Q1 2026 Recursion Pharmaceuticals Inc Earnings Call

May 6, 2026

Najat Khan: I've been focused on a singular question, how do we harness the full power of AI to consistently and with urgency create better medicines for patients? That requires bold ambition and a lot of focus and discipline to create value for patients and shareholders. Therefore, our approach has been deliberate. First, we're focusing on signal over noise, generating proofs and proof points across our both wholly owned programs and our partner programs with the goal to showcase that AI can truly make a difference in creating value. Second, we are continuing to evolve our platform into a repeatable AI-driven product engine. Not tech for the sake of tech, but tech that creates products of value. Third, underpinning it all is a strong commitment to financial discipline and thoughtful capital allocation, ensuring we're constantly being data-driven to prioritize and invest in our highest conviction opportunities to deliver durable value.

Speaker #1: Focus on a singular question: how do we harness the full power of AI to consistently and with urgency create better medicine for patients? That requires bold ambition and a lot of focus and discipline.

Speaker #1: To create value for patients and shareholders. And therefore, our approach has been deliberate. First, we're focusing on signal over noise. Generating proof and proof points across our both fully owned programs and our partner programs with the goal to showcase our AI can truly make a difference in creating value.

Speaker #1: Second, we are continuing to evolve our platform, into a repeatable AI-driven product engine, not tech for the sake of tech, but tech that creates products of value.

Speaker #1: And third, underpinning it all is a strong commitment to financial discipline and thoughtful capital allocation. Ensuring we're constantly being data-driven to prioritize and invest in our highest conviction opportunities to deliver durable value.

Speaker #1: Today, I'm excited to share some of our updates. We're making meaningful progress across all these fronts, which I along with Vicky and Ben will share more with you today.

Najat Khan: Today, I'm excited to share some of our updates. We're making meaningful progress across all these fronts, which I, along with Vicki and Dan, will share more with you today. With that, let's dive in. Before we do, please note that today we'll be making forward-looking statements on this call. Therefore, please refer to our SEC filings for more information. To put the progress in context, I think it's worth briefly stepping back to how we built the foundation to enable it. Look, Recursion has been on an intentional and in many ways a pioneering journey. Early on, Recursion recognized both the immense potential of AI in drug discovery, as well as the reality that, unlike many other domains, the underlying foundation, whether it's data or compute in biology and broadly in science, is still being built.

Speaker #1: With that, let's dive in. But before we do, please note that today we'll be making forward-looking statements on this call, and therefore please refer to our SAC filings for more information.

Speaker #1: To put the progress in context, I think it's worth briefly stepping back to how we built the foundation to enable it. Look, RECURSION has been on an intentional and in many ways a pioneering journey.

Speaker #1: Early on, RECURSION recognized both the immense potential of AI in drug discovery as well as the reality that unlike many other domains, the underlying foundation, whether it's data, compute, in biology, and broadly in science, is still being built.

Speaker #1: Good morning, everyone, and thank you for joining us. Since stepping into this role, I've been focused on a singular question: how do we harness the full power of AI to consistently and with urgency create better medicine for patients?

Speaker #1: That requires bold ambition and a lot of focus and discipline. To create value for patients and shareholders. And therefore, our approach has been deliberate.

Speaker #1: The map is still not complete, and that fundamentally changed how you think about applying AI. So we made a deliberate choice to invest ahead of the curve.

Najat Khan: The map is still not complete, that fundamentally changed how you think about applying AI. We made a deliberate case to invest ahead of the curve to generate and curate proprietary data, which we'll talk about more today, to build a scaled compute infrastructure, to integrate automation, and very importantly, to develop models that are purposeful and in a true closed loop lab-in-a-loop system. In a phrase that has become much more in vogue now, designed not just to predict, but to test, validate, and continuously learn. That has led to a differentiated foundation, which we continue to expand and refine today. In parallel, what's critically important is our focus now on translating that foundation into tangible proof, advancing programs, high-quality candidates, and overall demonstrating repeatability as we evolve toward a truly product-focused AI engine. Let's make this all much more concrete.

Speaker #1: To generate and curate proprietary data, which we'll talk about more today, to build a scale compute infrastructure, to integrate automation, and very importantly, to develop models that are purposeful, and in a true closed-loop, lab-in-a-loop system, you know a phrase that has become much more in vogue now, design not just to predict, but to test, validate, and continuously learn.

Speaker #1: First, we're focusing on signal over noise. Generating proofs and proof points across our both fully owned programs and our partner programs with the goal to showcase their AI can truly make a difference in creating value.

Speaker #1: Second, we are continuing to evolve our platform into a repeatable AI-driven product engine, not tech for the sake of tech, but tech that creates products of value.

Speaker #1: That has led to a differentiated foundation, which we continue to expand and refine today. But in parallel, what's critically important is our focus now on translating that foundation into tangible proof.

Speaker #1: Advancing programs, high-quality candidates, and overall demonstrating repeatability as we evolve toward a truly product-focused AI engine. But let's make this all much more concrete.

Speaker #1: Today, I'm excited to share some of our updates. We're making meaningful progress across all these fronts, which I along with Vicky and Ben will share more with you today.

Speaker #1: With that, let's dive in. But before we do, please note that today we'll be making forward-looking statements on this call, and therefore, please refer to our SAC filings for more information.

Speaker #1: As a result, where are we today? What are some of the facts? So first, we have established our clinical proof of concept, our first clinical proof of 4881 allosteric MEC12 inhibitor focused on SAP.

Najat Khan: As a result, where are we today? What are some of the facts? First, we have established our clinical proof of concept, our first clinical proof of concept, with our REC-4881 allosteric MEK1/2 inhibitor focused on FAP. We showed significant reduction in the precancerous polyps that are a huge driver of the progressive nature of the disease, as well as showing durability, something that's quite unique in the data we've shared today. Why is this important? That these are patients that have no therapeutic solutions to date and require life-altering surgeries and have near inevitable CRC risk. This is a great example of how we can translate AI-derived insights from our platform into true outcomes. More on the latest there shortly. Look, this is not just a single asset story at Recursion.

Speaker #1: We share significant reduction in the precancerous polyps, that are a huge driver of the progressive nature of the disease, as well as showing durability, something that's quite unique in the data we've shared today.

Speaker #1: And why is this important? Now, these are patients that have no therapeutic solutions to date, and require life-altering surgeries, and have near inevitable CRC risk.

Speaker #1: Early on, Recursion recognized both the immense potential of AI in drug discovery as well as the reality that, unlike many other domains, the underlying foundation—whether it's data, compute, in biology, and broadly in science—is still being built.

Speaker #1: This is a great example of how we can translate AI-driven insights from our platform into true outcomes. More on the latest there shortly. But look, this is not just a single asset story in RECURSION.

Speaker #1: The map is still not complete, and that fundamentally changed how you think about applying AI. So we made a deliberate choice to invest ahead of the curve.

Speaker #1: We now have five wholly owned programs each with clear inflection points over the next 12 to 18 months. Creating not just a consistent cadence of catalysts, but also a way for us to test, learn, and also be disciplined in our areas of programs that we invest in.

Najat Khan: We now have 5 wholly owned programs, each with clear inflection points over the next 12 to 18 months, creating not just a consistent cadence of catalysts, but and also a way for us to test, learn, and also be disciplined in our areas of programs that we invest in. We'll share more data from one of these programs, REC-1245, our RBM39 degrader. This momentum is not just in our wholly owned pipeline. It also extends in our partner portfolio, with over $500 million in inflows, and more importantly, I would say, 10 milestones delivered to date. I underscore that. You know, it's one thing to announce partnerships, but we are really focused on delivering value from these partnerships, including many of which are first in industry.

Speaker #1: To generate and curate proprietary data which we'll talk about more today, to build a scale compute infrastructure, to integrate automation, and very importantly, to develop models that are purposeful, and in a true closed-loop, lab-in-a-loop system in a phrase that has become much more in vogue now, design not just to predict, but to test, validate, and continuously learn.

Speaker #1: And we'll share more data from one of these programs REC 1245, our RBM 39 degrader. But this momentum is not just in our wholly owned pipeline.

Speaker #1: It also extends in our partner portfolio. With over 500 million in inflows and more importantly, I would say, 10 milestones delivered to date. I underscore that.

Speaker #1: That has led to a differentiated foundation, which we continue to expand and refine today. But in parallel, it's critically important as our focus now on translating that foundation into tangible proofs.

Speaker #1: You know, it's one thing to announce partnerships with real, really focused on delivering value from these partnerships, including many of which are first in industry.

Speaker #1: Advancing programs, high-quality candidates, and overall demonstrating repeatability as we evolve toward a truly product-focused AI engine. But let's make this all much more concrete.

Speaker #1: This underscores a track record of delivering tangible, differentiated outcomes, and we are deeply grateful to our partners. For their close collaboration in everything that we do.

Najat Khan: This underscores a track record of delivering tangible, differentiated outcomes, and we are deeply grateful to our partners for their close collaboration in everything that we do. Underpinning all of this is, of course, our platform, an end-to-end AI native product engine across biology, chemistry, and clinical development, powered by proprietary data and a lab-in-a-loop system and designed for repeatability. I'll share some of the latest stats from our platform later in the presentation. Importantly, look, we have to do this with focus and discipline, extending our runway into early 2028 while reducing our operating expenses by 30% year over year. This is how we are moving from promise to proof. Let me walk you through how it all comes together.

Speaker #1: As a result, where are we today? What are some of the facts? So first, we have established our clinical proof of concept, our first clinical proof of concept, with our REC 4881 allosteric MEK12 inhibitor focused on FAP.

Speaker #1: Underpinning all of this is, of course, our platform, an end-to-end AI-native product engine across biology, chemistry, and clinical development. Powered by proprietary data and a lab-in-the-loop system, and designed for repeatability.

Speaker #1: We share significant reduction in the precancerous polyps that are a huge driver of the progressive nature of the disease, as well as showing durability—something that's quite unique in the data we've shared today.

Speaker #1: And I'll share some of the latest stats from our platform later in the presentation. And then importantly, look, we have to do this with focus and 2028, where reducing our operating expenses by 30% year over from promise to proof.

Speaker #1: And why is this important? These are patients that have no therapeutic solutions to date, and require life-altering surgeries, and have near-inevitable CRC risks.

Speaker #1: So let me walk you through how it all comes together. How do we pull this together for the ultimate goal of delivering better medicines for patients?

Najat Khan: How do we pull this together for the ultimate goal of delivering better medicine for patients? At the foundation is an AI-native product engine that combines proprietary multimodal data, integrated wet and dry labs, purpose-built models, and scale compute. We hear those words a lot, but what differentiates us is not one model, it's not one data set, it's not one program. It's the integration of our tools, technologies, and our team. Look, our proprietary multimodal data has both proprietary data that we have generated in our labs, which we also integrate with public data. We sit in the sweet spot of leveraging both. Our automated wet labs in Salt Lake City and Milton Park, Oxford for those that are not as familiar with Milton Park, are interconnected with purpose-built AI models, and we have in-house supercomputer resources to rapidly build those algorithms and learn from them.

Speaker #1: As the foundation, it's an AI-native product engine that combines proprietary multimodal data, integrated wet and dry scaled compute. Now, we hear those words a lot, but what differentiates us is not one model.

Speaker #1: We now have five wholly owned programs, each with clear inflection points over the next 12 to 18 months, creating not just a consistent cadence of catalysts, but also a way for us to test, learn, and also be disciplined in our areas of programs that we invest in.

Speaker #1: program. It's the integration of our tools, technologies, and our teams. Look, our proprietary multimodal data has both proprietary data, that we have generated in our labs, which we also integrate with public data.

Speaker #1: And we'll share more data from one of these programs REC 1245, our RBM 39 degrader. But this momentum is not just in our wholly owned pipeline.

Speaker #1: We sit in the sweet spot of leveraging both. Our automated wet labs and solid city and Milton Park, I've heard for those that are not as familiar with Milton Park, are interconnected with purpose-built AI models.

Speaker #1: It also extends in our partner portfolio. With over 500 million in inflows and more importantly, I would say, 10 milestones delivered to date. I underscore that.

Speaker #1: And we have in-house supercompute resources It's not one data set. to rapidly build those algorithms and learn from them. And I have to say, and it's not just It's not one words, we've truly mean it.

Speaker #1: It's one thing to announce partnerships but we are really focused on delivering value from these partnerships, including many of which are first in industry.

