Alphafold 3.0: the AI protein predictor gets an upgrade

This episode delves into the advancements in AI-driven protein prediction technology with the release of Alphafold 3.0 by DeepMind.

1. Alphafold 3.0 has broadened its scope to predict how proteins interact with other cellular components like DNA and RNA.
2. The upgrade represents a significant improvement in modeling complex protein behaviors, crucial for understanding cellular functions and disease mechanisms.
3. A new nuclear clock concept, potentially more precise than atomic clocks, was discussed, highlighting its use in testing fundamental physical laws.
4. The episode provides insights into the challenges and potential of using Alphafold 3.0 in drug discovery and other scientific fields.
5. Alphafold's technology is a prime example of how AI can drive forward scientific discovery and application.

1. Introduction to Alphafold 3.0

The episode begins with an overview of Alphafold's impact on biological sciences and introduces its latest upgrade. Nick Bertra Chow: "Alphafold and its successor, Alphafold 2, have been game changers in biology."

2. The Science of Nuclear Clocks

Discussion on advancements in timekeeping technology that could lead to the development of nuclear clocks. Lizzie Gibney: "A nuclear clock... uses the energy states in the nucleus itself."

3. Deep Dive into Alphafold 3.0

Detailed exploration of Alphafold 3.0's new capabilities, emphasizing its predictive precision and integration with other molecular players. Nick Bertra Chow: "Alphafold three... predicts proteins alongside all the other players of the cellular ecosystem."

4. Implications for Science and Medicine

Analyzes how Alphafold 3.0 could influence future scientific research and medical advancements. Nick Bertra Chow: "It's really kind of embedding proteins in their ecosystem, in their environment."

1. Explore AI tools for research: Researchers should consider integrating AI tools like Alphafold 3.0 into their studies for enhanced predictive capabilities.
2. Stay updated with AI advancements: Keeping abreast of the latest developments can provide early advantages in applying new technologies.
3. Collaborate across disciplines: Cross-disciplinary collaboration can maximize the benefits of complex tools like Alphafold 3.0.
4. Engage with technology developers: Direct interaction with AI developers can tailor tools to specific research needs.
5. Advocate for open scientific resources: Supporting initiatives for open-access tools can democratize advanced technologies for broader use.

Nuclear clocks — based on tiny shifts in energy in an atomic nucleus — could be even more accurate and stable than other advanced timekeeping systems, but have been difficult to make. Now, a team of researchers have made a breakthrough in the development of these clocks, identifying the correct frequency of laser light required to make this energy transition happen. Ultimately it’s hoped that physicists could use nuclear clocks to probe the fundamental forces that hold atoms together.

People

Nick Bertra Chow, Benjamin Thompson, Lizzie Gibney, Ewan Calloway

Companies

DeepMind

Content Warnings:

None

Nature Podcast
The Nature podcast is supported by Nature Plus, a flexible monthly subscription that grants immediate online access to the science journal Nature and over 50 other journals from the Nature portfolio.

More information at go dot nature.com. Plus, life is full of what ifs.

UnitedHealthcare
Some awesome like what if AI could fold your laundry? And some, well, less awesome, like what if you have unexpected medical costs? UnitedHealthcare can help get you covered with health protector guard fixed indemnity insurance plans. They supplement your primary plan to help you manage out of pocket costs, no deductibles, no enrollment periods, and especially no more what ifs. Visit, uh, one.com to find the health protector guard plan for you.

Nick Bertra Chow
Like it sounds so simple. They had no idea, but now the data split. I find this not only refreshing, but.

Benjamin Thompson
At some level, astounding.

Nick Bertra Chow
Nature.

Benjamin Thompson
Welcome back to the Nature podcast.

This week, a clock that could probe.

Nick Bertra Chow
The laws of physics and alphafold gets an upgrade. I'm Nick Bertra Chow.

Benjamin Thompson
And I'm Benjamin Thompson.

As we've heard in recent podcasts, timekeeping is super important to science, and the precision of clocks has gotten pretty good, to put it mildly, with the development of optical clocks, which keep time so well they only lose a second every 30 billion years or so. But scientists want to do better than that. And a paper came out last week which describes a big step towards making a new type of clock that shows potential to be even more precise, but perhaps more excitingly, could allow researchers to even test the very laws of physics. Our regular clock correspondent, Lizzie Gibney has been reporting on the story, and as sure as tick follows tock, she joins me now. Lizzie, hi.

