The new era of AI-powered protein design | César Ramírez-Sarmiento

0:07You're listening to TED Talks Daily, where we bring you new ideas to spark your curiosity every day. I'm your host, Elise Hu. Today's talk is part of our new 2025 TED Fellows films adapted for podcasts just for our TED Talks daily listeners. We'll be releasing these special episodes showcasing our amazing fellows on certain Fridays throughout the rest of 2025 and into the new year. The TED Fellows program supports a network of global innovators, and we are so excited to share their work with you. Today, we'd love for you to meet protein engineer, designer, and TED Fellow Cesar Ramirez Sarmiento.

0:45What if we could take one of nature's fundamental biological building blocks, proteins, and redesign them to tackle some of humanity's biggest challenges? Cesar's lab is based in Santiago, Chile, and it uses AI to design new proteins with both therapeutic and environmental applications. His creative approach to protein design and AI shows why Latin America is emerging as such a leader in this space and why we should look to enzymes for everything from breaking down PET plastics to developing new healthcare solutions. After we hear from Cesar, stick around for his conversation with TED Fellows Program Director, Lily James Olds.

1:25It's coming up.

1:31My name is Cesar Ramirez-Armiento. I'm based in Santiago, Chile. I'm a protein engineer and designer. Proteins are macromolecules which are composed of amino acids. They are made of 20 different types of amino acids. They are represented by letters. So you can imagine an alphabet of amino acids. And you can imagine that these amino acids are connected to each other like beads on a string. And so that allows for them to come together in different geometries. And so they get a shape. They get a three-dimensional structure that allows for them to dictate their functions. We have many different proteins with many different shapes that actually perform different biological functions in cells.

2:12They allow us to digest food. They allow us to transport ions for electrical signals to go through neurons. They allow for the expression of different genes that regulate how our cells or how our body responds. Proteins are the workhorse of cells. They are like a toolbox for cells to do whatever they have to do. Proteins have been evolving for millions of years for performing functions that are important for cellular life. They have been perfected by nature to do what they do now. But when it comes to problems that are important for humankind, like plastic contamination, carbon dioxide problems in health.

2:48We want to make them better. We just don't have a thousand years to wait for it. We have to do it now. Protein engineering, in short, it's asking yourself if you can change the amino acid composition of your protein and by doing so, if you can get improvements in some properties of that protein. We can use different tools for that. We can use experimental approaches. We can use computational approaches. but overall what they are doing is that they are changing this sequence of amino acids that compose proteins in order to improve these properties. This is like giving nature a little push. And that's where the use of artificial intelligence comes in.

3:29In the last five years, we have seen breakthroughs in artificial intelligence for designing proteins that we never imagined. They allow us for designing new protein structures, new protein shapes that encode bespoke functions for solving all types of problems. Before the advent of AI, the success rate for protein design was about 1 % or less, which means if you created 100 proteins with 100 different sequences, maybe one of them would work. Now with the advent of AI, we see about 10 to 20%. So if you now take your hundred sequences that you generated in the computer, about 20 of them will actually have the desired activity.

4:08And some of them will be actually better than the input sequences of the protein of interest that you're working with. When I was a kid, I was interested in arts because it was allowing for a space for creativity. But then when I was in high school, I opted for science because I saw that I could provide much more for the benefit of society by pursuing science instead of arts, in my case. But I think both disciplines are actually playgrounds for creativity. For science, artificial intelligence is another tool for coming with creative solutions for different problems. My dream future for protein engineering is that we have a strong community of protein engineers and designers in Latin America.

4:49so that we can create solutions for problems that are specific to our countries. We are usually not fully aware of the advances of the use of artificial intelligence for protein engineering and design that is happening in other parts of the world. But at the same time, we have many people that are interested in creating new proteins. And so the idea of working in Chile is that we can actually create a critical mass of scientists that can work on these problems. We are actually working on how to educate the next generation of scientists from Latin America and how to use these tools. I always had this belief that we had to come together to try to do something bigger than what we can do as individuals.

5:27We can think about other compositions of nature that we haven't seen before. In the case of proteins, we can navigate untapped terrain that nature hasn't explored yet. We can navigate through those landscapes of different protein structures, different protein sequences, and see whether those spaces that contain these protein structures and sequences are actually good for resolving the issues that are the most pressing problems for humankind.

5:58And now a special conversation between César and TED Fellows Program Director Lily James Olds, coming up right after the break.