Najat Khan: I have to say, it's not just words, we truly mean it. Spanning all of this is our greatest research. You've heard me say this over and over again, bilingual talent. AI researchers who appreciate the humility in making medicines and who bring a completely different take to how we can make medicines, and drug developers and drug hunters with reps under their belts that have seen what it really takes to make a drug from start to finish, and who are open-minded about unlocking the potential of AI. Make no mistake, the culture and the talent and the integration it takes is one of the hardest things to do in this space, and I'm excited that we have made so much great progress there. These in all these ingredients come together in a vertically integrated AI-native platform, starting first with biology.

Speaker #1: Spanning all of this is our greatest resource. So you've heard me say this over and over again, bilingual talent. AI researchers who appreciate the humility in making medicines, and who bring a completely different take to how we can make medicines, and drug developers and drug hunters with recs under their belts that have seen what it really takes to make a drug from start to finish.

Speaker #1: This underscores a track record of delivering tangible differentiated outcomes and we are deeply grateful to our partners. For their close collaboration in everything that we do.

Speaker #1: Underpinning all of this is, of course, our platform—an end-to-end, AI-native product engine across biology, chemistry, and clinical development. Powered by proprietary data and a lab-in-the-loop system, and designed for repeatability.

Speaker #1: And who are open-minded about unlocking the potential of AI. Make no mistake, the culture and the talent and the integration it takes is one of the hardest things to do in this space.

Speaker #1: And I'll share some of the latest stats from our platform later in the presentation. And then importantly, look, we have to do this with focus and discipline.

Speaker #1: And I'm excited that we have made so much great progress there. Now, these all these ingredients come together in a vertically integrated AI-native platform, starting first with biology.

Speaker #1: Extending our runway into early 2028 while reducing our operating expenses by 30% year over year. This is how we are moving from promise to proof.

Speaker #1: So we can simulate and understand biology much more effectively when we really want to move away from the stats that we only the industry only understands about 10% of biology.

Najat Khan: We can simulate and understand biology much more effectively when we really want to move away from the stats that the industry only understands, like, 10% of biology. This is what allows us to identify novel targets. This is where we're pushing the boundaries to really understand the root cause of disease. The next click, this really came from the integration with Exscientia, applying generative chemistry and active learning and many other approaches to design precisionally created differentiated molecules. This is what helps us create both first-in-class programs for those novel targets, as well as really high-value best-in-class programs. For instance, optimizing therapeutic index for programs that have been around but haven't fully maximized their potential to date in industry.

Speaker #1: So let me walk you through how it all comes together. How do we pull this together for the ultimate goal of delivering better medicine solutions?

Speaker #1: This is what allows us to identify novel targets. This is where we're pushing the boundaries to really understand the root cause of disease. The next click, this really came from the integration with Exscientia, applying generative chemistry and active learning and many other approaches to design precisionly created differentiated molecules.

Speaker #1: As the foundation, it's an AI-native product engine that combines proprietary multimodal data integrated wet and dry labs, purpose-built models, and scaled compute. Now we hear those words a lot, but what differentiates us is not one model.

Speaker #1: It's not one data set. It's not one program. It's the integration of our tools, technologies, and our teams. Look, our proprietary multimodal data has both proprietary data that we have generated in our labs, which we also integrate with public data.

Speaker #1: This is what helps us create both first-in-class programs for those novel targets as well as really high-value best-in-class programs. For instance, optimizing therapeutics index for programs that have been around but haven't fully maximized their potential to date in industry.

Speaker #1: We fit in the sweet spot of leveraging both. Our automated wet labs and solid city and Milton Park are perfect for those that are not as familiar with Milton Park.

Speaker #1: And third, this is something we've built over the last year or so, applying our data and insights to also inform a smarter, more effective, and patient-centric path to all of clinical development.

Najat Khan: Third, this is something we've built over the last year or so, applying our data and insights to also inform a smarter, more effective, and patient-centric path to all of clinical development. Look, all of this is great to have, but we take it together to build a broad and diversified portfolio, both internally and with our close partners, with the ultimate goal of developing differentiated medicines for patients with significant unmet needs. We do it faster, we want to do it better. How do we do this? You know, our strategy remains unchanged from what you heard the last time. We want to be clear, focused, disciplined, while being ambitious. First, translating proved products. We are advancing our deep pipeline learnings, the goal is to have revenue-generating medicines for patients.

Speaker #1: Our interconnected with purpose-built AI models and we have in-house supercompute resources to rapidly build those algorithms and learn from them. And I have to say, and it's not just words, we truly mean it.

Speaker #1: Look, all of this is great to have, but we take it together to build a broad and diversified portfolio. Both internally and with our close partners.

Speaker #1: Expanding all of this is our greatest resource. You've heard me say this over and over again, bilingual talent. AI researchers who appreciate the humility in making medicine and who bring a completely different take to how we can make medicines and drug developers and drug hunters with reps under their belts that have seen what it really takes to make a drug from start to finish.

Speaker #1: With the ultimate goal of developing differentiated medicines for patients. With significant unmet needs. We do it faster, we want to do it better. But how do we do this?

Speaker #1: You know, our strategy remains unchanged from what you've heard the last time. We want to be clear, focused, disciplined, while being ambitious. First, translating proofed products.

Speaker #1: And who are open-minded about unlocking the potential of AI. Make no mistake, the culture and the talent and the integration it takes is one of the hardest things to do in this space.

Speaker #1: We're advancing our deep pipeline learnings and the goal is to have revenue-generating medicines for patients. And we do it by applying a rigorous rate of difference, prioritization, approach.

Speaker #1: And I'm excited that we have made so much great progress there. Now these all these ingredients come together in a vertically integrated AI-native platform, starting first with biology.

Najat Khan: We do it by applying a rigorous data-driven prioritization approach so that we only invest behind the most highest confidence opportunities. Second, as you heard me say, scaling a differentiated AI-native product engine. Look, the platform is the heartbeat of so much that we do, where each prediction and experimentation allows us to compound our learning and advantage to drive repeatability in creating better products. Third is pairing that bold ambition with disciplined execution. You know, rigorous capital allocation is something we think about constantly, ensuring that there is operational focus and that our milestones are measurable to sustain that long-term value creation. You'll hear more about that from Ben. Let's just dive in into one of our first pillars, which is our wholly owned pipeline. Look, I'm proud to share how the strategy is beginning to translate into early signals of pipeline progress.

Speaker #1: So that we only invest behind the most highest confidence opportunities. Second, as you heard me say, scaling a differentiated AI-native product engine. Look, the platform is the heartbeat of so much that we do.

Speaker #1: So we can simulate and understand biology much more effectively where we really want to move away from the stats that we only the industry only understands about 10% of biology.

Speaker #1: Where each prediction and experimentation allows us to compound our learning and advantage to drive repeatability in creating better products. And third is pairing that bold ambition with discipline execution.

Speaker #1: This is what allows us to identify novel targets. This is where we're pushing the boundaries to really understand the root cause of disease. The next click, this really came from the integration with Exscientia trying generative chemistry and active learning and many other approaches to design precision-created differentiated molecules.

Speaker #1: You know, rigorous capital allocation is something we think about constantly. Ensuring that there is operational focus and that our milestones are measurable to sustain that long-term value creation.

Speaker #1: You'll hear more about that from Dr. Shelby. So let's just dive in into one of our first pillars. Which is our wholly owned pipeline.

Speaker #1: This is what helps us create both first-in-class programs for those novel targets as well as really high-value, best-in-class programs. For instance, optimizing therapeutics index for programs that have been around but haven't fully maximized their potential to date in industry.

Speaker #1: Look, I'm proud to share how the strategy is beginning to translate into early signals of pipeline progress. What you see here is a broad and increasingly diverse set of programs, built on two key areas.

Speaker #1: And third, this is something we've built over the last year or so, applying our data and insights to also inform a smarter, more effective and patient-centric lab to all of clinical development.

Najat Khan: What you see here is a broad and increasingly diverse set of programs built on two key areas. Number one, clear rationale for differentiation coming from our platform. Second, a defined path, a rapid and defined path, I should say, to upcoming milestones and decision points. The differentiation across these programs takes two forms. One, in some cases, it starts with a novel biological target or novel mechanistic insights. You'll see more of these coming from our discovery part of our platform. The other is driven by differentiated molecular designs. The third, more recently, as we built out the clinical development AI platform, how we design the patients that we pick, how do we design our protocols, and how do we execute them in the clinic?

Speaker #1: Number one, clear rationale for differentiation, coming from a platform. And second, a defined task of rapid and defined path, I should say, to upcoming milestones and decision points.

Speaker #1: Look, all of this is great to have, but we take it together to build a broad and diversified portfolio—both internally and with our close partners.

Speaker #1: And the differentiation across these programs takes two steps. One, in some cases, it starts with a novel biological target or novel mechanistic insights. You'll see more of these coming from our discovery part of our platform.

Speaker #1: With the ultimate goal of developing differentiated medicines for patients. With significant unmet needs. We do it faster, we want to do it better. But how do we do this?

Speaker #1: And then the other is driven by differentiated molecular design. And then the third, more recently, as we've built up the clinical development AI platform, how we design with patients to be picked, how do we design our protocols, and how do we execute in the clinic.

Speaker #1: Our strategy remains unchanged from what you've heard the last time. We want to be clear, focused, disciplined while being ambitious. First, translating proofed products.

Speaker #1: We're advancing our deep pipeline learnings, and the goal is to have revenue-generating medicines for patients. We do this by applying a rigorous, beta-driven prioritization approach.

Speaker #1: Let me double-click some of the latest highlights from the last quarter on these slides. A period that is marked by strong and accelerating clinical momentum.

Najat Khan: Let me double-click some of the latest highlights from the last quarter on these slides, a period that is marked as strong and accelerating clinical momentum. Let's start with REC-4881. This is our allosteric MEK1/2 inhibitor. As you recall, this program is rooted in a novel mechanistic insight with the potential to become a first precision therapy for FAP. As I mentioned earlier, and I can't mention it enough, a serious and under-served condition where patients often face very limited treatment options and no medical or therapeutic options to date. We have generated compelling proof of concept, and we're continuing to advance the program with urgency and vigor, including we've already initiated FDA engagement to define a potential registrational path forward. We're very excited to share more update on this in the H2 of this year. Next, turning to REC-1245.

Speaker #1: So let's start with Rec 48.1. This is our allosteric micronutrient inhibitor. As you recall, this program is rooted in a novel mechanistic insight, but the potential to become a first precision therapy for FAP.

Speaker #1: For each prediction and experimentation allows us to compound our learning and advantage to drive repeatability in creating better products. And third is pairing that bold ambition with discipline execution.

Speaker #1: As I mentioned earlier, and I can't mention it enough, a serious and underdeserved condition for patients often face very limited treatment options and no medical or therapeutic options to date.

Speaker #1: Rigorous capital allocation is something we think about constantly. Ensuring that there is operational focus and that our milestones are measurable to sustain that long-term value creation.

Speaker #1: We have generated compelling proof of concept, and we're continuing to advance the program with urgency and rigor, including we've already initiated FDA engagement to define a potential registrational path forward.

Speaker #1: You'll hear more about that from Ben Taylor. So let's just dive in to one of our first pillars, which is our wholly owned pipeline.

Speaker #1: We're very excited to share more update on this in the second half of this year. Next, turning to Rec 1245. This is our platform derived first-in-class target and degrader.

Najat Khan: This is our platform-derived first-in-class target and degrader with the potential to address multiple solid tumors and lymphomas. We're excited to share today early clinical data around the safety, tolerability, and PK profile as promised. To date, we have observed a well-tolerated profile with no dose-limiting toxicities to date, and we're continuing to advance the program with additional data expected later this year. In a few minutes, Dr. Vicki Goodman, our Chief Medical Officer, will walk through the details more in detail. Finally, REC-4539. This is our LSD-1 inhibitor for the potential treatment in solid tumors, including small cell lung cancer and also in AML. What differentiates this program is the underlying molecule designed with our generated platform to overcome some of the treatment limiting on-target toxicity seen to date in earlier LSD-1 inhibitors.

Speaker #1: With the potential to direct multiple solid tumors and lymphomas. We're excited to share today early clinical data around the safety, tolerability, and PK profile as promised.

Speaker #1: Number one, clear rationale for differentiation coming from a platform. And second, a defined task of rapid and defined path, I should say, to upcoming milestones and decision points.

Speaker #1: To date, we have observed a well-tolerated profile with no dose-limiting toxicities to date. And we're continuing to advance the program with additional data expected later this year.

Speaker #1: In a few minutes, Dr. Vicky Goodman, our chief medical officer, will walk through the details more in detail. And finally, Rec 4539. This is our LSD1 inhibitor for the potential treatment and solid tumors, including small cell lung cancer and also in AML, with different shapes this program is the underlying molecule.

