The Veritasium video discusses a groundbreaking advancement in biology: solving the protein folding problem using AI. The AlphaFold project by DeepMind has dramatically accelerated the understanding of protein structures which has significant implications for solving global challenges, such as developing treatments for diseases and environmental issues. By leveraging AI, scientists have been able to predict the structure of nearly every protein known, enabling researchers to focus on practical applications, from drug discovery to new material creation.
Highlights
AlphaFold solved the protein structure enigma, greatly aiding biology and medicine 🧬.
AI has enabled the prediction of 200 million protein structures, revolutionizing research 🔍.
This discovery may help design vaccines, understand diseases, and even combat environmental issues 🌍.
AI's application to protein science exemplifies its transformative power across multiple fields.
DeepMind's use of AI in biology could be just the beginning of scientific revolutions powered by AI 🌟.
Key Takeaways
AI can revolutionize science by significantly speeding up our understanding of biological structures 🌐.
AlphaFold has made predicting the structure of nearly all known proteins possible in a fraction of the time previously expected 🏆.
This breakthrough has wide-ranging implications, from healthcare advancements to environmental solutions 🌿.
AI models like AlphaFold can solve complex problems that human intuition struggles with due to their computational nature 🔍.
AI's success in protein folding is a big leap but also a hint at the vast possibilities in other scientific fields 📈.
Overview
In a critical breakthrough, AI has managed to tackle one of biology’s most challenging puzzles: protein folding. The successful prediction of protein structures has implications far beyond biology, addressing global issues like health and environmental recovery. AlphaFold, developed by DeepMind, has drastically reduced the time taken to understand protein structures, going from decades to just months, thus revolutionizing how scientists approach biological mysteries.
AlphaFold's success lies in its advanced AI algorithms that mimic human problem-solving intuition but on a computational scale. This game-changing technology has been likened to unveiling the secrets of DNA. It not only predicts protein structures with high accuracy but does so using evolutionary and geometrical data, making it a comprehensive tool for researchers.
The implications of AlphaFold’s success are vast. With the ability to map out 200 million protein structures, diseases can be understood at a molecular level, leading to better treatments and interventions. The same processes can be used to address climate change challenges and create new sustainable materials, representing a new frontier in scientific exploration.
Chapters
00:00 - 00:30: Introduction This chapter explores the potential of a groundbreaking scientific breakthrough that could address numerous global challenges, such as climate change, disease treatment, and plastic waste disposal. The solution, possibly linked to advancements in understanding protein structures, is seen as pivotal in tackling these issues. The breakthrough is compared to solving Fermat's Last Theorem in significance within the field of biology.
00:30 - 01:00: Protein Structure Determination A team of biologists initially determined the structure of 150,000 proteins over many years. Recently, a smaller team significantly increased this number to 200 million proteins, covering almost every known protein in nature. This remarkable feat holds promise for solving a wide range of problems beyond biology. The process begins with proteins that start as simple strings of amino acids, with each amino acid featuring a central carbon atom.
01:00 - 01:30: Amino Acids and Protein Folding In this chapter titled 'Amino Acids and Protein Folding,' the focus is on the structure and interaction of amino acids in forming proteins. Amino acids are characterized by having an amine group on one side and a carboxyl group on the other, with a side chain that distinguishes one amino acid from another. There are 20 different amino acids, each identified by its unique side chain. The chapter explains the formation of peptide bonds, which occur when the amine group of one amino acid reacts with the carboxyl group of another, resulting in a chain of amino acids. These chains form due to various interactions, including electrostatic forces, driving the process of protein folding.
02:00 - 02:30: Protein Crystallization and X-Ray Diffraction This chapter delves into the process of protein crystallization and the importance of X-ray diffraction in determining the 3D structures of proteins. It emphasizes the role of hydrogen bonds and solvent interactions in the folding of proteins into their functional three-dimensional shapes, which are crucial to their roles in biological systems. The chapter highlights the specificity of these shapes in biological functions, using hemoglobin as an example of a protein that has a perfect binding site for carrying oxygen. It also touches upon the importance of the correct orientation of proteins to function effectively as molecular machines, such as in muscle movements.
