patient populations.
28:30 Chuck Nice? Hmm.
28:30 Speaker 03 But in a world where it's so much cheaper, so much easier to get to these drug molecules, then that opens up like all of this space. Okay.
28:39 Neil deGrasse Tyson? Like the cheaper it is, the
28:40 Chuck Nice? Right.
28:40 Neil deGrasse Tyson? the easier you can justify going down that
28:44 Chuck Nice? Right down the risk list.
28:45 Speaker 03 And this is a big guiding star for us. Like that's, this is why we're doing this.
28:47 Chuck Nice? That's beautiful.
28:48 Neil deGrasse Tyson? I see what you did there.
28:49 Chuck Nice? Guiding star, yeah. You know, it'd be great though.
28:51 Gary O'Reilly? He's picked up the environment. He's not silly. Why is chief AI officer?
28:55 Chuck Nice? Yeah. I'm interested to how active the company is in shaping policy around what you're doing, because there's going to be a great deal of legislative policy that is going to be tied to what you're doing. All of the patent implications, there's going to be, you know, research implications. There's going to be a lot of things tied to this.
29:17 Speaker 03 Yeah, yeah. I mean, we, we've been talking in this conversation about drug design, but then, once you've designed the drug, you've got to go into patients in clinical trials.
29:24 Chuck Nice? Right.
29:24 Speaker 03 And that's a really long process.
29:26 Gary O'Reilly? Yeah.
29:27 Neil deGrasse Tyson? That's why we have mice.
29:28 Speaker 03 But even these mice models, they're not actually very predictive. Like you do all these studies in mice and then they don't, you know, it doesn't translate into success in people.
29:36 Chuck Nice? Right.
29:36 Gary O'Reilly? You've got to go up the evolutionary scale and then get to the human bit.
29:39 Speaker 03 Yeah, exactly. And so there's, you know, you can imagine a world where we can design loads of new drugs. We've got to be changing the way that we're doing clinical trials, you know, how we can actually get these drugs to patients who really, really need them in a timely manner. Um, so I think there's a lot to be done and like rethought there.
29:55 Gary O'Reilly? Is the ultimate goal for Alpha Fold and I think medical science as a whole, to be able to bespoke medication for you as the individual, rather than the broader spectrum medication that we find ourselves with all the side effects. So are you able to then design a drug or a medication that has zero side effects and works exactly for me?
30:16 Speaker 03 This is the goal, right? This is, this is what we're shooting for. You know, imagine a world where we can sequence your particular cancer mutations.
30:25 Chuck Nice? Right.
30:25 Speaker 03 And then based on those, your individual mutations, be generating specific drugs for you.
30:31 Chuck Nice? Right.
30:32 Speaker 03 That even these are like, you know, 3D printed or something around the corner.
30:35 Chuck Nice? Okay. Yeah, this is, um, I mean,
30:37 Speaker 03 We're not there yet.
30:38 Chuck Nice? We're in the very nascent stages of that right now with immunotherapy for cancer treatments and.
30:43 Neil deGrasse Tyson? But how many of these yet to be cured diseases lend themselves to solutions that involve protein folding? And how many are just? Plain old, old fashioned chemistry.
30:55 Speaker 03 Proteins make up like pretty much all of our molecular machinery. So there's, there's a class of disease which is due to misfolding. But then there's many, many other diseases which are due to, for example, a protein not being expressed properly.
31:08 Neil deGrasse Tyson? Right.
31:08 Speaker 03 Or, you know, a, a, a cell going wrong in a certain.
31:12 Neil deGrasse Tyson? If I have a bacterial infection, I give myself antibacterial chemicals and then I'm done. Do I need you for that?
31:20 Speaker 03 But those chemicals are interacting with the proteins in the bacteria.
31:24 Neil deGrasse Tyson? Okay.
31:25 Speaker 03 So proteins are the fundamental machinery and the chemicals which are drugs are modulating those proteins. Whether it's like in our cells, in bacteria.
31:33 Neil deGrasse Tyson? All right.
31:33 Chuck Nice? So it's basically everything you're talking about is, is all happening on the cellular level.