Speaker #1: Designed with our generative platforms to overcome some of the treatment-limiting on-target toxicities since to date in earlier LSD1 inhibitors. We've now initiated our phase one clinical trial and dosed our first patient with additional updates coming second half of 2027.

Najat Khan: We've now initiated our phase I clinical trial and dosed our first patient with additional updates coming H2 2027. I'll talk more about the program, the biology, unmet need, as well as the platform insight, shortly. All of the other programs remain on track. Now, we're also continuing to see strong, consistent execution across our partner pipeline, where our platform is being applied in close partnership with our esteemed partners, whose deep expertise, collaborations, and capabilities we are deeply grateful for. What is emerging, I wanna highlight, is 2 potential unlocks. As an example, with Sanofi, the unlock is use of AI on the chemistry design side. They're taking difficult and diverse protein targets in immunology and oncology, using our platform and AI in partnership with Sanofi to drug these historically challenging targets.

Speaker #1: Let me double-click some of the latest highlights from the last quarter on these slides. A period that is marked by strong and accelerating clinical momentum.

Speaker #1: I'll talk more about the program, the biology, unmet need, as well as the platform insight shortly. All of the other programs remain on track.

Speaker #1: So let's start with REC4881. This is our allosteric micronutrient inhibitor. As you recall, this program is rooted in a novel mechanistic insight with the potential to become a first precision therapy for FAP.

Speaker #1: Now, we're also continuing to see strong consistent execution across our partner pipeline. Where our platform is being applied in close partnership with our esteemed partners, whose deep expertise collaborations and capabilities we are deeply grateful for.

Speaker #1: As I mentioned earlier, and I can't mention it enough, a serious and underdeserved condition for options and no medical or therapeutic options to date.

Speaker #1: We have generated compelling proof of concept and we're continuing to advance the program with urgency and rigor, including we've already initiated FDA engagement to define a potential registrational path forward.

Speaker #1: And what's emerging, I want to highlight, is two potential unlocks. As an example, with Sanofi, the unlock is use of AI on the chemistry design side.

Speaker #1: We're very excited to share more update on this in the second half of this year. Next, turning to REC1245. This is our platform derived first-in-class target and degrader.

Speaker #1: You know, taking difficult and diverse protein targets in immunology and oncology, using our platform and AI in partnership with Sanofi to drug these challenging historically challenging targets.

Speaker #1: With the potential to address multiple solid tumors and lymphomas. We're excited to share today early clinical data around the safety, tolerability, and CK profile as promised.

Speaker #1: These programs are progressing to a key inflection point over the next 12 months, including a potential for development candidate, which is a big unlock in terms of potentially onboarding that asset into our partners' portfolio.

Najat Khan: These programs are progressing to reach key inflection points over the next twelve months, including potential for development candidates, which is a big unlock in terms of potentially onboarding that asset into our partnership portfolio. With Roche Genentech, the unlock is on the biology side. You know, Roche Genentech have been pioneers in really thinking about, you know, leveraging biology perturbation at scale to really take large scale multimodal maps and translate them into actionable and validated programs. The unlock here is, I mean, you hear a lot around large scale data sets being generated across the industry. Well, the unlock is how do we translate that using foundation models that we're building and robust experimental target validation into not only validated targets, but potential first-in-class programs, something the field has long aspired to do.

Speaker #1: To date, we have observed a well-tolerated profile with no dose-limiting toxicities to date. And we're continuing to advance the program with additional data expected later this year.

Speaker #1: And with Roche Genentech, the unlock is on the biology side. You know, Roche Genentech has been pioneers in really thinking about, you know, leveraging biology perturbation at scale to really take large-scale multimodal maps and translate them into actionable and validated programs.

Speaker #1: In a few minutes, Dr. Vicky Goodman, our Chief Medical Officer, will walk through the details in more detail. And finally, REC4539—this is our LSD1 inhibitor for the potential treatment of solid tumors, including small cell lung cancer, and also in AML. With different shapes, this program is the underlying molecule.

Speaker #1: So the unlock here is, you know, you hear a lot around large-scale data sets being generated across the industry. Well, the unlock is how do we translate that using foundational models that we're building and robust experimental target validation into not only validated targets, but potential first-in-class programs.

Speaker #1: Designed with our generative platforms to overcome some of the treatment-limiting on-target toxicities seen to date in earlier LSD1 inhibitors. We've now initiated our Phase One clinical trial and dosed our first patient, with additional updates coming in the second half of 2027.

Speaker #1: Something the field has long aspired to do. So we have a potential first on track in the next 12 months or so. Look, we talked a lot about our wholly owned programs, our partnered programs, excited about the momentum we're building here, and about a platform that underscores it.

Najat Khan: We have a potential first, on track in the next 12 months or so. We talked a lot about our whole genome programs, our partnered programs, excited about the momentum we're building here and about our platform that underscores it. The secret sauce of any organization is talent. Talent is critical to everything we do. Continuing to build a strong, experienced, ambitious, and humble team is a key part of how we drive value. With that, I am really pleased to introduce our newest member of our executive leadership team, Dr. Vicki Goodman, our new CMO. Now, Vicki comes to us with an incredibly strong track record of delivering transformational medicines for patients across many parts of the industry, starting at the FDA, large pharma, and biotech. You can read about all her credentials on the slide, which I won't go through in detail.

Speaker #1: I'll talk more about the program, the biology, unmet need, as well as the platform insight shortly. All of the other programs remain on track.

Speaker #1: But the secret sauce of any organization is talent. Talent is critical to everything we do. And continuing to build a strong experienced, ambitious, and humble team is a key part of how we drive value.

Speaker #1: Now, we're also continuing to see strong consistent execution across our partner pipeline. We're a platform is being applied in close partnership with our esteemed partners whose deep expertise collaborations and capabilities we are deeply grateful for.

Speaker #1: And with that, I am really pleased to introduce our newest member of our executive leadership team, Dr. Vicky Goodman. Our new CMO, you know, Vicky comes to us with an incredibly strong track record of delivering transformational medicines for patients.

Speaker #1: And what's emerging, I want to highlight, is two potential unlocks. As an example, with Sanofi, the unlock is use of AI on the chemistry design side.

Speaker #1: Across many parts of the industry, you know, starting at the FDA, large pharma, and biotech, you can read about all her credentials on the slide, which I won't go through in detail.

Speaker #1: Taking difficult and diverse protein targets in immunology and oncology, using our platform and AI in partnership with Sanofi to drug these challenging historically challenging targets.

Speaker #1: But simply put, you know, Vicky is the right person with the right skill set to lead recursion's clinical development in this next chapter of the journey.

Najat Khan: Simply put, you know, Vicki is the right person with the right skill set to lead Recursion's clinical development in this next chapter of the journey, but more importantly, with the right heart and perseverance to go through the trials and tribulations that's drug discovery and development. With that, I'm gonna turn it over to Vicki. Vicki, why don't you kick us off with a few words about joining Recursion, and then more details about our pipeline to follow.

Speaker #1: But more importantly, with the right heart and perseverance to go through the trials and tribulations that drug discovery and development. With that, I'm going to turn it over to Vicky.

Speaker #1: Vicky, why don't you kick us off with a few words about joining Recursion and then more details about Rec 1245?

Speaker #1: And with Roche Genentech, the unlock is in the biology side. Roche Genentech has been pioneers in really thinking about leveraging biology perturbation at scale to really take large-scale multimodal maps and translate them into actionable and validated programs.

Speaker #2: Thank you, Najat, for the kind introduction and for the opportunity to work with you and the rest of the Recursion team. One of the reasons I joined Recursion is because the breadth and differentiation of our pipeline represents one of the most exciting opportunities to translate AI advances into meaningful therapies for patients.

Vicki Goodman: Thank you, Najat, for the kind introduction and for the opportunity to work with you and the rest of the Recursion team. One of the reasons I joined Recursion is because the breadth and differentiation of our pipeline represents one of the most exciting opportunities to translate AI advances into meaningful therapies for patients. Today marks exactly one month since I joined, and even in that short time, I've found Recursion to be a place where scientific rigor, intellectual curiosity, and a deep spirit of innovation are brought to bear on the creation of new medicines that matter. It's wonderful to be part of the team, and I look forward to continuing this important work. Today, I have the privilege of presenting an exciting clinical update for REC-1245 from the ongoing DAHLIA phase I study, including preliminary safety and pharmacokinetics.

Speaker #1: So, the unlock here is, you hear a lot about large-scale data sets being generated across the industry. Well, the unlock is, how do we translate that—using foundational models that we're building and robust experimental target validation—into not only validated targets, but potential first-in-class programs.

Speaker #2: Today marks exactly one month since I joined, and even in that short time, I've found Recursion to be a place where scientific rigor, intellectual curiosity, and a deep spirit of innovation are brought to bear on the creation of new medicines that matter.

Speaker #2: It's wonderful to be part of the team, and I look forward to continuing this important work. Today, I have the privilege of presenting an exciting clinical update for Rec 1245 from the ongoing Dahlia phase one study, including preliminary safety and pharmacokinetics.

Speaker #2: Rec 1245 is an RBM39 degrader currently in phase one for the treatment of patients with solid tumors and lymphomas. RBM39 is a novel target which plays a central role in splicing fidelity.

Vicki Goodman: REC-1245 is an RBM39 degrader currently in phase I for the treatment of patients with solid tumors and lymphomas. RBM39 is a novel target which plays a central role in splicing fidelity. When RBM39 is degraded, it induces widespread splicing defects to which tumors that are already under stress, such as those with DNA damage repair deficiencies, global genomic instability, or replication stress may be particularly sensitive. Additionally, RBM39 is highly expressed in certain tumors and is associated with disease progression and poor survival. The relevant patient population is estimated to be over 100,000 patients in the US and EU5. That's the why RBM39 is an interesting target. The how we came to be working on RBM39 is a story we've touched on before. It's an example of how the biology element as our AI-driven platform enables the identification of novel therapeutic targets.

Speaker #1: And with that, I am really pleased to introduce our newest member of our executive leadership team, Dr. Vicky Goodman, our new CMO. Vicky comes to us with an incredibly strong track record of delivering transformational medicines for patients.

Speaker #2: When RBM39 is degraded and induces widespread splicing defects, to which tumors that are already under stress, such as those with DNA damage repair deficiencies, global genomic instability, or replication stress, may be particularly sensitive.

Speaker #1: Across many parts of the industry, starting at the FDA, large pharma, and biotech, you can read about all her credentials on the slide, which I won't go through in detail.

Speaker #2: Additionally, RBM39 is highly expressed in certain tumors, and is associated with disease progression and poor survival. The relevant patient population is estimated to be over 100,000 patients in the US and EU side.

Speaker #1: But simply put, Vicky is the right person with the right skill set to lead recursion's clinical development in this next chapter of the journey.

Speaker #2: So that's the why RBM39 is an interesting target. The how we came to be working on RBM39 is a story we've touched on before.

Speaker #1: Vicky, why don't you kick us off with a few words about joining Recursion and then more details about REC1245?

Speaker #2: It's an example of how the biology element of our AI-driven platform enables the identification of novel therapeutic targets. Using genome-scale phenomic mapping, our maps of biology, RBM39 emerged as a functional analog of CDK12.

Vicki Goodman: Using genome-scale phenomics mapping, our maps of biology, RBM39 emerged as a functional analog of CDK12. This novel relationship, which came from an unbiased platform insight, was not obvious from sequence homology or traditional pathway analysis. CDK12 is a well-known oncology target for its role in DNA damage response modulation, but it has generally suffered from challenges in selectivity because of how homologous to CDK13 it is. Following our insight, we developed molecular glues and degraders for RBM39, and we showed that these phenotypically mimic CDK12 loss, but not CDK13. This provides a druggable potential analog for CDK12 without the CDK13-driven toxicity. We progressed from target ID to IND-enabling studies with roughly 200 compounds synthesized in 18 months, which is significantly faster than traditional approaches. We needed to correlate our insights with the mechanism of action for RBM39 to translate them into clinically actionable hypotheses.

Speaker #2: This novel relationship, which came from an unbiased platform insight, was not obvious from sequence homology or traditional pathway analysis. CDK12 is a well-known oncology target for its role in DNA damage response modulation, but it has generally suffered from challenges in selectivity because of how homologous to CDK13 it is.

Speaker #2: It's wonderful to be part of the team, and I look forward to continuing this important work. Today, I have the privilege of presenting an exciting clinical update for REC1245 from the ongoing DALIA phase one study, including preliminary safety and pharmacokinetics.

