Good morning, everyone, and thank you for joining us. Before we begin, I'd like to remind everyone that today's discussion will include forward-looking statements. Please refer to today's press release and our SEC filings for additional details. At Recursion, our mission is to decode biology to radically improve patient lives. We do this by building transformational medicines with an AI-native product engine. Over the past year, we have reached an important inflection point. We are no longer just discussing the potential of our platform; we are demonstrating the ability of our AI-native product engine to generate differentiated programs and medicines. As a reminder, the engine shown earlier is built as a continuous learning system. Proprietary multimodal data created in our data factory powers Frontier AI models, and those models generate new hypotheses that are experimentally tested. Each cycle strengthens both the engine and the products it creates. Ultimately, the measure of any engine is its output. So let's talk about that. First, our internal pipeline continues to mature. We now have five clinical-stage programs, including REC-4881 in FAP, where we have generated some of the most promising clinical data in the company's history in a disease with no approved therapy and a total addressable market of almost $10 billion. Second, we continue to make significant progress in our partnerships while learning from the best in the industry and validating our engine externally. Together with leading biopharma partners, we have generated more than $500 million in realized inflows while advancing differentiated programs with Sanofi and Roche-Genentech. Today I will share how we continue to strengthen our product engine and how we are translating these advances into differentiated medicines, differentiated partnerships, and ultimately better outcomes for patients. What makes our product engine different? Many companies are applying AI to drug discovery, but our advantage is not AI alone. It is a combination of three capabilities that reinforce one another. First, we generate our own proprietary multimodal biological and molecular data at scale. AI can only learn well from high-quality data, and much of the most valuable biology has never been measured systematically. Our 50 petabytes of data is designed specifically to train models, discover new biological relationships, and improve over time as new algorithms emerge. Second, we connect these models directly to experimentation through a Lab-in-the-Loop system spanning biology, design, and increasingly the clinic. Every prediction is validated experimentally, and every result feeds back into those models. That recursive loop helps us move faster, improve decision quality, and systematically build confidence in our programs. Third, and most importantly, we convert these capabilities into differentiated assets. That includes our internal clinical programs such as REC-4881 in FAP and REC-1245 targeting RBM39 in solid tumors, as well as our partnered programs with Sanofi and Roche-Genentech. How are we doing? Looking back over the first half of the year, I am very pleased with the progress across all three dimensions of our business: our internal pipeline, our partnerships, and the continued advancement of our AI-native product engine. On the internal pipeline, we advanced REC-4881 with our initial FDA engagement following encouraging Phase II data, with additional Phase II data coming later this year that Vicki will discuss. We have continued to build confidence in REC-1245 with early clinical safety and pharmacokinetic data, and we just received IND clearance for REC-7735, positioning it to enter the clinic later this year. At the same time, our partnerships are also making progress. Earlier this year, we achieved another milestone with Sanofi—our fifth to date—by developing a novel lead series for a very challenging first-in-class oncology target. I also want to highlight a new milestone announced today. Together with Roche-Genentech, we are thrilled to announce that Genentech advanced the collaboration's first neuroscience target, a previously unexplored target in neuroscience, into a joint early discovery program. This provides early evidence that Recursion's platform can generate novel biologically validated targets for drug discovery. To me, this represents more than another partnership milestone. In an area where progress has been slow for decades, it provides early evidence that a fundamentally different approach—combining proprietary disease-relevant atlases, purpose-built foundation models, and rigorous computational and experimental assays—can build confidence that these targets are actually causal. Deep scientific and technical collaboration with a partner can uncover previously unexplored therapeutic targets. While it is still early, I believe this is an important proof point for both Recursion and the broader field. It suggests that an AI-native engine can move beyond optimizing known biology to discovering new biology compelling enough to advance into drug discovery with one of the world's leading neuroscience organizations. Now, more on what’s ahead. For REC-4881, we will present additional Phase II data at the CGA-IGC Conference, a premier medical congress for inherited GI disorders, and provide an update on our FDA interactions as we continue advancing what we believe could become