Curing All Disease with AI with Max Jaderberg

Speaker 1 Tron Aries has arrived. I would like you to meet Aries, the ultimate AI soldier.

Speaker 2 He is biblically strong and supremely intelligent.

Speaker 3 You think you're in control of this?

Speaker 3 You're not. On October 10th.
What are you?

Speaker 4 My world is coming to destroy yours, but I can help you.

Speaker 3 The war for our world begins in IMAX.

Speaker 5 Tron Aries, suited PG-13. Maybe inappropriate for children under 13.
Only in theaters, October 10th. Get tickets now.
I'm gonna put you on, nephew.

Speaker 6 All right, Uncle.

Speaker 7 Fuck on the McDonald's.

Speaker 8 Can I take your order?

Speaker 5 Miss, I've been hitting up McDonald's for years. Now it's back.

Speaker 6 We need snack wraps.

Speaker 3 What's a snack wrap?

Speaker 5 It's the return of something great.

Speaker 3 Snack wrap is back.

Speaker 3 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.

Speaker 9 Well, no, you pointed it in a good direction, aimed it at a good place, and we're getting somewhere.

Speaker 3 To solve our diseases.

Speaker 10 Yeah, so now it's going to cure us of all disease

Speaker 10 before it makes us its slaves.

Speaker 9 Because we need healthy slaves.

Speaker 3 All that and more coming up on Star Talk.

Speaker 3 Welcome to Star Talk,

Speaker 3 your place in the universe where science and pop culture collide.

Speaker 3 Star Talk begins right now.

Speaker 3 This is Star Talk, Special edition neil degrasse tyson your personal astrophysicist special edition means we've got gary o'reilly in the house gary hi neil former soccer pro apparently yeah and soccer announcer yes yes absolutely and you still do that don't you i do chuck nice baby hey announcing that i know nothing about soccer You're in my club then.

Speaker 3 Announcing that you are American. American dove going as real football.
Violence.

Speaker 3 So we're talking about AI today. That's a favorite topic.
We revisit that often.

Speaker 13 Only the future of the entire world.

Speaker 3 AI as it matters in biology. Oh, wow.
Now that's a big deal. I know.

Speaker 3 I know.

Speaker 3 Because people are thinking about composing your term paper

Speaker 3 or winning a chess.

Speaker 3 But it's got a whole frontier ready to be explored. Yeah.
And so tell me what you and your producers cooked up today. Okay.

Speaker 9 So we've been on the case to get these guys involved for some time, but they are so busy.

Speaker 14 So here we go. I'll say it.

Speaker 9 I'm made of proteins.

Speaker 14 Yes.

Speaker 9 You're made of proteins from strings of amino acids that fold into shapes that put

Speaker 3 all together form us.

Speaker 9 But there's a fundamental problem in biology

Speaker 9 that has implications for all of medicine. How do these proteins fold up?

Speaker 3 Oh.

Speaker 9 For this solution, we looked at AI and a Google DeepMind tool called AlphaFold.

Speaker 9 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?

Speaker 3 Appreciate AI win all the Nobel Prizes. Yeah, let's give it to her now.

Speaker 10 Just park them all up.

Speaker 9 Now, the isomorphic labs together with Google DeepMind developed and released AlphaFold 3.

Speaker 9 Yes, we're on the third iteration. And that was last year, and applied these new AI models for drug discovery.

Speaker 3 Oh, that's great.

Speaker 9 All right, so think this through. Could our next generations of treatments be computer generated?

Speaker 3 Oh, yeah.

Speaker 9 Oh, by the way, Neil, let's introduce our guest.

Speaker 3 I will. We've got Max Yaderberg.
Did I pronounce that correctly?

Speaker 18 Yeah, you got it. You got it right.

Speaker 3 Let's hear you say it.

Speaker 19 Let's hear what you say. Me say it.

Speaker 13 Yeah. Max Yoderberg.

Speaker 3 Oh, that's exactly what I said. That's what I got.
Yeah.

Speaker 3 He was practicing. He was practicing.

Speaker 3 So you studied AI at Oxford? That's right. That's right.
And now I hear that's a community college?

Speaker 3 Oxford Community College. That's exactly right.
In Oxford, England. Yes.

Speaker 3 so uh specialized in deep learning algorithms i got your little bio here for understanding images nice yeah 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 yeah yeah i mean you know this this was 10 15 years ago back before ai was cool right um right 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.

Speaker 27 We couldn't actually do that very well.

Speaker 3 I searched my 9,000 images on my computer for the word telescope. Yeah.
And it found telescope written in Chinese

Speaker 3 on a photo taken at an angle in one of my images.

Speaker 3 Wow. When I was visiting China.

Speaker 27 Yeah, this is it.

Speaker 11 During my PhD, we took all of the BBC's back catalog.

Speaker 30 No.

Speaker 18 And we ran...

Speaker 28 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.

Speaker 3 and so you know seriously

Speaker 10 if you're doing interesting when you do that do you tie so when the 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 we're really just intuiting an image when we see it as right exactly that's how we do it but the ai it's like a holistic process of holistic processing ai actually sees the image and what it's seeing is pixels.

Speaker 3 That's right.

Speaker 10 And 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?

Speaker 10 Or is the search just the AI knows the actual image itself?

Speaker 35 This was like the big breakthrough back then when I was doing my PhD.

Speaker 22 And this is what deep learning as well is all about.

Speaker 17 You can imagine if you have

Speaker 36 this image full of pixels, how do you actually code up how to read text from there?

Speaker 25 How do you tie it to the language of the text?

Speaker 38 It's unimaginably hard to code that up by hand.

Speaker 18 So instead, what you do is you put these, what they're called, neural networks.

Speaker 40 They look at all of the pixels of the image, and you give it lots and lots of examples of images that have somewhere it's got the text in it, and you tell the neural network what the text is.

Speaker 43 I see.

Speaker 25 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.

Speaker 3 Wow. So you're currently chief AI officer at isomorphic labs.
This is a biology place. That's right.
Do you have any biology in your background? Formal biology? No. No, okay.
No.

Speaker 3 So they want you for your AI.

Speaker 18 That's right. That's right.

Speaker 27 So I was at a place called DeepMind beforehand.

Speaker 3 Oh, Google.

Speaker 39 Google Deep Mind.

Speaker 45 Exactly. I was there for a long time.