Speaker #2: Following our insight, we developed molecular glues and degraders for RBM39, and we showed that these phenotypically mimic CDK12 loss but not CDK13. This provides a druggable potential analog for CDK12 without the CDK13-driven toxicity.

Speaker #2: REC1245 is an RBM39 degrader currently in phase one for the treatment of patients with solid tumors and lymphomas. RBM39 is a novel target which plays a central role in splicing fidelity.

Speaker #2: We progressed from target ID to IND enabling studies with roughly 200 compound synthesized in 18 months, which is significantly faster than traditional approaches. We then needed to correlate our insights with the mechanism of action for RBM39 to translate them into clinically actionable hypotheses.

Speaker #2: We confirmed through in vitro studies that there is a greater sensitivity to Rec 1245 in cell lines that have higher replication stress and DNA repair vulnerability versus cell lines that don't have higher replication stress.

Vicki Goodman: We confirmed through in vitro studies that there is a greater sensitivity to REC-4545 in cell lines that have higher replication stress and DNA repair vulnerability versus cell lines that don't have higher replication stress. In the panel on the right, you can also see that in vivo tumor regression in an MSI-high ovarian CDX model was also demonstrated. We've carried these insights forward into the design of our DAHLIA phase I/II clinical trial. Our early clinical strategy focuses on tumor types with those same characteristics that suggested sensitivity in our preclinical experiments. The safety and PK data we are sharing today is from 16 patients enrolled across the first 4 dose levels. All patients have advanced solid tumors, and 7 of the 16 have MSI-high or mismatch repair deficient tumors. Importantly, REC-4545 is well-tolerated.

Speaker #2: And in the panel on the right, you can also see that in vivo tumor regression in an MSI high ovarian CDX model was also demonstrated.

Speaker #2: So that's the why RBM39 is an interesting target. The how we came to be working on RBM39 is a story we've touched on before.

Speaker #2: We've carried these insights forward into the design of our Dahlia phase one two clinical trial. Our early clinical strategy focuses on tumor types with those same characteristics that suggested sensitivity in our preclinical experiments.

Speaker #2: It's an example of how the biology element of our AI-driven platform enables the identification of novel therapeutic targets. Using genome-scale genomic mapping, our maps of biology, RBM39 emerged as a functional analog of CDK12.

Speaker #2: The safety and PK data we are sharing today is from 16 patients enrolled across the first four dose levels. All patients have advanced solid tumors and seven of the 16 have MSI high or mismatch repair deficient tumors.

Speaker #2: Importantly, Rec 1245 is well tolerated. Across the dose levels evaluated to date, there have been no doubt dose limiting toxicities reported. The most common treatment-related adverse events that have been observed are GI-related, constipation, nausea, and vomiting, as you can see these are generally low-grade with one grade three event of nausea and vomiting reported.

Vicki Goodman: Across the dose levels evaluated to date, there have been no dose-limiting toxicities reported. The most common treatment-related adverse events that have been observed are GI-related: constipation, nausea, and vomiting. As you can see, these are generally low-grade, with one grade 3 event of nausea and vomiting reported. There have been no treatment-related serious adverse events. Dose escalation is ongoing, recruitment is on track. We have an early PK/PD summary from the evaluated patients to date, we'll have more dose escalation data and a fuller PK/PD update in H2 of the year. So far, we are seeing predictable dose-dependent exposure, with exposures continuing to increase as we move through the dose levels and PK data that are supportive of daily dosing. Our initial PD data also confirm target engagement.

Speaker #2: There have been no treatment-related serious adverse events. Dose escalation is ongoing and recruitment is on track. We have an early PKPD summary from the evaluated patients to date, and we'll have more dose escalation data and a fuller PKPD update in the second half of the year.

Speaker #2: So far, we are seeing predictable dose-dependent exposure with exposures continuing to increase as we move through the dose levels and PK data that are supported of daily dosing.

Speaker #2: We confirmed through in vitro studies that there is a greater sensitivity to REC1245 in cell lines that have higher replication stress and DNA repair vulnerability versus cell lines that don't have higher replication stress.

Speaker #2: Our initial PD data also confirm target engagement. We expect, as we move through the next two dose levels, to see exposures that are correlated with tumor regressions in mice.

Vicki Goodman: We expect, as we move through the next two dose levels, to see exposures that are correlated with tumor regressions in mice. Overall, RBM39 represents an end-to-end example of how we're using AI to translate a novel insight into a potential medicine, not just identifying a target, but building a coherent biological hypothesis that informs clinical strategy. I look forward to sharing more data with you later this year. With that, I'll turn it back to Najat Khan.

Speaker #2: Overall, RBM39 represents an end-to-end example of how we're using AI to translate a novel insight into a potential medicine. Not just identifying a target, but building a coherent biological hypothesis that informs clinical strategy.

Speaker #2: And in the panel on the right, you can also see that in vivo tumor regression in an MSI high ovarian CDX model was also demonstrated.

Speaker #2: We've carried these insights forward into the design of our DALIA phase one two clinical trial. Our early clinical strategy focuses on tumor types with those same characteristics that suggested sensitivity in our preclinical experiments.

Speaker #2: I look forward to sharing more data with you later this year, and with that, I'll turn it back to Najat.

Speaker #1: Thank you, Vicky. Now moving on to LSD1, Rec 4539. You know, first, I'm pleased to share and announce that we have dosed the first patient in our phase one clinical trial.

Najat Khan: Thank you, Vicki. Moving on to LSD-1, REC-4539. You know, first, I'm pleased to share and announce that we have dosed the first patient in our phase I clinical trial. Taking a step back, let's discuss a little bit as to why we think that LSD-1 is an interesting target for Recursion. As many of you know, LSD-1 is an epigenetic regulator with a range of cellular functions and a promising oncology target across multiple cancer types. You know, however, so far clinically, the potential of LSD-1 inhibitors have not been fully met. Previous clinical attempts to drug LSD-1 have shown some efficacy but have been limited by on-target and dose-limiting thrombocytopenia. While the biology is understood, the challenge has been at the level of the molecules.

Speaker #2: The safety and PK data we are sharing today is from 16 patients enrolled across the first four dose levels. All patients have advanced solid tumors, and seven of the 16 have MSI-high or mismatch repair-deficient tumors.

Speaker #1: But taking a step back, let's discuss a little bit as to why we think that LSD1 is an interesting target for recursion. As many of you know, LSD1 is an epigenetic regulator with a range of cellular functions and a promising oncology target across multiple cancer types.

Speaker #2: Importantly, REC1245 is well tolerated. Across the dose levels evaluated to date, there have been no doubt dose limiting toxicities reported. The most common treatment-related adverse events that have been observed are GI-related, constipation, nausea, and vomiting, as you can see these are generally low-grade with one grade three event of nausea and vomiting reported.

Speaker #1: You know, however, so far clinically, the potential of LSD1 inhibitors has not been fully met. Previous clinical attempts to drug LSD1 have shown some efficacy, but have been limited by on-target and dose-limiting thrombocytopenia.

Speaker #1: So while the biology is understood, the challenge has been at the level of the knowledge. And therefore, we believe this has the potential to unlock a meaningful therapeutic opportunity particularly in settings like extensive-stage small cell lung cancer where there are approximately 45,000 patients in the US and EU side with emerging but still limited treatment options after progression on first-line dose.

Najat Khan: Therefore, we believe this has the potential to unlock a meaningful therapeutic opportunity, particularly in settings like extensive stage small cell lung cancer. There are approximately 45,000 patients in the US and EU5 with emerging but still limited treatment options after progression on first-line therapy. For this program, the starting point matters, you know, and this is where our chemistry AI part of the platform really shines.

Speaker #2: So far, we are seeing predictable dose-dependent exposure with exposures continuing to increase as we move through the dose levels and PK data that are supported of daily dosing.

Speaker #1: So for this program, the starting point mattered. You know, and this is where our chemistry AI part of the platform really shines. We intentionally moved away from traditionally traditional biased chemistry chemical space and instead used a blank white sheet, active learning to explore a broader or information-rich space.

Speaker #2: Our initial PD data also confirm target engagement. We expect, as we move through the next two dose levels, to see exposures that are correlated with tumor regressions in mice.

Najat Khan: We intentionally moved away from traditional bias chemistry chemical space, and instead used a blank slate machine, active learning to explore a broader but information-rich space, which allowed us to identify novel starting points that wouldn't typically. What that led us to is identifying a new scaffold, and we iteratively just refined it, ultimately arriving at the compound REC-4539 in approximately 20 months in just over 400 synthesized compounds, much faster and fewer than what is industry standard. You know, compare that also to what Vicki had mentioned with RBM39, 18 months and about 209 compounds synthesized to date. You're starting to see these, as I like to call them, green shoots in terms of the number of compounds synthesized, the speed, and the efficiency in how we're generating novel compounds.

Speaker #1: Which allowed us to identify novel starting points that wouldn't typically be pursued. What that led us to is identifying a new step, and we iteratively refined it.

Speaker #1: Ultimately arriving at the compound Rec 4139, 4539, in approximately 20 months and just over 400 synthesized compounds. Much faster and pure than what is industry standard.

Speaker #2: I look forward to sharing more data with you later this year, and with that, I'll turn it back to Najat.

Speaker #1: Thank you, Vicky. Now moving on to LSD1, REC4539. First, I'm pleased to share and announce that we have dosed the first patient in our phase one clinical trial.

Speaker #1: You know, compare that also to what Vicky had mentioned with RBM39, 18 months and about 209 compound synthesized to date. So you're starting to see these what I like to call them green shoots in terms of the number of compound synthesized, the speed, and also the efficiency and how we're generating novel compounds.

Speaker #1: But taking a step back, let's discuss a little bit as to why we think that LSD1 is an interesting target for Recursion. As many of you know, LSD1 is an epigenetic regulator with a range of cellular functions and a promising oncology target across multiple cancer types.

Speaker #1: The focus here, though, was designing a molecule with properties that directly address the limitations we've seen in this class to date. Specifically, reversibility and a shorter predicted human half-life.

Najat Khan: The focus here, though, of designing a molecule with properties that directly address the limitations we've seen in this class to date, specifically reversibility and a shorter predicted human half-life to potentially reduce the risk of thrombocytopenia that have been one of the dose-limiting factors for prior LSD1 inhibitors. We're sharing here also some preclinical data in small cell lung cancer that demonstrate that this compound had more minimal impact on platelets while maintaining efficacy, which is not shown here, but we've seen that data as well, while being comparable in efficacy to other agents in the class, but having more minimal impact on platelets versus other agents in this class. In addition, there's also another feature of this compound, it's brain penetrant, which may be particularly relevant for patients with small cell lung cancer, where up to 50% develop brain mets.

Speaker #1: However, so far, clinically, the potential of LSD1 inhibitors has not been fully met. Previous clinical attempts to drug LSD1 have shown some efficacy, but have been limited by on-target and dose-limiting thrombocytopenia.

Speaker #1: To reduce potentially reduce the risk of cytopenias that have been one of the dose-limiting factors for prior LSD1 inhibitors. And we're sharing here also some preclinical data.

Speaker #1: While being comparable in efficacy to other agents in the class, but having more minimal impact on platelets versus other agents in this class. In addition, there's also another feature of this compound, its brain penetrant.

Speaker #1: Which may be particularly relevant for patients with small cell lung cancer or up to 50% developed brain mets. This differentiation and the potential to improve tolerability has encouraged us to advance the compound into phase one.

Speaker #1: So for this program, the starting point matters. And this is where our chemistry AI part of the platform really shines. We intentionally moved away from traditionally traditional biased chemistry chemical space and instead used a blank white sheet, active learning to explore a broader or information-rich space.

Najat Khan: This differentiation and the potential to improve tolerability has encouraged us to advance the compound into phase I. We had our first patient dosed in April. This is a dose escalation study in select solid tumors, including small cell lung cancer, with expansion cohorts planned following the initial escalation phase. I want to make one thing really clear, you know, Vicky and team are structuring these programs to enable rapid data-driven decision-making. This is how we really manage our capital allocation, specifically to address rapidly whether the emerging clinical profile really supports that hypothesis of, you know, mitigating or reducing the risk of thrombocytopenia. We expect to share initial PK and safety data in H2 2027.

Speaker #1: We had our first patient dosed in April. This is a dose escalation study in select solid tumors, including small cell lung cancer, with expansion towards planned following the initial escalation phase.

Speaker #1: Which allowed us to identify novel starting points that wouldn't typically be perceived. What that led us to is identifying a new step, and we iteratively refined it.

