Biotech 2050 Podcast

Revolutionizing Proteomics: Sujal Patel, Co-Founder & CEO of Nautilus, on Drug Development

Synopsis:

Sujal Patel, co-founder and CEO of Nautilus Biotechnology, discusses their innovative work in proteomics and its impact on drug development. Sujal shares his transition from tech to biotech, the formation of Nautilus with Parag Mallick, and their revolutionary approach using multi-affinity probes. The conversation highlights the importance of proteomics in drug discovery, the broad applications of their technology, and the significance of product-market fit and fiscal discipline in building a sustainable business.

Biography:

Sujal Patel is the co-founder of Nautilus Biotechnology, a life sciences company working to create a platform technology for quantifying and unlocking the complexity of the proteome. Nautilus’ mission is to democratize access to the proteome and, in doing so, enable fundamental advancements across human health and medicine.

Sujal founded Isilon Systems in 2001, a storage company built for the future of unstructured, file-based data. In 2006, Isilon completed one of the most successful initial public offerings of the year. EMC (since acquired by Dell) acquired Isilon in December 2010 for $2.6 Billion, the largest acquisition in EMC’s history. Sujal served as the president of EMC’s Isilon Storage Division from the acquisition until November 2012, driving significant revenue growth, market expansion, and organizational scale.

Prior to EMC and Isilon, Sujal served in various engineering roles at RealNetworks, Inc., in part as the chief architect behind the company’s second-generation core media delivery system. Sujal holds nineteen patents in the areas of storage, networking, and media delivery and five patents for innovations related to the development of Nautilus Biotechnology’s technology. He is a well-known speaker on entrepreneurship and has received a variety of industry awards.

Currently, Sujal serves on the board of directors at Qumulo and Rainier Scholars and helps direct the philanthropic efforts of his family’s foundation. He graduated from the University of Maryland College Park in 1996 with a degree in computer science.

Duration:: 36m
Broadcast on:: 11 Jul 2024
Audio Format:: mp3

(upbeat music) - Hello and welcome to the BioTech 2050 podcast. BioTech 2050 is the think tank chronicling the disruptions changing the biotech industry over the next several decades. Check out our website at BioTech 2050.com. I'm today's host, Alok Tai. I'm the CEO and co-founder of Vibe Bio. Vibe is an investment platform focused on the biotech industry. I'm really excited today to be joined by Sejal Patel, the co-founder and CEO of Nautilus Biotechnology. Today, we're gonna be talking a little bit about the proteome, some of the work he's done in the tech world, as well as some of the exciting things they're doing to drive biological insights or drug development. Sejal, thanks so much for joining us today. Really appreciate it. - Thanks, Alok. I really appreciate the opportunity to talk to your listeners. - Maybe to kick us off, love it if you could share a little bit about your background and how you got to where you are today. - Great, I'd be happy to. I'm actually a unique hybrid. Having spent most of my career in the tech world before moving over to biotech about seven and a half years ago, I entered the workforce after college and as a software engineer in 1996. And I spent the first four and a half years of my life working on the backend technologies on a company called RealNetworks that brought audio and video to the internet for the very first time. And one of the big challenges that our customers face as we were beginning to build big media infrastructures was that storage was a huge problem. Data storage was really built for, if you think back to the '90s, built for tech space information. It was built for databases, things like credit card numbers that are associated with an airline ticket information. They weren't built for video and audio and big source of unstructured data. And having always wanted to be an entrepreneur and always thinking about solving problems in the world, I decided to go and start a company with another one of my colleagues at RealNetworks that focused on building a storage system for unstructured data. And that company was a great success. We got, it started just after the dot com bubble in 2001 and went public in 2006. And then ultimately sold that business for 2.6 billion in 2010. Today that business is super successful. Multiple billions of dollars revenue. It's highly profitable business was profitable before we sold it profitable still today. And that was a really great journey. One of the things that I learned on that journey was a lot about biomedical research. The life sciences and biomedical research vertical markets were big customers of ours. And that really started in '04 and '05 as the next generation genomics era really began. We had a lot of customers in various vertical markets, including proteomics. And in 2004, I actually met a guy named Barack Malick who was at the time running clinical proteomics at the Center for Medical Center. He became a big customer of ours 'cause he had a lot of proteomic immitchated to store. And I got to know him really well. And about 11 years ago, he went off to Stanford to start a new lab sitting at the intersection of computing and biochemistry and data science. And my wife and I have been so impressed with Proog for over a decade that we've philanthropically supported his lab for more than a decade now. And that built close relationship with us. And our paths really became intertwined after I sold my last business in 2016 when Proog called up one day and said, "Hey, I've been working on this challenge of looking at proteins in sample." And you know, it's