Speaker 47 I absolutely love this core AI technology called deep learning.

Speaker 33 That's what I've been developing.

Speaker 18 my whole career so far.

Speaker 17 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 you know back then it was about

Speaker 25 yeah and and because the world didn't know what ai was so we were trying to prove that this was even a thing right 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 where it begins yep

Speaker 10 it's always where the terminator starts it's always the innocent dreamer

Speaker 49 who says this can change the world for such good and it's in my closet now.

Speaker 3 Would you like to see it?

Speaker 10 And then it's always like some evil businessman who's just like, with my weather machine, I will one day rule the world.

Speaker 3 You know, so

Speaker 12 apart from that, carry on.

Speaker 3 Yes. The good thing is there's some pretty strictly good applications of AI that we can drive.

Speaker 25 And, you know, Demis Asabis started Isomorphic Labs, spinning that out of Google DeepMind to really think how can we apply AI to actually completely solve all disease.

Speaker 3 Okay, so it has genetic links back to its origin story within Deep Mind. I feel better about that now.
Okay. You happy? Yeah, I'm happier now.

Speaker 14 Yes.

Speaker 48 So I moved over as part of that founding team to head up AI in this space.

Speaker 23 And it's been about three and a half years now.

Speaker 47 It's been a crazy journey, but it's fascinating.

Speaker 53 It's so much fun.

Speaker 3 So you've got this AI expertise, and Alpha Folds spins off this biological application of it. First, tell me the word isomorphic.
What does that mean in biology?

Speaker 17 Isomorphic is this technical term which is

Speaker 25 a one-to-one mapping of space, right?

Speaker 18 And the reason we're called isomorphic labs is really that we believe that biology is really, really complicated.

Speaker 48 In the world of physics, we can write down equations for physics with maths.

Speaker 48 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.

Speaker 47 It's just too complicated.

Speaker 3 Biology is the most complex expression of chemistry. Yes.
that we know.

Speaker 54 There's just so many moving parts.

Speaker 3 Did you just make that up? Yeah.

Speaker 9 So we're looking for a Rosetta Stone here for the language of biology. Exactly.

Speaker 25 And so what could be that perfect description language for biology?

Speaker 18 We believe AI and machine learning is that.

Speaker 33 So that there could exist an isomorphism, a mapping between the biological world and the world of AI machine learning.

Speaker 25 Hence the name.

Speaker 3 Hence the name. Gotcha, gotcha, gotcha.
All right. So tell us about...
protein folding. Because, you know, when we learn about chemistry, we learn about chemical reactions.

Speaker 3 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.
And when you write down the chemical equations,

Speaker 3 there's no shape in there. There's just what elements and molecules comprise it.

Speaker 10 And those equations don't really ever represent the three-dimensional nature.

Speaker 3 Exactly. You don't even know which, if it's, it has handedness.
Yes. Yes.
Right. So take us from there.

Speaker 17 We think about proteins.

Speaker 22 Proteins are these fundamental building blocks of life. They're inside of everyone.
They make up everything we have, basically.

Speaker 56 And they're made up of what's called a sequence of amino acids.

Speaker 38 Each amino acid is a molecule.

Speaker 43 There's about 20 different amino acids.

Speaker 42 And you put them together in a long sequence.

Speaker 20 Ever or just in life?

Speaker 57 In life, you can have non-natural amino acids as well that you can make as well.

Speaker 20 You can make them.

Speaker 22 You can make them and actually use those for drugs sometimes.

Speaker 43 You string these amino acids together, and that becomes a protein, but they don't exist as these strings.

Speaker 40 They fold up spontaneously in the cell to create these 3D shapes.

Speaker 28 And why that's important is that these proteins, they're basically molecular machines.

Speaker 44 They don't just exist by themselves. They actually create these little pieces of machinery.

Speaker 22 They interact with other proteins.

Speaker 41 They interact with other biomolecules like DNA and RNA.

Speaker 3 And that interaction is a shape-fitting.

Speaker 14 Exactly. Exactly.
So these proteins are... It's a puzzle.

Speaker 3 It's a 3D puzzle.

Speaker 39 It's a 3D puzzle.

Speaker 18 Exactly.

Speaker 3 A 3D jigsaw puzzle.

Speaker 18 And it's not static.

Speaker 3 Which is way harder than a 2D jigsaw puzzle.

Speaker 22 And these are not static things.

Speaker 36 It's not just static puzzle pieces coming together.

Speaker 17 They change shapes.

Speaker 40 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.

Speaker 20 And that's what I was going to ask you.

Speaker 9 What speeds is this folding taking place?

Speaker 9 Is it continuous? Once it folds, that's it. But you've just told me, no, it just keeps moving through the whole thing.

Speaker 3 Yeah,

Speaker 42 these are really, really complex dynamical systems.

Speaker 18 Yeah.

Speaker 25 You know, composed of thousands, millions, trillions of atoms within our cells, unfolding over the course of microseconds and beyond.

Speaker 10 And this dynasism that you're talking about.

Speaker 3 What word is that?

Speaker 57 Dynozism?

Speaker 3 That's a word? Isn't that a word?

Speaker 55 Dynoism? I think I just made it up.

Speaker 3 Mism.

Speaker 10 Oh, dynamism. No, dynamism.

Speaker 3 Dynamism. Thank you.
Thank you. I'm correcting Grammar.
This is a first.

Speaker 3 This is.

Speaker 10 Dynamism. Dynamism.

Speaker 3 So you're kind of dinosaur. Dynamism.
Not dynamos. Dinosaur.
Dynasism. Dinosaur.

Speaker 49 Yeah, dinosaur.

Speaker 10 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

Speaker 10 execution and blueprint, we all come out so different.

Speaker 10 Is that part of the process that you are looking at and mapping?

Speaker 3 I would say to a jellyfish, we all look identical. True.
Okay. They're not saying, oh, is your skin color slightly different? Are you slightly taller? Yes.

Speaker 3 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?

Speaker 3 That can then solve problems that we encounter that the natural universe has not.

Speaker 3 So, oh, that was a good question.

Speaker 3 You're happy with yourself. Happy with yourself today.
Happy with yourself. Happy with myself today.
Yeah.

Speaker 56 This is really interesting.

Speaker 33 We have these little molecular machines, these proteins, and we care about that 3D structure and how they work for two reasons.

