Recursion, thanks for attending the 2026 Bank of America Global Healthcare Conference. My name is Alec Stranahan. I cover Recursion, and SMid Biotech at Bank of America. I'm pleased to be joined today by Ben Taylor, Chief Financial Officer of Recursion. Thanks for being here, Ben.
Happy to be here. Thanks for the invite. It's always good to come out every year.
Yeah. Yeah. Great. Well, maybe just to start, there's a lot going on at Recursion. This is AI-enabled drug discovery for those who are uninitiated. Recursion is really a trailblazer here. They've been doing it for many, many years. I guess, Ben, to start, you know, you've got sort of 3 value drivers at the company. You've got your internal pipeline, you've got your pharma partnerships, and you've also got the Recursion OS platform itself. I guess, where do you see the biggest re-rating opportunity for the company? Is it from the pipeline validation? Is it from advancing and expanding your partnerships, or is it really from the platform and sort of what you're deriving from that?
Well, at the heart of it, we're a therapeutics company. We really focus on making sure that we're advancing the pipeline and getting the value drivers from that. I mean, if you look at 1 of the fundamental tenets of the business is to create a more risk-diversified biotech model. That has, over the last decade plus, involved a lot of platform and a lot of the partnerships as well. In the end, it's all for the goal of actually developing therapeutics that are gonna reach patients. Right now what we have is 5 different clinical programs that all have clinical data in the next 12-18 months that's really impactful for showing proof of concept and/or we've got 4, 1 that's starting its registrational trial.
Those are really the core value drivers, not only from an investor perspective, but also just for the core mission of advancing medicines towards the patients. The other components, it's funny because for us it's a continuous stream. We don't really view the platform separately from the pipeline and the partnerships. We're actually just doing the same work that we would do on our internal programs, but we're getting paid an advance for it and a nice NPV on it. All of it really flows back to, does this drug have differentiation and is it likely to be a good product for patients?
Great. Maybe for those less familiar with the company, maybe you can just talk about sort of the full stack capabilities that you have and how that's evolved over time, where you're sort of at today and how you sort of see yourself settling to the rapidly evolving AI landscape.
Yeah. If you take a step back and you think about, all right, how can you make a differentiated model in biotech, there's two components that you have to do. One is improve the probability of success. If you've got a 90% plus failure rate in the industry, you're always guessing. That's the part that really focuses on building a better data-driven model to it. If you think about how we continue to advance along and bring up the other pipeline programs, what we've been able to do is show that we can do that across a number of different facets on where that probability of success can come down. If you think about a program as a whole, you need to think about the failure of a clinical trials being based on the statistics.
It could be chemistry, it could be biology, it could be patient selection, it could be trial design. All of our systems are actually saying, "Can I create a better predictive model to be able to solve that reason of Understand that patient better?" I want to be able to explore the biology better. I want to go through completely novel chemical space. There's not a single point of technology that really defines us. We just have the largest integrated tool set to be able to solve those problems that cause failure for clinical trials. I think that is a massive differentiator for us, the fact that it's been created within a unified system so that it works together, where most of the companies in the space right now are really developing point solutions for a single area.
The other aspect is the data. I mean, because we've been doing applied work for so long, we've created a massive data set, over 50 petabytes of internal proprietary data that allows us to build better models. If you're just using the public data or even if you're just using data that has been generated outside of the ML context, the fidelity of it is pretty low, and so it doesn't actually drive a lot of predictability. What you really need to do is create something that supports a better data analysis. We just had a paper published that showed a much smaller data set of highly annotated data actually creates far more predictive models than a massive data set of poorly annotated data.
Hmm. Interesting. I wanna talk about something that, like, you got asked at our breakfast this morning, and I thought your answer was pretty interesting. Just thinking in the near term, you know, the industry's evolving in terms of where innovation is being rewarded, right?
Typically that was through pharma partnerships like what you have. A lot of the pharmaceutical companies are going to China now as well. I guess on the AI drugs, development landscape, with like AlphaFold kind of established now, where's the next sort of wide space for development in the next couple of years?