incredibly important to the world because proteins are the functional unit inside of the cell. They're most of our drug targets. So 95% of our FDA approved drug targets. They're most of our molecular diagnostic targets. And so if we can't understand proteins in sample, we really can't do a good job of building precise drugs quickly and cost effective. Can't do a good job of delivering diagnostics that enable precision medicine. And he said, "In 2016, I came up with this new idea." And I sat down with Proog and I was like, "I did this idea as crazy and I can get back to try and figure out what to do with my life." Or, "This is gonna be an enormous innovation for the world." And Proog and I got this company, Nautilus Biotechnology off the ground at very end of 2016, beginning of 2017. That was my foray into the biotech world in seven and a half years now of that company and our product through early research, feasibility, early research, and laid into our development site. Here, I'm happy to talk more about that as we get through this podcast. - Amazing, I think the first one that kind of really intrigued me about your background is this transition from building software and hardware and tools for a variety of industries, but end up honing in on the biotech landscape. And then now moving into a far more focused kind of biotech platform and business. There's a lot of folks, to be honest with myself, who include him, who are also both making the transition, I was interested in that transition. Curious if you could walk us through that experience, what you were able to translate from running and building a company in the tech space to now in the biotech space, as well as what things you had to learn and pick up net new to be successful with Nautilus. - Yeah, let me touch on a few pieces of that. I think the first piece of that transition is really motivation, right? I had an incredible journey in tech when I was exclusively in the tech world. I spent four and a half years at a company that was at the forefront of a new technology in the birth of the internet, the era of the beginning of the internet. I spent four and a half years there, felt like dog years, felt like 20 years, jumped into a startup where we built a business from nothing to a business that was closing in on a $100 million revenue in a quarter and then growing that to over a billion dollars run rate just in the course of the two years after our acquisition. So really fast journey and a really exciting one. But for me, what I was thinking about next is, hey, I want to solve a really big problem. That's what makes me tech. I like solving huge, big, hairy problems, but I want to do it in a space that's closer to impacting humans. And that could mean working on something in clean tech, which was interesting to me. It could meant going into something that was related to medical research. And on the life sciences, medical research side, it was an area where I'd spent quite a bit of time at a surface level understanding the needs in the marketplace and servicing the marketplace because it was a big customer segment from my last company. So it had a really interesting place for me in my heart wanting to go and do something. So from there, okay, the desires there, Karab came up, it showed me a huge problem in this space that you really could go tackle. And it was an area where I knew I could bring bunch of expertise over from the tech world. So first and foremost, in tech, we solve hard problems. Here we solve hard problems too. And because we're building a new platform, it's not just a chemistry problem. It's not just a biology problem. We have our company, biochemists. We have fabrication engineers. I have surface functionalization experts which work on semiconductor chips. I have software engineers, hardware engineers, electrical, mechanical, a single molecule biophysicist. I have one of everything that you can imagine and all of those pieces have to integrate together. That sort of complex systems engineering is something that really is core to my experience and we had to do in the last place too. And I think a lot of those skills transfer over. I think that from a business model perspective, the direct sales force that you would use at a company like ours and the direct sales force that you use inside of a tech company, any software company really is exactly the same. What I found is that the marketing and the sales is exactly the same. We just changed all the titles, right? Instead of a sales engineer, it's a field application scientist. And instead of a service engineer, it's a field service engineer. It's just the total set change. But the skill transfer is really quite interesting and a little surprising. Now, there are some areas where the skills don't translate at all. I walked in and put on a whiteboard all of the different pieces of the solution that we have to build and how it works. And it took a long time to understand and I didn't understand the core chemistry, biology, physics. I forgot all of those classes through high school at college. And so one of the first things that I had to do was really drink from a fire hose and learn as much as I could about space first. I had to get to the point where I had basic knowledge. So I got on YouTube. I found every college level class, every instructional video I could, I watched them at 2x and got to the point where they could go and at least read some research papers and start to consume information that was more specific to what we're doing. And over the course of the next two years, I think I read a thousand papers. Once I got to the point that I had this base level of knowledge and every day for those first couple of years when the company was really small, just prerogged myself and maybe a handful of people, every day I would go to Prague and I would come with a list of