a transformational therapy for patients with FAP. For REC-1245, we are continuing dose escalation and generating additional Phase I data, and we expect to have a more comprehensive update later this year. With Sanofi, we expect the potential nomination of an oral inflammation and immunology development candidate, an important milestone that would further validate our ability to design differentiated small molecules against challenging targets with potential impact across multiple immune-mediated diseases. Finally, we expect to initiate the Phase I study for REC-7735, further expanding our clinical oncology pipeline with another precision-designed program from our engine. Taken together, these milestones reflect a company delivering ambitious proof points while executing with focus and discipline. Equally important, we continue to strengthen the engine itself. I will show a few examples of how innovation across biology, chemistry, and clinical development is making our engine faster and smarter. Starting with biology: much of human biology remains unexplored, and the answer is not simply building larger AI models. It is generating proprietary, disease-relevant data that models can actually learn from. To do that, we have generated and aggregated more than 50 petabytes of multimodal biological data, creating one of the largest proprietary data sets in the industry. As that data set grows, our models become better at discovering novel biology, and every new discovery strengthens the engine. That learning carries into design. Because our biology models generate higher-confidence hypotheses, our chemistry platform focuses on designing better molecules more efficiently. One example: we are advancing candidates using roughly 330 compounds over approximately 1.5 years, compared with industry benchmarks for small molecules of roughly 2,500 compounds over four years. That is a meaningful improvement in both speed and capital efficiency. We extend the same philosophy into the clinic. Clinical development is where a lot of value is created and where many programs fail. By bringing AI into trial design, selecting the right patients, and choosing the right sites, we're already seeing improvements in enrollment speed and patient matching, helping us run smarter and more efficient studies. Importantly, these are not three separate capabilities but one continuous learning system. Every experiment improves our data, better data improves our models, better models make better molecules, and clinical data is fed back into the system to make the next generation of products even stronger. Perhaps the best example of the flywheel in action is what we demonstrated with Roche-Genentech, announced today, where our biology engine discovered a previously unexplored neuroscience target. I’d like to take you behind the scenes to explain how we got there and why we believe this represents an important new approach to discovering medicines. Together with Roche-Genentech, as we worked to discover a new unexplored target from our AI-driven map of biology, we focused on a few key elements. First, this effort was not about finding another target within well-studied biology; it was about uncovering previously unexplored biology and building enough experimental evidence to advance it into drug discovery with a leading neuroscience organization. Second, we believe this validates something bigger than a single target: when you combine the right data, build the right models, perform rigorous computational and experimental validation, and pair that with the right collaborative structure, you can systematically uncover novel biology. We believe this is just the beginning because the underlying biological maps are reusable and have the potential to generate many therapeutic opportunities over time. Finally, across our collaboration with Roche-Genentech, we have now achieved more than $260 million in upfront and milestone payments, with the opportunity for more than $300 million in additional development, commercialization, and sales milestones for each future small molecule program. Why neuroscience? Neuroscience remains one of the greatest unmet needs in medicine. More than three billion people worldwide are affected by neurological diseases, yet CNS drugs continue to have some of the lowest approval rates in the industry. Neuroscience is particularly challenging because the biology is extraordinarily complex, difficult to model, and the field has repeatedly returned to the same small set of well-understood targets with only incremental success. We believe meaningful progress will require discovering new biology, not just optimizing what is already known, and that is exactly what this collaboration was designed to do. What does it take to discover a target that people will have confidence in? First and foremost, everything starts with disease-relevant biology. We asked a simple question: are we setting neurons in a context that actually reflects human disease? For us, that meant creating iPSC-derived neuronal and microglial cells at an unprecedented scale—more than one trillion neurons and hundreds of billions of microglia. This creates a rich disease-relevant atlas that can be reused to discover multiple future targets, and we view this atlas as a major long-term competitive advantage. Generating proprietary data is crucial but not sufficient; the next challenge is making