Lizzie Gibney
Hi, Ben.

Benjamin Thompson
Now, Lizzie, the most precise clocks are all atomic clocks, but researchers have wanted to make something else, a nuclear clock. Now, they kind of sound similar, but they're actually quite different things, right?

Lizzie Gibney
Yeah, there's a quite similar fundamental principle there. But in an atomic clock, what we're talking about is pumping an electron up an energy state. You've got electrons whizzing around an atom. You pump that up or down an energy state. You might remember these shells from GCSE or high school level chemistry. And when you do that, that's the same energy difference. And that means you've got a kind of fundamental number that will apply to any atom like that in the world, in the universe. That's the kind of thing that makes for a good clock. We use as the actual ticking, the frequency of the light that you need to shift that electron up or down. So the frequency of the light is that tick. Now, what a nuclear clock is, is not looking at the electrons in the shells around an atom, it's actually the nucleus itself. So the neutrons, the protons that are inside the nucleus of the atom, and you can imagine they're much more strongly bound. And you've got this teeny, tiny, dense little hub, rather than these big, whizzing round electrons. We're using the energy states in that instead. So it's the same principle in that you're going to have kind of low energy state and then one slightly higher energy state, and it's the frequency of light that it takes to do that, which becomes your clock.

Benjamin Thompson
Now, these have been quite hard to make, though, as I understand, like, in principle, that was a fantastic idea. But the actual gap between in principle and reality has proven quite difficult to get across.

Lizzie Gibney
That's right. So there are two big reasons why it's tricky. One is you need to find a nucleus where this actually applies. So although we have these energy states that you can raise nucleus to, most of them are going to be a huge energy difference. What we want to be able to do to nudge it with a laser that you'd have in a lab that we can practically use to make a clock. Right. So the most nuclei is going to be really, really big energy difference. There's one, which is thorium 229, which is an isomer, the type of the radioactive metal thorium, where it's a real anomaly, and it has a teeny, teeny tiny transition. This energy to go from its lowest state to its first energy state is very, very small. So it's just about accessible with a laser. First of all, we found our nucleus, but then the second thing you need to do is know exactly what energy to trigger it at. So the way in which these clocks work is you fire a laser at it, and when you get it right, the photons of light get absorbed by the nucleus and it goes up to the state and then it releases them and emits them when it falls back down again. So you need to fire the right energy at it. And actually, it's really, really hard to know exactly what frequency of light you need. Theory actually doesn't help us here, because the most accurate they can figure out using theory making calculations is many, many times greater than the actual number that we need. So it gives us a ballpark much bigger than is useful. So instead, we have to rely on experiment.

So it's been looking for a needle in a haystack.

Benjamin Thompson
So we know that thorium 229 doesn't need much energy to nudge it up to this next state. But exactly what that frequency is, then there's quite a wide spectrum, I suppose, and that's been slowly narrowed down, but now the researchers are really trying to pinpoint the exact one, then that is required.

Lizzie Gibney
Exactly. There have been lots of different methods of trying to figure out exactly what this frequency is, and it's been decades of work, lots of different groups, they've been getting closer and closer, but this is really a milestone paper because they've narrowed it down. The precision is about 800 times greater than next best effort. And it was a little bit in the end of just sweeping a laser up and down this region that we know this frequency is hiding in until they found it, and they found it by this crystal, which had the thorium studied in it, until that crystal glowed. It fluoresced when the thorium was nudged into this high energy level and then released the photons again.

Benjamin Thompson
Right. So a little bit like tuning on FM radio for the younger listeners. And so they found it then at the right frequency. And what does that mean then? Because this actually isn't a clock itself, this is just a step towards it.

Lizzie Gibney
Right, exactly. They found their ticking mechanism, the frequency of that light that becomes your tick. So now they've got that, they've got the basis of the clock. What they need is a few things. They need to check that the system they've got it made in doesn't affect that frequency somehow, the fact that they've done it in this crystal, that isn't messing with the frequency somehow. And they also need to narrow down the number of frequencies that are contained within the laser that they're using to do this, nudging up an energy state. It's still quite broadband at the moment. This was one, you know, the laser was made by the lab themselves. You know, you can't buy a laser like this off the shelf at the moment. Essentially, they're sending in loads of photons that are doing absolutely nothing because some of them are hitting this exact frequency, but many of them are. So that laser needs to get much, much, much better in resolution. Now, that's going to be a lot of work, but it's also the kind of thing that people I spoke to for the story said is doable. Like, there's not a huge amount of doubt that we should be able to make that laser, which means this kind of clock should be possible. We're just not there yet.