dumb questions. I'd call him a dumb question at the day list and he's a professor, he's very patient and he would answer my questions sometimes he'd be five minutes, sometimes it'd take two hours. But I really had to build up this huge base of knowledge to be able to run a company like ours effectively. And so at this point, I think that the marriage of all of those skills together and the marriage of my and Prague's experience coming from this problem from two different avenues is super important to us as a company and really unique. - One thing that sounds really impressive is obviously the depth to which you have to dig into the science and the pace at which you were able to do that, right? As you mentioned, right, there's probably entire PhDs or multiple PhDs that would have to go into doing what you did, but it sounds like the curiosity and the motivation really enabled you to pick up that information quickly. And if I'm hearing you quickly, it also sounds like the balance of the execution of company building was more or less transferable from prior endeavors. Does that sound right? - Absolutely right. And I think that company building is a really difficult thing. And I think that one of the skills that I have in company building that has translated really well is that I always get into a new business and they focus first on product market fit. What are we going to build? And why is it absolutely necessary for a customer and why do they have to have it? And what benefit is it going to bring to their business? And I think that 90% of the time, if startups fail, it's because that product market fit wasn't quite right. And we started focusing on that very early on in our customer's life. When we went out and we did a seed round, one of the things that we had to do was start talking to customers and start to understand what are those use cases, was Parog's initial guess as to what we were going to do with this product, correct? And that was an interesting process for us. Parog is a key opinion leader in the proteomics space. He already knows 20 things he wants to do with the platform we're building was available. But I had to go and validate that and then also spread our horizons a little bit, see what else is out there. And I had Parog introduce us even before the first round of funding to 20 customers. And I did a call with him. We learned, we probed, we asked a lot of questions. And then I disinvited Parog from the rest of the calls. I did them myself and I probed and they asked questions about what are the price points of the products that you use today. Are you going to pay for it? If we were able to provide these differentiated capabilities, how would you be willing to pay? How much more? What capabilities are most important to your research? If we were able to deliver this, where would the bottleneck be next? And that exploration, which we then expanded after that first round of funding to hundreds of customers is super, super critical. And that's the skill that transfers really well for company building in any space. The other thing that's served us very well is that at our last company and at this company, we pride ourselves on being really scrappy in how we build our organization. And when we started this company 2017 to 2020, the capital markets were just on fire. You could raise money easily and companies that were competing with renew approaches and proteomics were spending two or three times what we were spending. We have been disciplined since day one. We raised roughly a half billion dollar since inception. I still have on my balance sheet well more than half of that money on the balance sheet available to invest in the future, not already spent behind us. And we haven't raised money in years. And that discipline of really building a scrappy business and right sizing the organization, it's a little jarring sometimes to people who come from companies which spend money more and more liberally. But today, in a capital constrained environment and in an environment where making every dollar count is important, it's been incredibly valuable. Like those are the sorts of lessons that translate to any space I think are serving this company really well today. - Yeah, amazing. Looking at fiscal prudency, I think also enables you to be the offensive when opportunities arise, right? Especially as you land product market fit and maybe see other opportunities in the markets. That's awesome. - If you're an HR or hiring manager in biotech, you know all too well that the pool of experts seeking full time employment is shrinking. Filling key full time positions can be a long, drawn out ordeal. It can slow the pace of execution and growth. Throw away the old hiring playbook. Now you can build a biotech dream team in a fraction of that time. Find out how. Visit chlora.com. Chlora, talent optimized. - Coming back now to a Nautilus, really exciting to hear an inspirational to hear your transition from tech into the biotech world, would love to hear what the early days of Nautilus was like. It sounds like you had deep trust and collaboration with Parag while he was an academic. We'll have to hear what those early days were like starting up the company as well as some of the foci you have now on the proteome and perhaps among the early folks making a big bet in that space. - Yeah, the early days of Nautilus were really interesting and they were very different for me because having me and one other person in the company is very different than running a 2,000 person organization and trying to manage something where there's millions of dollars of revenue per day. For us at Nautilus, if I'm kind of just distilled down the crux of the idea behind Nautilus, in biology, if you want to identify a molecule, the simplest way to do that is an assay that's been used for decades. I have an antibody