05:00 - 05:30: CASP Competition and Early Solutions This chapter discusses the early methods of determining protein structures and the inception of the CASP competition. Scientists initially relied on experimental techniques, especially x-ray crystallography, to discern protein shapes. Proteins could slightly change shape to perform functions, adding complexity to structural determination efforts. The structural understanding of proteins, essential for advancements in biochemistry, took considerable time and intricate calculations to achieve.
10:00 - 10:30: DeepMind and AlphaFold Development The chapter describes the challenges faced by British biochemist John Kendrew in determining the structure of a protein, myoglobin. Kendrew spent 12 years working on this project, initially using a horse heart, which provided small crystals due to insufficient myoglobin. Understanding that diving mammals possess higher levels of myoglobin due to their ability to conserve oxygen, Kendrew sourced a large piece of whale meat from Peru. This allowed him to obtain sufficiently large crystals, leading to the successful unveiling of the myoglobin structure.
15:00 - 15:30: AlphaFold 1 and Evolutionary Inputs The chapter discusses the development and implications of AlphaFold 1, which utilized evolutionary inputs to predict protein structures. It highlights the initial surprise and complexity encountered in x-ray diffraction images, likened to the intricate appearance of a rocket motor. Despite the complexity, such structural revelations, including one humorously dubbed the 'Turd of the century,' earned John Kendrew the Nobel Prize in Chemistry in 1962. The following two decades saw the resolution of only about a hundred more structures, emphasizing the early challenges and slow progress in this field before the advent of advanced computational methods like AlphaFold.
19:30 - 20:00: AlphaFold 2 and Breakthrough Protein crystallization remains a significant challenge in scientific research. The process is so complex and demanding that achieving just a couple of successful protein structures can constitute an entire PhD study. Some researchers may spend their whole academic research journey working towards just one structure. Additionally, the method is quite costly; X-ray crystallography, a typical technique used in this field, can cost tens of thousands of dollars per protein. Due to these challenges, scientists have been motivated to seek alternative methods to ascertain protein structures. Interestingly, determining a protein's amino acid sequence is significantly cheaper, with costs around one hundred dollars. This cost disparity and the complex nature of traditional methods have driven innovation and breakthroughs in protein structure determination.
22:30 - 23:00: Applications of AlphaFold This chapter discusses the significance of AlphaFold in predicting protein folding, which can save resources in terms of time, effort, and money. It emphasizes the importance of understanding molecular dynamics to predict protein structures. Additionally, it references Linus Pauling's work on predicting the helical and sheet-like structures of proteins through geometric analysis, illustrating an example of successful prediction in biology.
30:00 - 30:30: Designing New Proteins and Applications The chapter discusses the concept of secondary protein structure, which includes local twists and turns such as helices and sheets. It highlights the challenge biochemists face in identifying reliable patterns that determine the final structure of proteins. The difficulty arises because protein evolution is not a deliberate design process but rather an accumulation of beneficial traits over time, akin to a programmer adding features without a clear plan, resulting in intricate and complex structures.
35:00 - 35:30: AI's Impact on Science The chapter "AI's Impact on Science" discusses the differences between AI and human-designed machines, emphasizing the lack of inherent purpose in AI systems compared to human creations. It cites an example from MIT biologist Cyrus Levinthal, who calculated the vast number of possible configurations for a protein chain with just 35 amino acids, illustrating the complex challenges in scientific computations. The text alludes to the idea that even if AI or computers could analyze tens of thousands of configurations every nanosecond, the scope of possibilities in scientific data, like protein folding, is still enormous.
40:00 - 40:30: Future Implications and Conclusion The chapter discusses the vast complexity and computational challenge of predicting protein structures, indicating it would take an impossibly long time using traditional methods. In response to this challenge, Dr. John Moult from the University of Maryland launched the CASP competition in 1994. The competition aims to inspire the creation of computer models capable of predicting the structure of proteins based on amino acid sequences, without prior knowledge of the actual structure. The predicted structures are then compared to experimentally determined ones to assess accuracy.