31:38 Speaker 03 Yeah.
31:38 Neil deGrasse Tyson? If what you're describing is happening inside of cells, proteins doing their thing, their 3D jigsaw puzzle. And you have a solution for that, a remedy, you have to get your remedy inside the cell to interact with that folding.
31:52 Chuck Nice? The delivery.
31:53 Neil deGrasse Tyson? And how do you do that other than through like a Trojan horse virus or something? Cause viruses get in there pretty on command.
32:02 Speaker 03 Yeah. Well, if you think about the drugs that you take as pills, drug, drug design is really hard because it's not just about targeting these proteins. We've got to get them to the right place.
32:10 Chuck Nice? Mm hmm.
32:10 Speaker 03 We might want a pill that you take. So you take this pill. It's got to be absorbed by the body.
32:15 Chuck Nice? Right.
32:15 Speaker 03 So it's got to be soluble.
32:16 Chuck Nice? Right.
32:16 Speaker 03 It's got to go through the gut wall. It's got to go through the bloodstream to the particular tissue type, the cell type you care about. Then it's got to go through the cell membrane to be able to actually target maybe a target which is within the cell. So you need all of these properties in a single molecule. So we're actually designing these molecules, not just to hit the protein, but also to be soluble, to be cell permeable. There's so many different factors and then you don't want this molecule to be toxic. So you want it to hit the target of interest, but not hit anything else.
32:46 Neil deGrasse Tyson? Right. So I can see how a molecule gets through the cell wall.
32:49 Speaker 03 Yeah.
32:49 Neil deGrasse Tyson? A, a simple molecule, but a full up. Protein, red-blooded protein, how's that getting through the cell wall?
32:55 Speaker 03 Exactly, there's different types of drugs. Some are what we call small molecules, things you could take as pills. Others are made from proteins. They're the often things that you would inject directly inside.
33:07 Gary O'Reilly? Right.
33:08 Speaker 03 And some of those might be cell permeable, they'd be things like peptides. But often these protein-based drugs, things like antibodies, they're injected, but they don't go in the cell. They're just interacting with proteins on the surface of cells. So you don't need that permeability. So it really depends on what your target is and how do you want people to be able to take that drug? Sometimes a pill is the best thing, but actually sometimes injecting is the best thing.
33:32 Gary O'Reilly? Yes.
33:32 Neil deGrasse Tyson? And remind me what a peptide is?
33:34 Speaker 03 A peptide is a really small protein. So you've got full-blown proteins, which are these big molecular machines. And then you've got small proteins made up of, you know, five to 50 amino acids.
33:46 Neil deGrasse Tyson? Those are peptides.
33:47 Speaker 03 Those are peptides, they're smaller, so sometimes in some configurations, they can get through the cell wall.
34:11 Gary O'Reilly? So with this computer science, are we upending chemistry as we've known it? And are we going to find it kind of moving on?
34:20 Neil deGrasse Tyson? With AI?
34:20 Gary O'Reilly? Yeah. With the AI, is it then sort of moving into the other sciences? Are we going to just see it stick in one particular area?
34:28 Speaker 03 Chemistry is always going to exist. It's like, to me, it's like any field of science at the moment. Doing science like chemistry without maths, you wouldn't think about that now. And it's going to be the same thing with AI, it already is in my mind. You just wouldn't do chemistry without AI, you wouldn't do biology without AI. It's just that fundamental tool that allows us to understand the world better.
34:49 Chuck Nice? So chemists will not one day be like coal miners? Just like, I remember my grandpapa used to go into the lab.
35:01 Gary O'Reilly? So going back to an issue Chuck was mentioning.
35:03 Neil deGrasse Tyson? He come home smelling like chemicals.
35:08 Gary O'Reilly? Who's actually going to be able to access AlphaFold 3 or AIs of this iteration? Is it exclusively isomorphic labs or this comes out in license?
35:17 Neil deGrasse Tyson? I want a home kit.
35:19 Gary O'Reilly? That's it, exactly.