that's specific to a AGFR molecule, the antibody binds the molecule, somehow I know that binding event occurred and I say, "Hey, there's an AGFR molecule." Our technology is very different. What we're doing is building a completely new class of antibodies that we call multi affinity probes that essentially don't just bind one protein molecule. They bind thousands of different protein molecules and they're very nonspecific. So one antibody may bind 5, 10% of the proteins in the human proteal. And if you're an analytical chemist, you'll tell me that's the world's worst antibody. I don't get any information from that. But what Parog's idea was in 2016 was that if I could take a molecule and get a question with one antibody and then ask a different questions with a second antibody and a third and fourth and a fifth, by the time I had hundreds of those data points, I could combine those data points together in silico and come up with a shockingly precise identification of what the molecule was. And if you could do that in parallel for billions of molecules at its time, then you would be able to deliver this type of solution that has the scale to match the proteome. So that's essentially what we had to go do is we had to go and figure out how do we go and build those types of antibodies? How do we build an array of them? How do we go and build all of the different pieces that it would take to be able to take all of these measurements from different antibodies that are binding or not binding proteins that combine those together computationally to go and come up with an identification of the molecule and then do that in parallel billions of times so I could understand what's in a sample completely. So that's the end to end challenge that we had to go and build. - Yeah, amazing. And one of the things that you had mentioned that really caught my ear when we were catching up earlier is how you're able to ingest essentially any organism and deduce the proteome within it. Love to maybe start to dig into some of the implications of the proteome as well as some of the ways in which you're starting to see that information start to translate into true insights that would it be from a drug development standpoint or a biology standpoint to help patients ultimately. - Yeah, and that's a really interesting question. I think that one of the great things about our solution is that we're building a solution that is agnostic to the type of sample and the type of organism. And so we've talked to customers that want to go and use it for drug discovery. We've talked to customers that want to do animal research, which is a critical part of a lot of different medical research types of applications. We've talked to customers that want to build a better-tasting hamburger and want to use proteomics to do that. And so across those types of markets, agricultural science, environmental science, even affecting climate change and the long run, proteomics has a significant plan. And so the thing that's exciting about our solution is that any organism that has DNA, we can use existing technologies to go and figure out what the DNA is. And now we know what all the possible proteins are inside of that organism. And then with that as an input, we can combine all those data points that I was talking about and be able to tell you what proteins in that front that are derived from that genome that we pulled from the organism are. And that's really important because human is, of course, the biggest and most important market today. But on the way to human, there are models using different bacteria, they're using different animals. There are applications outside of human as well. And being able to surface all of them in one form is a pretty important advantage. If you think about the proteomics world today, the gold standard that exists today is a technique called mass spectrometry, which is really a class of products that were built for the research of atomic reactions and atomic materials during the nuclear bomb programs of the last century. And we've adapted that technology to do some proteomic analysis by measuring the weights of the different peptides that are the constituent parts of the proteins and then backing into what proteins are an example. Those technologies are one of the only other agnostic to organism types of techniques out there. But the limitations is that they have very poor sensitivity and they can't dig into a sample very deeply so they don't see the vast majority of the proteins that are in a sample. So today, if you're developing a new drug using the techniques that exist, you really have a very incomplete picture and you're trying to build a very precise drug molecule and understand how it impacts different organs in your body and whether there's cross-rativity, but you have a very narrow window that you're able to see into what's actually going on. - Yeah, it's amazing. When we think of, for instance, that David Wald, one of the founders of Illumina is a close friend, has an SAB that for a company I started previously. And obviously, genomics has had a huge revolution of his important underpinning from biology. But at the end of the day, biologically, proteins are really what affects kind of change in the body, despite what the genomics may or may not do. So I'm curious as you start to see the variety of different places where nautilus could have a direct impact, you mentioned the animal model side, you mentioned on the in vitro testing side, you mentioned even from a biomarker standpoint. Curious if there's one thread within the market that's really pulling you forward faster than the rest, or are you seeing that the broader platform play with a cohesive story around it? That's having the greatest attraction. - It's a really interesting question, and you alluded to the difference between the genome and the proteome there. David Wald and Illumina, which he was part of in the early days, has done an incredible job democratizing access to the genome. But the average human, like you or I, has 37 trillion cells, and other than errors and cancer, they all carry the same genome, and they carry the same genome from the day you're born, the day you die. They don't carry any of the dynamic state of what's going on. They don't do any of the real work inside of cells. And if you want to understand what's going on in a cell, you have to understand the proteome. 