AI Breakthrough: Designing Life-Like Enzymes from Scratch

Scientists use AI to design life-like enzymes from scratch

Researchers have used artificial intelligence (AI) to design brand-new enzymes that can go through multi-step reactions, a key feature of natural enzymes. The structures they made accelerated a four-step chemical reaction pivotal to many biological and industrial processes, including plastic recycling. "This is a milestone in enzyme engineering," says Huimin Zhao, a synthetic biologist at the University of Illinois Urbana-Champaign. "[It] shows that now it's possible to design enzymes with native-like activity that could make them useful practically." Earlier efforts to design enzymes from scratch using AI have had limited success, often producing ones that stall after the first step of a reaction. In the latest study, published in Science on 13 February, researchers overcame this challenge by combining several machine-learning approaches. The new enzymes were 60,000 times better at speeding up the reaction than ones previously designed to work in a similar way. Earlier efforts have focused on tweaking the structures of existing enzymes to create new ones that work faster or have different functions. But this approach makes it difficult to create efficient enzymes capable of multi-step reactions. "It is like going to the thrift store and buying a suit, and that suit probably won't fit you perfectly. That's what happens when we try to design enzymes that way," says study co-author Anna Lauko, a protein designer at the University of Washington in Seattle. Lauko and her colleagues wanted to build enzymes that can undergo a four-step chemical reaction called serine hydrolysis, which involves breaking an ester bond between molecules. Serine hydrolases are the natural enzymes that carry out this reaction, and they are involved in many biological processes, including digestion, metabolizing fats and blood clotting. The researchers started with an AI tool called RFdiffusion, a program they had previously developed to generate new enzyme structures from scratch. They then created a deep neural network, called PLACER, to refine the structural design by modelling the locations of atoms in the enzyme and the molecules it binds to during every step of the reaction. This AI works like "a filter", says Zou: it checks whether the enzyme's active sites -- the parts that interact with molecules -- are compatible and properly arranged to carry out each step of the reaction. This is "very innovative", says Zhao. Using these AI tools together helped in "getting this bespoke tailored suit that's going to fit perfectly", says Lauko. The newly designed enzymes completed all four steps of serine hydrolysis. "This is going to enable us to design from scratch more complicated enzymes that weren't really possible to make," says Lauko. The researchers emphasize that their work is just a proof of principle, and that although the new enzymes are promising, they are not yet as efficient as natural serine hydrolases. They hope that more fine-tuning of the enzymes' structures will improve their speed and efficiency, bringing the technology one step closer to real-world applications. "We can use all of these principles ... to try to design serine hydrolases to break down plastic," says Lauko. The AI tools in the study could one day be used to design enzymes capable of entirely new chemical reactions that do not exist in nature, says Noelia Ferruz, who specializes in AI protein design at the Centre for Genomic Regulation in Barcelona, Spain. "The limitations are just basically your imagination; you can design anything."

Enzymes are the engines of life - machine learning tools could help scientists design new ones to tackle disease and climate change