Speaker #1: And I want to make one thing really clear. You know, Vicky and team are structuring these programs to enable rapid data-driven decision-making. This is how we really manage our capital allocation.

Speaker #1: Ultimately arriving at the compound REC4139, 4539, in approximately 20 months, and in just over 400 synthesized compounds—much faster and fewer than what is industry standard.

Speaker #1: Specifically to address rapidly whether the emerging clinical profile really supports that hypothesis of, you know, mitigating or reducing the risk of thrombocytopenia. We expect to share initial PK and safety data in the second half of 2027.

Speaker #1: Compare that also to what Vicky had mentioned with RBM39—18 months and about 209 compounds synthesized to date. So you're starting to see these, as I like to call them, green shoots in terms of the number of compounds synthesized, the speed, and also the efficiency in how we're generating novel compounds.

Speaker #1: So look, I won't, you know, I think I've covered most of this, but similar to what Vicky shared, here's another example where we use our AI platform to solve for design challenges around a biology that's more validated, optimizing molecules where we believe there's been limitations to date.

Najat Khan: Look, I won't, you know, I think I've covered most of this, but similar to what Vicky shared, here's another example where we use our AI platform to solve for design challenges around a biology that's more validated, optimizing molecules where we believe there's a limitation to date. Recall, there are no FDA-approved LSD-1 inhibitors to date, despite a well-defined patient population and significant unmet need that remains for patients. We look forward to sharing more clinical data for this program this year. Now let's go to our second pillar, which is incredibly important. Beyond our portfolio, you know, underpinning a lot of what we're doing is continuing to advance our end-to-end AI product engine, pushing the boundaries so we continue to remain at the forefront of AI-driven innovation.

Speaker #1: The focus here was designing a molecule with properties that directly address the limitations we've seen in this class to date—specifically, reversibility and a shorter predicted human half-life.

Speaker #1: And recall, there are no FDA-approved LSD1 inhibitors to date. Despite a well-defined patient population and significant unmet needs that remain for patients. We look forward to sharing more clinical data with this program next year.

Speaker #1: To reduce potentially reduce the risk of cytopenias that have been one of the dose-limiting factors for prior LSD1. And we're sharing here also some preclinical data.

Speaker #1: In small cell lung cancer, that demonstrated that this compound had more minimal impact on platelets while maintaining efficacy, which is not shown here, but we've seen that data as well, while being comparable in efficacy to other agents in the class, but having more minimal impact on platelets versus other agents in this class.

Speaker #1: Now let's go to our second pillar, which is incredibly important. Beyond our portfolio, you know, underpinning a lot of what we're doing is continuing to advance our end-to-end AI product engine.

Speaker #1: Pushing the boundaries so we continue to remain at the forefront of AI-driven innovation. Let me walk you through the platform and also some of the facts and the stats around how we're doing.

Speaker #1: In addition, there's also another feature of this compound, its brain penetrant. Which may be particularly relevant for patients with small cell lung cancer where up to 50% develop brain metastases.

Najat Khan: Let me walk you through the platform and also some of the facts and the stats around how we're doing. You know, we built the Recursion platform specifically to address the most persistent bottlenecks in drug discovery and development. We're always looking at how we're doing versus industry. Let's start with biology. Look, we have generated more than 10 high-dimensional maps of disease biology. What's interesting here is more than half of them have been in partnership with Roche Genetics. These are already driving multiple novel programs, novel target programs in our internal pipeline. We're also working actively with our partners at Roche Genetics to translate these maps into novel targets and first-in-class programs. This is an important unlock. Why are these maps important? Biology is a systems-level approach.

Speaker #1: You know, we built the recursion platform specifically to address the most persistent bottlenecks in drug discovery and development. And so we're always looking at how we're doing versus industry.

Speaker #1: This differentiation and the potential to improve tolerability has encouraged us to advance the compound into phase one. We had our first patient dosed in April.

Speaker #1: So let's start with biology. Look, we have generated more than 10 high-dimensional disease data. We have generated more than 10 high-dimensional maps of disease biology.

Speaker #1: This is a dose escalation study in select solid tumors, including small cell lung cancer, with expansion towards planned following the initial escalation phase. And I want to make one thing really clear.

Speaker #1: And what's interesting here is more than half of them have been in partnership with Roche Genentech. And these are already driving multiple novel programs that will target programs in our internal pipeline and then we're also working actively with our partners with Roche Genentech to translate these maps into novel targets and first-in-class programs.

Speaker #1: Vicky and team are structuring these programs to enable rapid, data-driven decision-making. This is how we really manage our capital allocation. Specifically, to address rapidly whether the emerging clinical profile really supports that hypothesis of mitigating or reducing the risk of thrombocytopenia.

Speaker #1: This is an important unlock. Why are these maps important? Biology is a systems-level approach. We need to understand the interconnected net circuits. And therefore, enhancing our ability to identify and prioritize targets with better confidence, with better understanding of the underlying biology, is critical to really determining the root causes.

Speaker #1: We expect to share initial PK and safety data in the second half of 2027. So look, I won't I think I've covered most of this, but similar to what Vicky shared, here's another example where we use our AI platform to solve for design challenges around a biology that's more validated, optimizing molecules where we believe there's been limitations to date.

Najat Khan: We need to understand the interconnected exotropics, and therefore enhancing our ability to identify and prioritize targets with better confidence, with better understanding of the underlying biology is critical to really determining the root cause of disease. Let's go to the next slide. We are also synthesizing, as you heard me share, briefly, more and more compounds where we are designing 90% or synthesizing 90% fewer compounds of the industry benchmark. About 330 compounds on average versus 2,500 to 5,000 compounds, which is the industry standard to date, while also advancing these programs to advanced and development candidates roughly 2 times as fast. This is a meaningful step change in both efficiency and cycle time, and something that we watch very carefully on an ongoing basis. The next slide, our ClinTech capabilities.

Speaker #1: So go to the next slide. We are also synthesizing, as you heard me share, briefly, more and more compounds where we are designing 90% of synthesizing 90% fewer compounds of the industry industry benchmark.

Speaker #1: So about 330 compounds on average versus 2500 to 5,000 compounds, which is the industry, standard today. While also advancing these programs to advancing development candidates roughly twice as fast.

Speaker #1: Now let's go to our second pillar, which is incredibly important. Beyond our portfolio, underpinning a lot of what we're doing is continuing to advance our end-to-end AI product engine.

Speaker #1: This is a meaningful step changing both efficiency and cycle time. And something that we want very carefully and an ongoing basis. The next slide.

Speaker #1: Our clintech capabilities. You know, where we have deployed it, we're already seeing about 30 to 60% faster trial enrollment. This is very important for us, both for rare diseases and competitive areas such as, you know, oncology.

Najat Khan: You know, where we have deployed it, we're already seeing about 30% to 60% faster trial enrollment. This is very important for us, both for rare diseases and competitive areas such as in oncology, while increasing the eligible patient population for some of these programs from 10% to 40%. This directly impacts our timelines and speed at which we can generate high-quality clinical data. Look, underpinning it all is an integrated platform with more than 50 terabytes of proprietary multimodal data. This is incredibly critical for not just building purposeful models, but ensuring that we have our data moat that we not just invest in, but continue to expand. Suffice to say, these are not theoretical or isolated improvements.

Speaker #1: We built the Recursion platform specifically to address the most persistent bottlenecks in drug discovery and development. And so we're always looking at how we're doing versus industry.

Speaker #1: While increasing the eligible patient population for some of these programs, from 10 to 40%. This directly impacts our timelines and speed at which we can generate high-quality clinical data.

Speaker #1: So let's start with biology. Look, we have generated more than 10 high-dimensional disease data. We have generated more than 10 high-dimensional maps of disease biology.

Speaker #1: And look, underpinning it all is an integrated platform with more than 50 petabytes of proprietary multimodal data. This is incredibly, critical for not just building purposeful models, but ensuring that we have our data mode that we not just invest in, but continue to expand.

Speaker #1: And what's interesting here is more than half of them have been in partnership with Roche and Intel. And these are already driving multiple novel programs that will target programs in our internal pipeline and then we're also looking actively with our partners with Roche and Intel to translate these maps into novel targets and first-in-class programs.

Speaker #1: So suffice to say, these are not theoretical or isolated improvements. These are real tangible gains that we keep measuring and focusing on to reinforce how our platform is changing the way we are discovering and developing our medicines.

Najat Khan: These are real, tangible gains that we keep measuring and focusing on to reinforce how our platform is changing the way we are discovering and developing our medicines. Again, I always like to say they are green shoots, but this is how we are pushing the frontier of what's possible with our platform. Now let me double-click on a couple of recent examples in the biology layer where we're really pushing the next generation of our models that were recently published. Big picture, one area of focus for us in our biology platform is learning the language of biology. Sounds simple, not easy. Incredibly important. We do it across many data layers by generating perturbations at scale, whether it's genetic, chemical, and so forth. Why is that important? What is our goal? Our goal is to, A, understand biology more comprehensively.

Speaker #1: This is an important unlock. Why are these maps important? Biology is a systems-level approach. We need to understand the interconnected exotics. And therefore, enhancing our ability to identify and prioritize targets with better confidence, with better understanding of the underlying biology, is critical to really determining the root causes.

Speaker #1: Again, I always like to say there are green shoots, but this is how we are pushing the frontier of what's possible with our platform.

Speaker #1: Now let me double-click on a couple of recent examples in the biology layer where we're really pushing the next generation of our models. And we're recently published.

Speaker #1: So go to the next slide. We are also synthesizing, as you heard me share, briefly, more and more compounds where we are designing 90% of synthesizing 90% fewer.

Speaker #1: Big picture, one area of focus for us in our biology platform is learning the language of biology. Sounds simple, not easy. Incredibly important. And we do it across many data layers.

Speaker #1: By generating perturbations at scale, whether it's genetic, chemical, and so forth. Why is that important? What is our goal? Our goal is to, A, understand biology more comprehensively.

Speaker #1: B, and then be able to predict and simulate perturbations before we are even running a single experiment. And third, that we can actually generalize beyond the data that we've already seen.

Najat Khan: Then be able to predict and simulate perturbations before we are even running a single experiment. Third, that we can actually generalize beyond the data that we've already seen. That's really important with these foundation models. You want to predict responses in new out-of-distribution contexts, such as novel targets, combinations, and cell types. Why does it all matter? Well, given the vastness of the biological scale and how little, you know, depth in industry, you know, 10%, this has the potential to unlock areas that remain intractable or intractable today. That becomes even more powerful when we connect different data layers, high-content cell imaging, transcriptomics, proteomics, patient data, and more, to really have a more unified view of biology. Now, it's not just in theory. We're making progress there already. Step one is to actually develop a new generation of models.

Speaker #1: That's really important with these foundation models. You want to predict responses in new, out-of-distribution contexts such as novel targets, combinations, and subtypes. And why does it all matter?

Speaker #1: Look, given the vastness of the biological space and how little, you know, benefit industry, you know, 10%, this has the potential to unlock areas that remain untractable or intractable today.

Speaker #1: And that becomes even more powerful when we connect different data layers. High-quantum cell imaging, transcriptomics, proteomics, patient data, and more. To really have a more unified view of biology.

Speaker #1: Now it's not just in theory. We're making progress here already. Step one is to actually develop a new generation of model. So let me share with you two recent advances in transcriptomic foundation models that we just published in the last month.

Najat Khan: Let me share with you 2 recent advances in transcriptomics foundation models that we just published in the last month. The first is TxPert, which we recently published in Nature Biotechnology. TxPert is a model designed to predict how gene expression changes in response to different perturbations, essentially helping us to understand biology and how it will respond before we run the experiment. Similar to what you saw in chemistry, you know, the reason why we can reduce the number of compounds we synthesize is so we predict and simulate more, and then of course, we make more. How can we do that more in biology? It's important for us to understand the systems approach in biology across different data layers and be able to predict well so that we can do less experimentation and only do the experimentation that really matters.

Speaker #1: The first is TXPERT, which we recently published in Nature Biotech. TXPERT is a model designed to predict how gene expression changes in response to different perturbations.

Speaker #1: Essentially helping us to understand biology and how it will respond before we run an experiment. So similar to what you saw in chemistry, you know, the reason why we can reduce the number of compounds we synthesize is because we predict and simulate more.

Again, I always like to say there are green shoots, but this is how we are pushing the frontier of what's possible with that platform.

Now, let me double click on a couple of recent examples in the biology there where we're really pushing the next generation of our models.

Speaker #1: And then, of course, we make more. And how can you do that more in biology? It's important for us to understand the systems approach in biology across different data layers and be able to predict well.

