How AI Is Cracking The Biology Code

Primary Topic

This episode explores the revolutionary impact of AI on protein science, particularly how it's advancing our understanding of protein structures and functions.

Episode Summary

In this engaging episode of "Short Wave," hosts Emily Kwong and Burleigh McCoy delve into the profound influence of artificial intelligence on protein science. They discuss how AI has resolved longstanding challenges in determining protein structures, a problem that has perplexed scientists for over six decades. Using tools like Google DeepMind's AlphaFold, scientists can now predict protein shapes accurately, a breakthrough that significantly accelerates biological research and potential applications in medicine and environmental science. The episode also highlights how AI not only aids in understanding existing proteins but also in designing new ones with specific functions to tackle contemporary issues like disease and climate change.

Main Takeaways

  1. AI has transformed the field of protein science by predicting protein structures with high accuracy.
  2. This advancement allows scientists to bypass lengthy and complex experiments traditionally needed to determine protein shapes.
  3. Newly designed AI-powered models can now also predict the structures of other biomolecules, enhancing our understanding of biological interactions.
  4. The episode discusses the practical applications of these technologies in medical research and environmental sustainability.
  5. AI's role in protein design is paving the way for innovative solutions to modern challenges.

Episode Chapters

1: Introduction to AI in Protein Science

Emily Kwong and Burleigh McCoy introduce the topic of AI's role in revolutionizing protein science. They discuss the background and significance of understanding protein structures.

  • Burleigh McCoy: "AI has shaken up the field of protein science, fundamentally changing how we understand the building blocks of life."

2: The Impact of AlphaFold

The hosts discuss AlphaFold's breakthrough in the protein folding problem and its implications for scientific research.

  • Burleigh McCoy: "AlphaFold blew the competition away with its accuracy in predicting protein structures."

3: Designing New Proteins

Exploration of how AI assists scientists in designing new proteins to address specific problems like diseases and environmental issues.

  • David Baker: "We can now create really new proteins that solve these problems that weren't really relevant during evolution."

Actionable Advice

  1. Stay informed about AI developments in science to leverage these technologies effectively.
  2. Explore AI tools like AlphaFold for research or educational purposes to enhance understanding of complex biological structures.
  3. Consider the ethical implications of designing new biological molecules and their long-term impacts.
  4. Support open-access AI tools to foster collaboration and innovation in the scientific community.
  5. Engage with scientific communities to discuss and address the challenges posed by AI in biology.

About This Episode

As artificial intelligence seeps into some realms of society, it rushes into others. One area it's making a big difference is protein science — as in the "building blocks of life," proteins! Producer Berly McCoy talks to host Emily Kwong about the newest advance in protein science: AlphaFold3, an AI program from Google DeepMind. Plus, they talk about the wider field of AI protein science and why researchers hope it will solve a range of problems, from disease to the climate.

People

Emily Kwong, Burleigh McCoy, Julian Bergeron, David Baker, Pushmeet Kohli

Companies

Google DeepMind, King's College London, University of Washington

Books

None

Guest Name(s):

David Baker

Content Warnings:

None

Transcript

NPR Sponsor
This message comes from NPR sponsor the Schizophrenia and Psychosis Action alliance, shattering barriers to treatment, survival and recovery. People with schizophrenia can recover and thrive more@wecanthrive.org. Dot this message comes from NPR sponsor CFP certified financial planner professionals committed to acting in their clients best interests. Learn more@letsmakeaplan.org. Dot this message comes from NPR sponsor train a high performing business takes a high performing building. Reach organizational goals while enhancing systems and reducing emissions with trane energy services. Explore their consultative approach@trane.com.

Emily Kwong
Energyservices, you're listening to short wave from NPR.

Hey, hey, short waivers. Emily Kwong here with producer Burleigh McCoy. What's up, burly?

Burleigh McCoy
Hey, Emily. Hello.

Emily Kwong
What do you have for us today?

Burleigh McCoy
Okay, so, Emily, today I want to dig into how AI has shaken up the field of protein science, as in the fundamental building blocks of life. Proteins.

Emily Kwong
I've heard of them, yeah. I mean, this is like what you studied back in your scientist days. Yes, yes.

Burleigh McCoy
I love proteins.