6:12Hi, César. Hey, how are you doing? Welcome. Thanks. I'm so excited to talk to you today. Me too. Very excited to talk about different things today. Wait, can you tell me where are you right now? Yeah, I'm in Louisville in Kentucky. I've been four days into a festival called Louder Than Life, in which one of my favorite metal bands have played. Incredible. What's been the highlight so far? For me personally, it was a slip token. I've seen them live once before in Germany, and now I had the chance to see them again. They released a new album this year. And they have, yeah, they have a huge fan base right now.

6:49They're exploding and they're like a really cool show to see. Dude, these images from Sleep Token look insane. I'm looking at the photo. I'm like fascinated. Yeah, they're good. Okay, I gotta listen. This is like pretty epic. Yeah, I mean, something that is very interesting about Sleep Token is that they combine different music genres into like one piece, right? They combine from hip-hop and jazz and soul and R &B and metal and deathcore. It's like everything just mixed into one piece of music. And I think of the work that we do in Collab and our collaborations with other people from my country and also from other countries as something similar.

7:33that we're trying to put a lot of effort into combining different things to think out of the box and do something different from what we have done in the past, which has been only learning about proteins and then characterizing them. Now we're thinking more about, oh, what if we put this protein in a cell and then we do whatever we were thinking about doing with just proteins. Now we do it with living cells and we provide a solution for that. That's amazing. So you talk about how using AI for protein engineering is like, I like how you say, giving nature a little push, you know, speeding up the process.

8:10Can you give me one or two concrete examples where AI engineered proteins are being used to help solve a problem and what impact they're having? Yeah, actually, one of the things that we were thinking about a lot with one of my colleagues in Chile is about how to create new proteins to put them into cells that are very resilient, to conditions in mining so that we can use them for bio-leaching, which is like try to recover different minerals using biotechnological solutions. And those are kind of the things that it's like try to combine very disparate scientific endeavors into one piece and then try to see if that works or not.

8:53I think one of the cases that we're seeing a lot of impact right house and the elimination of pollutants from the environment or trying to develop technologies to do so. And so there's a few companies that are working now on degrading plastic. And these proteins that perform chemical reactions are called enzymes. And enzyme design is a problem of its own that is like very difficult to tackle. But there's one company in France and there's another company in China that are working on developing with the use of AI different enzymes that can actually degrade different types of plastics. And the idea behind it is that we are then using that plastic as a feedstock for creating new plastic afterwards.

9:38So the enzymes, what they will do is they will decompose the plastic into small molecules that you can use them for making new plastic afterwards. In the best scenario, it will be like an infinite recycling process. And that would be great for humanity. And how does it work exactly? Can you tell us a few more details? So biological information goes from gene, which is on any living cell's genome. So that's DNA. And DNA encodes proteins. So we go from DNA to proteins. What you do in the computer is that you go from protein back to DNA. So you have different scenarios. And for them, you have different ways of working with them.

10:15And so the idea is that you can train artificial intelligence models on this information about the sequence of a protein. So the sequence of amino acids that compose a protein. Or you can train models on the structures of proteins, or you can train them on both. And then in the computer, after like a few days or weeks of work, you will have a set of different sequences that will encode these structures or these different protein functions. and then what you do after that is that you backtrack those designs from protein information into DNA information, so another form of alphabet, and then you purchase those genes from these companies that synthesize your genes and then put them into different bacterial or animal cells for expression of these proteins and then testing them out in the lab.

11:07And hopefully afterwards, you will test them out in like real cases in areas such as pilot plant for like plastic degradation or in animal models for testing for like how to cure a disease. That's so wild and futuristic to someone like me who is not doing this every day in a lab. I'm thinking about a conversation we had before, Cesar, where you spoke about kind of being inspired by snails and being inspired by natural processes and then putting that into your work in the lab. Yeah. Yeah, that was kind of a funny thing that happened when I was younger. I think maybe I was like eight years old or something like that.

11:50My mom, she had some like plastic pottery for plants that she was like growing in the garden. And she said that the snails were eating through them. I was like, there's no way that that can happen. But the idea remained there for like a long time. I was like thinking, oh, maybe it's possible. But I just remembered that memory, right? And then when I was in university, I was actually learning about biochemistry, learning about proteins and enzymes and all of these things. And then we had a class about enzymes and how they perform different chemical reactions. And one friend of mine said, oh, what if they degrade plastics?

12:31And I was like, well, that doesn't exist. But little did I know that enzymes that could degrade plastics were being discovered. So the first one was, I think, 2003 or something like that. So that turned into my research topic when I became a professor. So it's kind of a cool origin story, I would call it. Yeah. I love that so much. I remember that with snails in the backyard as well. I'm curious, is there a particular local challenge in Chile or Latin America that you think protein engineering is especially well-suited to tackle? Yeah. I mean, there's a few. So we have a huge fishing industry, right?