sense of it. Before asking models to find something new, we grounded every analysis in causal biology we understand today, especially genetics. We introduced hundreds of disease-causing perturbations and anchored our searches around well-established drivers of neurological disease. That grounding ensures that every subsequent prediction starts from causal genetics and disease biology rather than searching blindly across the genome. With that foundation in place, our foundation models can ask a much more interesting question: what is not seen? What unexplored biology might exist? Instead of evaluating one hypothesis at a time, our models compare the biological signatures of more than 17,000 genes across tens of millions of data points. They build relationships across the entire genome and identify genes that consistently behave like known disease drivers even if they have never been implicated before. That allows data and models, rather than preconceived hypotheses, to compile a prioritized list of novel potential targets. AI can generate hypotheses, but medicines require evidence. Together with Roche and Genentech, we evaluated every predicted target through a rigorous experimental validation cascade. We built confidence in layers. First, we established that the target sits in the right biological pathway. Second, we showed that changing the target can improve cellular function, for example in neurons or microglia. Third, critically, we demonstrated that modulating the target can meaningfully affect disease-relevant biology using multiple orthogonal assays, including multi-omic layers such as proteomics and transcriptomics. No single experiment tells the whole story, so we build a body of causal evidence before advancing a target. Putting it all together, our collaboration combines four capabilities: generating disease-relevant biology at unprecedented scale; using foundation models to systematically explore that biology; navigating from well-understood disease mechanisms toward previously unexplored biology; and experimentally validating predictions before advancing them. Our first neuroscience target has advanced into a jointly developed small molecule discovery program supported by our design platform. What excites us most is not only this target but that the underlying data is highly reusable, allowing us to mine it repeatedly for unexplored targets. This was not the result of one algorithm or one experiment; it was the result of a new operating model for discovering medicines. Before I hand it over to Vicki, I want to highlight our internal pipeline. We have multiple programs in the clinic and we continuously make data-driven decisions for REC-4881 in FAP, where no therapies are approved today, and for REC-1245 targeting RBM39, a novel first-in-class degrader with limited clinical competition to date. Combined with additional internal and partner assets, we believe this creates a diversified portfolio with multiple opportunities to create value in the coming years. With that, I will turn it over to Vicki to walk you through the internal pipeline in more detail.
Thank you, Najat. I'll start off this morning by talking about our REC-4881 program in FAP. FAP is a rare disease that requires lifelong management. Patients with FAP develop hundreds to thousands of adenomatous polyps in their GI tract and require colectomy to reduce the risk of colorectal cancer. Following colectomy, polyps may continue to develop and grow, both in the residual lower GI tract as well as in the duodenum in the upper GI tract. Patients require ongoing endoscopic surveillance, may require additional surgeries, and they continue to be at risk for GI cancers. With over 50,000 post-colectomy patients in the U.S. and EU5, there are no approved systemic therapies to alter the course of disease. This represents an over $10 billion potential addressable market. REC-4881 is an oral MEK1/2 inhibitor with a differentiated dual mechanism of action in FAP with the potential to inhibit both new polyp formation via cross-talk inhibition of the beta-catenin pathway as well as to directly interrupt signaling of the MAP-kinase pathway, which is a key signaling pathway in advanced disease. So again, blocking potentially both new polyp formation as well as the existing polyps within the GI tract. So with that, I'd like to take a minute to discuss the impact of this disease on patients through a story of a woman named Jenny, who lives with FAP. Like approximately 70% of FAP patients, Jenny inherited the genetic mutation responsible for FAP from a parent, in her case, her mother. Seeing what her mother experienced had profound psychological impacts on Jenny, who knew from the young age of 8 that she also carried this mutation. She has since had to endure multiple surgeries, which have led to chronic and life-altering complications, including frequent bowel movements, malabsorption and dehydration, chronic abdominal pain and anxiety with medical PTSD from all of the surgeries and procedures. We have heard from both patients like Jenny as well as their treating physicians an interest in a pharmaceutical intervention that can prevent polyp growth and disease progression and ultimately lead to a reduction in the need for repeat surgical procedures. REC-4881 has shown promising clinical data in the ongoing Phase II TUPELO study. Patients who had undergone colectomy for FAP receiving