'Cause every cell's got a different proteome, which is makeup of all those proteins, every cell's proteome is changing constantly, your proteins will be different, depending on what you ate last night, and whether you're getting sick or not. And so measuring those proteins is really important. So when we talk to customers, the interesting thing first and foremost to think about is that there's two really big customer segments that are important to us. One is that on the commercial side, it's the pharma and DX companies, and then on the nonprofit side, it's academic and nonprofit research, which are both very big markets. Inside of both of those types of customers, there is basic science and translational science that's going on that's focused on improving human health. And so inside of the pharma companies, that's really developing better drugs. And inside of the DX companies, it's either detecting disease earlier or better, or understanding what therapy is the right therapy, or monitoring whether therapy is effective. And so if you double click on each of those, there are some common themes where customers are looking for help. On the drug development side, for example, target discovery is a really big piece of the drug development process. If you want to understand how you can build a new drug for arthritis, you should look at some cells that are afflicted with arthritis and some that are healthy. You should go to the cell surface where there's lots of proteins that are expressed that understand where are the rare biomarkers that differentiate healthy in sick cells. You should go and develop compounds that may regulate or down regulate a protein or a panway. And then you should understand, using proteomic analysis, are those targets specific to the disease cell that I'm trying to target? What's the therapeutic window where I can affect something, affect or change the proteins regulation and have a positive impact on a human? I need to be able to, after I've got that target discovery done, I've got to be able to look at potential drug compounds and say, "Hey, what's the mechanism by which they're acting inside of the body? What do they do to the protein network inside of a cell?" To get past that, I have something that might be a good drug. What does that do to the heart, to the kidney, to the liver? It doesn't have any toxic effects. Are there any effects that occur that I'm not able to see with today's technology? All of these are applications where you can use proteomics. And when we talk to scientists who are really forward-thinking, they envision a day where you could take all of this biological insight, combine it with computation and do a lot of this analysis without having to just take a potential compound, put it into an animal model and see what happens, and then go to human and see what happens, because the see what happens has led to a lengthening of the cycle time to build a new drug. It's made it incredibly costly, and the odds of making a drug that's successful and gets all the way through the FDA successfully into the hands, patients, is very small. When we think about first and foremost, those big applications where we can have a really significant impact, those are the types of applications that are most interesting to us. On the DX side, you have the same sort of story. What's a specific biomarker that's going to be indicative of disease or tell me about therapeutic response, or help speed pick whether I should use therapy A or therapy B? And that's for pharma companies, a really interesting area as well. We've talked to a number of pharma companies that want to use DX to make their drugs better, right? I have a new drug. It works incredibly well on 30% of the patients, but it doesn't work at all in 70%. And so how do I know if this is a drug I should give them or not? The answers are likely in the proteome, but for a lot of these types of questions that these customers want to answer, they don't have a good tool that it's going to be able to give them a solution today. Yeah, that's awesome. And I'm curious, in your case, given that the ability to inform a lot of these different critical scientific questions, do you see yourselves needing to think about which diseases people care about, which drugs they're pursuing, which pathways are most relevant? Do you see yourselves really having to think about the development path of the drug, or is it really more focusing on the science and the mechanisms that underpin the biology? If the little of both, there is a great deal of knowledge that's to be gained by just having highly sensitive platform that can look at a lot of protein molecules inside of cells, inside of blood serum, and giving that data to a customer. But we know that proteomics has some applications that are really, really more critical and going to be more interested by being able to measure the whole proteome. Things like cardiology, neurology, autoimmune disorders. And in those sites of applications, there are more specific questions customers already wanted. For example, we're working with the Genentech, this is one of our early collaborators on understanding the pattern of modifications on the tau protein. Protein is a key neurological marker that is a protein that has various dysfunctions based on how their