Benjamin Thompson
Let's sort of fast forward to when someone does crack this. Researchers have wanted to make one of these nuclear clocks for quite a while. Why? Like, how much better are these than the sort of the optical clocks which we've discussed on the show fairly recently?

Lizzie Gibney
So there are a few advantages. You could get greater precision, because, as we discussed with optical clocks there, you're using optical visible light. Here it's uv. That's a little bit higher frequency. That's kind of getting more ticks in your more finely slicing time, so you can increase the precision a bit. Optical clocks are getting better all the time as well. So that's not the main selling point. I would say the best part about this clock is that it's really, really stable. It's really robust because the ticking and mechanism come from within the nucleus, which is this really tightly bound little nugget inside the atom. It's much harder for fluctuations in electric or magnetic fields or temperature or anything like that to affect your clock. And that can happen when what you're looking at is these electron levels as you are in an optical clock. So that fundamental difference makes it more stable. So your clock is likely to keep time better over time. And then also this system that it's in this solid state, the fact that it's inside a crystal maybe could mean it's more portable, maybe. Again, that's more amenable to use than one of these massive vacuum systems that you use in the lab for an atomic clock. And there's one more thing that's really, really cool that this enables. So the nuclear clock, this frequency that we need to nudge the nucleus up, that energy depends on what's going on within the nucleus. So it depends on the strength of the fundamental forces, the strong nuclear force, the electromagnetic force.

And so we can actually use this ticking of the clock to figure out if anything strange is going on at very, very, very fine level within physics. So if, for instance, some kinds of dark matter are hypothesized to affect these fundamental constants, the strength of the strong nuclear force, for instance, then we'd be able to see that that would be revealed in a slight wavering in the ticking of this clock. So that has got physicists quite excited.

Benjamin Thompson
So it's only in the nucleus, then, that you can see these potential slight changes between how neutrons and protons and so forth are interacting. And this wouldn't work just using electrons, as are in current atomic clocks. Right?

Lizzie Gibney
So electrons have some sensitivity to the strength of these forces. But this is about 10,000 times more sensitive than you could get with an atomic clock, which you could get from the dynamics of what happens to electrons? The nucleus extends because we're talking about these more massive and more strongly bound entities. They are much more affected by any changes in the strength of these forces. So it gets revealed. It gets amplified in a nucleus.

Benjamin Thompson
And you said researchers are kind of excited about this. What have they been telling you?

Lizzie Gibney
Well, even based on this paper, which, as we said, was, you know, a very broad bandwidth of laser, and they found this frequency, but it's very preliminary, they're already using that to put some limits on the kinds of dark matter that can be out there. So different kinds of dark matter would affect these fundamental constants in different ways. And so there's going to be a lot of different studies and testing a lot of different hypotheses about dark matter just through using these plots. So people are quite excited. And actually, if I can quote also one of my colleagues. So when we were talking about this story, David Castelvecchi, another physics reporter here, said something nice, which I wish one of our interviewees had said, that whenever we use a new system like this, here we are tapping right into the nucleus of an atom, that we're going to open ourselves up to lots more scientific discoveries. This is really finely tuned, peering into the nucleus in a very, very exact way. And we don't really know yet maybe what all of the uses are going to be, but it's going to be, I think, really exciting.

Benjamin Thompson
Well, we'll link to your story in the show notes, but until next time, Lizzie, thank you so much for joining us.

Lizzie Gibney
Thank you. Maybe more clocks again? We'll see.

Nick Bertra Chow
Coming up, the powerful protein prediction tool alphafold can now accurately model complex combinations of proteins and other molecules. Right now, though, it's the research highlights with Dan Fox.

Dan Fox
If you look around our plant covered planet, you may think that green is a good indicator for life.

And indeed, visible light colours are one of the variables used by researchers when searching for life on other planets. But not all life is green. And now a new guidebook will help astronomers look for purple, brown, orange and yellow hues that could be reflected from worlds dominated by certain kinds of bacteria.

Plants are the dominant lifeform on Earth, and the chlorophyll they use to make food absorbs the blue and red wavelengths from sunlight and reflects back green. But the color of life could be different on other planets.