Speaker 61 One, we want to understand how our cells work, because if something goes wrong with that, which is the case for disease, then we want to understand, okay,

Speaker 32 where do we actually need to go in and start fixing that?

Speaker 10 Or how we can stop it from actually going wrong in the first place.

Speaker 18 Exactly, exactly.

Speaker 13 So that's one thing.

Speaker 59 And then when we think about, okay, how can we go and fix that?

Speaker 31 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?

Speaker 40 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.

Speaker 50 Or and so we stop that protein working or we make it work better.

Speaker 25 These are the sort of things we do in drug design.

Speaker 10 It reminds me of messenger RNA vaccines that we developed for COVID.

Speaker 60 Yeah, you know, there's so many different types of molecular mechanisms that we take advantage for for drug design.

Speaker 63 A massage chair might seem a bit extravagant, especially these days.

Speaker 3 Eight different settings, adjustable intensity, plus it's heated, and it just feels so good.

Speaker 63 Yes, a massage chair might seem a bit extravagant, but when it can come with a car,

Speaker 63 suddenly it seems quite practical.

Speaker 64 The all-new 2025 Volkswagen Tiguan, packed with premium features like available massaging front seats, that only feels extravagant.

Speaker 65 The best business-to-business marketing gets wasted on the wrong people. Think of the guy on the third floor of a 10-story apartment block who's getting bombarded with ads for solar panels.

Speaker 65 What a waste.

Speaker 65 So when you want to reach the right professionals, use LinkedIn ads.

Speaker 65 LinkedIn has grown to a network of over 1 billion professionals and 130 million decision makers and that's where it stands apart from other ad buyers.

Speaker 65 You can target your buyers by job title, industry, company, role, seniority, skills, company revenue. So you can stop wasting budget on the wrong audience.

Speaker 65 It's why LinkedIn Ads generates the highest business-to-business revenue on ad spend of all online ad networks.

Speaker 14 Seriously. all of them.

Speaker 65 Spend $250 on your first campaign on LinkedIn Ads and get a free $250 credit for the next one. No strings attached.
Just go to linkedin.com/slash star talk. That's linkedin.com/slash star talk.

Speaker 65 Terms and conditions apply.

Speaker 5 I'm gonna put you on, nephew.

Speaker 66 All right, um, welcome to McDonald's.

Speaker 8 Can I take your order?

Speaker 5 Miss, I've been hitting up McDonald's for years. Now it's back.

Speaker 6 We need snack wraps.

Speaker 3 What's a snack rap?

Speaker 5 It's the return of something great.

Speaker 3 Snack wrap is back.

Speaker 67 I'm Olicon Hemraj, and I support Star Talk on Patreon. This is Star Talk with Neil deGrasse Tyson.

Speaker 9 Are the folding proteins generally following a set pattern? in the way that they do fold and you're able to map them and when they misfold

Speaker 9 that's when you're able to flag that up or have i just reinvented something or talked rubbish.

Speaker 3 There we go.

Speaker 13 No, no,

Speaker 38 you're onto something.

Speaker 13 So

Speaker 13 great.

Speaker 39 So, you know,

Speaker 30 like the, I mean, the amazing thing is that we can actually, turns out, predict how these proteins fold.

Speaker 3 So they are. So modeling that.

Speaker 27 Yeah, we're modeling that with deep learning, with neural networks.

Speaker 38 That's what AlphaFold, you know, and all its generations are all about.

Speaker 43 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.

Speaker 45 And normally this would take people months, if not years, to work out this 3D structure.

Speaker 3 So how is it that alpha fold knows how

Speaker 3 a large molecule wants to fold?

Speaker 13 Again, it's got to know that in some way.

Speaker 48 It's learnt this from a few hundred thousand examples.

Speaker 43 So chemists, biochemists over the last 50 years, they've been working out these protein structures by hand.

Speaker 40 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.

Speaker 36 It's a pretty hard process, but people have been doing that.

Speaker 3 That's your way to photograph what the shape of the molecule is. That's your way to photograph in reality.
With it, with that kind of it's basically an electron microscope at that level.

Speaker 25 Yeah, similar. It's like electron scattering, yeah, yeah, exactly.

Speaker 18 And so people have been doing that for the last 50 years and depositing these structures.

Speaker 44 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.

Speaker 61 Right.

Speaker 57 And the amazing thing is, and this is really remarkable, is that you can then train this on the last 50 years of data.

Speaker 23 That's a couple of hundred thousand protein and biomolecular systems.

Speaker 32 But you can apply it seemingly to everything we know about in the protein universe, in the proteome.

Speaker 3 Well, it has

Speaker 3 the proteome. Oh, we like that.
Oh, proteome.

Speaker 3 Proteome. Proteome.
Proteome.

Speaker 9 So how accurate is AlphaFold and AlphaFold?

Speaker 9 We're 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?

Speaker 18 Yes.

Speaker 3 So AlphaFold 2

Speaker 4 was that big jump.

Speaker 43 where we started to get experimental level accuracy for just proteins.

Speaker 20 And that's what won the Nobel Prize.

Speaker 9 So you balanced it off against empirical experimental level.

Speaker 22 Yeah, the benchmark is doing the real lab work itself.

Speaker 41 So AlphaFold II reached that level.

Speaker 40 Now AlphaFold 3 expands from just proteins to incorporate other biomolecular types.

Speaker 46 So proteins with other proteins, proteins with DNA, with RNA, with what's called small molecules, which are the same.

Speaker 3 They go to the neighborhood. They start mixing all that up.

Speaker 3 Or maybe not the neighborhood.

Speaker 9 Maybe the neighborhood gets a little bit of an upgrade.

Speaker 10 No, that's when you make the superhuman. So

Speaker 3 I'm trying to be the terminator.

Speaker 10 It's not going to be the terminator. It's going to be the superhuman.
And then they're going to be like us, and they're going to look down on us and go, you know, why do we need you guys?

Speaker 3 And that's it.

Speaker 10 So, anyway, you're able to predict these.

Speaker 33 And

Speaker 10 have you actually taken any of the modeled predictions and made the proteins?

Speaker 3 Yeah. Oh, yeah.
Or tell us where you expect these to lead to new and innovative drugs. Because otherwise, it's just

Speaker 3 a puzzle exercise. Yeah.

Speaker 55 It's a great Lego set.

Speaker 3 Lego set.