35:20 Neil deGrasse Tyson? Right, right, right. My DNA goes in.
35:21 Gary O'Reilly? Kitchen sink.
35:22 Neil deGrasse Tyson? There's an AlphaFold going on. Out comes a pill and I take it and I don't even need you at that point.
35:26 Chuck Nice? That would be so cool. You just finger prick or like put your finger on a sensor or something and it figures it all out.
35:33 Neil deGrasse Tyson? Make your own pill in the, at home.
35:34 Speaker 03 Yeah, yeah. Look up the Theranos story for that one.
35:39 Chuck Nice? Wow, that's the woman that went to prison, right?
35:42 Speaker 03 But no, you, you can access AlphaFold. So if you search for AlphaFold server, um, there's a whole web-based system where you can, you can fold proteins there for, you know, academic uses. It's, it's really cool. So you can just put your system in, get the 3D fold out from AlphaFold 3, download it, yeah.
35:58 Chuck Nice? Oh, cool, man.
35:59 Gary O'Reilly? I mean, how far away are we from modeling an entire human being, which I suppose touches on to your fears?
36:04 Neil deGrasse Tyson? Modeling or creating?
36:05 Gary O'Reilly? Either or.
36:06 Chuck Nice? Once you model, the next step is creating.
36:09 Neil deGrasse Tyson? Yeah, that's true.
36:10 Chuck Nice? That's all there is to it.
36:11 Neil deGrasse Tyson? That's true.
36:12 Speaker 03 That, that's the dream. We kind of need to work up the scales here. So, you know, we, we, we can model how two atoms interact. We can write down those equations. We can simulate small atomic systems. With things like AlphaFold, we get into bigger atomic systems, things on the scale of like multiple proteins. Now we've got very, very accurate AlphaFold 3. Maybe we can actually bootstrap off that to get to more sort of even bigger systems. What we call pathways, how all of these things interact.
36:39 Neil deGrasse Tyson? It's only just now clicking within me because you can look up in a book the tables of, um, action potentials for the interactions of, of atoms and molecules. And so you'd have a very good sense of which molecules will combine. Is it exothermic? Is it endothermic? But these are atoms and molecules. And as powerful and as convenient as that is, that's just the first rung in this ascending ladder of complexity that you are gaining control over.
37:11 Speaker 03 Yeah, and there's, there's trillions of atoms within a single cell, let alone the whole human body.
37:17 Chuck Nice? Right.
37:18 Speaker 03 It's just unfeasible to simulate the whole thing, but. What you can do is you can, you know, we do have good measurement techniques at different levels of scale, so we can measure things like protein folding. We can measure the amount of protein within a cell. We can measure the number of cells of certain type within a tissue. And so we have these like- The bigger it is, the easier it would be to measure. So we have these little windows into this sort of microscopic world. And then we can use AI to sort of fill in the gaps and bootstrap off the stuff we can do well, the atomic level, and start building up that scale of modeling, if that makes sense. We can rebuild it.
37:52 Chuck Nice? I read this article like God knows how long ago.
37:55 Speaker 03 God, how long did Chuck read the article?
37:57 Chuck Nice? God, because you know God. Anyway, it was talking about when a fertilized cell starts to proliferate and become a person. And basically what it determined, what the scientists determined at that point, and this is many years ago, is that the only way they could describe it is there's a bunch of noise. Like, there's just a bunch of noise. We can't really see anything. We can't make sense of any of it, because it's just basically, if we were to look at it as data, it would just be noise. Are you able to pierce that veil and see into that?
38:33 Speaker 03 I mean, we haven't been looking at that specific thing.
38:36 Chuck Nice? Okay.
38:36 Speaker 03 But this is where you start to understand more about, you know, a really granular scale. And then you, you can integrate that and create these sort of, I don't know, coarser measurements and coarser predictions. This is what we do in lots of areas of science, right? We, we don't simulate the whole universe at the atomic scale, but we, we find these rules of thumb or ways to describe sort of broader collections of molecules. And that's what we can start to build up and actually learn with these neural networks.
39:02 Chuck Nice? Cool.