molecules phosphorylated. And there's a similar type of mechanism that's present in patients that have Alzheimer's as well with a different protein. And so being able to answer some of these more specific questions that are disease specific is also interesting for customers. And it's fun with our platform is we're not at the point yet where we can show you what all the proteins are in a sample. We still have solid Europe development to get to that point, maybe more, maybe less. But because parts of our planet form have matured, we are able to answer some questions like understanding the detailed phosphorylation landscape of a molecule like tau because we can already take a tau molecule and probe it over and over again with different antibodies that are specific to site specific phosphorylation events and give customers information that there is no other way to get today. And so we've been showing at various conferences data with Genentech and with other customers Amgen that show how you can get detailed information on modification of proteins. So to answer your question, it's going to be a little bit of both. There's big parts of our platform that are universally usable by all customers, but there are also very specific questions that our customers have that are critical to different disease areas where we are getting involved and we will do a lot more. Yeah, amazing. It motivates a different question, too, is that given the level of effort that goes in on your side to help probe these really unique kind of biological changes, as well as the different types of industries that are interested in it, as well as the different types of insights you can derive, it motivates a question in my mind around the business model and how you think about monetizing this sort of capability. I feel like today, especially there's a lot of discussion about how platforms broadly can monetize their insights, given that the vast majority of the public markets and pharma companies care about the asset, but there does seem to be some value in the technology and the underlying platform as well. Would love to hear your experience as you explored different business models and maybe if you could also provide some insight for budding entrepreneurs in this space of how they should be thinking about the business models that will really enable them to succeed. Yeah, this is such an interesting area to explore. We as a company, when we got started about seven and a half years ago, we spent a lot of time thinking about how do we want to bring the technology to the market. We could go and build a proteomic measurement platform that has better sensitivity and capabilities than anything else out there, and we could keep it to ourselves and build our own drugs. Or we could find targets or help customers with toxicity profiling and partner with them and get some upside into those drug development programs. We could go all the way to the other side and say, I'm going to build a platform and give it to the customer and let the customer do their analyses and they get the upside. And we spent a lot of time blogging myself with our early business team, with our board members and advisors thinking through this. And I think the decision to build a platform, meaning we sell it to the customer and make the discoveries and monetize them, I think is important for a number of reasons. First and foremost, as a company, we wanted to find the highest velocity way to get a platform into the hands of as many customers as possible so that it could make discoveries that do good for human health. That was like a poor goal that we had. But in addition to that, we knew that if we could do that rapidly, that it would serve us well from a business perspective as well. One of the early analyses I did for the board, this is probably 2017 and 2018, was looking back then at some of the very best pharma companies that were the new coz, Genentech, Regeneron and how again, companies like that, and looking at Illumina, taking the best 12-year period of shareholder value building for each of those two groups, the pharma companies versus Illumina. There wasn't anyone who took the top 12 years of Illumina, which started with the launch of their first NGS Sequencer, posted their acquisition of Select, so it's got an in-depth space in the 12 years after. And that's because when you have a platform that's able to deliver a significantly new type of biological information that's valuable, you can grow business pretty explosively. And as we thought about the potential of doing that in proteomics, and then the longer-term potential of software add-ons and monetizing data and algorithms that help our customers develop insight, not just get information from us, we thought that was a much, much better business model. So today, what we've settled on is that we sell, we are starting in 2025, we are going to sell a platform, and the platform is an instrument, software, services support, it's everything you need to put a machine on your bench. And then the ongoing business model is selling consumables. So for every one of the instrument, you've got consumables, which is our FLSL, our chip and RV agents. And that's the core business that we're building. There's a software layer to that business. It's basic software at the beginning, but we're going to continue to add more and more capabilities to that. And then there's always going to be an arm of our business, which is focused on helping customers partner closely with us to answer questions where the customer doesn't have the ability to use the base product to do what they want, but we have the ability with our platform to do something that is more custom to them. And those types of opportunities were open to any business model, really. That's not a lot different than Illuminal looks like today, where there's the