Speaker 9 We want the guests to enjoy this.

Speaker 3 Yeah.

Speaker 3 It's like, oh my God, how much that Lego set costs?

Speaker 10 Only $10 billion.

Speaker 3 Sorry, go ahead.

Speaker 18 Yeah, yeah.

Speaker 28 So if you take a particular disease and

Speaker 47 we think that we can actually, you know, solve this disease by modulating a particular protein.

Speaker 22 The question is how we do that.

Speaker 36 So we design a drug molecule and we want it to fit to this protein in a certain way.

Speaker 59 And so this is where traditionally you would have to actually either just guess or go into

Speaker 3 and

Speaker 10 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.

Speaker 3 Isn't this what you call the

Speaker 9 target proteins?

Speaker 3 Yes. Wow.

Speaker 9 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.

Speaker 9 And now we become the sort of detective. And has this AlphaFold 3 produced how many clues and how many answers?

Speaker 49 Or are we still grappling with that?

Speaker 10 That's interesting. Yeah.
Instead of trying to figure out the drug, the AI actually figures out the drug for you.

Speaker 14 Discovery.

Speaker 13 Well, exactly.

Speaker 3 If you let the guy speak, we might be able to,

Speaker 3 the two of you. Okay.
We're figuring out this whole industry ourselves, Gary.

Speaker 49 Yes.

Speaker 3 Yeah,

Speaker 50 this is exactly where it's going.

Speaker 29 So

Speaker 19 we can start actually rationally designing these drugs.

Speaker 61 Traditionally, you would take

Speaker 46 a million random molecules and you would just throw them at these proteins and see what sticks.

Speaker 59 And that's how so many drugs have been created historically.

Speaker 31 You go back further and you're sifting through mud to find these sort of molecules.

Speaker 9 This is why there's been such a low percentage of success rates with the sort of drugs for whatever the problem is.

Speaker 28 That's part of it because

Speaker 44 we don't necessarily understand how these molecules are working.

Speaker 47 But with something like AlphaFold 3, you can put the molecule, put the target protein into the system, into the neural network, and you get out the 3D structure.

Speaker 46 And as a chemist, you can start to understand, okay, how is this small molecule drug modulating this protein?

Speaker 57 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?

Speaker 32 You know, it's estimated there's like 10 to the power of 60 possible drug-like molecules out there.

Speaker 40 That's 10 with 60 zeros.

Speaker 3 How many people know what 10 to the 60s are? Yeah, yeah, yeah.

Speaker 3 Don't be rude.

Speaker 46 Even if you had the perfect alpha fold, you'd have to run that across 10 to the power of 60 molecules, which is just computationally impossible.

Speaker 47 It's unfeasible.

Speaker 3 Until quantum computing.

Speaker 44 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.

Speaker 3 Oh, because the 10 of the 60 is if you just did it randomly. Exactly.
Right, but you're throwing it out, anyway.

Speaker 3 If you don't do it randomly, then you can.

Speaker 13 Yeah, but randomly is the state-of-the-art method.

Speaker 37 That's how people do it.

Speaker 3 It's how people currently do it.

Speaker 52 It's how people currently do it. Old school.

Speaker 3 Well, he calls it state of the art.

Speaker 10 You're the state of the art.

Speaker 3 Thank you.

Speaker 3 Let's use the word properly here.

Speaker 9 So what if the protein turns left

Speaker 9 when you've mapped it to turn right? Is that when we have issues that even AlphaFold 3 has a problem with?

Speaker 3 Exactly.

Speaker 22 These are not perfect models at the end of the day.

Speaker 23 They're very, very accurate, but they will make some mistakes.

Speaker 35 So you still do...

Speaker 43 currently need to go into the lab occasionally but the amount of lab work you have to do is so much less right than

Speaker 40 And often you can find the area of molecular space where these models work really, really well.

Speaker 23 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.

Speaker 3 So back to an earlier point, in the old days, like last month,

Speaker 3 the pharmaceutical companies, big pharma, would

Speaker 3 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

Speaker 3 there's some truth to

Speaker 3 this first pill

Speaker 3 cost $50 million.

Speaker 3 The second pill cost 10 cents because they had to research to get the formula for that first pill. If you have narrowed the search space,

Speaker 3 then the cost of developing that first pill can be manifold smaller.

Speaker 22 It costs on average $3 billion to create a new drug.

Speaker 3 Wow.

Speaker 53 That's on average.

Speaker 38 Yeah.

Speaker 14 And so yeah, there's a reason.

Speaker 3 I was low when I said $100 billion. You were low-balling.
I was low-balling it.

Speaker 36 So this is a massive opportunity to completely change just like the cost, the speeds.

Speaker 55 The business model.

Speaker 39 And the business model as we do that.

Speaker 10 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 company A, right? It's mine and I get to determine everything.

Speaker 10 If you're an AI company company and you're just doing this, okay, so that you can sell it, then it's yours.

Speaker 10 Which one will be, will make prices lower for the consumer?

Speaker 56 Our goal is to is to like really redefine this way you do drug design. So it becomes so much cheaper.

Speaker 24 We have so much more abundance of potential drugs and chemical matter that it really does change.

Speaker 19 the business model and it changes the economics of the space.

Speaker 10 So you can actually revolutionize the cost of making drugs.

Speaker 14 Yeah,

Speaker 14 that's where we're going.

Speaker 3 That's where we're going. All right.

Speaker 9 Is one of the next steps with AlphaFold, whichever it's three 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.

Speaker 39 Wow.

Speaker 22 So actually the misfolding of a protein is another thing.

Speaker 59 That's what causes some types of disease, where you'll have a genetic mutation, a mutation in your DNA, which will change a particular amino acid in that protein.

Speaker 69 And so it doesn't fold the normal way it should fold.

Speaker 38 And so it doesn't function as it normally should as a molecular machine.

Speaker 22 And so things like AlphaFold can help us understand what are those mutations that cause misfolding.

Speaker 32 They're called missense mutations.

Speaker 47 And then, you know, these could be potential drug targets.

Speaker 31 So we could think about molecules that could mitigate against that.

Speaker 3 If I understand correctly, if you look at the PDR, it is this thick, and

Speaker 3 the physician's desk reference. Thank you. It's this thick.
So it's the size of an old-style Manhattan phone book. Okay, it's very thick, multiple inches across.

