TechTalk: Biotech Startup Evolving the Journey to Therapeutic Antibody Discovery

Andrew Satz:

Thanks so much for having me, Fritz. 

Fritz Spencer: 

Of course. And to get us started, I'd love if you could tell our listeners a little bit more about yourself and a brief background. 

Andrew Satz: 

Sure. I'm a data scientist by training. I've been building technology across industries for most of my career. Most notably and most recently, prior to founding EVQLV, I helped bring three peptide-based drugs from discovery to clinic at an early stage biotech and seeing the process of turning a molecule into something that you can inject into humans and all the failure that comes about, thought we could model some of that in the computer and that's how EVQLV was born. 

Fritz Spencer: 

Great, and you touched on it a little bit there, so EVQLV, tell us more about what you're building and the model that you're following. 

Andrew Satz:

Sure. So at EVQLV, we leverage advances in computation like artificial intelligence to transform the process of the discovery and engineering of therapeutic antibodies for biotech's and pharmaceutical companies around the world. Antibodies represent one of the largest groups of drugs in the doctor's arsenal. The number one selling drug in the world is an antibody, and so we focus on designing those types of molecules. We act as sort of an intellectual property as a service, kind of a quasi-mix between the biotech business model and a SaaS business model. 

Fritz Spencer: 

Interesting, interesting. And I want to mention that I met you several years ago through one of the Florida Venture Forum events, and at that event, I believe you took first place and then I saw you again at another event where you took first place and I think maybe even a third time I saw you at a different event where you took third place, you've been winning awards left and right. Can you tell me a little bit about those accolades and awards that you guys have won and maybe why you feel like you've won them? 

Andrew Satz: 

Yeah, so as you mentioned, we won the grand prize at the Florida Early-Stage Venture Capital Conference. There was a large group of applicants, I think there were about 500 applicants to that. They ended up choosing about 25 companies to present to a smaller group, and then the final 10, we ended up winning that one. That was a grant from Space Florida. Then we also competed at Synapse, which is the largest technology event in central Florida. And again, there was a large group of really amazing companies that competed there. We awarded the grand prize was a $150,000 investment from DeepWork Capital and a couple of other venture capital groups. And then more recently we competed at eMerge Americas, which is the largest technology conference in Florida, and I think in the Southeast, if I'm not mistaken, it really brings together Latin America and US-based companies. In that case, I don't know how many there were in the initial pool. I think it's probably 1,000 applicants, and they brought it down to about-

Fritz Spencer: 

At least. 

Andrew Satz: 

Yeah, and they brought it down to 110, then to 25, and then the top five, and we ended up winning that. That was a $520,000 investment. I think part of the reason why we're winning these things probably for four different reasons, number one is that the long-term impact that a company like EVQLV can have in driving down the cost of medicine, making it more accessible, innovating in new kinds of medicines, basically speeding these things up. One of the other reasons was that we're applying some really very novel technology or cutting edge. Whenever I say AI, I always do it in air quotes, because it just doesn't really mean anything anymore because it's lost its meaning. But we've been doing this quote quite a long time. I've been building AI-related tools for a decade and been in this space for 20 years. The third reason I think has to do with a skill set that I really spent a lot of time honing, which is story crafting and storytelling. Now, it doesn't necessarily mean that that's going to convert into raising capital, being able to pitch is definitely going to get you past the gatekeeper, but I think there's the diligence, the ability to understand the business that's going to really the next stage, but being able to craft a story and tell a story because we're doing something very, very, very complex and the audiences we were presenting to, most of them don't understand machine learning. Most of them don't understand the pharma industry or antibodies. I have to explain all of this very complex industry biology technology in under five minutes and being able to do that I think is a certain skill and it wasn't something I was born with. I really devoted time and invested in myself in becoming a better storyteller and better story crafter. 

Fritz Spencer:

Well, I've listened to you pitch at least two or three times now, and I can tell you each time it's definitely entrancing and grabbing and activating. I thoroughly enjoy it each time and it's always a no brainer to me why the rest of the crowd is also that way as well as the investors that are listening. It is a very complex thing that you're talking about and being able to bring it to its basis and so that it's explainable and understandable, that's where I see the traction. So you story tell this problem that you guys are solving and the investors hear that and they want to contribute, what is that problem? How did you identify it and how did you get people on board with it? 