13:14And that fishing industry for some of the crustaceans that we're extracting from the sea, a lot of it's not consumable. A lot of it's waste. And then almost all of the technologies for reutilizing those waste from crustaceans are typically treated with very harsh chemicals. And so trying to develop new technologies using enzymes for achieving the same result, which is like treating these waste for like creating fertilizers or creating other types of solutions that can be used afterwards. But instead of using chemicals, using enzymes that will perform the same chemical reactions, but it will be like environmentally friendly because you're using like a biological mean for that.

14:00We have been discussing with a few colleagues in Chile that we can try to pursue. And what's a new protein designer structure that you are really excited about right now? And why and what will it help to change or make better, do you think? Oh, I'm very excited about Chris Ball, another TED fellow, his company, AI Proteins. And what they're developing in his company is that this very, very tiny proteins, very few amino acids, right? When you make them too short, they don't fold into like a shape. Imagine like if you have like a piece of rug and you want to fold it. If it's too short, you cannot fold it, right?

14:36But if you have like a piece that is long enough, then you can fold it. So proteins also fold upon themselves. And so they're making these very, very tiny proteins that actually fold upon themselves. So they have a shape. And that shape is complementary to different target cells that have proteins that are involved in cellular processes that are related to different diseases that can go from like different allergic reactions to even like treatments for cancer. So the idea is to develop like this very, very tiny proteins that you can use as a pharmaceutical, as a drug. And that would be a better solution than developing different chemical compounds that do not offer the same capabilities that these proteins have.

15:23So I'm really looking forward to see what they do with it. The advances that I've learned about from you are just so incredible. I'm curious with all of these examples you're giving and how much AI is making protein design more successful, where do you see the field of protein design in three to five years from now? What do you think will be possible? You've outlined a little bit of that, but what does that future look like in your best imagination? Yeah, that's an interesting question. So I think that I'm seeing a lot of advances right now in making new enzymes. So enzymes are very difficult to make.

16:01They have very specific sites on the protein surface. So if you imagine that you have like a sphere as a protein, then they have like a little hole on the surface that is called the active set. and the chemical reaction actually happens on that site and that site alone, which means that there has to be very specific amino acids from your protein in very specific positions. So the methods that we had like a year ago were like pretty bad at the enzyme design. And so before we will take an enzyme that we know it has some activity for some thing that we wanted to do, like there's a lot of enzymes that do plastic degradation, so we will improve the sequence, but we will never change the structure.

16:42But nowadays, there's a lot of methods that actually can afford that. And so the idea is that you can create new structures that have never seen before in nature of enzymes, of new enzymes. And that allows for thinking about new chemical reactions that we can create from scratch. So that's very exciting. And I think that the field is moving forward very fast towards developing these new enzymes or new chemical reactions. I think the place that my mind and I'm sure many others go is like, what are the risks and the dangers and unintended consequences of designing proteins that nature hasn't made before?

17:18Is this something that you're thinking about? Yeah, I mean, a lot of people talk a lot about the guardrails that we need for different AI technologies. So the risk with all AI technologies is their dual use. So you can use them for benefits or you can use them for harmful impact. So viruses are composed primarily of proteins and they infect our cells. with all of these AI architectures for protein design. And you can think that somebody can take a given virus and then can use these AI models for protein design to improve their transmissibility or their infection rate. So those are like harmful decisions.

18:05But fortunately, there have been different approaches from governments and also from companies to try to assess the risk of these models with different evaluations and try then to make sense of what will be the risk that we can have when releasing these models to the public. Just to go a step further, how do we regulate it? I mean, obviously regulation always lags behind innovation, but I'm just curious, can you speak to the current relationship between your work and the policy and protections in place And, you know, what do you hope this relationship will look like as this technology continues to grow that both allows for the innovation that is obviously creating the possibilities for incredible problem solving for humanity and also those dangers that you're touching on?

18:58So a bunch of scientists, including myself and other very well-known scientists in the realm of artificial intelligence for everything about biology, not only about protein designs, signed some guidelines that were called Responsible AI for Biodesign that indicate that we will do significant efforts to identify risk in the different models that we develop for different types of biodesign. using artificial intelligence and then try to indicate those risks whenever we release the models or try to do what people call unlearning, which is try to make models to somehow not capture this harmful potential when you release them to the public.

19:50For now, you still need an expert scientist because they are not very easy to use. But if you combine them with these large language models that allow for having a conversation with your computer without having the expertise for creating something. So the risk over there is that any person can, in principle, ask to, for example, to one of these language models, can you please create a very harmful biological thing? Both the UK and the US and also the European Union have AI safety institutes. And what they do is that they evaluate the risk of using these different technologies. And so they have these different thresholds for determining whether it's a very high risk and we have to do something about it or it's very low.