The Most Useful Thing AI Has Ever Done Transcription
00:00 - 00:30 What if, all of the world's biggest
problems from climate change, to curing diseases, to
disposal of plastic waste, what if they all had the same solution? A solution so tiny it would be invisible. I'm inclined to believe this is possible, thanks to a recent
breakthrough that solved one of the biggest problems
of the last century. How to determine the
structure of a protein? - It's been described to me as equivalent to Fermat's last theorem, but for biology. - Over six decades, tens of thousands
00:30 - 01:00 of biologists painstakingly worked out the structure of 150,000 proteins. Then in just a few years, a team of around 15 determined the
structure of 200 million. That's basically every protein
known to exist in nature. So how did they do it and why does this have the potential to solve problems way
outside the realm of biology? A protein starts simply as
a string of amino acids. Each amino acid has a
carbon atom at the center.
01:00 - 01:30 Then on one side is an amine group, and on the other side is a carboxyl group. And the last thing it's
bonded to could be one of 20 different side chains, and which one determines which of the 20 different amino
acids this molecule is. The amine group from
one amino acid can react with the carboxyl group of
another to form a peptide bond. So a series of amino acids
can bond to form a string and pushing and pulling between countless molecules,
electrostatic forces,
01:30 - 02:00 hydrogen bonds, solvent interactions can cause this string to
coil up and fold onto itself. This ultimately determines the
3D structure of the protein. And this shape is the thing that really matters about the protein. It's built for a specific purpose, like how hemoglobin has
the perfect binding site to carry around oxygen in your blood. - These are machines, they need to be in their correct orientation
in order to work together to move, for example, the
proteins in your muscles.
02:00 - 02:30 They change their shape a little bit in order to pull and contract. - But it would take people a long time to get the structure of just one protein. - Absolutely. So what should proteins look like? Was only started to answer really with experimental techniques. - [Derek] The first way protein
structure was determined was by creating a crystal
out of that protein. This was then exposed to x-rays to get a diffraction pattern, and then scientists would work backwards to try to figure out what shape of molecules would create such a pattern.
02:30 - 03:00 It took British biochemist,
John Kendrew, 12 years to get the first protein structure. His target was an oxygen storing
protein called myoglobin, an important protein in our hearts. He first tried a horse heart, but this produced rather small crystals because it didn't have enough myoglobin. He knew diving mammals would have lots of myoglobin in their muscles since they're the best
at conserving oxygen. So he obtained a huge chunk
of whale meat from Peru. This finally gave Kendrew
large enough crystals
03:00 - 03:30 to create an x-ray diffraction image. - And when it came out,
it looked really weird. People expected something kind of logical,
mathematical, understandable, and it almost looked, I
wouldn't say ugly, but intricate and complex and kind of like if you see a rocket motor, and all the parts hanging off. - [Derek] This structure,
which has been called "Turd of the century," won Kendrew, the 1962
Nobel Prize in chemistry. Over the next two decades, only around a hundred more
structures were resolved.
03:30 - 04:00 Even today, protein crystallization
remains a big challenge. - Frankly it is not uncommon that just a couple protein structures can be someone's entire PhD. Sometimes just one, sometimes
even just progress toward one, - And it's expensive. X-ray crystallography
can cost 10s of thousands of dollars per protein. So scientists sought another way to work out protein structure. It only costs around a hundred dollars to find a protein sequence of amino acids.
04:00 - 04:30 So if you could use this to figure out how the protein would fold, that would save a lot of
time, effort, and money. I kind of know how carbon behaves and I know how carbon sticks to a sulfur and how that might stick
next to a nitrogen. And if these ones are here, then I can imagine this one
folding, making that bond there. So it seems like if you have some sense of basic molecular dynamics,
you might be able to figure out how this protein's gonna fold. - One of the few true
predictions in biology was actually Linus Pauling
looking at just the geometry of the building blocks of proteins and saying, actually they
should make helices and sheets.