Andrew Satz:

So my co-founder and I met in grad school and he came from the financial services world before grad school, and I came from a variety of industries prior to grad school. We both study data science and data sciences are arguably some of the most advanced technical people on the planet, computational technical people on the planet. You're fusing statistics, algorithm design, just combining math and algorithms and then programming. Those are complex spaces to be in. And when we looked at the market, about 65% of all data scientists at the time were in one of two fields. They were either in finance and neither one of us wanted to go into that space or they were in marketing because Google still makes close to 90% of its money off of AdWords. So you're looking at big tech, it's mostly advertising companies, not all of them, but for the most part they were really advertising companies and they're the ones that were hiring most data scientists. Neither one of us wanted to work in that space. We wanted to do something that was impactful. When we looked at the market, we saw that less than 5% of data scientists were in the entire healthcare ecosystem. That's healthcare, pharma, biotech, and that's 20% of GDP. So there's a big gap between 5% and 20%. And so we're like, well, let's go do something in healthcare. And we weren't sure what. We started a consulting firm for AI for healthcare consulting. This was in 2017, and did work for all sorts of organizations within the healthcare ecosystem, payers, providers, hospice. Then we helped a biotech with a certain kind of scan to teach machines to read a certain kind of scan, and they asked us to do stuff that was not related to AI. We're like, "Hey, can you help us with other stuff?" Because they were like, "Here are the two guys that seem to have their heads on right." And we did and we helped them bring three drugs to clinic and saw all the failure and said, "Hey, let's apply what we've done to drug discovery." At the same time, my co-founder's mother was diagnosed and treated and saved from cancer with an antibody. His wife was treated for an autoimmune disorder with an antibody. We're like, "Well, let's go look at antibodies." We didn't really know anything about antibodies at the time, but there's two sides of this. You have to understand machine learning, you have to understand biology. And so we just started working on the problem and spent about a year and a half just building the first version of the technology. We had a breakthrough in late 2019 and we're like, "Okay, let's start a company." And that was really what led to the birth of EVQLV. And it's been five years of just hard work, really complex challenges, because it's not just the technology, it's also the market. 

Fritz Spencer:

Yeah. So you mentioned a little bit about the tech side. You guys have a very strong tech background and you're using it to solve healthcare related problems. And I do agree with you that I think that the term AI has been so oversaturated that it has almost completely lost its meaning. Can you tell me what, not only just in regards to your tech, but what AI means to you and how you guys are using it to help basically accelerate your solutions? 

Andrew Satz:

Yeah. So I actually think that there are multiple kinds of AI. I've written about this before and I think there's probably about six different kinds of AI. We use various kinds. We're doing generative, we're molecules using our technology, we're doing predictive. So we're trying to predict whether these molecules will function in a certain way or whether they'll behave in a certain way. And so those are probably the two types that we're using now. That's more sort of like a 50,000 foot view. And then you talk about more of the technical side of things. We're doing types of deep learning. There's various types of learning that we're using in the machine learning space. And so the technical aspect, if I drill into the technical aspect, if you want to really get super technical, I'm happy to do that, but I think people might probably use this to put themselves to sleep. 

Fritz Spencer: 

I mean, it is called Tech Talk, so if you want to dive in a little bit. Go ahead. 

Andrew Satz:

Yeah. So in my view, there are basically six kinds of artificial intelligence. The first really is about meticulously gathering and arranging data sets. It's really a foundational step that ensures that the data is really ready for deeper analysis, and that's really complex in the space that we're in because you have to understand the biology to be able to standardize the data. I mean, just think about if I was an alien coming from another planet and I saw all the different ways that we write dates, you write 1/1/21, January 1, 21, if you're from Europe, you're going to flip it around. The month comes second, which is, I actually think those the right way, because it makes more sense. But just think about that, we know how dates work out, but now think about it, you have completely new sector like biology and specifically in antibodies and how do you structure the data? So that's one part of what we have to do. We really have to set all the data up in a very standardized way so the machines can interpret it. I think that the next two stages of artificial intelligence, there's analytic and automated. So automated is really a repetitive task that you would do over and over again. We integrate that as well. It's going to transform something that's manual, monotonous into something automated. This could be a robot in assembly or just auto-filling cells in Excel and just kind pull down. We do that kind of stuff as well. We're automating these sort of repetitive processes. How do you standardize the data in an automated way? So a new piece of data comes in, how are you splitting it up? How are you interpreting it into, in the case of an antibody, V(D)J pieces, sorry, it's not my area of expertise, but there's also analytic intelligence. This is having a math or a stats whiz in your pocket. So you think about a calculator, I don't know how calculator works from the inside and despite being a data scientist, that's not my area of expertise. But you want to be able to do complex equations that can analyze vast amounts of data to make an informed decision. So this is kind of business intelligence. So what this part is really speeding up mental effort. And so what we do is we'll take what we would do mentally to try to analyze an antibody and then create it algorithmically. You also have things like predicting models, so it's accelerated intelligence where you're trying to predict the future, and that's really analyzing patterns in the data, forecasting what an outcome could be. And we're doing that for a variety of features in antibodies, because if you think of an antibody like a key and a disease like a house, you have to be able to figure out is the key that I'm creating going to fit into lock? Is the key that I'm creating going to open the lock and am I even picking the right lock? Am I choosing the right lock? Because if I put a door handle on a wall, it's a decoration, which is what biology seems to do a lot of. You could just be picking the wrong spot. It's kind of poking the key at the door. And so that's really where predicting these types of things is really important. And you also want to kind of remember that just because I have an antibody that works to open the lock, if I have a key, if I can't manufacture it at scale because it's made out of some material that we don't have or it's flimsy and it falls apart every single time, you don't have a drug. You have a solution, but not a drug. And that's another problem. Just because can make something work doesn't mean I can manufacture it at scale. Then there's generative, what a lot of people are talking about generative AI where you're really generating new designs. And we do that at the very beginning and all of that comes together to really augment intelligence, because I really do think that AI is kind of a tool and it's really about augmenting us. Just like a screwdriver, a screwdriver, I could bang on a nail if I wanted to with my hand, but if I use a hammer, it's going to be better. And so you just got to think of it as just more advanced tool than a hand or a rock. 

Fritz Spencer: 

Yeah, I love that. I love that analogy and I like to hear the way that you're taking all the different, because there are so many different spaces in AI and you're taking all of them and using them as they're intended to help you out, to build the hammer, to hit the nail on the head, if you will. And it sounds like you guys have really figured it out because you guys have had such great success over the last few years. I know you mentioned you guys have been at operating profit for several years now, or is that a true statement? 

Andrew Satz: 

We've been profitable since 2024. The company was mostly research and development from 2019 when we founded the company until 2023. In 2023 in the middle of the year, we went commercial as a company. Since the middle of last year, we've signed 35 deals with 23 companies. Deals like these normally take 24 to 36 months. We were able to do signed most of these in less than six, and that's what's made EVQLV a profitable business, and now we're just starting to grow more and more and more. 

Fritz Spencer: 

Congratulations on that, first of all. And second of all, we didn't mention the spelling of EVQLV, which I love personally. It's E-V-Q-L-V, which in all caps looks like EVQLV, but maybe you could give us a quick shed some light on why that is. 

Andrew Satz: 

Yeah. So I'll need to do a little science explanation here. So all living things are made up of amino acids. We're all made up of proteins. Proteins are made of amino acids. You've all probably heard about them at some point on a commercial or something. 

Fritz Spencer: 

Mitochondria is the powerhouse of the cell, yeah. 

Andrew Satz: 

There are 20 common amino acids that make up most of life. By the way, I'm not a biologist, so if a biologist says, "Hey, that's wrong." I only pretend to be a biologist. Because there's 20 of them, you can represent them by letters of the alphabet. Now, antibodies are also made up of amino acids, and if you look at the first five amino acids of many human antibodies, the sequence of letters is E-V-Q-L-V. And so when we were first writing the algorithms out, we kept writing out the amino acid sequences trying to figure out what the algorithmic process is, and everybody kept writing it. They're always written in capitals, and I was like, "Wow, that looks like the word evolve." That's actually where the name came from. 