39:03 Gary O'Reilly? So, question on behalf of Chuck. Could Alpha Fold discover a hallucinogenic that could make him see God? Or any other deity or being?
39:14 Chuck Nice? Thank you for asking. Welcome. I would like a very real answer, please.
39:21 Speaker 03 You can go on the AlphaFold server and try that out.
39:23 Chuck Nice? Okay. All right, invitation.
39:25 Speaker 03 Hey, listen, I'm all about it.
39:27 Gary O'Reilly? So, we've looked in previous shows, talking to biomedical engineering, and if we are to travel off-world and deep space, we are probably going to need different upgrades for us to be able to do that. Are we going to be able to, with AlphaFold or AI like this, be able to upgrade ourselves to make this sort of deep-space travel?
39:52 Neil deGrasse Tyson? Or upgrade ourselves for anything?
39:54 Gary O'Reilly? Yeah, I mean, this is a sci-fi, you know, the...
39:57 Speaker 03 Yeah, now we're sort of beyond, you know, solving disease into like, actually, can we enhance ourselves?
40:02 Gary O'Reilly? Right, yeah.
40:03 Speaker 03 I don't know, I think like, there's probably potential, right, to think about creating chemical matter that we can take or ingest that...
40:11 Chuck Nice? I mean, aging alone would be a huge application for this.
40:16 Speaker 03 I mean, there's crazy research on aging.
40:17 Chuck Nice? Because aging is basically cellular degeneration, and if you're able to, on a molecular level, kind of restart that process or jump-start it or, you know, boost it.
40:27 Speaker 03 Aging is an interesting one. You know, this is a really nascent area of research, where people are just starting to work out what are some of the factors that reverse the age of cells. There are these things called Yamanaka factors.
40:38 Gary O'Reilly? Yes.
40:39 Speaker 03 And there's even potential that people are finding of creating molecules that stabilize particular protein... Yamanaka factors are proteins, they're transcription factors that read DNA. Can stabilize these things, maybe that is what reverses some of the age of cells. This is super nascent.
40:55 Neil deGrasse Tyson? So what is the connection between wanting to modify a genome and your ability to fold proteins to interact with our physiology? I ask that because I'm reminded, there was a scene in the film Gattaca, where they didn't manipulate your genome, but they selected your pre-existing genome for certain properties.
41:14 Chuck Nice? Oh, yeah.
41:15 Neil deGrasse Tyson? And there's a person giving a piano recital, and it was very rich sound, I mean, it was beautiful. And then the camera came around to the front, and the person had 12 fingers.
41:24 Chuck Nice? That's right.
41:24 Neil deGrasse Tyson? And... Bread for that.
41:27 Chuck Nice? Yes.
41:28 Neil deGrasse Tyson? Right, you get two extra notes for every.
41:30 Chuck Nice? For everything, right.
41:31 Neil deGrasse Tyson? Everything going on.
41:32 Chuck Nice? She could only play the stuff, like, nobody could play what she could play.
41:34 Neil deGrasse Tyson? Nobody could play with it.
41:35 Chuck Nice? Nobody could play with it.
41:36 Neil deGrasse Tyson? So, this would be modifying not to go into space, necessarily.
41:39 Chuck Nice? Yes.
41:40 Neil deGrasse Tyson? But just to sort of enrich the diversity of the human species.
41:44 Speaker 03 We're, we're not doing genetic modification.
41:46 Neil deGrasse Tyson? So he says.
41:49 Gary O'Reilly? He's English, you must trust him.
41:51 Speaker 03 To be honest.
41:52 Gary O'Reilly? Thank you.
41:53 Chuck Nice? Thank you. Well done.
41:55 Neil deGrasse Tyson? Well, well played. What, so, but, can you? Is it the same thing?
42:00 Speaker 03 Some particular types of drugs are, you know, things that would manipulate your genome.
42:06 Chuck Nice? Um, yeah.
42:07 Speaker 03 That's how people, you know, start to target some diseases. This is not the class of drugs we're working on. When we think about the big ambition of solving a disease, maybe this is something that we need to be, um, doing over time as, as we wanna really crack, like, the whole spectrum of disease.