REC-4881 showed a median polyp burden reduction of 43% after 3 months of treatment. That treatment effect was durable with sustained reductions after 3 months off treatment. Additionally, reductions in polyp burden were seen in both duodenal disease in the upper GI tract as well as the lower GI tract. The upper GI tract in particular is an area of high unmet need as approximately 90% of FAP patients will develop upper GI polyps. When removal of these upper GI polyps becomes necessary, the thin mucosal wall of the upper GI tract increases the likelihood of complications, including bleeding and perforation. REC-4881 has a manageable safety profile with predominantly mild to moderate adverse events, consistent with the safety profile of other MEK inhibitors. We continue to enroll patients on the Phase II TUPELO trial, including patients 18 years of age and older as well as a dose optimization cohort. We are pleased to share that additional REC-4881 data will be presented during the Presidential Plenary session at the CGA-IGC Conference in November. As Najat mentioned earlier, this conference is focused specifically on inherited GI cancer syndromes with a target audience that includes physicians who treat FAP patients. We also look forward to providing an update on FDA discussions later this year. Now I'll move on to REC-7735. PI3-kinase is frequently mutated in several cancers and is a clinically validated therapeutic target. Lack of selectivity for the mutated form over the wild type is a key challenge for existing agents as inhibition of wild-type PI3-kinase drives hyperglycemia. Increases in blood glucose are both a safety issue, which often limits dosing, and an efficacy issue as the resulting hyperinsulinemia can reactivate signaling through the PI3-kinase pathway, undercutting the efficacy of less selective drugs. REC-7735 is precision designed to be greater than 100-fold selective for the H1047R mutation, which is the most frequent activating mutation in PI3-kinase. Recursion's AI-native platform identified a previously unpublished binding site and delivered a development candidate in 10 months with no identified off-target liabilities. As hyperglycemia and the resultant hyperinsulinemia are driven by inhibition of wild-type PI3K, the selectivity of REC-7735 is expected to result in an improved safety profile with respect to hyperglycemia and may allow expansion into patients such as diabetic and prediabetic patients who are unable to tolerate current PI3-kinase targeting options. An improved therapeutic index, as I have described, may allow us to expand treatable patient populations, both within existing PI3-kinase alpha inhibitor indications as well as in additional solid tumors in which PIK3CA mutations are prevalent including potentially triple-negative breast cancer, ovarian cancer and endometrial cancer, just to name a few. Additionally, the improved therapeutic index may allow expansions into earlier stages of disease within oncology as well as non-oncology populations such as PI3-kinase-driven vascular anomalies. With the IND now cleared by FDA, we intend to initiate the Phase I ZINNIA trial later this year. Dose escalation will begin in patients with PIK3CA-H1047R mutant solid tumors. Once tolerability is confirmed at an active dose, we intend to expand into the hyperglycemia-vulnerable patient cohort to confirm the improved tolerability in this patient population. Dose optimization of two active and tolerated doses will then be performed in ER-positive HER2-negative breast cancer patients. We may also expand into additional tumor types based on emerging data. We expect to share the first data from this dose escalation part of the trial in the first half of 2028. And with that, I'll turn it back over to Najat.
Thanks, Vicki. And shifting gears a bit, we often get asked about whether advances in Frontier AI can reduce or increase Recursion's competitive advantage. We believe we have a truly unique competitive edge. As reasoning models and agents continue to improve, they become dramatically more powerful when paired with proprietary data, automated labs and real experimental feedback. That's exactly the system we've been building for years. Now we are deploying agents across biology, chemistry and clinical development, across the engine and alongside our scientists. In biology, here are some very quick examples. Our target discovery connector is helping scientists interrogate our proprietary biological maps in hours rather than weeks. These are the large maps we just talked about earlier in our partnership with Roche-Genentech, but also the internal maps that Recursion has built over years, accelerating the discovery of novel targets. In chemistry, our design agent reasons across structure, SAR and experimental data to prioritize the next design hypothesis at critical inflection points in programs. This helps our scientists decide what to make next and compresses design cycles from roughly four hours of structural analysis to about 30 minutes. And in clinical development, the agentic workflows are already improving patient enrollment, contributing to about a 1.3- to 1.6-fold improvement over historical benchmarks. That's significant. These are still early examples, but I will have Chris Radoux, our Director of Structure-based Technology, who is in this day in and day out, walk you through a real example in practice. Chris?