04:30 - 05:00 That's what we call secondary structure, the very local kind of twists
and turns of the protein. - But beyond helices and sheets, biochemists could not figure
out any reliable patterns that would lead to the final
structure of all proteins. One reason for this is that
evolution didn't design proteins from the ground up. - It's kind of like a programmer that doesn't know what they're doing, and whenever it looked good, they just kept adding that kind of thing. And that's how you end up with these both amazing objects and incredibly complex
and hard to describe.
05:00 - 05:30 They don't have purpose
underneath them in the same way as like a human designed machine would. - [Derek] To illustrate just
how complicated this process can get, MIT biologist Cyrus Levinthal did a back-of-the-envelope calculation, and he showed that even
a short protein chain with 35 amino acids can fold in an astronomical number of ways. So even if a computer checked
the energy instability of 30,000 configurations every nanosecond,
05:30 - 06:00 it would take 200 times
the age of the universe to find the correct structure. Refusing to give up, the University of Maryland
professor John Moult started a competition called CASP in 1994. The challenge was simple,
to design a computer model that could take an amino acid sequence and output its structure. The modelers would not
know the correct structure beforehand, but the output from
each model would be compared to the experimentally
determined structure.
06:00 - 06:30 A perfect match would
get a score of a hundred, but anything over 90 was
considered close enough that the structure was solved. CASP competitors gathered
at an old wooden chapel turned conference center
in Monterey, California, and at any point where a
prediction didn't make sense, they were encouraged to tap
their feet as friendly banter. There was a lot of foot tapping. (foot tapping) In the first year, teams
could not achieve scores higher than 40.
06:30 - 07:00 The early front runner was
an algorithm called Rosetta, created by University of
Washington biologist David Baker. One of his innovations
was to boost computation by pooling together processing
power from idle computers in homes, schools, and
libraries that volunteered to install his software
called Rosetta at Home. - As part of it, there was a screensaver that showed basically the course of the protein folding calculation. And then we started getting
people writing in saying that they were watching the screensaver and they thought they could
do better than the computer.
07:00 - 07:30 - So Baker had an idea. He created a video game. (upbeat music) The game called Fold It, set up a protein chain capable of twisting and turning into different arrangements. - But now instead of the
computer making the moves, the game players, the
humans could make the moves. - Within three weeks, more than 50,000 gamers pooled their efforts to decipher an enzyme that plays a key role in HIV. X-Ray crystallography showed
their result was correct.
07:30 - 08:00 The gamers even got credited as co-authors on the research paper. Now, one man who played Fold It was a former child chess
prodigy named Demis Hassabis. Hassabis had recently started
an AI company called DeepMind. Their AI algorithm, AlphaGo made headlines for beating world champion
Lee Sedol at the game of Go. One of AlphaGo's moves, move
37, shook Sedol to his core. But Hassabis never forgot about
his time as a Fold It gamer.
08:00 - 08:30 - So of course I was fascinated this just from games design perspective. You know, wouldn't it be
amazing if we could mimic the intuition of these gamers
who were only, by the way, of course, amateur biologists. - After returning from Korea, DeepMind researchers had
a week-long hackathon where they tried to
train AI to play Fold It. This was the beginning of
Hassabis' longstanding goal of using AI to advance science. He initiated a new
project called Alpha Fold to solve the protein folding problem.
08:30 - 09:00 Meanwhile at CASP, the quality of prediction from the best performers, including Rosetta had plateaued. In fact, the performance went
downhill after CASP eight. The predictions weren't good enough, even with faster computers and a growing number of structures in the protein data bank to train on. DeepMind hoped to change
this with AlphaFold. Its first iteration, AlphaFold 1, was a standard off-the-shelf
deep neural network like the ones used for computer
vision at that time. The researchers trained it on lots
09:00 - 09:30 and lots of protein structures
from the protein data bank. As input, AlphaFold took the
protein's amino acid sequence and an important set of
clues given by evolution. Evolution is driven by mutations, changes in the genetic code, which in turn change the amino acids within a given protein sequence. But as species evolve, proteins
need to retain the shape that allows them to perform
their specific function. For instance, hemoglobin looks
the same in humans, cats,
09:30 - 10:00 horses, and basically any mammal. Evolution says, if it
ain't broke, don't fix it. So we can compare sequences of the same protein
across different species in this evolutionary table. Where sequences are similar, it's likely they are important in the protein structure and function. But even where the
sequences are different, it's helpful to look at where
mutations happen in pairs because they can identify
which amino acids are close to each other
in the final structure. Say two amino acids, a
positively charged lysine
10:00 - 10:30 and a negatively charged
glutamic acid attract and hold each other in the folded protein. Now, if a mutation changes lysine to a negatively charged amino acid, it would repel glutamic acid and destabilize the whole protein. Therefore, another mutation
must replace glutamic acid with a positively charged amino acid. This is known as co-evolution. These evolutionary tables were an important input for AlphaFold.