42:21 Chuck Nice? Right.
42:21 Gary O'Reilly? Can, is it even possible to consider that without considering the whole area itself as, all bleeds in together at some point?
42:29 Speaker 03 Yeah, I mean, we need to understand the genome and, and all the effect, you know, how, how you, how changing a particular base pair on your DNA is gonna change, you know, what proteins are expressed or in what abundance and how that, all the knock-on effect on the pathways. You really want this, like, basically this virtual cell to be able to manipulate this cell on a computer.
42:50 Chuck Nice? Right.
42:50 Speaker 03 To do experiments there.
42:51 Neil deGrasse Tyson? Here, here's what I want you to do.
42:53 Chuck Nice? It's like your cell template that you.
42:54 Neil deGrasse Tyson? Talking about prioritizing, and I'm not asking much, cause it already happens in the animal kingdom. You know, for so long, decades even, centuries, we imagined ourselves at the top of some evolutionary.
43:06 Chuck Nice? Yeah. Triangle, where the apex of the triangle.
43:09 Gary O'Reilly? Without any arrogance whatsoever, yeah.
43:11 Neil deGrasse Tyson? And, alright, yet, a newt can regenerate a limb.
43:16 Chuck Nice? Mm-hmm.
43:16 Neil deGrasse Tyson? And we can't.
43:17 Chuck Nice? Yeah.
43:18 Neil deGrasse Tyson? And so, it seems to, and they're vertebrates. So, it seems to me there ought to be some way to extract from animals that do things that we could benefit from, and then make that a priority. So, people, especially veterans who've lost limbs.
43:33 Chuck Nice? Right.
43:34 Neil deGrasse Tyson? In, in, in conflict.
43:35 Chuck Nice? Yep. So. Or, or even geckos with their sticky hands, like, maybe, um, I could be Spider-Man one day.
43:41 Gary O'Reilly? Well, so, all gonna end up as.
43:42 Neil deGrasse Tyson? Let's prioritize that, Chuck.
43:45 Gary O'Reilly? Or become superheroes.
43:48 Neil deGrasse Tyson? So the regeneration of limbs, that's gotta be a protein thing going on in there, isn't it?
43:54 Speaker 03 Yeah, I mean, you know, all of our mechanisms are protein, same for nukes as well. So there is some mechanism there. I don't know what it is.
44:00 Neil deGrasse Tyson? Okay.
44:01 Chuck Nice? Gotcha.
44:01 Neil deGrasse Tyson? But that would be a mechanism to emulate, if you could.
44:04 Chuck Nice? If you could, yeah.
44:05 Neil deGrasse Tyson? And then install it into our own physiology.
44:08 Speaker 03 It's a big if.
44:09 Chuck Nice? Yeah, that's a lot. How about this? Would you be able to look at drugs that are already here? And there are some drugs that are just not well tolerated. And you'd be able to reconfigure them in such a way that you get the benefit of the drug without the side effects?
44:23 Speaker 03 Yeah, exactly. So you often have these first generation of drugs that do something, but they have these side effects. Then there's a big opportunity to understand better how these drugs work. Things like AFOP 3, things like our models that understand toxicity of drugs. Can then allow us to potentially modify these to become better drugs and have less side effects, less toxic effects.
44:45 Chuck Nice? Cool.
44:46 Gary O'Reilly? Wow, that's going back through the medical catalog and reanalyzing, which is exactly what an AI would be perfect for.
44:52 Chuck Nice? Right, exactly. Yeah, you guys are gonna make a lot of money, man.
44:55 Gary O'Reilly? Stop seeing dollar signs and see some.
44:58 Chuck Nice? How do I get a piece of this company? I need to get a piece of this company. You guys are gonna make, I mean, I can't even imagine the amount, the gobs and gobs of money. More money than cells in my body. This is amazing.
45:13 Neil deGrasse Tyson? We're on the doorstep of quantum computing, and I know what impact that would have in my field. In your field, would it make your entire life's work look like it was done on an abacus?