Enzymes are molecular machines that carry out the chemical reactions that sustain all life, an ability that has captured the attention of scientists like me. Consider muscle movement. Your body releases a molecule called acetylcholine to trigger your muscle cells to contract. If acetylcholine sticks around for too long, it can paralyze your muscles - including your heart muscle cells - and, well, that's that. This is where the enzyme acetylcholinesterase comes in. This enzyme can break down thousands of acetylcholine molecules per second to ensure muscle contraction is stopped, paralysis avoided and life continued. Without this enzyme, it would take a month for a molecule of acetylcholine to break down on its own - about 10 billion times slower. You can imagine why enzymes are of particular interest to scientists looking to solve modern problems. What if there were a way to break down plastic, capture carbon dioxide or destroy cancer cells as fast as acetylcholinesterase breaks down acetylcholine? If the world needs to take action quickly, enzymes are a compelling candidate for the job - if only researchers could design them to handle those challenges on demand. Designing enzymes, unfortunately, is very hard. It's like working with an atom-sized Lego set, but the instructions were lost and the thing won't hold together unless it's assembled perfectly. Newly published research from our team suggests that machine learning can act as the architect on this Lego set, helping scientists build these complex molecular structures accurately. What's an enzyme? Let's take a closer look at what makes up an enzyme. Enzymes are proteins - large molecules that do the behind-the-scenes work that keep all living things alive. These proteins are made up of amino acids, a set of building blocks that can be stitched together to form long strings that get knotted up into specific shapes. The specific structure of a protein is key to its function in the same way that the shapes of everyday objects are. For example, much like a spoon is designed to hold liquid in a way that a knife simply can't, the enzymes involved in moving your muscles aren't well suited for photosynthesis in plants. For an enzyme to function, it adopts a shape that perfectly matches the molecule it processes, much like a lock matches a key. The unique grooves in the enzyme - the lock - that interact with the target molecule - the key - are found in a region of the enzyme known as the active site. The active site of the enzyme precisely orients amino acids to interact with the target molecule when it enters. This makes it easier for the molecule to undergo a chemical reaction to turn into a different one, making the process go faster. After the chemical reaction is done, the new molecule is released and the enzyme is ready to process another. How do you design an enzyme? Scientists have spent decades trying to design their own enzymes to make new molecules, materials or therapeutics. But making enzymes that look like and go as fast as those found in nature is incredibly difficult. Enzymes have complex, irregular shapes that are made up of hundreds of amino acids. Each of these building blocks needs to be placed perfectly or else the enzyme will slow down or completely shut off. The difference between a speed racer and slowpoke enzyme can be a distance of less than the width of a single atom. Initially, scientists focused on modifying the amino acid sequences of existing enzymes to improve their speed or stability. Early successes with this approach primarily improved the stability of enzymes, enabling them to catalyze chemical reactions at a higher range of temperatures. But this approach was less useful for improving the speed of enzymes. To this day, designing new enzymes by modifying individual amino acids is generally not an effective way to improve natural enzymes. Researchers found that using a process called directed evolution, in which the amino acid sequence of an enzyme is randomly changed until it can perform a desired function, proved much more fruitful. For example, studies have shown that directed evolution can improve chemical reaction speed, thermostability, and even generate enzymes with properties that aren't seen in nature. However, this approach is typically labor-intensive: You have to screen many mutants to find one that does what you want. In some cases, if there's no good enzyme to start from, this method can fail to work at all. Both of these approaches are limited by their reliance on natural enzymes. That is, restricting your design to the shapes of natural proteins likely limits the kinds of chemistry that enzymes can facilitate. Remember, you can't eat soup with a knife. Is it possible to make enzymes from scratch, rather than modify nature's recipe? Yes, with computers. Designing enzymes with computers The first attempts to computationally design enzymes still largely relied on natural enzymes as a starting point, focusing on placing enzyme active sites into natural proteins. This approach is akin to trying to find a suit at a thrift store: It is unlikely you will find a perfect fit because the geometry of an enzyme's active site (your body in this analogy) is highly specific, so a random protein with a rigidly fixed structure (a suit with random measurements) is unlikely to perfectly accommodate it. The resulting enzymes from these efforts performed much more slowly than those found in nature, requiring further optimization with directed evolution to reach speeds common among natural enzymes. Recent advances in deep learning have dramatically changed the landscape of designing enzymes with computers. Enzymes can now be generated in much the same way that AI models such as ChatGPT and DALL-E generate text or images, and you don't need to use native protein structures to support your active site. Our team showed that when we prompt an AI model, called RFdiffusion, with the structure and amino acid sequence of an active site, it can generate the rest of the enzyme structure that would perfectly support it. This is equivalent to prompting ChatGPT to write an entire short story based on a prompt that only says to include the line "And sadly, the eggs never showed up." We used this AI model specifically to generate enzymes called serine hydrolases, a group of proteins that have potential applications in medicine and plastic recycling. After designing the enzymes, we mixed them with their intended molecular target to see whether they could catalyze its breakdown. Encouragingly, many of the designs we tested were able to break down the molecule, and better than previously designed enzymes for the same reaction. To see how accurate our computational designs were, we used a method called X-ray crystallography to determine the shapes of these enzymes. We found that many of them were a nearly perfect match to what we digitally designed. Our findings mark a key advance in enzyme design, highlighting how AI can help scientists start to tackle complex problems. Machine learning tools could help more researchers access enzyme design and tap into the full potential of enzymes to solve modern-day problems.