Yeah. Well, it's just, it's absolutely massive. If you think about all of the pharma industry, all of the biotech industry for as long as they have both been running, and all of the approved medicines and all of the drugs that are currently in clinical trials, you only cover a little over 10% of the genome. That means, you know, almost 90% of biology is sort of in the dark to us from a therapeutic perspective. The chemical space is actually in a similar state as, if not even worse. First of all, there's a lot of white space that we need to explore, and that's part of why we need new techniques to be able to evaluate it.
I really think where we're gonna continue to see evolution is 1, over the next 2 years. Well, where we are right now, people understand that patient selection is important, right? If you get the right patients into the trial, you can increase probability of success, and obviously we've got a lot on that in ClinTech. What I think people are just starting to understand is the chemistry space, which is really, potency and even selectivity are only a small piece of the puzzle because realistically, how is it absorbed? How is it metabolized? You know, what are the other interactions that you're dealing with? We in Legacy Exscientia had predicted multiple clinical trials that failed before there was any data on the clinical trials, just looking at the chemistry.
I think people are just starting to understand, okay, a potent compound that works in mice, which is, by the way, a preclinical model that's basically designed just to focus on potency, you know, does not actually take into picture the entire patient environment and all of the biology. The biology side of it, people still think of very linearly. You know, ABC 1 connects to XYZ 2, and that's how biology works, which of course, is not true. It's incredibly complex, multivariate problem. I think we are just starting to get the tools to be able to explore that better and be able to get into areas that are far off that what I was talking about earlier was really exciting.
virtual cell is obviously a big word a lot often used, but the publication that we just had in Nature Biotechnology, basically what it showed is for a number of different cell lines, we were able to experimentally predict what would happen in that cell without having it be at all part of the training data. We're actually getting to the point where you can use multimodal biology, so, cellular genomics, which is what Recursion was originally founded on, combined with transcriptomics, combined with other different aspects that you can bring in. That signal that's so cloudy in any single medium becomes much more clear, and you can make predictions on actual underlying biology even without having original knowledge.
Still a long way to go there, but we're just tip of the iceberg on it.
Yeah. I mean, the way I think about AlphaFold is you had a good data set and there's not that many I mean, there's a lot of different ways that proteins can fold and interact, but it's not as complicated as like neutrons and electrons in like small molecules, right?
Right.
Like the multi-modality of that made it an easier first step, actually.
Yeah
which was a little bit counterintuitive. Is the right way to be thinking about it that it's, if you're just going up in orders of complexity, going from proteins to small molecules and then to a virtual cell?
Well, it's really interesting, and I think there's gonna be different starts across all the categories. You're absolutely right in a way, like the AlphaFold, which by the way is completely amazing and fantastic discovery, but it was based on 30 years of annotated protein data that existed in the public space so that there was a much larger base to be able to build from. Being able to put that together, it's you're basically looking at physics principles and how that combines together, and it becomes a computational statistical problem. With chemistry, just to put it into context, like if you take all of the antibodies, for example, that are known and out there, you're talking about 10 to the 15th about.
If you take all the potential medicinal chemistries, you're talking about something around 10 to the 60th, so effectively infinite, you know, from what we're thinking about. The biology, obviously, you're interacting between all of those different pieces. I think what's really important is AlphaFold itself didn't solve all proteins. It may be far better at estimating and predicting what then you can prove out experimentally later on in proteins that are not well known, but the prediction capability is far higher in areas where there's a lot known about proteins. The same is true in chemistry, like generative systems work better around areas where there's been a lot of data created.
What you'll see is there's gonna be aspects of biology, let's call it the most complex, because you're now combining all of those different 10 to the whatever it's. You're gonna have amazing breakthroughs in that, but they're gonna be around areas that you can build off of, just like, you know, we're continuing to advance in proteins and continuing to advance in chemistry.