For recently published.

Big Picture 1 area of focus for us. In our biology platform is learning the language.

Sounds simple.

Speaker #1: So that we can do less experimentation. And only do the experimentation that really matters. What's particularly exciting about this model, and listen, we're still in early days, but it's great to see the progress from our teams, is learning patterns in biology.

Incredibly important, and we do it across many data layers by generating perturbations at scale, but

Najat Khan: What's particularly exciting about this model, and listen, we're still in early days, but wait till see the progress from our teams, is learning patterns in biology. It's not just memorizing, it's actually learning the underlying patterns. The second is generalizing beyond the data it was trained on. This is an important start. It's a start to predicting responses to new perturbations, new combinations, and even new cell types. Watch this area more. I think this is gonna be really, really important in biology and the foundation models just given the vastness of what we're working with. It's an important first step towards how we think about building a virtual cell, a term that is overused. The importance of it is, again, can we simulate and explore biology more comprehensively, more computationally before we move into the lab?

genetic chemical and so forth.

Why is that important? What is our goal? Our goal is to ah, understand biology more comprehensively

Speaker #1: Not just memorizing it, it's actually learning the underlying patterns. The second is generalizing beyond the data it was trained on. This is an important start.

B. And then be able to predict and stimulate perturbations.

Before we have even running a single experiment.

Speaker #1: It's a start to predicting responses to new perturbations, new combinations, and even new subtypes. Watch this area more. I think this is going to be really, really important in biology and the foundation models just given the vastness of what we're working with.

And third that we can actually generalize beyond the data that we've already seen.

That's really important with these Foundation models. You want to predict responses from you out of distribution context, such as not, a Target combination and soft type.

Speaker #1: And it's an important first step towards how we think about building a virtual cell. A term that is overused to be importance of it is, again, can we simulate and explore biology more comprehensively, more computationally, before we move into the lab?

And why does it almost?

Given the vastness of the biology.

And how little you know best in Industry. You know. 10% this has the potential to unlock areas that remain on trackable or intractable today.

Speaker #1: This is incredibly important so that we can be more effective and efficient and ultimately improve the probability of the targets that we could put into our programs.

Najat Khan: This is incredibly important so that we can be more effective and efficient and ultimately improve the probability of the targets that we could put into our programs. Next is another model which is complementary. TxFM, our transcriptomics foundation model, which represents a significant step of actually connecting lab biology to patient biology. I won't go into the details here, but just want to highlight a couple of things. First, it is built on a highly curated combination of both proprietary and public data, bringing together diverse data sets into a shared representation space. Why is this important? You know, there's a lot of conversations here. Quantity important or quality? Both matters. You'll see from some of the early insights here that the quality and the model architecture was really important to ensure great model performance here. What's exciting is the following.

And that becomes even more powerful when we connect different data layers, high content cell Imaging transcriptions, 30 application data and more to really have a more unified view of biology.

Speaker #1: Next is another model, which is complementary. TXFM, our transcriptomic foundation model, which represents a significant step of actually connecting lab biology to patient biology.

Speaker #1: I won't go into the details here, but just want to highlight a couple of things. First, you know, it's built on a highly curated combination of both proprietary and public data.

Now it's not just in theory we're making progress here already. Step 1 is to actually develop a new generation of models. So let me share with you 2 recent advances in transfer stomach Foundation models that we just published in the last month.

The first STS.

Which were recently published in nature biotech.

Speaker #1: Bringing together diverse data sets into a shared representation slate. Why is this important? You know, there's a lot of conversations. Is. Quantity important or quality?

The expert is a model designed to predict how gene expression changes in response to different prohibitions.

Speaker #1: Both matters, but you'll see from some of the early insights here that the quality and the model architecture was really important to ensure great model performance here.

Essentially helping us to understand biology and how it will respond before we run.

So similar to what you saw in chemistry, you know, the reason why we can reduce the number of compounds, we synthesize is we predict and stimulate more. And then, of course you make that,

Speaker #1: So what's exciting is the following. Number one, the result is a model that surfaces much richer understanding of biology. And reducing experimental noise. Batch effects and so forth, very, very important in this space.

Najat Khan: Number 1, the result is a model that surfaces much richer understanding of biology and reducing experimental noise, batch effects, and so forth. Very, very important in this space. Number 2 is it outperforms a lot of leading foundation models. More importantly, it outperforms models that are trained on 100x larger datasets, demonstrating that advantage I was mentioning on just the data curation approach, and also model architecture. What I like is the interpretability. That's where we're starting to go. Again, early days. It doesn't just rank genes, but it reveals the gene networks, the circuits, the patient subtypes from RNA data, so that transcriptomics can in time become a more systematic engine for understanding the mechanistic and target hypotheses that underpin these than just one-off analysis. There is so much richness data, and we're driving to understand that even better.

And how can we do that more in biology? It's important for us to understand the systems approach and biology across different data layers, and be built to predict, well,

Speaker #1: Number two is that outperforms a lot of leading foundation models. But more importantly, it outperforms models. That are trained on 100x larger data sets.

Speaker #1: Demonstrating that advantage I was mentioning on just the data, data curation approach and also model architecture. And what I like is the interpretability. That's where we're starting to go.

Is that we can do less experimentation. And only do the experimentation that really matters. What's particularly exciting about this model? And the thing we're still in early days, but it's great to see the progress from our team. If learning patterns in biology, not just memorizing is actually learning the underlying pattern.

The second is generalizing beyond the data of the chain box.

Speaker #1: And again, early days. It doesn't just rank genes, but it reveals the gene networks, the circuits, the patient subtypes from RNA data. So that transcriptomics can in time become a more systematic engine for understanding the mechanistic and target hypotheses that underpinning than just one-off analysis.

This is an important start. It's a start to predicting responses to new perturbations, new combinations, and even new cell types. Watch this area more. I think this is going to be really, really important in biology and Foundation models. Given the fact that what we're—

working with

Speaker #1: There is so much richness data and we're driving to understand that even better. And practically, again, it's how do we get more efficient in the experiments we run?

Najat Khan: Tactically, again, it's how do we get more efficient with experiments we run? How can we do less re-runs? How can we do better cross-study comparisons and efficiently use our resources? Today, both these models are starting to be deployed in our platform. For TxFM, we're starting to leverage it for target identification, better mechanistic understanding, and patient stratification. Sharing some latest and greatest here, and we will, as always, in the months to come and years to come, share how this is truly impacting our platform. That's what we care about. How do we take data models to really show the translation of proof into our programs, into our partner programs, and progress better medicines for patients? With that, I'm going to turn over for our third pillar, which is how do we drive all of this important work with good discipline and big ambition? Ben?

and it's an important first step towards how we think about building a virtual sound a term that is overused, but the importance of it is again, can we simulate and explore biology more? Comprehensively more computationally?

Speaker #1: How can we do less re-runs? How can we do better cross-study comparison? And efficiency use our resources. So today, both these models are starting to be deployed in our platform.

Or we move into the lab, this is incredibly important so that we can be more effective and efficient and ultimately improve the probability of the targets that we've been put into our programs.

Speaker #1: And for TXFM, we're starting to leverage it for target identification, better mechanistic understanding, and patient stratification. So sharing some latest and greatest here and you will, as always, in the months to come, in years to come, share how this is fully impacting our platform.

Next is another model, which is complementary.

TX FM our transcriptomics foundation model which represents a significant step of actually connecting lab biology to Patient biology.

Speaker #1: That's what we care about. How do we take data, models, to really show the translation of proof into our programs and to our partner programs and progress better medicines for patients?

I won't go into the details here but just want to highlight a couple of things first. It is built on a highly curated combination of both proprietary and public data. Bringing together diverse data sets into a shared representation space.

Why is this important? You know, there's a lot of conversations.

Speaker #1: With that, I'm going to turn over for our third pillar, which is how do we drive all of this important work with good discipline and good ambition?

Speaker #1: Thanks.

Speaker #2: Thank you, Yuzan. Our core focus from a financial perspective is ensuring we have adequate runway to achieve multiple upcoming milestones. We continued our trend of operating discipline with a 30% year-over-year reduction in cash operating expenses.

Ben Taylor: Thank you, Nisha. Our core focus from a financial perspective is ensuring we have adequate runway to achieve multiple upcoming milestones. We continued our trend of operating discipline with a 30% year-over-year reduction in cash operating expenses. We were able to achieve these savings while also growing our pipeline, partnerships, and platform by focusing only on those operations that had clear and measurable impact. In addition to our operational discipline and infrastructure simplification, we also expect ongoing efficiency gains from our technology advancements and the adoption of agents. During the quarter, we received our fifth milestone from Sanofi, advancing a potential first-in-class program for a novel biological target. We closed the quarter with $665 million in cash equivalents, which we believe provides operating runway through early 2028 without additional financing.

Exciting is the following number 1.

The result is a model that surfaces much richer understanding of biology and reducing experimental noise, batch effects and so forth. Very, very important.

Speaker #2: We were able to achieve these savings while also growing our pipeline, partnerships, and platform by focusing only on those operations that had clear and measurable impact.

Number 2 is that I've performed a lot of leading Foundation models.

But more importantly, it outperforms models that are trained on 100x, larger data sets.

Speaker #2: In addition to our operational discipline and infrastructure simplification, we also expect ongoing efficiency gains from our technology advancements and the adoption of agents. During the quarter, we received our fifth milestone from Sanofi, advancing a potential first-in-class program for a novel biological target.

Demonstrating that Advantage. I was mentioning on, just the data data curation approach, and also model of

And what I like is the interpretability, that's what we're starting to go. And again, early days.

Speaker #2: We closed the quarter with $665 million in cash equivalents, which we believe provides operating runway through early 2028 without additional financing. For 2026, we are maintaining our cash operating expense guidance of less than $390 million, which fully funds our expected milestones and partnerships during the period.

it doesn't just rank jeans, but it reveals the gene networks, the surface, the patient subtype of RNA, RNA data,

Ben Taylor: For 2026, we are maintaining our cash operating expense guidance of less than $390 million, which fully funds our expected milestones and partnerships during the period. To take you through those milestones, I'll turn it back over to you then, John.

So, that transcript can in time become a more systematic engine. For understanding the mechanistic and target typography that's underpinning, and just one-off analysis, there's so much richness in the data, and we're driving to understand that even—

Speaker #2: And to take you through those milestones, I'll turn it back over to John.

And practically again. It's how do we get more efficient and experimentally run? I think we use less rebut.

How can we do better for our studies in person?

Speaker #3: Thank you so much, Ben. And look, I'm going to close by saying that we have a lot of important work ahead of us and very exciting ahead of us, work ahead of us.

Najat Khan: Thank you so much, Ben. Look, I'm going to close by saying we have a lot of important work ahead of us and very exciting work ahead of us. As we look ahead, we have a clear and consistent cadence of milestones, both across our wholly owned pipeline and our partner portfolio. In our wholly owned pipeline, we expect multiple clinical readouts over the next 12 to 18 months. In fact, for every single one of our clinical stage programs. Continuing to build on clinical evidence and test the hypotheses underlying our platform. In parallel, we're seeing continued progress across our partner portfolio. I'll recap the two potential unlocks I mentioned. One, looking at the use of AI to develop novel compounds for difficult to drug targets.

And efficiently. Use our resources.

Speaker #3: As we look ahead, we have a clear and consistent cadence of milestones. Both across our wholly owned pipeline and our partner portfolio. In our wholly owned pipeline, we expect multiple clinical readouts over the next 12 to 18 months.

So today, both these models are starting to be deployed in our platform for ksfm. We're starting to leverage it for Target identification. Better mechanistic understanding and patient stratification.

Speaker #3: In fact, for every single one of our clinical stage programs. Continuing to build on clinical evidence and test the hypotheses underlying our platform. In parallel, we're seeing continued progress across our partner portfolio.

So sharing some latest and greatest here. And we will, as always in the months to come and use to Come Share, how this is sleep, impacting, our platform. That's what we care about. How do we take data models to really show the translation of proof into our programs into our partner programs and programs better medicine,

Speaker #3: I'll recap the two potential unlocks I mentioned. One, looking at the use of AI to develop novel compounds with difficult-to-drug targets we're excited about our work with Sanofi here and some of the development candidate decisions coming up in the next 12 to 18 months.

With that, I'm going to turn over for our third pillar, which is how do we drive all of this important work with good discipline, and get ambition.