base set of products, and then there's other things that they do on the side that bring value to their customers. But for us, that business model that we've settled on, we think enables us to get the technology into the world, where it could do a lot of good. It enables us to build a business with some velocity and gives us lots of opportunities to monetize the product. Yeah, super interesting. At some point, love to opine about what is the platform versus even abstracting it away and say it's a service, right? You know, that's still the same kind of end result for the customer, but a different sort of implementation and manifestation. Definitely could see the value to the end customer. And also, I think scientists generally love to be hands-on with new tech, too. And it seems like you're really playing into that. I'm curious on the software side, just given my personal experience and interest in that area, how do you think about the potential for different types of algorithms or apps, if you will kind of on the software platform side, given the variety of use cases and workflows you could potentially support? That's an interesting question. I will opine with you for 30 seconds on what you talked about earlier, which is that there certainly are a lot of different business models we could choose from once you've decided to become a platform. And we will use services to help customers try the systems out before they buy an instrument. We'll use services to give customers the ability to have burst capacity if they want to do more analysis than their instrument or instruments is capable of doing. But in the end, like you said, scientists like to be hands-on. They like to have control over the instrument and the samples. And there's already existing budget and capital spend that goes into best spectrometers and other equipment that's used for proteomics. And so it makes sense to be able to tap into that and not have the customer to have to change business models at the same time. So that certainly is an interesting piece of it. So on the second piece of your question, we think that the ability to monetize the software side of the platform in the long run is really interesting. If you look at what customers want to do today, the first and foremost, like the most basic data you can get out of our platform is a list of all the proteins that we saw and the quantities that we saw them. And the cool thing about our platform is we're a single molecule counter. And so we're going to tell you how many molecules of each of these different proteins I saw. And that's really interesting. But by the time that you look at hundreds and thousands of cells, you're talking about 10 billion different molecules. As you start looking at multiple samples, you start looking at them across time, this is a data set that gets very, very large very quickly. And so there are some basic analyses, understanding where there are deviations from control samples, trying to do simple pathway analysis. Those are the sorts of things that customers are very used to today. They've got different visualizations they want to see. But in the long run, there's so much data here that it's going to be difficult without having data science techniques that are evolving very rapidly and techniques like AI that are evolving rapidly, it's going to be very difficult to make sense of that data without using some of those types of techniques. And there are plenty of new companies that are being built, AI for drug discovery, data science to do better x or better y. But when we go talk to customers, we talk to the large pharma organizations, we talk to the newer midsize companies, companies that represent quarter trillion dollars of pharma R&D worldwide. The general capability level to analyze massive trends of data is very little. They don't understand how they're going to do it. They don't know how to leverage these technologies well. And we're going to be experts of this new type of data. So for us, figuring out what are the algorithms that help our customers get insight from that data is going to be really important. We can also start building repositories of control samples, different Oregon models, different organism models, and to have as data that our customers can reference, we can provide the ability to do some hypothesis 3 and 3 analysis of what we're seeing. There's all sorts of applications that we think will enable us to build software value on top of that base solution over time. And that's important one because it's going to provide value to our customers. And then for us, for our business standpoint, it's really something that we can monetize over a long period of time. And so for us, that's a really exciting opportunity. But one that it's not black or white, but it starts from the point we have a platform in the marketplace, and now we're generating all this data. Yeah, wow, wonderful. As usual, we just want to say thank you, again, for being on the podcast today. Obviously, a really exciting time. I'm sure both in biotech, but also specifically in Nautilus, and really grateful for you to share with us a little bit about the journey of how you got to where you are today, but also what's on the horizon and the periphery here as we look into 2025. So thank you again. And looking forward to having you on again as your new platform launches soon. Thank you. It looked really nice talking to you today. And I look forward to doing it again sometime. Wonderful. Thank you. Thank you for listening to this episode of biotech 2050. This episode is hosted by me, Rahul Chaturvedi, and Alok Taiyi. If you enjoyed this episode of biotech 2050, please subscribe to our podcast and leave us a review. Also, follow us on Twitter and Instagram and biotech 2050 pod. Again, that's biotech 2050 pod. Until next time. [MUSIC PLAYING] [MUSIC PLAYING] You