10:30 - 11:00 As output, instead of directly
producing a 3D structure, AlphaFold predicted a simpler
2D pair representation of that structure. The amino acid sequence is laid out horizontally and vertically. Whenever two amino acids are close to each other in the final structure, their corresponding row
column intersection is bright. Distant amino acid pairs are dim. In addition to distances, the pair representation
can also hold information
11:00 - 11:30 on how amino acid molecules are twisted within the structure. AlphaFold 1 fed the protein sequence and its evolutionary table
into its deep neural network, which it had trained to predict
the pair representation. Once it had this, a
separate algorithm folded the amino acid string based on the distance and torsion constraints. And this was the final
protein structure prediction. With this framework,
AlphaFold entered CASP 13 and it immediately turned heads.
11:30 - 12:00 It was the clear winner
after many additions, but it wasn't perfect. Its score of 70 was not enough to clear the CASP threshold of 90. DeepMind needed to get
back to the drawing board to get better results. So Hassabis recruited John
Jumper to lead AlphaFold. - AlphaFold 2 was really
a system about designing our deep learning. The individual blocks to be
good at learning about proteins, have the types of geometric
physical, evolutionary concepts
12:00 - 12:30 that were needed and put it
into the middle of the network instead of a process around it. And that was a tremendous accuracy boost. - [Derek] There were three key steps
to get better results with AI. First, maximum compute power. Here, DeepMind was
already better positioned than anybody in the world. It had access to the enormous
computing power of Google, including their tensor processing units. Second, they needed a
large and diverse data set. Is data the biggest roadblock and why?
12:30 - 13:00 - I think it's too easy to
say data's the roadblock and we should be careful about it. AlphaFold 2 was trained on
the exact same data with much, much better machine
learning as AlphaFold 1. So everyone overestimates
the data blockage because it gets less severe
with better machine learning. - [Derek] And that was the third key
element, better AI algorithms. Now AI is not just good
at protein folding. It can do all kinds of tasks that no one likes from writing emails to answering phone calls.
13:00 - 13:30 Something I hate is building
and maintaining a website. It's so much work from
optimizing the website for different platforms,
finding a good design so it looks professional
to constantly updating it with new information about
the business as it grows. That's why we partnered with Hostinger, the sponsor of today's video. Hostinger makes it super
easy to build a website for yourself or your business. And with their advanced AI
tools, you can simply describe what you want your website to look like.
13:30 - 14:00 And in just a few seconds, your personalized website
is up and running. Hostinger is designed to
be as easy as possible for beginners and professionals. So any tweaks you need to make after that are super easy too. Just drag and drop any pictures or videos you want, where you want them, or just type what you want to say or have the AI help you here too, if writing isn't your thing either. And if you still want that
human touch, Hostinger is always available with 24/7 support if you
ever run into any issues. But when you're done building
in just a few clicks, your website is live.
14:00 - 14:30 It's all incredibly
affordable too, with a domain and business email included for free. So to take your big idea online today, visit hostinger.com/ve or
scan this QR code right here. And when you sign up, remember
to use code VE at checkout to get 10% off your plan. I wanna thank Hostinger for sponsoring this part of the video. And now back to protein folding. As the AlphaFold 2 team
searched for better algorithms, they turned to the transformer. That's the T in ChatGPT.