Great. That's really interesting. Yeah, maybe we can move from the theoretical now to the practical.
You got me going.
Yeah, yeah. I think it's super interesting. In terms of what moves stocks, including Recursion.
Yeah
this tends to be the tangible aspect of what's coming out of the platform, and for you guys, that would be your clinical and preclinical program. Maybe we can just go down the list. You've got a bunch of interesting programs.
Yeah
in your pipeline. Maybe starting with 4881 in FAP.
Yeah.
For those less familiar, maybe just talk a little bit about sort of what this disease is. There's really no approved therapies here, although there's maybe some context that you can put, you know, 4881 into that makes sense from a biologic perspective. What's the clinical course for these patients and what are you trying to solve for with treatment?
Yeah, really tough disease state. This is usually identified hereditary, though there probably are a lot of somatic mutations that cause this as well. 50,000 plus, and that's primarily the hereditary population who, throughout their entire life, as long as they live, are going to continue to get hundreds or even thousands of malignant polyps throughout their GI tract. This usually starts up in adolescence or teens. Patients will usually have a colectomy before they're 30. They'll continue to get further resections as time goes on. They're likely going in and having excisions of all of the polyps, can be on a several month basis. Really difficult disease state, very high comorbidities, and completely chronic.
What we've been able to show with the data is, within 3 months of treatment, the polyp burden was reduced by about 50%, and we were able to actually also take patients off of drug and maintain that polyp benefit, which is really important for a chronic disease drug. Those aspects basically gave us confidence that we would be able to move forward with a registrational pathway. We're currently in FDA discussions on starting the pivotal trial, and we'll give another update on that later on this year. Huge unmet needs. There's no approved therapies for it. You know, we're really excited because that was a discovery that came out of our BioAI platform.
It was a novel connection that we were able to look and say, "Okay, how can we potentially reverse this APC-driven mutational effect with a drug and then convert that drug into now a patient proof of concept?
Yeah. I guess, you know, as we're thinking about the translation of polyps reverted to functional outcomes.
for patients, I know you've got a pretty substantial kind of natural history set.
Yeah
that really helps you understand, sort of, the patients with this disease. I guess, how should we kind of bridge that gap between the 50% polyp reverted to functional endpoints, like, I don't know, CRC prevention?
and other-- And-
Yeah
what's most important for the FDA, I guess?
Absolutely. Well, every single one of those polyps is pre-cancerous. Basically, if left untreated, all of these patients will progress into colorectal cancer. That's obviously one of the endpoints, but there's a number of different endpoints that you can look at with the FDA. There are things like, there's a Spigelman score, which is sort of a composite of polyp burden and dysplasia that leads clinical assessment and treatment. There are excisions, because when someone without FAP goes in for a colonoscopy and gets a polyp or 2 removed, you know, it's painful, it's uncomfortable. When you're going in every 3 or 6 or 9 months and having a 100 polyps removed, you're talking about massive excisional burden, bleeding, infections, quality of life changes. You can look at those pieces.
You can look at resections and serious surgeries. These polyps actually can go up into the duodenum, and you can't do like a colonoscopy to be able to remove those polyps. You actually need a different endoscopic procedure. Which is, you know, a far more serious procedure. There's a lot of different true clinical endpoints. If you talk to the clinicians, they view polyp burden as being incredibly important because it basically determines how they stage patients.
The other thing that we were able to do, and this is sort of an example of how we have the infrastructure, because we have the supercomputer, because we have AI scientists, because we have access to, you know, 300 million patients of real-world data, literally in the course of a week, we created an LLM that looked across those 300,000 patients, found 250,000 patient records associated with FAP, created something that we could query and say, "Okay, what is the standard of care in this setting?
How many surgeries are these patients getting. The answer is 10, by the way, across their lifetime of serious surgeries, not counting all of the colonoscopies. That gives us a lot of insight, that never existed before that we can also take to the FDA and talk to them about the pathway.