Speaker 3 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

Speaker 3 rather than through protein folding?

Speaker 3 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.

Speaker 3 Is that, did I say any of that right?

Speaker 38 I think that that is the majority of drugs.

Speaker 42 They are chemicals that we take.

Speaker 3 The chemical is not going to fix the fold. It's going to treat the symptoms of the misfolding that happens.

Speaker 44 We're not changing the mutations mutations of the proteins.

Speaker 42 That could be something like gene therapy.

Speaker 42 But these are chemicals that come in and will attach themselves to these proteins and somehow mitigate

Speaker 47 something like a misfold or it'll change an interface, change how these molecular machines work.

Speaker 9 That's weird. Is there a particular disease isomorphic labs are focusing upon right now or is this a more of a broad spectrum?

Speaker 22 Let's go for proteins and cherry-pick out certain things or are we really looking at one particular the technology we're creating it's really really general we want to be able to apply this drug design engine on any protein any target any disease area that comes our way now saying that you know practically as a company and and that you want to focus on a particular area we're focusing at the moment on you know a lot on cancer and a lot on immunology of course

Speaker 3 two biggies

Speaker 9 and the two that probably lend themselves best to what you're trying to accomplish actually 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?

Speaker 69 I mean, it's going really well, to be honest.

Speaker 17 We're seeing these algorithms actually

Speaker 50 change the way that we're able to do drug design.

Speaker 44 We're able to discover completely novel chemical matter against some of these targets that people have been working on for even over a decade.

Speaker 42 So really, really hard stuff, making amazing progress.

Speaker 47 Still really early in the company, but it's super exciting.

Speaker 10 And have you sent anything to be photographed yet?

Speaker 69 We send some things for molecular photographs, yeah.

Speaker 18 Okay.

Speaker 3 Yeah, yeah.

Speaker 10 I know you're not allowed to talk about it. I know.

Speaker 3 I get it. But we're all very happy.
Okay, there you go.

Speaker 3 Listen, I'm with you.

Speaker 10 I'm picking up what you're putting down.

Speaker 55 That's cool.

Speaker 3 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

Speaker 3 image of the DNA molecule to know that it was a double helix. Exactly.
That becomes public knowledge at that point.

Speaker 3 So someone with tools access to AlphaFold 3, would any company have access to this once you have published the blueprint for it?

Speaker 62 In drug design, often these blueprints come out in the patents.

Speaker 43 So, when you're going to go into clinical trial, you need to patent these molecules.

Speaker 69 And in those patents, you'll have a lot of data around the molecules, the formula.

Speaker 3 I was talking about earlier. Yeah, yeah, yeah.
Okay. Yeah.
All right. So,

Speaker 3 the

Speaker 3 immune system, the cancer, these are leading leading causes of maladies in this world. What of the

Speaker 3 genetic disorders that affect one in 100,000 people? Wow.

Speaker 3 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.

Speaker 10 Yeah, it's also not profitable. Well, yeah, because you don't have enough of a market there to sell the drug.

Speaker 69 Right.

Speaker 13 I mean, you know, it's exactly that point, Chuck.

Speaker 38 Traditionally, it might not be that attractive commercially to go after

Speaker 22 very small patient populations.

Speaker 47 But in a world where it's so much cheaper, so much easier to get to these drug molecules, then that opens up all of this space.

Speaker 3 The cheaper it is,

Speaker 3 the easier you can justify going down that risk list.

Speaker 22 And this is a big guiding star for us.

Speaker 20 This is why we're doing this. That's beautiful.
I see what you did there.

Speaker 3 Guiding star.

Speaker 3 You know, great though. He's picked up in the environment.
He's not sitting.

Speaker 3 Why is chief AI officer?

Speaker 10 I'm interested 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.

Speaker 10 All of the patent implications, there's going to be

Speaker 19 research implications.

Speaker 10 There's going to be a lot of things tied to this.

Speaker 69 Yeah, yeah.

Speaker 27 I mean, 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.

Speaker 42 And that's a really long process.

Speaker 4 Yeah.

Speaker 3 And the mice.

Speaker 61 But even these mice models, they're not actually very predictive.

Speaker 38 Like you do all these studies in mice, and then they don't, you know, it doesn't translate into success in people.

Speaker 3 Right.

Speaker 9 You've got to go up the evolutionary scale and then get to the human bit.

Speaker 18 Yeah, exactly.

Speaker 48 And so there's, you know, you can imagine a world where we can design loads of new drugs.

Speaker 47 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.

Speaker 31 So I think there's a lot to be done and like rethought there.

Speaker 9 Is the ultimate goal for AlphaFold 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?

Speaker 9 So are you able to then design a drug? or a medication that has zero side effects and works exactly for me?

Speaker 18 This is the goal, right?

Speaker 21 This is what we're shooting for.

Speaker 44 You know, imagine a world where we can sequence your particular cancer mutations.

Speaker 32 Right.

Speaker 50 And then based on those, your individual mutations be generating specific drugs for you.

Speaker 70 Right.

Speaker 25 That even these are like, you know, 3D printed or something around the corner.

Speaker 3 Okay. Yeah, this is.

Speaker 3 We're not there yet, right?

Speaker 10 We're in the very nascent stages of that right now with immunotherapy for cancer treatments.

Speaker 3 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?

Speaker 33 Proteins make up like pretty much all of our molecular machinery.

Speaker 3 So

Speaker 22 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.

Speaker 40 Right.

Speaker 18 Or, you know, a cell going wrong in a certain tissue.

Speaker 3 If I have a bacterial infection, I give myself antibacterial chemicals and then I'm done. Do I need you for that?

Speaker 41 But those chemicals are interacting with the proteins in the bacteria.

Speaker 19 Okay.

Speaker 44 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.

Speaker 3 All right.

Speaker 10 So basically everything you're talking about is all happening on the cellular level.

Speaker 3 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.

Speaker 3 The delivery soldier. And how do you do that other than through like a Trojan horse virus or something? Because viruses get in there pretty

Speaker 3 on command.

Speaker 17 Yeah, well, if you think about the drugs that you take as pills,

Speaker 42 drug design is really hard because it's not just about targeting these proteins.

Speaker 38 We've got to get them to the right place.

Speaker 27 We might want a pill that you take.

Speaker 4 So you take this pill.

Speaker 47 It's got to be absorbed by the body.