Fritz Spencer: 

That's perfect. 

Andrew Satz: 

It's really funny because one time someone came to me and said, "Your name is terrible." And I was like, "Our customers love our name." And they're like, "Your name's perfect." 

Fritz Spencer: 

It's all about perspective, isn't it? 

Andrew Satz: 

Exactly, exactly. 

Fritz Spencer:

Well, speaking of evolving and the growth that you guys have seen, I'd love to know what is next for you guys? What is next for EVQLV? What's next for Andrew Satz? 

Andrew Satz: 

So for EVQLV, we're scaling the business now. We're growing. We're in the middle of a fundraise at the moment. Seems to be going pretty well considering what we're hearing in the market. We're in diligence with several groups at the moment. That's really allowing us to fund our growth as a company and to continue to leapfrog ahead and we continue to build out more features of our technology that solve challenges for our customers. And we're very much focused on growing the sales base of the business. For myself, it's just staying heads down, focused on EVQLV, trying to hire the right people to come in. We're not a big company, and so as the CEO I do all the things the CEO does plus I do marketing, business development, sales, contract negotiation, project management, customer success. And so it's a lot to do and so I spend a lot of time doing that. And so I think for me, what'll be great is being able to bring in the next group of amazing team members that can get the job done and help support our growth. 

Fritz Spencer: 

I think as a founder, and I think this will resonate really well with our listeners, is that at the beginning you end up wearing every hat you really are, and then it's your job to find the best heads for those hats to land on really, on top of building a strong foundation of that company that sounds like you guys have really accomplished. And you mentioned, real quickly I want to touch on, you mentioned your customers. They're the ones that are so keen on you solving their problems that we talked about earlier. What kind of customer base do you have? Who is your customer? Who should we be on the lookout for? 

Andrew Satz: 

Yeah, so I'll go from sort of largest to smallest. Our customer base in terms of company type are pharmaceutical companies, biotechnology companies, research reagent companies, because that's a massive industry that powers a lot of the research. And antibodies are a big portion of that. Diagnostic antibody companies as well, and then academic researchers, so academics, and within that if you're working on a disease or a particular area where antibodies can solve the problem. So a lot of antibody engineers, discovery scientists, those are our customers. 

Fritz Spencer: 

Great. Well, Andrew, I want to thank you so much for not only the deep dive into AI, but biopharmaceuticals as well as EVQLV. Thanks again for joining us and if there's anything you'd like to say to our listeners, feel free to take a moment. 

Andrew Satz: 

Yeah, I think one thing that you mentioned, especially for the early-stage founders is that there's no better sales person for your product than you. And so I think really trying to be as close to your customer as possible, talking to them, engaging with them. I also think that it's super important as builders of companies to be using the AI tools that are out there. Now, whether you're choosing ChatGPT or Claude or Perplexity, they all have their different sort of use cases. Like Perplexity is a great research tool. I really encourage people to start to use them right away. I mean, for me, it's turned eight hour processes into one-hour processes, and it's not difficult to get up to speed and get better and better at it using it every day. If you're an investor out there and you'd love to chat, feel free to reach out, happy to have a conversation. And then if you're just in general curious about AI or want to understand how it can be applied to your specific field, there's a lot of research out there, but I'm also happy to be of service to others. I think it's super important to give as much of the community as possible and the universal will allow that to cascade to helping others as well.

Fritz Spencer: 

Great. Those are some wonderful last remarks. I really appreciate it. And if you want to connect with Andrew or learn more about EVQLV, we'll have those links in the article below. And I want to send out a special thanks to our listeners for tuning into Tech Talk, the very entrepreneurs and innovators who turn to EisnerAmper for accounting, tax and advisory solutions. Subscribe to EisnerAmper's podcast to listen to more TechTalk episodes or visit eisneramper.com for more tech news that you can use.

^{Transcribed by Rev.com}