Even on Earth, there are purple bacteria found from shallow waters to deep sea hydrothermal vents.

These actually come in a range of colors because they rely on other compounds that absorb red and infrared light to produce energy.

Microorganisms like these could thrive on worlds orbiting stars redder than our own sun.

And so a team of astrobiologists have analyzed the light reflected by various kinds of purple bacteria, recording the spectrum for each species and modelling what spectra from exoplanets covered by such bacteria would look like.

From this, they created a database of spectra, which will help astronomers to broaden their search for life on newly discovered exoplanets.

You can read that in full in monthly notices of the royal Astronomical Society.

A fluid that retains its magnetic structure even after an external magnetic field is removed could form the basis of new liquid bio electronics.

A ferrofluid is a substance consisting of nanometer sized magnetic particles dispersed throughout a fluid.

In the presence of an external magnetic field, the particles align and the ferrofluid exhibits useful magnetic properties. But if you turn off the external field, the particles become randomly oriented and the properties are lost.

Now, researchers have produced a new ferrofluid like material that lacks this drawback. The substance comprises magnetic nanoparticles suspended in a viscous fluid. When exposed to an external magnetic field, these particles self assemble into an intricate 3d network that remains intact even after the field is removed. The team used their substance to make liquid bio electronics that could be injected into the body and convert biomechanical motion into detectable electrical signals. These kinds of devices could be used for self powered and wireless monitoring of the cardiovascular system.

If you are magnetically attracted to that research, you can read it in nature materials.

Nick Bertra Chow
Alphafold and its successor, Alphafold two, have been game changers in biology, as the AI's have made it easier than ever to predict the structures of proteins, molecules that make up so much of life.

And now there's a new version, Alphafold three, which promises even greater predictive abilities.

To dive into the details of this upgrade, I'm joined by Ewan Calloway, who's been writing about alphafold, well, basically since the beginning, for years now, and has been working on a new story about the latest iteration, Alphafold three. Ewan. Hi. How's it going?

Nick Bertra Chow
It's good. I like to see alphafold three as the return of the Jedi of alphafold kind of completing the trilogy, or the Godfather three.

I don't know which was deemed better.

Nick Bertra Chow
Hopefully it's not godfather three because that one was not the best one, in my opinion. But let's start off by talking about what this version can do. So what is it that alphafold three promises that maybe the other versions lacked?

Nick Bertra Chow
Yeah. So the real revolution was alphafold two, mark one. It did a lot, and it won this competition of protein prediction. But alphafold two was the game changer, and what it did was you'd input a sequence of amino acids, acids, which are the building blocks of proteins, and it would give you a pretty darn good prediction of what that protein looked like in three dimension. The only problem, I wouldn't say a problem, was that it just predicted protein structures. It didn't predict proteins alongside all the other players of the cellular ecosystem. That was just not part of alphafold two's language, part of its abilities. And so alphafold three, this latest update, is exactly that. It brings in the rest of the ecosystem. All these other players, you know, predicts proteins alongside of them.

Nick Bertra Chow
So when you say, like these other players, this is things like DNA, rna.

Nick Bertra Chow
Yeah, all of these things. So say you've got a protein that's involved in copying our DNA, which is something that's one of the most basic features of life. Well, that that protein needs to attach to DNA, and alphafold three can do that. So you've got proteins that are helping to turn, you know, DNA into proteins by an rna intermediate, you got some proteins that recognize rna. Well, fold three can do that. There are lots of modifications. You know, you plunk on something called a phosphate group. It's called phosphorylation, and that activates many proteins, and they propagate signals throughout cells. And so it's really kind of embedding proteins in their ecosystem, in their environment, you know, what they do with all these, like, complex roles. You really need to know about these other players.

Nick Bertra Chow
And, I mean, given how many different kinds of molecules and how many different proteins there are, like, it seems like this would be a huge challenge to actually bring these things together in all the possible iterations they could be. How have they managed it?

Nick Bertra Chow
I mean, it's a very sophisticated neural network, but I think the principle that I understood from talking with John Jumper, who led the development of alpha one three, was that all this information, all these modifications, all these accessory molecules, they're experimental examples, real world examples of them with their protein partners sitting in this database called the protein data bank that alphafold one two, and now three was trained on. And so you've got lots of examples, lots of good data for a machine learning model and artificial intelligence to learn from. And, you know, with a bunch of bells and whistles that I won't bore you with, like transformer and diffusion and embeddings, they've, you know, created a model that can represent all this additional data, not just the protein sequence, but all these other atoms that are sitting there in this database.