Speaker 39 So it's got to be soluble.

Speaker 22 It's got to go through the gut wall.

Speaker 47 It's got to go through the bloodstream to the particular tissue type, the cell type you care about.

Speaker 47 Then it's got to go through the cell membrane to be able to actually target maybe a target which is within the cell.

Speaker 39 So you need all of these properties in a single molecule.

Speaker 44 So we're actually designing these molecules not just to hit the protein, but also to be soluble, to be cell permeable.

Speaker 24 There's so many different factors.

Speaker 21 And then you don't want this molecule to be toxic.

Speaker 42 So you want it to hit the target of interest,

Speaker 3 but not...

Speaker 46 hit anything else.

Speaker 3 Right.

Speaker 3 So I can see how a molecule gets through the cell wall. Yeah.
A simple molecule, but a full-up protein, red-blooded protein, how's that getting through the cell wall? Exactly.

Speaker 43 There's different types of drugs.

Speaker 31 Some are what we call small molecules, things you could take as pills.

Speaker 38 Others are made from proteins.

Speaker 27 There, they're often things that you would inject directly inside.

Speaker 44 And some of those might be cell permeable.

Speaker 53 There would be things like peptides.

Speaker 22 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 the surface of cells.

Speaker 53 So you don't need that permeability.

Speaker 47 So it really depends on what your target is and how do you want people to be able to take that drug.

Speaker 32 Sometimes a pill is the best thing, but actually sometimes injecting is the best thing.

Speaker 3 Yes. And remind me what a peptide is.

Speaker 25 A peptide is a really small protein.

Speaker 25 So you've got full-blown proteins, which are these big molecular machines.

Speaker 26 And then you've got small proteins made up of

Speaker 62 five to fifty amino acids.

Speaker 36 Those are peptides. Those are peptides.

Speaker 62 They're smaller, so sometimes in some configurations they can get through the cell wall.

Speaker 5 That's the sound of the fully electric Audi Q6 e-tron and the quiet confidence of ultra-smooth handling. The elevated interior reminds you this is more than an EV.

Speaker 5 This is electric performance redefined.

Speaker 67 Honey, do not make plans Saturday, September 13th, okay?

Speaker 7 Why, what's happening?

Speaker 67 The Walmart Wellness Event. Flu shots, health screenings, free samples from those brands you like.

Speaker 3 All that at Walmart.

Speaker 51 We can just walk right in. No appointment needed.

Speaker 16 Who knew we could cover our health and wellness needs at Walmart?

Speaker 71 Check the calendar Saturday, September 13th.

Speaker 67 Walmart Wellness Event.

Speaker 3 You knew. I knew.

Speaker 66 Check in on your health at the same place you already shopped. Visit Walmart Saturday, September 13th for our semi-annual wellness event.
Flu shots subject to availability and applicable state law.

Speaker 66 Age restrictions apply. Free samples while supplies last.

Speaker 8 At Capella University, learning online doesn't mean learning alone.

Speaker 8 You'll get support from people who care about your success, like your enrollment specialist who gets to know you and the goals you'd like to achieve.

Speaker 8 You'll also get a designated academic coach who's with you throughout your entire program. Plus, career coaches are available to help you navigate your professional goals.

Speaker 8 A different future is closer than you think with Capella University. Learn more at capella.edu.

Speaker 9 So with this computer science, are we upending chemistry as we've known it? And are we going to find it kind of moving off?

Speaker 3 Even with AI? Yeah, we go from there.

Speaker 9 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?

Speaker 22 Chemistry is always going to exist.

Speaker 62 It's like, to me, it's like any field of science at the moment.

Speaker 31 Doing science like chemistry without maths, you wouldn't think about that now.

Speaker 25 And it's going to be the same thing with AI.

Speaker 53 It already is in my mind.

Speaker 56 You just wouldn't do chemistry without AI.

Speaker 48 You wouldn't do biology without AI. It's just that fundamental tool that allows us to understand the world better.

Speaker 10 So chemists will not one day be like coal miners.

Speaker 10 Just like I remember, my grandpa used to go into the lab.

Speaker 9 So going back to an issue challenge.

Speaker 3 He comes home smelling like chemicals.

Speaker 9 Who's actually going to be able to access Alpha Fold 3 or AIs of this iteration? Is it exclusively isomorphic labs or this comes out in license?

Speaker 3 I want a home kit. That's it, exactly.
Right, right, right. My DNA goes in.

Speaker 3 There's an alpha fold going on, out comes a pill, and I take it, and I don't even need you at that point. That would be so cool.

Speaker 10 You just finger prick or at least put your finger on a sensor or something, and it figures it out.

Speaker 3 You make your own pill at home.

Speaker 31 Yeah, yeah. Look up the Theranos story for that one.

Speaker 10 Wow, that's the woman that went to prison.

Speaker 51 But no, you can access AlphaFold.

Speaker 22 So if you search for AlphaFold server,

Speaker 22 there's a whole web-based system where you can fold proteins there for academic use.

Speaker 18 It's really cool.

Speaker 22 So you can just put your system in, get the 3D fold out from AlphaFold 3, download it.

Speaker 31 Yeah.

Speaker 3 Oh, cool, man.

Speaker 9 I mean, how far away are we from modeling an entire human being, which I suppose touches onto your fears?

Speaker 3 Modeling or creating? Either or.

Speaker 10 Once you model,

Speaker 10 the next step is creating. Yeah, that's true.
That's all there is to it.

Speaker 3 That's true.

Speaker 43 That's the dream.

Speaker 19 We kind of need to work up the scales here.

Speaker 18 So

Speaker 46 we can model how two atoms interact.

Speaker 48 We can write down those equations.

Speaker 46 We can simulate small atomic systems.

Speaker 22 With things like AlphaFold, we get into bigger atomic systems, things on the scale of like multiple proteins. Now we've got very...

Speaker 52 very accurate AlphaFold 3.

Speaker 35 Maybe we can actually bootstrap off that to get to more sort of even bigger systems,

Speaker 4 what we call pathways, how all of these things interact.

Speaker 3 It's only just now clicking within me because you can look up in a book the tables of

Speaker 3 action potentials for the interactions of atoms and molecules. And so you'd have a very good sense of which molecules will combine.
Is it exothermic? Is it endothermic?