45:22 Speaker 03 Yeah, I mean, this is gonna change things. I think open question, how this changes machine learning, like what can AI do with quantum computing? But for chemistry, even near term, there are some real applications of quantum computers for understanding the properties of small molecule drugs. Because actually, some of the things that people do do today with quantum computers is simulate these small chemical systems. Like, we actually, even in the company, we have a quantum simulation team. That are, you know, not using quantum computers, but simulating, you know, the quantum effects of molecules. Now, if you had a quantum computer that could work on that scale, you could use that instead, so.
46:02 Chuck Nice? Wow.
46:03 Neil deGrasse Tyson? I think of so many needs on the frontier of chemistry in modern society. Uh, one of them is, you know, what do we do with all the plastic that's in our environment? That's still there in the ocean. Is there some life form you can create that'll digest the plastic and turn it back into its original molecules? Is, are proteins something that could be applied there? If not in your world, then you're describing an ability more than you're describing a specific solution to a problem. You, you're empowering the chemist in ways never previously imagined.
46:39 Speaker 03 Yes, so you can use the capability of, of AlphaFold to understand, you know, understanding structural proteins. People are using this outside of drug, drug design.
46:48 Neil deGrasse Tyson? Exactly, exactly.
46:49 Speaker 03 People are using this, for example, to create bacteria that have enzymes that could potentially digest plastics, like you're talking about. You could think about this for engineering, um, you know, more resilient types of crops, these sort of things.
47:01 Chuck Nice? Yeah, so just like AI, this is a platform upon which you can rest the technology of any field, so.
47:08 Speaker 03 Yeah, that's the amazing thing about the protein folding problem. Once you start to solve that, you unlock so many new things for a whole broad spectrum of science.
47:16 Gary O'Reilly? There's a lot of downstream benefits, I would say.
47:19 Neil deGrasse Tyson? Okay, last thing.
47:20 Chuck Nice? Here's the last thing. How, how do I, how do I get a piece of this company?
47:24 Neil deGrasse Tyson? Chuck is good dollar times in his eyes. Last thing. La, last thing. What is the worst possible outcome of your work?
47:32 Chuck Nice? Ooh, what a question.
47:35 Neil deGrasse Tyson? What guardrails are necessary as we go forward? Cause any new technology with awesome power comes with awesome responsibility.
47:42 Speaker 03 Yeah, I mean, I, I think, um, you know, you have this with AI, you have this, you know, creating new biology or, or, or chemicals. You know, you, you just need to think about how to use this responsibly, like what you're putting out into the world openly versus what you, um, close off, uh, you know, many safety reasons. So I think there's, there's a lot of things to consider there, yeah.
48:02 Neil deGrasse Tyson? Cause famously in one of the Jurassic Park films, they withheld lysine, amino acid, from one of the dinosaurs in case it escaped. It would die because it would need the lysine for its survival. And that was a kind of a, an insurance plan that put in, but life always finds a way.
48:26 Chuck Nice? Yeah. There you go.
48:29 Neil deGrasse Tyson? Anyway, Maxwell Yadeberg. Yeah. Thank you for joining us on StarTalk. We're gonna be watching your company and Chuck wants a piece of it. Yes. I don't know what that means. But anyhow, this is, I'm delighted to just be able to look through your lens at the birth of an entire frontier in human physiology. I mean, what a time this is.
48:50 Speaker 03 No, thank you so much. It's been super, super fun to talk.
48:52 Neil deGrasse Tyson? No, thank you. Excellent, excellent. All right, I think we're done here. Mm-hmm. It's been another installment of StarTalk Special Edition. Talking about AI, human physiology, and the future of drugs. Oh, yeah. Gary, good to have you always. Pleasure, Neil. Chuck? Always a pleasure. As always. This has been StarTalk. Neil deGrasse Tyson, your personal Asher physicist. Keep looking up.
Previous Things You Thought You Knew – Zombie Apocalypse Next Quantum Quandary: StarTalk Live! With Brian Greene & Janna Levin Page updated September 29, 2026 · transcript and summary are machine-generated