14:30 - 15:00 And it relies on a
concept called attention. In the sentence, the animal didn't cross the
street because it was too tired. Attention recognizes
that it refers to animal and not street based on the word tired. Attention adds context to any
kind of sequential information by breaking it down into chunks, converting these into
numerical representations or embeddings and making
connections between them. In this case, the word it and animal.
15:00 - 15:30 3Blue1Brown has a great series of videos specifically about
transformers and attention. Large language models use attention to predict the most appropriate
word to add to a sentence, but AlphaFold also has
sequential information, not sentences, but amino acid sequences. And to analyze them, the AlphaFold team built their own version of the transformer called an EVO Former. The EVO Former contained two towers, evolutionary information
in the biology tower and pair representations
in the geometry tower.
15:30 - 16:00 Gone was AlphaFold 1's deep
neural network that started with one tower and predicted the other. Instead, AlphaFold 2's EVO Former builds each tower separately. It starts with some initial guesses, evolutionary tables taken from
known data sets as before, and the pair representations based on similar known proteins. And this time there's a bridge
connecting the two towers that conveys newly found
biological and geometry clues back and forth.
16:00 - 16:30 In the biology tower, attention applied on a column identifies amino acid sequences
that have been conserved. While along a row, it
finds amino acid mutations that have occurred together. Whenever the EVO Former finds
too closely linked amino acids in the evolutionary table. It means they are important to structure and it sends this information
to the geometry tower. Here attention is applied to help calculate distances
between amino acids. - There's also this thing
called triangular attention that got introduced,
16:30 - 17:00 which is essentially about letting triplets attend to each other. - [Derek] For each triplet of amino acids, AlphaFold applies the triangle inequality. The sum of two sides must
be greater than the third. This constrains how far apart these three amino acids can be. This information is used to
update the pair representation, - And that helps the model produce like a self-consistent
picture of the structure. - [Derek] If the geometry
tower finds it's impossible for two amino acids to
be close to each other, then it tells the first tower
17:00 - 17:30 to ignore their relationship
in the evolutionary table. This exchange of information
within the EVO Former goes on for 48 times, until information within
both towers is refined. The geometrical features
learned by this network are passed onto AlphaFold
2's second main innovation, the structure module. - For each amino acid, we pick three special
atoms in the amino acid and say that those define a frame. And what the network does is it imagines that all the amino acids
start out with the origin and it has to predict the
appropriate translation
17:30 - 18:00 and rotation to move these frames to where they sit in the real structure. So that's essentially what
the structure module does. - But the thing that sets
the structure module apart is what it doesn't do. - Previously, people might
have imagined that you would like to encode the fact that
this is a chain, you know, and that certain residue
should sit next to each other. We don't really explicitly
tell AlphaFold that. It's more like we give
it a bag of amino acids and it's allowed to position
each of them separately. And some people have
thought that that helps it
18:00 - 18:30 to not get stuck in terms of
where things should be placed. It doesn't have to always be
thinking about the constraint of these things forming a chain, that's something that
emerges naturally later. - [Derek] That's why live
AlphaFold folding videos can show it doing some
weirdly non-physical stuff. The structure module outputs a 3D protein, but it still isn't ready. It's recycled at least three more times through the Evo Former to
gain a deeper understanding of the protein only then the
final prediction is made.
18:30 - 19:00 In December, 2020, DeepMind
returned to a virtual CASP with AlphaFold 2, and
this time they did it. - I'm going to read an
email from John Moult. "Your group has performed
amazingly well in CASP 14, both relative to other groups and in absolute model accuracy. Congratulations on this work." - [Derek] For many proteins,
AlphaFold 2 predictions
19:00 - 19:30 were virtually indistinguishable
from the actual structures and they finally beat the
gold standard score of 90. - For me, having worked
on this problem so long, after many, many stops and starts, and suddenly this is a solution. We'd solved the problem. This gives you such excitement
about the way science works. - [Derek] Over six decades,
all of the scientists working around the world on
proteins painstakingly found about 150,000 protein structures.
19:30 - 20:00 Then in one fell swoop, AlphaFold came in and unveiled over 200 million of them. Nearly all proteins
known to exist in nature. In just a few months,
AlphaFold advanced the work of research labs worldwide
by several decades. It has directly helped us
develop a vaccine for malaria. It's made possible the breaking down of antibiotic resistance enzymes, which make many life-saving
drugs effective again.