Speaker 3 But these are atoms and molecules. And as powerful and as convenient as that is, that's just the first rung in in this ascending ladder of complexity that you are gaining control over.

Speaker 18 Yeah, and there's trillions of atoms within a single cell, let alone the whole human body.

Speaker 22 It's just unfeasible to simulate the whole thing.

Speaker 17 But what you can do is you can, you know, we do have good measurement techniques.

Speaker 41 at different levels of scale.

Speaker 25 So we can measure things like protein folding.

Speaker 26 We can measure the amount of protein within a cell.

Speaker 44 We can measure the number of cells of a certain type within a tissue.

Speaker 54 And so we have these.

Speaker 3 The bigger it is, the easier it would be to measure.

Speaker 57 So we have these little windows into this sort of microscopic world.

Speaker 70 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.

Speaker 3 We can rebuild it. I read this article like...

Speaker 10 God knows how long ago.

Speaker 3 God, how long did Jack read the article?

Speaker 10 Because you know, God.

Speaker 10 Anyway, it was talking about when a fertilized cell starts to proliferate and become a person.

Speaker 10 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.

Speaker 10 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.

Speaker 10 Are you able to pierce that veil and see into that?

Speaker 22 I mean, we haven't been looking at that specific thing.

Speaker 3 Okay.

Speaker 43 But this is where you start to understand more about, you know, a really granular scale.

Speaker 32 And then you can integrate that and create these sort of, I don't know, coarser measurements and coarser predictions.

Speaker 22 This is what we do in lots of areas of science, right?

Speaker 43 We don't simulate the whole universe at the atomic scale, but we find these rules of thumb or ways to describe sort of broader collections of molecules.

Speaker 22 And that's what we can start to build up and actually learn with these neural networks.

Speaker 3 Cool.

Speaker 9 So question on behalf of Chuck. Could AlphaFole discover a hallucinogenic that could make him see God

Speaker 9 or any other deity or being?

Speaker 3 Thank you for asking.

Speaker 3 Welcome.

Speaker 55 I would like a very real answer, please.

Speaker 69 You can go on the AlphaFole server and try that out.

Speaker 3 Okay. All right.
Invitation.

Speaker 55 Hey, listen, I'm all about it.

Speaker 9 So we've looked

Speaker 9 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

Speaker 9 are we going to be able to with alpha fold or AI like this be able to upgrade ourselves to make this sort of deep space travel

Speaker 3 or or upgrade ourselves for anything anybody

Speaker 18 fire you know the yeah now now we're sort of beyond you know solving disease into like actually can we enhance ourselves right yeah I don't know I think like there's there's probably potential right to to think about creating chemical matter that we can take or ingest that that i mean aging alone is would be aging huge

Speaker 10 application for this i mean there's crazy research on aging aging is basically cellular degeneration yeah and if you're able to on a molecular level kind of restart that process or jumpstart it or you know boost it 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 um factors that that reverse the age of cells.

Speaker 26 There are these things called Yamanaka factors.

Speaker 3 Yes.

Speaker 43 And there's even potential that people are finding of creating molecules that stabilize particular proteins.

Speaker 22 Yamanaka factors are proteins.

Speaker 62 They're transcription factors that read DNA.

Speaker 44 Can stabilize these things.

Speaker 41 Maybe that is what reverses some of the age of cells.

Speaker 36 This is super nascent.

Speaker 3 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

Speaker 3 where they didn't manipulate your genome, but they selected your pre-existing genome for certain properties.

Speaker 3 And there's a person giving a piano recital, and it was a very rich sound. I mean, it was beautiful.
And then the camera came around to the front, and the person had 12 fingers. That's right.

Speaker 3 And

Speaker 3 bread for that. Yes.

Speaker 3 Right? You get two extra notes for every

Speaker 3 everything going on.

Speaker 10 She could only play the stuff. Nobody could play with you.

Speaker 10 Nobody could play with you. Nobody could play with you.

Speaker 3 So this would be modifying not to go into space, necessarily, but just to sort of enrich the diversity of the human species.

Speaker 22 We're not doing genetic modification.

Speaker 3 So he says.

Speaker 9 He's English. You must trust him.

Speaker 3 To be honest.

Speaker 3 Thank you.

Speaker 3 Thank you.

Speaker 3 Well done. Well played.

Speaker 3 Can you? Is it the same thing?

Speaker 70 Some particular types of drugs are

Speaker 41 things that would manipulate your genome.

Speaker 47 That's how people

Speaker 47 start to target some diseases.

Speaker 25 This is not the class of drugs we're working on.

Speaker 3 When we think about the big ambition of solving your disease, maybe this is something that we need to be doing over time as we want to really crack the whole spectrum of disease.

Speaker 9 Is it even possible to consider that without considering the whole area itself as it all bleeds in together at some point?

Speaker 48 Yeah, I mean, we need to understand the genome and all the effect,

Speaker 58 how changing a particular particular base pair on your DNA is going to change

Speaker 25 what proteins are expressed or in what abundance and how that, all the knock-on effect on the pathways.

Speaker 32 You really want this like basically this virtual cell to be able to manipulate this cell on a computer to do experiments there.

Speaker 20 Here's what I want you to do.

Speaker 3 Talking about prioritizing?

Speaker 3 And I'm not asking much because it already happens in the animal kingdom. You know, for so long, decades, even centuries, we imagined ourselves at the top of some evolutionary

Speaker 3 triangle structure with the gay pets. Without any arrogance whatsoever.

Speaker 3 And, all right. Yet, a newt can regenerate a limb, and we can't.
Yeah. And so it seems to, and they're vertebrates.
So it seems to me there ought to be some

Speaker 3 way

Speaker 3 to extract from animals that do things that we could benefit from and then make that a priority. So people, but especially veterans who've lost limbs

Speaker 3 in conflict.

Speaker 10 Or even geckos with their sticky hands, like maybe I could be Spider-Man one day.

Speaker 3 So organize. Let's prioritize that, Chuck.

Speaker 3 We'll become superheroes.

Speaker 3 So the regeneration of limbs,

Speaker 3 that's got to be a protein thing going on in there, isn't it?

Speaker 43 Yeah, I mean, you know, all of our mechanisms are proteins.

Speaker 19 Same for nukes as well.

Speaker 25 So there is some mechanism there. I don't know what it is.

Speaker 18 Okay. Gotcha.