Emily Kwong
Oh, we love that you love them. How has AI moved the needle in this field, though?

Burleigh McCoy
Well, scientists have used it to dig into a problem that protein scientists have struggled with for more than 60 years. And that is, what do these building blocks, of which there are millions, look like?

Emily Kwong
Like their shape. Like their shape, yeah, exactly. And why is that so important?

Burleigh McCoy
Well, the ability of a protein to do its specific job so, like, carry oxygen through your body or turn light into sugar, that relies wholly on its unique, complicated shape. So to understand how it works, you need to know its shape.

Emily Kwong
But why cant scientists just run an experiment to determine the shape they can for some proteins?

Burleigh McCoy
But those experiments can take years and years. And, Emily, that's because a scientist essentially needs to take the equivalent of a molecular photo of the protein to map its complicated shape. But getting the protein to cooperate, to get that photo, so, like, to hold still, for example, without falling apart, that can be super tricky. And it could take a grad student's entire PhD program to figure out a single protein.

And other proteins were just abandoned because they would never cooperate.

Emily Kwong
Proteins sound difficult, honestly. So the challenge is, how do you figure out a protein's shape without running these super tedious experiments? Is this where AI comes in? Yeah.

Burleigh McCoy
And to give you a sense of kind of how AI has changed the protein game, there's this protein competition that scientists run every other year.

Emily Kwong
Get out. A protein competition? Okay. Yeah.

Burleigh McCoy
And they've run it for the past 30 years, where groups will basically compete on who can accurately guess the most protein. Protein shapes. It's like nerd central for sure.

Emily Kwong
We love.

Burleigh McCoy
And for most of that 30 year history, participants have really only made incremental progress. But in 2020, Google DeepMind used alphafold two, that's its AI protein prediction model. And Emily Alphafold two blew the other competition out of the water completely.

Emily Kwong
Wow. Okay.

Burleigh McCoy
Game changer.

And now the Google DeepMind team has taken this AI tool to the next level by expanding it beyond proteins.

Emily Kwong
So today on the show, how scientists have taken a huge step to understanding the building blocks of life using AI.

Burleigh McCoy
Plus, how other researchers are using the tech to design brand new proteins, ones never before seen in nature, and how.

Emily Kwong
AI could help us solve the biggest problems we face today, from disease to climate.

You are listening to short wave, the science podcast from NPR.

NPR Sponsor
This message comes from NPR sponsor Dana Farber Cancer Institute breast cancer cells multiply faster because of cdk 46 proteins. But what if blocking those proteins and stopping runaway cell division was possible? Dana Farber scientists laid the foundation for cdk 46 inhibitors, new drugs that are increasing the survival rate for many advanced breast cancers. Dana Farber's momentum of discovery keeps finding new ways to outmaneuver cancer more@danafarber.org.

Everywhere Support for NPR
Everywhere support for NPR and the following message come from the American Cancer Society. Doctor Alpa Patel leads a team that researches cancer risk factors, and she shares how her team makes an impact.

Alpa Patel
We always do what we like to think of as actionable science. So the work that we do makes its way to things like nutrition and physical activity. Guidelinesforcancer.org, where millions of people come each year to learn about how they can better prevent cancer.

Everywhere Support for NPR
To learn more, go to cancer.org dot.

Emily Kwong
Ok BUrLeY so scientists, it seems, have been trying to figure out the complicated shapes of proteins for decades to better understand how they work. Why has this been such a complicated thing to figure out?

Burleigh McCoy
Well, the short answer, Emily, is that there are so many theoretical ways a single protein could fold that it's a big problem to solve. So if you unfolded a protein, it would kind of look like a bunch of beads on a long string.

Those beads are little molecules called amino acids.

Emily Kwong
Oh, I remember this from biology. There are like 20 types of amino acids. Yep. Each one is a little different, right?

Burleigh McCoy
So each one has a slightly different shape. And that kind of dictates how that part of the string can be folded up. Because proteins often have 100 or more amino acids, you can see how imagining all the ways it could fold would get complicated.

Emily Kwong
Yeah, it just sounds like thousands of different shapes or what, hundreds of thousands of different shapes?