Presentation.
What you just saw wasn't a chatbot answering a question. It was an AI agent reasoning across our proprietary experimental data, our in silico data, our historical project knowledge and structural biology to surface insights that would otherwise require scientists long time, but then also nonobvious insights. That's because in drug discovery, the bottleneck is really just generating ideas. It's finding the right idea quickly enough to keep the make, test, learn cycle moving. As these agents continue to improve alongside Frontier models, we believe they will become an incredibly powerful multiplier of what we have already built. And finally, I'd like to highlight another aspect of our AI strategy. AI is advancing incredibly quickly, and no single model will remain state of art forever. Our strategy isn't to depend on any one model. It's to build an AI-native product engine that can rapidly develop and adopt the best advances, whether they're developed at Recursion or by the broader Open Source community. Nesso-1 is a great example. We developed an open source this model. This is a binding affinity model that delivers Boltz-2 level accuracy with 10 to 20x faster inference, helping advance the field while enabling dramatically faster design cycles. But look, the real advantage is in the model itself. It's our operating system. It's our operating model. It's our ability to rapidly integrate these models into our proprietary data. That increases prediction performance, accelerates the make, test, learn loop and allows us to evaluate many more compounds at a lower cost. And finally, great technology only creates value if you have the right people to translate it into medicine. We firmly believe that. And that's why we have strengthened our leadership team in 2 critical areas. First, Dr. Hoifung Poon joins us as Chief AI Officer. Hoifung is one of the world's leading AI researchers with more than 15 years at Microsoft Research, where he led pioneering work in biomedical foundation models and AI for health care. Importantly, though, he's not just a researcher. He has repeatedly translated Frontier AI into real-world applications and deployed that at scale. At Recursion, he will unify our end-to-end AI strategy, bringing together Frontier research and Applied AI across biology, chemistry and the clinic. Second, Dr. Donovan Chin joins us to head up drug design. Donovan has spent more than 2 decades solving some of the hardest problems in drug discovery from small molecules and RNA-targeted therapeutics to proximity-based medicines and peptide modalities. Across Parabilis, Arrakis, and Novartis, he repeatedly helps unlock targets that were previously considered difficult or even impossible to drug. That breadth across modalities and that depth and experience of translating computational design into medicines is exactly the kind of capability we need to continue building at Recursion. Together, Hoifung and Donovan strengthened the 2 engines that will continue to define our future, world-class AI and world-class scientific design. Now I'm going to turn it over to Ben to give us a financial update.
Thank you, Najat. As I've said in the past, we want to continuously increase the impact of every dollar we spend. We are demonstrating this today by lowering our 2026 full year cash operating expense guidance to $375 million. In total, our revised 2026 guidance represents a nearly 40% reduction from comparable 2024 pro forma expenses. Through disciplined data-driven management, we have been able to continue lowering OpEx while still advancing our differentiated internal pipeline, achieving a series of partnership milestones and maintaining a leadership position in AI-powered drug discovery. We have been able to increase our return on investment through multiple levers across the company. In our clinical pipeline, we use our Cleantech platform to drive more efficient enrollment and planning of our clinical trials, reducing the time and cost to reach important data. Najat and Chris described some of the systems that we use to make our internal discovery both more efficient and more effective. We also focus our technologies on predicting and answering the hard questions first so that we can prioritize those programs with clear potential clinical and commercial differentiation as early as possible. Because we deliver outcomes that are truly novel and differentiated, like our Roche-Genentech milestone today, our partnerships have achieved over $500 million in cash inflows, including more than a dozen successful discovery milestones. All of our partnerships are designed to be breakeven or profitable on a direct cost basis from the start with substantial value growth as we achieve milestones. In our product engine, we are able to build, test and integrate AI models on real projects using the scale of our internal pipeline and partnerships. We know not only if the model benchmarks well, but if it matters when it's applied to a drug program. This direct application allows us to determine early which technology investments are likely to have real-world impact. We apply the same disciplined management style to our corporate operations. We have been able to maintain G&A at a relatively low percentage of total cost, which helps us maximize the scientific ROI of every dollar we spend. We ended the quarter with approximately $557 million in cash and equivalents, which we believe provides us with an operating runway through early 2028. And with that, I'll turn it back over to Najat.