Researchers led by University of Washington Nobel winner achieve a scientific breakthrough

A team from the University of Washington led by Nobel laureate David Baker is using artificial intelligence to design effective enzymes from scratch -- an accomplishment the researchers call "one of science's grand challenges." Enzymes are the wizards of the natural world, proteins that can transform molecules and rapidly accelerate chemical reactions under mild conditions. They're found in every living cell and are essential to life. Enzymes are already being harnessed for drug production and industrial processes. The newly developed tools for enzyme creation could unlock wide-ranging applications. "Now we can make these enzymes tailored to any reaction of interest, theoretically," said Anna Lauko, a recent Ph.D. graduate from Baker's lab. "It's sort of flipped the way that we would do enzyme design." Lauko is a co-lead author of a research paper being published today in the journal Science. Her co-leads are Sam Pellock, an acting instructor in the lab, and Kiera Sumida, one of Baker's graduate students. Last year Baker, a biochemist and director of the Institute for Protein Design at UW Medicine, won a Nobel Prize in chemistry for his work unraveling the molecular design of proteins and developing technologies for using AI to build and test new ones. In the past, scientists made Frankenstein enzymes, stitching together components of existing proteins in the hope that the assembled parts could manage a precise task. But enzymes often need to perform nuanced operations, changing shapes multiple times as they manipulate molecules. Pellock compared the old approach to enzyme design to going to a thrift store for a suit. "It's unlikely that you're going to find a suit that fits well," he said, and the enzymes were the same way. They included the basic pieces, but didn't perfectly match the molecules that they needed to interact with. The new approach produces bespoke proteins. To test their cutting-edge approach, the UW researchers focused on a well-studied enzyme called a serine hydrolase. The enzyme is able to cleave a chemical bond that's key to the structure of many carbon-containing molecules, including plastics, polyesters and a common fat in humans. The team used the RFdiffusion model, an AI program for generating proteins that was previously developed by Baker's lab and is open source. They combined that with a newer tool called PLACER that helped them identify the most promising de novo enzyme candidates. The scientists then tested the performance of the machine-created enzymes. "They're still not quite as good as native enzymes," Pellock said. "But out of the computer, these are among the best that have been made and they were made with very high accuracy." The accomplishment is a milestone and proves that the researchers are getting close to making new enzymes for human-driven tasks that could out-perform what nature has produced. Sumida, for example, is working to build an enzyme that could help degrade the planet's massive glut of plastic waste. Plastic is an incredibly new substance on an evolutionary scale so there hasn't been much time for enzymes to evolve that can break it down. There is an enzyme in the serine hydrolase family that can chop up the bonds in the plastic that's used to make water bottles and other products, but there are many other kinds of plastics out there that need to be disposed of sustainably. "We thought that it would be a really good application if we're able to build these enzymes from scratch," she said, and customize them for different types of plastic. The researchers are eager for the advent of high-performing, AI-designed enzymes after decades of largely disappointing efforts. "Hopefully you'll start hearing more about enzyme design projects," Pellock said, "because they'll actually yield a functional enzyme at the end of them." Additional authors for the Science paper are David Baker, Ivan Anishchenko, David Juergens, Woody Ahern, Jihun Jeung, Alex Shida, Andrew Hunt, Indrek Kalvet, Christoffer Norn, Ian Humphreys, Cooper Jamieson, Rohith Krishna, Yakov Kipnis, Alex Kang, Evans Brackenbrough, Asim Bera, Banumathi Sankaran and K. N. Houk.