Najat Khan: We're excited about our work with Sanofi here and some of the development candidate decisions coming up in the next 12 to 18 months. With Roche Genentech, take all of these large multimodal maps that is helping us understand biology better and really translating that to novel targets and first-in-class programs. You know, taken together, this creates a diversified set of catalysts and also the increasing momentum, as you are seeing month-over-month, week-over-week, as we look to take and harness all of what AI and our dramatically excellent team can do to turn that into meaningful outcomes. I will just close by saying we are focused on building an increasing body of evidence that this approach can translate, advancing differentiated programs, unlocking new biology, and doing that best with improved speed and efficiency. That is what gives us confidence in the path forward.

Speaker #3: And with Roche Genentech, take all of these large, multimodal maps as helping us understand biology better and really translating that to novel targets and first-in-class programs.

Okay, it's from a financial perspective. It's ensuring we have adequate runway to achieve multiple upcoming milestones.

We continue our trend of operating discipline with a 30% year-over-year reduction in cash operating expenses.

Speaker #3: You know, taken together, this creates a diversified set of catalysts and also the increasing momentum, as you're seeing month over month, week over week, as we look to take and harness all of what AI and our dramatically excellent team can do to turn that into meaningful outcomes.

We were able to achieve these savings while also growing, our pipeline Partnerships and platforms, my focusing only on those operations that had clear and measurable impact.

In addition to our operational discipline and infrastructure simplification, we also expect ongoing efficiency gains from our technology advancements and the adoption of Agents.

Speaker #3: I'll just close by saying we are focused on building an increasing body of evidence that this approach can translate. Advancing differentiated programs and unlocking new biology and doing that best with improved speed and efficiency.

During the quarter, we received our fifth Milestone, from sopia advancing, a potential first-in-class program for a novel biological Target.

We closed the quarter with 665 million in cash equivalents which we believe provides operating Runway through early 2028 without additional financing.

Speaker #3: And that's what gives us confidence in the path forward. The momentum you see the work that the teams are doing, but also the system behind it.

Najat Khan: The momentum you see, the work that the teams are doing, but also the system behind it and its potential to generate outcomes over time in a repeatable fashion for patients, our partners, and our shareholders. Thank you again for your time, and attention, and we will open it up now for questions. Great. Let's dive in. I have Vicki and Ben who will help me cover some of these questions. The first question is from Dennis at Jefferies and Priyanka at J.P. Morgan on the REC-1245 program. Can you talk about the level of target engagement that you feel is needed to drive efficacy and where you are relative to those levels? What are common on-target safety and tolerability issues that you're hoping to avoid with your approach? How are you thinking about biomarkers being useful?

For 2026, we are maintaining our cash operating expense guidance of

Speaker #3: And its potential to generate outcomes over time in a repeatable fashion for patients, our partners, and our shareholders. Thank you again for your time and questions.

90 million, which fully funds, our expected, milestones and Partnerships During the period.

And to take you through those milestones, I'll turn it back over to you then, John. Thank you so much, Ben.

Speaker #3: Time and attention. And we will open it up now for questions. Great. So let's dive in. I have Vicky and Ben, who will help me cover some of these questions.

And look, I'm going to close by saying that we have a lot of important work ahead of us and very exciting ahead of us was ahead of us. As we look ahead, we have a clear and consistent Cadence of milestones.

Both across our wholly owned Pipeline and our partners.

Speaker #3: So the first question is from Dennis, is, Jeffreys, and Priyanka at JPM on the REC 1245 program. Can you talk about the level of targeted engagement that you feel is needed to drive efficacy and where you are relative to those levels?

in our wholly owned pipeline, we expect multiple clinical readouts over the next 12 to 18 months, in fact, for every single 1 of us,

Continuing to build on clinical evidence and test to have processes underlying our platform.

Speaker #3: What are common on-target safety and tolerability issues that you're hoping to avoid with your approach? And how are you thinking about biomarkers being exposed?

In Paramount, we're seeing continued progress across our partner portfolio.

Speaker #3: Well, maybe I'll just kick it off and then I'll hand it over to Vicky to also share additional details. I'll go in order of second, third, and first.

Najat Khan: Well, maybe I'll just kick it off, and then I'll hand it over to Vicky to also share additional details. I'll go in order of second, third, and first. What are common on-target safety tolerability issues that you're hoping to avoid? Look, first of all, we are encouraged by the favorable safety and tolerability profile that we see to date. You know, as you saw, 90% of what we see so far are grade 1 and 2, mostly GI, and no DLTs to date. In terms of just RBMs, you know, areas that we would usually keep an eye on in terms of potential tox is Heme tox, and to date, we have not seen any grade 2 Heme tox at all. That is encouraging.

I'll recap the 2 potential unlocks. I mentioned 1. Looking at the use of AI to develop novel compounds,

And targets.

Speaker #3: So what are common on-target safety tolerability issues that you're hoping to avoid? Look, first of all, we are encouraged by the favorable safety and tolerability profile that we see to date.

Excited about our work with Pinoy here and some of the development candidate decisions.

And with row Chente.

Speaker #3: You know, as you saw, 90% of what we see so far are grade one and two, mostly GI. And no DLTs to date. In terms of just RBM, you know, areas that we would usually keep an eye on in terms of potential talks is heme talks and to date we have not seen any grade three heme talks at all.

Take all of these large multimodal Maps. That's helping us understand biology better. And really Translating that to novel targets, and first IMPACT Program,

It had taken together this creates a diversified set of catalysts and also the increasing momentum as you're seeing months over months and weeks over a week. As we look to take and harness all of what Ai and our

Speaker #3: So that is encouraging. But again, we're in the middle of dose escalation, so more to come as Vicky mentioned. Second half of 2027. And in terms of target engagement, we're early.

Najat Khan: Again, we're in the middle of dose escalation, so more to come, as Vicki mentioned, H2 2027. In terms of target engagement, you know, we have some PD data that we shared, and Vicki can share more about that, but we're seeing good target engagement. We've confirmed that to date. As we have more, you know, dose escalation, what we've seen pre-clinically is about, you know, 70% to 80% was sufficient at efficacious doses, but we'll be tracking that as we continue further. Vicki, did you want to add anything more to those two questions?

dramatically. Excellent team can do to turn that into meaningful health.

Speaker #3: You know, we have some PD data that we shared and Vicky can share more about that. But we're seeing good target engagement. We've confirmed that to date.

I'll just close by saying we are focused on building an increasing body of evidence.

Speaker #3: As we have more dose escalation, what we've seen pre-clinically is about 70 to 80% was sufficient. At efficacious doses, but we'll be tracking that as we continue further.

Efficiency.

And that's what gives us confidence in the path. Forward

The momentum, you see?

The work that the teams are doing but also the system behind it.

Speaker #3: Vicky, did you want to add anything more to those two questions?

Vicki Goodman: Sure. Coming back to the safety and tolerability issues, I mean, again, what we've seen so far is mostly low-grade GI tox. We'll certainly continue to monitor that as we move forward. Hematologic toxicity, which is a concern here, is something we're really not seeing at this point. Again, we'll continue to monitor as we continue to dose, and we'll have more data for you there in H2 of this year. Relative to target engagement, I think, you know, the estimates are spot on. I'll add that in, you know, we're coming close now within the next 2 dose levels to being at the exposure levels that where we saw tumor regressions in mice. I think that's an important point as well.

Speaker #2: So sure. So coming back to the safety and tolerability issues, I mean, again, what we've seen so far is mostly low-grade GI talks. We'll certainly continue to monitor that as we move forward.

And its potential to generate outcomes over time in a repeatable fashion for patients our partners and our shareholders.

Thank you again for your time and attention. We will open it up now for questions.

Speaker #2: Hematologic toxicity, which is a concern here, is something we're really not seeing at this point. Again, we'll continue to monitor as we continue to increase the dose.

Speaker #2: And we'll have more data for you there in the second half of this year. Relative to target engagement, I think the estimates are spot on.

Great. Um, so let's dive in. I have Vicky and Ben who helped me cover some of these questions. So the first question is from Dennis Jeffries and Fionna at JPM on the wreck 1245,

can you talk about the level of targeting engagement that you

Speaker #2: I'll add that in we're coming close now within the next two dose levels to being at the exposure levels that where we saw tumor regressions in mice.

To drive efficacy.

And where you are relative to those?

Speaker #2: So I think that's an important point as well. Obviously, we'll continue to monitor the target engagement in terms of RBM 39, degradation, and again, have more data, more wholesome update in the second half of the year.

What are common On? Target safety and tolerability issues. That you're hoping to avoid with your approach and how are you thinking about biomarkers?

Vicki Goodman: Obviously, we'll continue to monitor the target engagement in terms of RBM39 degradation, and again, have more data, a more fulsome update in H2.

Well, maybe I'll just kick it off and then I'll um, hand it over to Rick Angel to share additional details. I'll go in order of second

Speaker #3: Thank you, Vicky. And just a last question was, how are you thinking about biomarkers being exposed? You know, as Vicky mentioned during the presentation, we're looking across select biomarkers.

Najat Khan: Thank you, Vicky. Just the last question was, how are you thinking about biomarkers being sourced? You know, as Vicky mentioned during the presentation, we're looking across select biomarkers. Of course, you know, as the data matures, we will look at, you know, relative benefits versus not across those biomarkers. More to come, H2 2026. Thank you for the great questions. All right, next question from Gail and Needham, Alex from Bank of America, Sean from Morgan Stanley, Brandon from Cowen, and others on REC-4881. Given the encouraging phase II data for REC-4881 in FAP and ongoing F-FAP engagement, what are the key uncertainties around the registrational capital? We have 3 questions here. I'll just start 1 at a time so we can keep track. You know, I'll kick it off, but, Vicky, it would be great to get your thoughts.

Speaker #3: And of course, as the data matures, we will look at relative benefits versus not across those biomarkers. More to come second half of 2026.

Third and first. So what are common On Target safety? Travel ability issues that you're hoping to avoid look. Um, first of all, we are encouraged by the favorable safety and tolerability profile that we see today, you know? Um as you saw 90% of what we see so far, our grade 1 and 2, most of ghee.

Speaker #3: Thank you for the great questions. All right. Next question from Gil and Needham, Alec from Bank of America, Sean from Morgan Stanley, Brendan from Cowan, and others on REC 4881.

And no DLCs to date. In terms of just rvm areas that we would usually keep an eye on in terms of potential.

And to date.

Speaker #3: Given the encouraging face-to-data for REC 4881 in FAP and ongoing FDA engagement, what are the key uncertainties around the registrational pathway? We have three questions here.

Tops at all. So that is encouraging but again we're in the middle of those escalations. So more to come and think you mentioned second half of 2027.

Speaker #3: I'll just start one at a time so we can keep track. You know, I'll kick it off with, Vicky, it would be great to get your thoughts.

Najat Khan: We're very excited about the data that we see with FAP. With every day goes by, as we engage with more FAP patients, really the not just the unmet needs, but how underserved these patients are, is becoming even more and more apparent. We have a significant polyp burden reduction and durability that we've seen to date. I would say the main areas of focus with the FDA is what would be for any asset that's a first in disease, right? We have other assets in our portfolio that are best in class, where the regulatory approach is already very defined. For a first in disease, it's really around, you know, patient population, endpoint that has clinically meaningful benefit, and then, of course, dose and dose escalation.

Speaker #3: But we're very excited about the data that we see with FAP and with everyday that goes by, we engage with more FAP patients, really the not just unmet need, but how underserved these patients are.

Um, in terms of Target engagement, we're early, you know, we were, we have some PD data that we shared and people can share more about that, but we're seeing the target engagement. We've confirmed that date as we have more, you know, um, dose escalation. But we've seen 3, clinically is about, you know, 70 to 80% was sufficient at efficacious doses but we'll be we'll be tracking that as we continue.

Um, Vicky, did you want to add anything more to those two questions?

Speaker #3: It's becoming even more and more apparent. We have significant polyp burden reduction and durability that we have seen to date. I would say the main areas of focus with the FDA is what would be for any asset that's at first in disease, right?

Speaker #3: We have other assets in our portfolio that are best in class, where the regulatory approach is already very defined. For a first-in-disease, it's really around patient population, endpoint that has clinical meaningful benefit.

Speaker #3: And then, of course, dose and dose escalation. But those are the conversations and, as Vicky mentioned and I mentioned, we've already started that engagement.

Najat Khan: Those are the conversations, and as Vicky mentioned, and I mentioned, we've already started that engagement. Do you have anything to add?

Speaker #3: Anything to add?

Speaker #2: Yeah. So, you know, I think here because there really is a lack of regulatory precedent, it's really important for us to work closely with the FDA in terms of defining the registrational path to that end.