Speaker 3 But that would be a mechanism to emulate if you could. If you could, yeah.
And then install it into our own physiology. It's a big if.
Yeah, that's a lot. Yeah.

Speaker 10 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.

Speaker 10 And you'd be able to reconfigure them in such a way that you get the benefit of the drug without the side effects.

Speaker 18 Yeah, exactly.

Speaker 62 So you often have these first generation of drugs that do something, but they have these side effects.

Speaker 17 Then there's a big opportunity to understand better how these drugs work.

Speaker 47 Things like App Fog 3s, things like our models that understand the toxicity of drugs, can then allow us to potentially modify these to become better drugs and have less side effects, less toxic effects.

Speaker 9 Cool. Wow, that's going back through the medical catalogue.

Speaker 14 Yeah, man.

Speaker 15 Reanalyzing, which is exactly what an AI would be perfect for.

Speaker 3 Right, exactly. Yeah.

Speaker 10 Yeah, you guys are going to make a lot of money, man.

Speaker 3 I don't know how I get

Speaker 9 dollar signs.

Speaker 3 I see some

Speaker 3 benefits of this company. I'm going to invest in a company.

Speaker 10 I need to get a piece of this company.

Speaker 20 You guys are going to make, I mean, I can't even imagine the amount.

Speaker 3 The gobs and gobs of money.

Speaker 3 More money than cells in my body.

Speaker 3 This is amazing.

Speaker 3 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?

Speaker 32 Yeah, I mean, this is going to change things.

Speaker 40 I think open question how this changes machine learning.

Speaker 18 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.

Speaker 47 Because actually, some of the things that people do do today with quantum computers is simulate these small chemical systems.

Speaker 22 We actually, even in the company, we have a quantum simulation team

Speaker 44 that are not using quantum computers, but simulating...

Speaker 27 you know, the quantum effects of molecules.

Speaker 29 Now, if you had a quantum computer that could work on that scale, you could use that instead.

Speaker 25 Wow.

Speaker 3 I think of so many needs on the frontier of chemistry in modern society. 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?

Speaker 3 Is there some life form you can create that'll digest the plastic and turn it back into its original molecules?

Speaker 3 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.

Speaker 3 You're empowering the chemist in ways never previously imagined.

Speaker 28 Yes.

Speaker 39 So you can use the capability of AlphaFold to

Speaker 22 understand structure of proteins.

Speaker 34 People are using this outside of drug design.

Speaker 25 Exactly.

Speaker 3 Exactly.

Speaker 32 People are using this, for example, to create bacteria that have enzymes that could potentially digest plastics, like you're talking about.

Speaker 22 You could think about this for engineering

Speaker 70 more resilient types of crops, these sort of things.

Speaker 10 So just like AI, this is a platform upon which you can rest the the technology of any field.

Speaker 19 Yeah, I mean, that's the amazing thing about the protein folding problem.

Speaker 30 Once you start to solve that, you unlock so many new things for a whole broad spectrum of science.

Speaker 9 There's a lot of downstream benefits.

Speaker 3 Okay, last thing.

Speaker 10 Here's the last thing.

Speaker 10 How do I get a piece of this coming?

Speaker 3 How do I chuck his good dollar time?

Speaker 68 How do I get a piece of this? Last thing.

Speaker 3 Last thing. What is the worst possible outcome of your work? Ooh, what a question.

Speaker 3 What guardrails are necessary as we go forward? Because any new technology with awesome power comes awesome responsibility.

Speaker 47 Yeah, I mean, I think, you know, you have this with AI.

Speaker 25 You have this, you know, creating new biology

Speaker 19 or chemicals.

Speaker 25 You know, you just need to think about how to use this responsibly, like what you're putting out into the world openly versus what you close off for, you know, many safety reasons.

Speaker 21 So I think there's a lot of things to consider there.

Speaker 3 Because famously in one of the Jurassic Park films, they withheld lysine,

Speaker 3 amino acid, from one of the dinosaurs in case it escaped.

Speaker 3 It would die because it would need the lysine for its survival. And that was a kind of an insurance plan that put in.
But life always finds a way.

Speaker 3 There you go.

Speaker 3 Anyway, Maxwell Yoderberg. Yeah.
Thank you for joining us on Star Talk. We're going to be watching your company, and Chuck wants a piece of it.
Yes. I don't know what that means.
But anyhow,

Speaker 3 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.

Speaker 47 No, thank you so much.

Speaker 53 It's been super fun to talk.

Speaker 3 Thank you.

Speaker 3 Excellent. Excellent.
All right. I think we're done here.

Speaker 3 This has been another installment of Star Talk Special Edition, talking about AI, human physiology, and the future of drugs. Oh, yeah.
Gary, good to have you always.

Speaker 9 Pleasure, Neil. All right, Chuck.

Speaker 3 Always a pleasure. As always, this has been Star Talk, Neil DeGrasse Tyson, your personal astrophysicist.
Keep looking up.

Speaker 72 So, um, I was just parking my car and then I saw you, the Gecko, huge fan.

Speaker 49 I'm always honored to meet fans out in the wild.

Speaker 66 The honor's mine. I just love being able to file a claim in under two minutes with the Geico app.

Speaker 5 Well, the Geico app is top-notch.

Speaker 72 I know you get asked this all the time, but could you sign it?

Speaker 3 Sign what? The app? Yeah, sure.

Speaker 72 Oh, that means so much. Oh, it rubbed off the screen when I touched it.
Could you sign it again?

Speaker 3 Anything to help, I suppose.

Speaker 7 You're the best.

Speaker 3 Get more than just savings.

Speaker 11 Get more with Geico.

Speaker 67 Honey, do not make plans Saturday, September 13th, okay?

Speaker 7 Why, what's happening?

Speaker 67 The Walmart wellness event. Flu shots, health screenings, free samples from those brands you like.

Speaker 3 All that at Walmart.

Speaker 51 We can just walk right in. No appointment needed.

Speaker 16 Who knew we could cover our health and wellness needs at Walmart?

Speaker 71 Check the calendar Saturday, September 13th.

Speaker 67 Walmart Wellness Event.

Speaker 3 You knew. I knew.

Speaker 66 Check in on your health at the same place you already shop. Visit Walmart Saturday, September 13th for our semi-annual wellness event.
Flu shots subject to availability and applicable state law.

Speaker 66 Age restrictions apply. Free samples while supplies last.