20:35And then we do have to keep an eye on it, but without oversight. Yeah, I mean, obviously so much work still to be done, but it's always comforting to hear the things that are in place in terms of that kind of thinking and rigor. I guess that leads me to think also, you know, things are shifting so much, obviously, right now in the global landscape of science, you know, recent policy changes in the US around climate science and otherwise, the example that you just gave of, you know, who needs to be doing this work in terms of regulation around AI. Do you see this as an opportunity for other countries to kind of step in?

21:14I mean, I think, yeah, there's an opportunity for other countries to lead it. There's efforts, I know, in Europe. Denmark is putting a lot of funding into AI for biodesign. The UK is also investing a lot of funding into that. There's efforts, at least in Latin America, to also, like, step on these things and try to take the lead. So my country, actually, Chile, is leading for a while an initiative to ascertain the risk and the ethical usage of artificial intelligence for different purposes. And so there is an opportunity for using artificial intelligence for protein design methods in the country and be a leading country in Latin America for that.

21:56But yeah, since the U.S. has been experiencing some changes in the last year, yeah, there's a lot of countries that have been like stepping up and trying to take the lead in putting the sun. Okay, I'd love to touch on creativity for a minute and the relationship between art and science a little bit because I know it's something that's important to you. As you know, my background is also in the arts, in theater directing and film. And I'm curious, can you tell everyone a little bit about your background in the arts, Cesar? I think that arts and science have been always on my mind. When I was seven, I had the unfortunate reality of my dad passing away.

22:37And like after that, I remember that in high school, I kind of struggled a little bit. So my mom decided to put me into a lot of classes outside primary school and high school, which will be a lot of arts. So the first thing that I did was to learn how to do oil on canvas when I was like eight or nine. And yeah, I did that for several years until I was like 15 or something like that. I also started learning how to play the guitar by that time. I started also doing acting in high school. And so for me, arts and science are huge spaces for creativity. You can try to push the boundaries of what you can do, expand your horizons in terms of what you can create.

23:35Arts and science, I see them as like similar programs for like exploring those boundaries in creativity. And talking about proteins like between scientists is like kind of easy, right? But it's very complex for the citizenship. And so I've been thinking a lot of that arts can be a very powerful tool for actually expressing what these very complex topics are. So I've been thinking about which artistic renditions can actually provide an understanding of what a protein is and what they do. I think that by connecting art and science together, you can push the boundaries even further. I love that. I think that's so fascinating.

24:19Okay, my last question is just, what is something you're really scared of right now? And what is something that's giving you hope? I don't know. I think that after the pandemic, I'm always scared about, oh, what's going to come next? Right. So like, is there going to be another pandemic like that? And how are we going to respond to that? Instead of like being concerned about like our capacity to respond to things, I'm more concerned about like human behavior, which is like we're very forgetful. And we might forget that we were like, at least in our case in Chile, we were in quarantine for a while.

24:53And I don't want to be in that situation again. So what I'm hopeful for is that there's a lot of investment and interest also from scientists to work on solutions, biotechnological solutions for combating climate change. And plastic degradation is just one example, but there's a lot of efforts for trying to eliminate greenhouse gases. We know that there are some protein-based solutions and also some cell-based solutions, and there's a lot of interest for investing on them. So I'm very hopeful that in the future, and actually in the near future, we will see a lot of startup biotechs that are working on climate change and successfully.

25:39So that's going to be great. That's really exciting. Well, thank you. As always, this has been a really fascinating and energizing conversation. So thanks so much, Cesar. Happy to be here.

25:54That was Cesar Ramirez Sarmiento, a TED 2025 Fellow. To learn more about the TED Fellows program and watch all the TED Fellows films, just go to fellows.ted.com. And that's it for today. This episode was produced by Lucy Little, edited by Alejandra Salazar, and fact-checked by Eva Dasher. The audio you heard at the top comes from the short film made by Divya Gdenghi and Owen McClain. Story edited by Corey Hajim and produced by Ian Lowe. Video production manager is Searing Dolma. Additional support from Lily James Olds, Leonie Horster, and Allegra Pearl. TED Talks Daily is part of the TED Audio Collective.

26:33Our team includes Martha Estefanos, Oliver Friedman, Brian Green, Lucy Little, and Tonsika Sungmarnivong. Additional support from Emma Taubner and Daniela Ballarezzo. I'm Elise Hu. I'll be back tomorrow with a fresh idea for your feed. Thanks for listening.