Yeah, I guess how central is the real world data package to FDA discussions? You know, does this reduce the likelihood of a randomized controlled trial?
Yeah. I won't get in front of the FDA discussions, certainly. What I'd say is, it's definitely informative, definitely appreciated. I think even if it doesn't The FDA loves data and loves transparency. Anyone who thinks differently hasn't worked with them. They love it. Even if it doesn't make a difference with our FDA pathway, it makes a big difference with how we design that trial, which patients we go after.
We can do things like take a patient population and change our inclusion/exclusion criteria and say, "Okay, first of all, how does this change my patient population commercial opportunity across, you know, the U.S. and Europe?" Then we can say, "Where are the sites with patients that have this sort of demographic?" Then, you know, we can build in there. That's why we've seen a 30%-50% improvement in our enrollment rates across our clinical trials where we're using our ClinTech. It makes a big difference.
Yeah. That should pay dividends across the pipeline.
Yeah.
-where you're designing these studies. I guess on RBM39.
This is your molecule that can, I guess, take a side door to shutting down CDK12. We're expecting clinical data in the first half, I believe. You know, what's sort of the first in human data that you need to show to give you conviction to advance and, I guess, how quickly could you make this go, you know, on the market?
Absolutely. We RBM39, just to take a step back, was a program that we founded with our biologics platform that was basically CDK12 has been a very interesting oncology target for a long time. It's transcriptionally related, and so there's obviously a lot of opportunity with high mutational burden cancers. Incredibly difficult to target because the pockets of CDK12 and 13 look the same. You get a ton of side effects with CDK13. What we were able to do is say, "How can we identify the same biology in another target?" That was a novel connection. What sort of drug could then reverse that disease impact? Both of those were discovered phenotypically on our platform, and then we optimized the molecule.
What we have been enrolling in is looking at patient populations that generally are going to be higher in high like MSI-H populations or different areas that are gonna be potentially more susceptible to this type of drug. We wanted to do, like, an early look, almost like a futility analysis, and saying, "Okay, this is a completely novel target that no one's discovered." This is a degrader, which has its own benefits and potential concerns. We're doing, you know, early dose escalation, trying to be really efficient with all of our money. I'm sure we'll talk about that at some point soon too.
Yeah.
What we wanted to do was take a look, and this was the first look we did was last week on our earnings call. We had, we showed that we had PK/PD that was dose proportional. We had the profile that we wanted to see, which was basically this is a protein target that you'd need to knock down probably 70% plus on a pretty constant rate throughout the day. We were seeing that exactly how we had designed it to happen, which is great. We're just getting close to what would be the predicted therapeutic doses.
This is monotherapy, but, you know, there's potential to see signal coming out of monotherapy because if it was a cancer type that's exposed to synthetically lethal mechanisms or other things like that, we could potentially see a signal. That's where we're going next. The next readout will be a more thorough data set second half of this year and could be really, really exciting. That's actually a very large addressable patient population has different sort of splicing and stability disorders.
Right. I guess on that point, we'll be looking to see which tumors you select.
Is there a decision tree that you make either around which indications to pursue, like unmet needs versus the market opportunity? How do you make the decision to mono or combo?
Yeah. Yeah. As you will respect, we are incredibly data-driven. We do a lot of real-world profiling and statistical analysis around that. We also do that for our commercial analysis.
We can do both of those aspects in-house. We're gonna be looking scientifically at the data. We've got theories based on what we see coming out of the bio platform and what we believe to be true, and we're gonna be looking in the data and say what holds up and what doesn't.
Okay. Maybe shifting over to 7735, which you announced I think earlier this year.
This is your mutant selective PI3K inhibitor.
Yeah.
Obviously a pretty hot space.
Yeah.
-right now with
Of course.
and others. Relay, et cetera. I guess, here, I guess you have the potential to address some of the safety shortcomings with the hyperglycemia and dermatitis that's been seen. Is that really the leg you stand on from a competitive perspective? Is there something else you expect to gain from the molecule? If what is sort of the IND-enabling data you need to show to push this into the clinic?