Thanks, Ben. I'll close by looking ahead. We have built an AI-native product engine. Now the focus is expanding its impact while continuing to translate its capabilities into the right programs and repeatable proof points. So on our wholly-owned portfolio, you should expect to see continued progress across multiple programs, additional Phase II data for REC-4881 and a regulatory update before year-end, continued advancement of REC-1245 with a more wholesome update later this year, the initiation of REC-7735, that Vicki just mentioned, and progress across the broader pipeline. We are on track across those multiple fronts. With our partners, we expect to build on this year's momentum. Following the advancement of the first previously unexplored neuroscience target with Genentech, we see the potential for additional programs to emerge from our maps. And with Sanofi, we expect the potential to continue the progression of AI designed molecules towards development candidates and later-stage milestones. We're entering an exciting period with multiple opportunities to demonstrate the power of our engine. With that, thank you again for the time today, and I'd be happy to take your questions. Great. I'm going to go through some of the questions. The first question is from Alec at BofA and Sean at Morgan Stanley: How does the collaboration with Roche-Genentech form a template for how you can leverage your platform with other partners? Maybe two to three aspects that you think are transferable and provide proof points. That's a great question, thank you both. Big picture, the way we develop our novel data sets to create novel maps, and then take those novel targets and design compounds all the way into the clinic, that Lab-in-the-Loop approach is something we use for both our internal programs and our partner programs. That template will only get better and faster over time, and we can scale it with new partners or current partners. As I mentioned before, our differentiation really lies in three areas. One is that data factory. Especially in biology, where so much is not well understood, having access to excellent biology and high-quality data is incredibly important, and it takes years to build. I want to emphasize understanding how to generate that data, validate it, develop the models, and also having a supercomputer, which we have in a secure location in Salt Lake City. Having that entire stack to make sense of the data, feed it back into the lab, and validate it is something very few companies can do, and we continue to drive momentum there. Next question. This one is from Sean at Morgan Stanley, Gil at Needham, and Brendan at Cowen: Can you provide an update on FDA engagement on REC-4881 in FAP, the registrational pathway, and the data coming up at CGA-IGC? Vicki, do you want to start?
Sure. I'd be happy to. Maybe I'll start with the upcoming data at CGA-IGC. We presented data from the Phase II TUPELO trial for the first time back in December of last year via a webinar. We think it's really important to put these data in front of the physicians who treat patients with FAP. This will be an updated data set, presented in an oral presentation at the Presidential Plenary session at that meeting in November, where you may see additional analyses that help contextualize the clinical relevance of the data and potentially additional patients in that analysis as well. We look forward to sharing those details with the FAP-treating community later this year. With respect to the FDA engagement, as we've said, these are ongoing. It's important to remember there is very limited regulatory precedent in FAP, so our engagement is focused on derisking the study design from a regulatory standpoint, including determining the appropriate primary endpoint to demonstrate clinical benefit. Speaking as someone who worked at FDA many years ago, I would say those discussions have been productive and are helping us arrive at a better study design. So nothing out of the ordinary there. Again, this is a rare disease with limited precedent, and we continue to have a productive dialogue with FDA. Once we have something more concrete to share, we look forward to providing more details later this year.