Nick Bertra Chow
And so this has been developed, as you said, by Google, DeepMind. Have other researchers got to try out this new tool?

Nick Bertra Chow
Yeah, it seems like a fair number of researchers have got a little sneak preview of it. I actually spoke with somebody this morning who didn't get an official sneak preview, but reviewed the paper for me, and he was able to get onto the server. And people like it. They say it's really fast, it's really convenient. It lowers the barrier to entry, I think, compared to alpha fault two, which to use it, you almost sometimes had to download your own version and run it or run it on a server. This is, as far as I can tell, a web form where you input your sequence, pick some boxes of the sorts of modifications that you want to see, and bada bing, bada boom, ten minutes later, you've got a prediction that can help you do some experiments. So the limited feedback I've gotten so far is that it's really helpful.

Nick Bertra Chow
What are researchers hoping that this tool could be used for?

Nick Bertra Chow
I think it's part of maybe getting a better approximation of how your protein of interest is doing its job, how it's playing its part in the cellular ballet, whatever we want to call it. So the one example that I talked with, with the scientist who used it, he's a scientist at the Crick Institute across from nature hq in London. He studies DNA replication, and a lot of the proteins that his lab is interested in directly bind DNA, and there'll be portions of these proteins that bind DNA. And so with the predictions that he got from alphafold three, his lab started making mutations to their protein to try and alter how it bound DNA, and found that some of these really panned out, that the predictions were kind of on the spot. So it gives him some insight into how this protein hes interested in does its job.

Nick Bertra Chow
So one thing about alfolds previous iterations that researchers were a bit skeptical of was his ability to help with drug discovery. Do you think this new tool will help bridge that gap?

Nick Bertra Chow
Alphafold has been revolutionary, but I think with drug discovery, it's been maybe a mixed bag. There have been a lot of skepticism whether it's really a game changer. There have been some studies suggesting that its structures can be useful for drug discovery. But drug discovery is a complex process with lots and lots of steps. And one, AI is not going to disrupt this alphafold. Three, I think I talk with people because it can model, because it predict potentially how other molecules interact with proteins it could potentially be very useful for drug discovery. And in fact, Google DeepMind has a spinoff called isomorphic labs and they're using alphafold three to do just that. The hitch is that the way that Google DeepMind is making alphafold three accessible to the scientific community, they're not going to allow researchers to straightforwardly look for how their protein of choice binds to a new drug. That's just not possible for people to do. And that was this decision that Google DeepMind made. They put a lot of resources into developing it and they're going to reserve the commercial pursuits for their partners. But I did speak with some scientists who said that the paper that they published in Nature releases enough information about how this model was developed that within a year or so, other researchers can develop open source versions that you can plug any potential drug into it. So it could potentially have a really significant impact on drug discovery, not just for Google and its partners, but for the field as a whole.

I think that remains to be seen, but thats a possibility.

Nick Bertra Chow
Well, Ewan, thank you so much for joining me.

Nick Bertra Chow
Yeah, thank you.

Nick Bertra Chow
And listeners. For more on that, check out the show notes for a link to Ewan's news article.

Benjamin Thompson
That's all for this week. As always, you can keep in touch with us on x. We're at Nature podcast or send an email to podcastature.com. I'm Benjamin Thompson.

Nick Bertra Chow
And I'm Nick Perch Howe.

Nature Podcast
Deep dive into the world of science with nature.

From the vastness of the distant star systems to the intricacies of infectious diseases due to climate change, weve got you covered. Enjoy access to over 55 cutting edge journals, breaking scientific news, and over a thousand new articles every month. Whether youre a seasoned researcher or just curious, NaturePlus simplifies complex studies. Plus its all available right at your fingertips on nature.com.

NaturePlus, the key to unlocking the worlds most significant scientific advances. Subscribe today at Go dot nature.com.

UnitedHealthcare
Plus, we all have smartphones and we all know they're pretty amazing, but they can also be amazingly distracting, especially when we're around other people. So us cellular wants us to reset our relationship with our phones by putting down our phones for five. That's right. A company that sells phones wants us to put down our phones and see what we find. Learn more@uscellular.com builtforus that's uscellular.com builtforus.