20:00 - 20:30 It's even helped us understand how protein mutations lead to various diseases from
schizophrenia to cancer, and biologists studying little known and endangered species suddenly had access to proteins
and their life mechanism. The AlphaFold 2 paper has
been cited over 30,000 times. It has truly made a step function leap in our understanding of life. John Jumper and Demis
Hassabis were awarded one half of the 2024 Nobel Prize in
chemistry for this breakthrough.
20:30 - 21:00 The other half went to David Baker, but not for predicting
structures using Rosetta. Instead, it was for designing completely new proteins from scratch. - It was really hard to
make brand new proteins that would do things. And so that's kind of the
problem that we solved. - To do so, he uses the
same kind of generative AI that makes art in programs like Dall-E. - You can say draw a picture of a kangaroo riding on a rabbit or something, and it will do that. And so it's exactly what
we did with proteins. - His technique called
"RF Diffusion" is trained
21:00 - 21:30 by adding random noise to
a known protein structure, and then the AI has to remove this noise. Once trained in this
way, the AI can be asked to produce proteins for various functions. It's given a random noise input, and the AI figures out a brand new protein that does what you asked it to do. This work has huge implications. I mean, imagine you got
bitten by a venomous snake. If you're lucky, you'll have
access to anti-venom prepared by milking venom from
the exact kind of snake,
21:30 - 22:00 which is then injected into live animals, and the antibodies from
that animal are extracted and refined and then given
to you as an anti-venom. The trouble is often people
have allergic reactions to these antibodies from other organisms. But your odds of survival
can be a lot better with the latest synthetic
proteins designed in Baker's lab. They've created human
compatible antibodies that can neutralize lethal snake venom. This anti-venom could be
manufactured in large quantities
22:00 - 22:30 and easily transported to
the places where it's needed. With these tiny molecular machines, the possibilities are endless. What are the applications
you're most excited about? - So I think vaccines are
gonna be really powerful. We have a number of proteins that are in human clinical
trials for cancer, and we're working on
autoimmune disease now. We're really excited about problems like capturing greenhouse gases. So we're designing enzymes that can fix methane, break down plastic. - What makes this approach so effective is how fast they can create
and iterate the proteins.
22:30 - 23:00 - It's really quite miraculous for anyone who's a
conventional school biochemist or protein scientist. We can now have designs on the computer, get the amino acid sequence
of the design proteins, and then in just a couple days
we can get the protein out. Yeah. We've given a name to this, which is "Cowboy Biochemistry" because we just like, you
just got kind of go for it as fast as you can, and it
turns out to work pretty well. - What AI has done for
proteins is just a hint
23:00 - 23:30 of what it can do in other fields and on larger scales. In materials science, for example, DeepMind's GNoME program has
found 2.2 million new crystals, including over 400,000 stable materials that could power future technologies from superconductors to batteries. AI is creating transformative
leaps in science by helping to solve some
of the fundamental problems that have blocked human progress. - If we think of the
whole tree of knowledge, you know there are certain problems where you know if their root, no problems.
23:30 - 24:00 If you unlock them, if you
discover a solution to them, it would unlock a whole new
branch or avenue of discovery. - And with this, AI is
pushing forward the boundaries of human knowledge at a
rate never seen before. - Speed ups of 2x are nice, they're great, we love them. Speed ups of a 100,000x, change what you do. You do fundamentally different stuff and you start to rebuild your science around the things that got easy.
24:00 - 24:30 - And that's what I'm excited about. These discoveries represent
real step function changes in science. Even if AI doesn't advance
beyond where it is today, we will be reaping the benefits of these breakthroughs for decades. And assuming AI does continue to develop, well, it will open up opportunities that were previously thought impossible. Whether that's curing all diseases, creating novel materials, or restoring the environment
to a pristine state. This sounds like an amazing future as long
24:30 - 25:00 as the AI doesn't take over
and destroy us all first. (slow cosmic music)