Thank you, Vicki. All right. I'll move on to the next question. Ben, this is for you from Priyanka, JPM and Gil from Needham. Can you provide more color on what operating efficiencies were done to reduce the OpEx guidance? Is there potential for further belt tightening on OpEx in second half of 2026?
Yes. Great question. As Najat covered in the presentation, we haven't changed any of our full-year guidance on the outcomes we're trying to achieve this year. That's important to remember because this reduction in guidance reflects doing the same amount or more with less. We've focused on getting to the most important answers first. You heard the descriptions of the technologies Chris and Najat discussed, and those technologies change how we operate and deliver outcomes. We started the year with ideas about where we could go, and we've seen they have real impact. We're getting to answers faster and more cheaply. The numbers to use are those in our guidance: $375 million is our expectation for where we will be operating. At our core, we keep looking for better and faster ways to do everything we do. We are a technology company, and we should become more efficient over time. We will keep looking and update you as we know more. To reiterate, we are committed to ensuring every dollar goes further through improvements in our engine. For example, we design and physically make about 90% fewer compounds for the one that goes into the clinic, and our timelines are roughly 1.5 years versus the industry's four years. Those are meaningful improvements in the velocity of our engine, and they translate into lower spend. Earlier this year we changed our budget to an outcomes-based approach so that every aspect, including partnerships, is measured against the fully loaded cost of building and mapping a program. That helps ensure efficiencies are realized. We also continue to focus on G&A to ensure each dollar goes to our programs and partnerships. We will keep putting pressure on costs; that's our commitment, just as our commitment is to deliver proof points that can be value inflection points for the broader community through programs and the use of AI to create value.
Okay. With that, I'll go to the next question, a platform question from Alec from BofA and many others, okay. With multiple tech companies entering drug development and as Generative AI becomes increasingly available, how does Recursion differentiate itself today and in the future? And what do you believe remains Recursion's durable competitive advantage competitors will find hardest to replicate over the next 5 years? Great question, Alec, and everyone else who asked that. I think that's why you saw the second slide in the presentation was really around our durable moat and our differentiation, and that evolves over time. I think number one is the data factory. Look, you just said Generative AI is becoming increasingly available, maybe some would say even commoditized. Where does the differentiation come from? If 80%, 90% of biology, as I've known, it has to come from high-quality data generation. Models depend on good quality data to be trained on. And you saw with the example with Roche-Genentech that we shared today, but also across the board, starting with disease-relevant data sets also matters. That just doesn't exist. So in order to build that 1 trillion iPSC-derived neuronal cells, that's a cell manufacturing capacity that we have in our Salt Lake City Labs. Over years, we have gone through the pain and suffering of what works and what doesn't work. So think about it as a really mature and increasingly validated capability. So that's one on the data factory. And that's not just for biology. You heard from Chris Radoux, 10 years of actually doing small molecule design, millions to billions of virtual molecules that have been generated also gives us a lot of rich data, not just in areas that are known to the world like kinases, but actually other targets that are less known and not as available in the protein database, PDB, for instance, and others. So that's one big pillar. Second, I can't emphasize enough is that Lab-in-the-Loop, that operating model because it's one thing to have great data. It's another thing to have great models. But really important, we need to validate these predictions. The only way we get this to be useful, utility at the end of the day to make a drug is if you're validating it back into the lab and that feedback, good or bad goes back into the models to make them better and smarter. We do the same thing with AI agents. The more you engage with them, the more you give them feedback, they get better. I think that integrated Lab-in-the-Loop is hard to build. It's hard to build for 2 reasons. It takes a lot of technical expertise, yes. It takes a lot of years of knowing what works, what doesn't works, yes. It takes tons of reps and with partners that are some of the best in the industry, we learn faster. But so much of it is also culture. It's culture. I've always mentioned the piece that we have bilingual scientists that better understand both science and tech that have appreciation of the challenges and opportunities of both, that open-mindedness where an agent gives you a different hypothesis from what you started, when you're in medicinal chemistry that's worked in that space for decades, that takes a different mindset, and I cannot emphasize that enough. And then the third piece is what are we actually making from the agent? FAP, first-in-class oral for a disease where nothing has been approved. It's a stand-alone high-value asset. RBM39, first-in-class target, first-in-class degrader built from this platform with limited competition. So what you'll see in our pipeline is an incremental improvement but any 1 or 2 drugs that can actually be a stand-alone differentiated asset in its own right. And we all know that takes time. So I think those are the 3 big areas that are not just an advantage for today, but continues because with every week, we're doing 2 million more experiments in our labs, the data moat grows. With every week, we actually have people turning through that lab and learning, that grows. And as you can see, with every week, month, we're making progress in our pipeline. And that takes time, resilience, focus and discipline, and that's what we're doing. Okay. One more question for Vicki. PI3K questions from Brendan at Cowen and Dennis at Jefferies. Looks like REC-7735 passed your internal criteria for go/no-go decision with the Phase I to start for second half of 2026. Can you tell us a bit more about the go/no-go process? What it is about the preclinical profile that gives you confidence that this is the right candidate? And also, what the Recursion AI platform has told you about the best development path forward in terms of study design, patient selection, et cetera? And then there's another sub-question, but I'll start with that.