Burleigh McCoy
Okay, try billions of trillions, Emily. Like, there are theoretically more ways for one single protein to fold than there are stars in our night sky.

Emily Kwong
This sounds like a glorious nightmare, right? I'm so curious. Okay, so you said that AI has helped us make some leaps and bounds towards a solution. How does this technology work?

Burleigh McCoy
So, this alphafold model is a type of AI called a deep learning program, which is this huge network of data processing points called nodes. And the purpose of this network is to learn and then make predictions based on what it's learned. In alphafold's case and other models like it, it learns about proteins from a huge collection of protein structures that scientists have been building on for decades from their experimental data.

Emily Kwong
Okay, so the idea is that after these models use all of that carefully gathered experimental data to learn, they can then predict the shapes of proteins they do not know yet.

Burleigh McCoy
Exactly.

Emily Kwong
Okay. And going back to the protein competition in 2020, how did alphafold blow away the competition?

Burleigh McCoy
So they essentially changed the whole architecture of their model. They had been using AI before. But remember the beads on a string analogy? If amino acids are the beads, even if one bead is far from another on the string, when it all folds up, they could be right next to each other. So with alphafold two, the model looked at distances between all the different amino acids and previous knowledge from solved protein structures.

Emily Kwong
Awesome.

Burleigh McCoy
And the accuracy and speed of the predictions went way up.

Emily Kwong
Okay, I'm assuming that made a huge difference for scientists everywhere studying proteins.

Burleigh McCoy
Totally.

Julian Bergeron, a structural biologist at King's College London, is one of them. He studies the tail like appendage that propels bacteria. So it's called a flagellum, and it's pretty complicated.

Julian Bergeron
It's this huge assembly, so it's longer than the bacterial cell itself. It consists of 20 to 25 different proteins, but many of them have hundreds of thousands of copies of that protein.

Burleigh McCoy
And these huge propeller machines are what give some bacteria the ability to make you sick or build plaque on your teeth. So Julian's lab is trying to figure out how these giant machines work, what their pieces look like, and how it all fits together. And so when the alphafold two model came out, he just had to try it.

Julian Bergeron
And I input a sequence, and then a few hours later, I had the model, and I was like, oh, my God, this just did it. And we'd been struggling with that problem for, you know, months, if not years.

And all of a sudden, I messaged my lab and I said, we model everything, and we've had dozens of projects that immediately progressed thanks to this.

Emily Kwong
Okay, so it sounds like overnight Alphafold changed the trajectory of his lab.

Burleigh McCoy
Yeah, but how did he know that.

Emily Kwong
Using alphafold two would actually work?

Burleigh McCoy
Yeah, so the accuracy is super important, right? Especially when you're basing all of your other experiments on the results.

And it's important to note that, like other AI, alphafold two isn't right 100% of the time. So you can't just take the results at face value.

But unlike some other AI, included in the results is a score basically telling you how accurate each part of the structure is.

Emily Kwong
Okay. And are others in the field using alphafold, too? Yeah.

Burleigh McCoy
So this is something that actually sets alphafold apart from other protein prediction AI models. It's extremely user friendly. So essentially anyone who works on a protein, or even just has a sequence of a protein, can plug it in and get results. I talked to pushmit Kohli, vice president of research at Google DeepMind, and he told me why it was important for them to make this tool open access.

Pushmeet Kohli
The mission statement that we have for the science program at Google DeepMind is to leverage AI to accelerate and advance science.

Emily Kwong
Okay, so I am scrolling through the alphafold website and I am seeing scientists using this model for all kinds of things. They're working on malaria and cancer research, drug discovery, plastic eating enzymes.

Burleigh McCoy
And last week, DeepMind released a new version, alphafold three, which can predict the 3d structure of proteins and other kinds of biomolecules that they attach to.

Emily Kwong
Why are those other biomolecules important? Yes.

Burleigh McCoy
So I know we talked about how much proteins are super important. I love them, but I have to admit, they rarely work alone.

And if we actually want to know how biology works as a whole, we need to understand how proteins work with their partner molecules.

Pushmeet Kohli
So it really gives you a more detailed and more accurate picture of what is happening inside the body, where proteins are just not just sort of existing in isolation, they are interacting in a very rich biological space, or soup of rna and DNA and small molecules, and it really sheds light into those rich interactions.