Well, I mean, there are other things than the hyperglycemia, but that's a really big one, because this is always sort of the hidden secret in oncology drugs, is you see the results come up from a clinical trial, you should always go back and look at the inclusion, exclusion criteria.
Most patients right now, and we did this on our real-world analysis as well, I mean, if you've got diabetes or pre-diabetes, which is actually in a lot of the cancer indications, around half of the patients, you're not going to get this drug or you're not going to get a PI3K that are currently out there, or you are likely to come off it very quickly. The real-world times of being on, for example, PIQRAY, is only a couple of months. And that's because of side effects profile. Even if you don't have diabetes or pre-diabetes, you know, grade 3 hyperglycemia is a serious issue. That is a really big important part.
I think what is also interesting. We're seeing 150x selectivity over wild type. What that means is an ability, we believe, to drive deeper into the dosing of it for the mutants. I think there's 2 levels of the question. One is that orphan population that is not eligible for these therapies right now because of some sort of glycemia issue. The other aspect is, can we go deeper on dose to drive higher response rates in this population before you start to get to MTDs? We've seen a lot of drugs come up in the space. Our original thesis on this continues to hold.
As far as we can tell, we are about an order of magnitude more selective than the drugs that are currently advancing through development. We like this drug.
Mm-hmm. Yeah. No question. We'll stay tuned for the data from that program in the second half. I guess I wanna ask about another arm of your business, which is partnerships.
The two main ones that we hear talked about are Sanofi and Roche. Maybe we can roll this into sort of a capital allocation burn question, which is, how could milestones potentially bolster your cash position over the next 12 to 18 months?
Yeah.
How are these partnerships going, and how do you sort of see the allocation between your internal development, you know, servicing your partnerships?
Yeah.
being good stewards of capital?
Yeah. I'm gonna back it out into the capital allocation question as the core part to answer there, because I think, as I said earlier, we're a therapeutics company, and we think the long-term value is gonna come out of the drugs that we develop. If you think about how we invest in platform and what we do with our partnerships, it's gotta be towards driving that bigger goal.
First of all, on sort of the expense management, what we did post the merger was take a look at everything across the company and actually put a analytical framework to measure impact, and basically said, anything that we can't clearly see high impact from or high probability from, cut it. That literally took out 35% of the budget in, over the last year. We continue on with that framework now. Our expense guidance for 2026, even with the 5 clinical, 2 preclinical, the big partnerships with Sanofi and Roche, it's still so it's less than $390 million. We're focused on getting to that less number because we are, at our heart, a tech and efficiency company. We should always be getting more impact for less cost.
We're gonna continue doing that. We're also gonna continue to be really disciplined in how we make decisions. Right now, most people don't realize this, about two-thirds of our cost, almost 70%, is going directly into pipeline programs and our partnerships. There's not some big, you know, 30% of the budget going into platform development or something like that. That's not how we do it. It's applied platform and pipeline development. You know, what we like to be able to do is say, "Okay, is the pipeline advancing? Is the partnership advancing? And if it's not, I'm gonna cut all of the associated spend with that." If it is, great, because it's gonna be generating value on its own. From the partnership side, we've brought in over $500 million from those partnerships.
You know, just in the last about 2 years, we've had 7 partner milestones, 5 with Sanofi, 2 with Roche, that, you know, continue to bring in more money. Over time, that business right now we run it basically to the break-even to a mild profit, because our partners prepay us for our expenses. As we get to opt-ins on Sanofi, as we get into advanced states on Roche, actually, that becomes all profit. That rolls in on a go-forward basis because we have no more operational obligations.
Okay. Okay, great. There's obviously more we could talk about. Always a lot going on at Recursion, I think for time, we'll leave it there. Thank you, Ben, for the great-
Thank you.
Great discussion, and thanks everyone for your interest in Recursion. Thank you.
Thanks.