Sure. First, we believe there is room for improvement in the PI3-kinase space. This is a common mutation in certain malignancies, including hormone receptor positive breast cancer, and extends beyond breast cancer into other gynecologic malignancies, head and neck cancer, colon cancer, and others. It remains an important target with an unmet need to maximize the therapeutic index and ultimately improve patient outcomes. Our go/no-go process involved a rigorous evaluation and confidence building in our preclinical data set. The selectivity allows us to hit the target hard without seeing additional toxicity. In preclinical models we are seeing efficacy that looks similar to, and at least comparable to if not improved upon, competitor profiles, a favorable safety profile including the lack of hyperglycemia, and supportive GLP toxicology studies. These factors gave us confidence that this was the right molecule to move into clinical trials. After evaluating these data we decided to go forward, submitted an IND, and that IND is now cleared. We look forward to initiating the study this year. From the clinical perspective, patients will be selected based on the H1047R mutation, so a diagnostic will be required. One key way the AI platform is helping is by enabling us to find these patients, identify the right geographies and sites for the trial, and accelerate enrollment of this patient population.
Thank you, Vicki. Maybe just a couple of things to add. We talked about this early on: for this compound specifically it is over 100-fold active against the mutant versus wild-type, so it is wild-type sparing. Why is that important? It matters because it may allow patients to stay on higher dose intensity and longer dose duration, as Vicki mentioned, to try to improve outcomes within the therapeutic index. Even with a grade 1 or 2 increase in things like hyperglycemia, we have seen that can reactivate the PI3K pathway we are trying to suppress, which can compromise efficacy. There are multiple reasons why we want to test in the clinic whether this compound gives us a better safety profile and, in turn, a better efficacy profile that improves the therapeutic index. On the AI platform, as Vicki mentioned, one key area is recruitment. We know this is a competitive space. We are starting in solid tumors, but depending on the profile we observe, the compound gives us optionality to pursue either oncology or non-oncology indications. The platform can help us find the right patient groups and geographies and sites to accelerate enrollment and to select indications others may not have explored. A lot more work is to come, but step one is to go into the clinic and confirm the features the compound was designed for. Recall that the compound was designed in 10 months, with 242 compounds synthesized over 13 cycles, and it targets a previously unpublished pocket. We are not going after the same areas as others, which is why you see almost 130-fold selectivity over wild-type—very precise, very targeted. H1047R is one of the most frequent mutations in this space and one of the mutations most tied to disease causality and progression, so we are excited. This program is one of several we are pursuing, and we will make go/no-go decisions based on the data. One quick sub-question: when should we expect initial monotherapy data? I think Vicki mentioned the first half of 2028, so stay tuned. I’m not seeing any more questions on the screen. Thank you again for joining us today. We look forward to progress over the coming weeks and months, and as always, we’ll talk to you soon.