Burleigh McCoy
Now, previous versions of these protein prediction softwares would model where each amino acid was located. But in this new version, alphafold three, it maps things on an even smaller level. So it models where individual atoms are.

Emily Kwong
Wow.

Burleigh McCoy
So they can predict the structure of multiprotein complexes like the bacterial flagellum or something like proteins in the blood, which attach to iron atoms.

Emily Kwong
That is powerful. Okay, what are the limits to alphafold predictions?

Burleigh McCoy
Yeah, there are definitely limitations. Pushmete says that the model works best when a protein has a single defined structure, but some proteins have more than one shape, or they have sections that are kind of flimsy. Think cooked versus uncooked spaghetti.

Emily Kwong
Okay, so the model sounds like some trouble with prediction in some cases, and the results show that. Yeah.

Burleigh McCoy
So the idea is that these results would say, hey, I'm not so confident in this area of the protein, just so, like, users know.

Emily Kwong
Oh.

Burleigh McCoy
And another limitation is that the prediction ability depends on the amount of what's called training data available. So I mentioned that there's a lot of training data for proteins, but some.

Pushmeet Kohli
Categories have much less training data available.

For example, there's much less structural data available for rna's.

Emily Kwong
Okay, so the prediction is only as good as the data. Exactly, exactly.

Burleigh McCoy
But Emily. But Burleigh, there's another way scientists can use AI in the protein world.

Emily Kwong
Okay, what's that?

Burleigh McCoy
To generate brand new proteins, ones like, not found in nature anywhere.

Emily Kwong
Huh?

David Baker
Humans face new problems today, and, you know, we live longer for polluting and heating up the planet. And it's reasonable to think that if with another more millions of years of evolution, that some of these problems would be, would be solved. But we don't want to wait that long.

So the idea is that we can now create really new proteins that solve these problems that weren't really relevant during evolution to make the world a better place.

Burleigh McCoy
So this is David Baker. He's a biochemist and the director of the Institute for Protein Design at the University of Washington. And he's been working on proteins for years. He actually developed one of the earlier protein prediction models. His lab has a similar AI program to alphafold three. It's called Rosettafold all atom. But his big focus is designing these brand new proteins.

Emily Kwong
This sounds so futuristic, right? Like, what kind of new proteins?

Burleigh McCoy
So far, they've done things like design new protein antibodies, which are important for fighting infections, in this case, to fight influenza.

They've made something called a switch protein that could be used as an environmental sensor, and they've also made proteins that could help store carbon, which is a huge hurdle for fighting climate change.

David Baker
I think really, across medicine, sustainability, technology, I think there's huge opportunities to transform the current ways we do things with protein design.

Burleigh McCoy
So these predictive and generative AI models have fundamentally changed the protein science landscape. And again, there's definitely room for improving the prediction power, but with what the field has shifted to like in terms of prediction accuracy and design potential, I mean, it's really gotten this retired protein fanatic, like, missing my science days.

Emily Kwong
Burly, thank you so much for bringing us this big, big story about the little things in life.

Burleigh McCoy
Thanks, Emily.

Emily Kwong
This episode was produced by Rachel Carlson. It was edited by our showrunner Rebecca Ramirez. Burley checked the facts. Ko Takosugi Chernovan was the audio engineer.

Special thanks to Jeff Brumfield. Beth Donovan is our senior director and Colin Campbell is our senior vice president of podcasting strategy. I'm Emily Kwong. Thank you for listening to short wave from NPR.

Everywhere Support for NPR
This message comes from NPR sponsor, a new perspective on performance apparel, clothing designed with premium fabrics built to move in styled for life. For 20% off your first purchase, go to viori.com npr.

This message comes from NPR sponsor Rosetta Stone, an expert in language learning for 30 years. Right now, NPR listeners can get Rosetta stones lifetime membership to 25 different languages for 50% off. Learn more@rosettastone.com npr.

This is my voice
This is my voice. It can tell you a lot about me, and I'm not changing it for anyone. In NPR's Black Truths, you'll find a collection of NPR episodes centered on black experiences. Search NPR black stories, black truths wherever.

Julian Bergeron
You get your podcast.