Uh, so sure. Um, so coming back to the safety and tolerability issues, I mean again what we've seen so far is mostly low-grade GI talks and we'll certainly continue to monitor that as we move forward, human logic toxicity, which is a concern, here is something we're really not seeing at this point. Again, we'll continue to monitor as we continue to increase the dose and we'll have more data for you there. In the second half of this year, um, relative to Target engagement. I think, uh, you know, the estimates are spot on. I'll add that in. Um, you know, we're we're coming close now within the next 2 dose levels, just to being at the exposure levels that

Vicki Goodman: Yeah. I, you know, I think here, because there really is a lack of regulatory precedent, it's really important for us to work closely with the FDA in terms of defining the registrational path. To that end, we've already initiated that engagement within the oncology review division, also requested input from the GI division. Certainly, as we go about these, we're thinking about leveraging the rare disease framework as well. We can de-risk this program by really closely aligning with FDA on what are clinically meaningful endpoints for patients that will help us define the primary endpoint for our pivotal study.

Speaker #2: We've already initiated that engagement within the oncology review division, also requested input from the GI division. And certainly, as we go about these we're thinking about leveraging the rare disease framework as well.

Where we saw tumor, regressions, and mice. So I think that's an important Point as well. Obviously, we'll continue to monitor the the target engagement in terms of RBM 39. Um, degradation and again, uh, have more data more personal update in the second half of the year.

Speaker #2: So we can de-risk this program by really closely aligning with FDA on what are clinically meaningful endpoints for patients. That will help us to find the primary endpoint for our pivotal study.

Thank you, Vicki. And just the last question was, how are you thinking about biomarkers being stored? You know, as Vicky mentioned during the presentation, we're looking across select biomarkers and of course as the data, of course, we will look at, you know relative benefits for if not across those 5 more questions.

More to come as the second half of 2026.

Thank you for the great questions.

Speaker #3: The next question still on REC 4881. Has there been any shift to timing for SIP regulatory? And when will we see additional data? So a couple of things.

Najat Khan: The next question, still on, REC-4881. Has there been any shift to timing for FAP regulatory, and when will we see additional data? A couple of things. We're on track with it. We'd initiate FDA engagement H1 2026. We're actually a bit ahead of schedule. We have initiated FDA engagement, and as Vicky mentioned, we expect us to be working with the FDA very closely, given it's a first in disease, on, you know, our potential registrational study. When will we see additional data? Vicky, do you want to share that?

Speaker #3: We are on track. We said we would initiate FDA engagement first half of 2026. We're actually a bit ahead of schedule. We have initiated FDA engagement.

All right. Next question from Gail and Medium Alex from Bank of America, Sean from Morgan Stanley, Brandon from Ken, and others on the RED 4881. Given the encouraging SPACE-2 data, correct, 4881 in FAP and ongoing FA/FA engagement, what are the key uncertainties around the registration?

Speaker #3: And as Vicky mentioned, we expect this to be working with the FDA very closely, given it's a first-in-disease on our potential registrational study. And then when will we see additional data?

We have 3 questions here. I'll just start 1 at a time so we can keep track.

Speaker #3: Vicky, do you want to share that? I'm happy to take it. You know, in terms of additional data, you know, we have already initiated 18 and over patients.

Um, you know, I I'll kick it off but, uh, Vicky would be great to get your thoughts. Um, but we're very excited about the data that we see, um, with fap and, with everyday goals that goes by and we engage with more fap.

Vicki Goodman: Sure.

Najat Khan: I'm happy to take it. You know, in terms of additional data, you know, we have already initiated 18 and over patients. We're already recruiting those patients. We'll also have potentially additional data from our phase II that we will share, you know, either here or at a forum going forward. We're on track. Have you leveraged any ClinTech capabilities from your platform in assembling the proposed pivotal study design? Great question. A couple of areas. Number one, if you recall, the natural history that we did in parallel with our clinical program has been really, really important for a few reasons. This is a rare disease, limited literature, sort of natural history.

Speaker #3: They're already recruiting those patients. And we'll also have potentially additional data from our phase two that we will share either here or at a forum going forward.

Speaker #3: But we're on track. Have you leveraged any clean dev capabilities from your platform in assembling the proposed pivotal study design? Great question. A couple of areas.

Patients. Really be not just on that need. But how underserved these patients are is becoming even more and more apparent. So we have a significant poll of Burden reduction, in durability that we've seen to date. I would say the main areas of focus with the FDA is what would be for any access of the first interview. Right? We have other Assets in our portfolio that are best in class

Speaker #3: Number one, if you recall, the natural history that we did in parallel with our clinical program has been really, really important. For a few reasons.

Where the regulatory approach is already very defined for a person disease, is really around, you know, patient population, um, endpoint that has clinical the meaningful benefit and then of course, dose and dose escalation, but those are the conversations.

Speaker #3: This is a rare disease, limited literature, sort of natural history. This has allowed us not just to understand patient trajectory, but also helped us, as we think about how do we power the study, what endpoints are important, and so forth.

I think.

Najat Khan: This has allowed us not just understand patient trajectory, but also helped us as we think about how do we power the study, what endpoints are important and so forth. It gives us a much richer contextualization understanding, and then also incorporating that in terms of our study design as well. In addition to that, for our 18 and over, plus our potential registrational study, we are also going to be using our clinical development AI capabilities for recruitment. For a rare disease, we want to be much more efficient and use these approaches to go to where patients are and recruit with speed and with efficiency. Great. Next question from Bruce, Philip, Rushab, and others on the platform.

Speaker #3: It gives us a much richer contextualization understanding and then also incorporating that in terms of our study design as well. In addition to that, for our 18 and over plus, our potential registrational study, we are also going to be using our clinical development AI capabilities for recruitment.

Speaker #3: It's a rare disease. We want to be much more efficient and use these approaches to go to where the patients are and recruit at speed and with their purchase.

Yeah. So you know, I think here because there really is a lack of regulatory precedent. It's really important for us to work closely with the FDA in terms of defining, the registration of paths to that end, we've already initiated that engagement. Um, within the oncology review division also requested input from the GI Division. And certainly as we go about these, we're thinking about leveraging, the rare disease framework as well. So, um, we can do risk this program by really closely aligning with FDA on what are clinically meaningful endpoints for patients, um, that will help us to find the primary endpoint for our uh, civil study.

Speaker #3: Great. Next question from Bruce, Philip, Rashab, and others on the platform. How does recursion evaluate whether this platform is improving its ability to identify and eliminate lower candidate quality candidates earlier in the discovery process compared with prior years?

Najat Khan: How does Recursion evaluate whether its platform is improving its ability to identify and eliminate lower quality candidates earlier in the discovery process compared with prior years? Let me answer that one first. As I shared earlier today, we look at every segment of our platform, and we're really looking at how is it that we can design better molecules faster. You know, one of the things is you asked about lower quality candidates. This is where if you can actually simulate more, predict which compounds would actually have better versus worse admin properties. This is where active learning and the multi-parameter optimization, that complexity that we can do it in a very, the industry can do in a very sequential way, we do it in a much more efficient way.

Speaker #3: Let me answer that one first. So as I shared earlier today, we look at every segment of our platform, and we're really looking at how is it that we can design better molecules faster?

The next question I'm still on um back 4881 has there been any shift to timing for sit Regulatory and when will we see additional data? So a couple of things we are on track with that, you would initiate. Um, FDA engagement, first half of 2026 is actually a bit ahead of schedule. We have initiated FDA engagement and I'm thinking we expect this to be working with the FDA very closely given if the first in disease on, you know, our potential registration of study

Speaker #3: You know, one of the things is you asked about lower quality candidates. This is where, if you can actually simulate more, predict which compounds would actually have better versus worse admet properties.

Um, and then when will we see additional data? We could do want to share that.

Um,

Speaker #3: But this is where active learning in the multi-parameter optimization. That complexity that we can do it in a very the industry can do in a very sequential way.

Speaker #3: We do it in a much more efficient way to simulate online and only synthesize the compounds that we have confidence in. That's where you see some of the numbers shifting pretty dramatically cycle times becoming half and then also 90% less compounds synthesized.

I'm happy to take it. Um, you know, in terms of additional data, you know, we have already initiated 18 and over patients. They're already recruiting those patients. And we'll also have potentially additional data from our Phase 2 that we will share, you know, either here or at

Najat Khan: We simulate online and only synthesize the compounds that we have confidence in. That's where you see some of the numbers shifting pretty dramatically. You know, cycle times getting in half and then also 90% less compounds synthesized. That's just one example as to how we track it. The other thing I would say on the biology side, look, the maps of biology give you a lot of hypotheses in terms of potential novel targets, but we pair that with really robust experimental validation. I think that is incredibly important to do both. That allows us to look in targets that no one has looked at before. This is where novel biology is coming from, but we always pair that with rigorous experimentation.

the Forum going forward.

But we're on track.

Speaker #3: So that's just one example as to how we track it. The other thing I would say on the biology side, look, the maps of biology give you a lot of hypotheses in terms of potential novel targets.

Speaker #3: But we pair that with really robust experimental validation. I think that is incredibly important to do both. That allows us to look and target that no one has looked at before.

Speaker #3: This is where novel biology is coming from. But we always pair that with rigorous experimentation. And that's where the lab, the wet and dry lab, is incredibly important for us because we can do it with speed.

Najat Khan: That's where the lab, the wet and dry lab is incredibly important for us because we can do it with speed, we can learn fast, and all that data is captured to make our models better. We are a continuous and rapid learning organization. I will say the integration with Exscientia has really helped that, right? Now you have both the biology and the chemistry side sitting side by side, and we iterate and learn from that. Okay. What are the investments you're looking to make on the platform? Huge data generation model. Is this question from one of our leaders, AI leaders in the company? I'm just kidding. Look, our strategy is we invest in our programs with our platform, and that platform needs to remain differentiated. We surgically and invest in areas that matter.

Speaker #3: We can learn fast. And all that data is captured to make our models better. So we are in continuous and rapid learning organization. And I will say the integration with Exscientia has really helped there, right?

Speaker #3: Because now you have both the biology and the chemistry sites sitting side by side. And we iterate and learn from there. Okay. What are the investments you're looking to make on the platform?

Have you leveraged any claim? Any capabilities from your platform in assembling the proposed? Pivotal study design, um, great question, a couple of areas number 1. If you recall the natural history that we did in parallel with our clinical, uh, program has been really really important for a few reasons. This is a rare disease, limited literature, sort of Natural History. This is allowed us not just to understand patient trajectory, but also helped us as we think about how we power the study, what um, end points are important and so forth. So it gives us a much richer contextualization understanding and then also incorporating that in terms of our study design as well. In addition to that for our 18 and over plus our potential registration study. We are also going to be using our clinical development AI uh capabilities for recruitment. So you're ready to disease. We want to be much more efficient and use these approaches to go to a patient of ours and recruit

proceed under

great. Um, next question from Bruce Phillips rishab and others on the platform.

Speaker #3: Compute, data generation, models. Is this question from one of our leaders, AI leaders in the company? I'm just kidding. Look, we are our strategy is we invest in our programs with our platform, and that platform needs to remain differentiated.

How does recursion evaluate whether it's platform is improving, its ability to identify and eliminate lower quantity quality candidates earlier in the discovery process compared with prior years.

Speaker #3: So we surgically invest in areas that matter. So as an example, on the clinical development side, we've seen the investment we have made. But there's a reason.

Najat Khan: As an example, on the clinical development side, you've seen the investments we have made, there's a reason. It's to make a better product. How do we recruit faster? How do we pick the right patients? In our chemistry and design platform, we're continuously evolving and iterating on our models, we'll share more in due time. In our biology platform, you've seen the investments we're making in state-of-the-art transcriptomics models. Again, they're all with a purpose. How do we improve the targets that we're putting into our program, the compounds that are high quality, and ensuring that we execute our programs with flawless execution clinically, also pick the right patients and enhance our signal generically? Maybe I'll take one more question, because I want to take as many. I know we're a little bit over time.

Speaker #3: It's to make a better product. So how do we recruit faster? How do we pick the right patients? In our chemistry and design platform, we're continuously evolving and iterating on our models.

Speaker #3: And we'll share more in due time. And then in our biology platform, you've seen the investment we're making in state-of-the-art transcriptomics models. So that's but again, they're all with a purpose.

Speaker #3: How do we improve the target that we're putting into our programs, the compounds that are high quality, and ensuring that we execute our programs with smallest execution, clinically, but then also pick the right patients and increase our signal genomics.

Let me answer that 1 first. Um, so as your, um, as I shared earlier today, we look at every appointment of our platform and we're really looking at, how is it that we can design better molecules faster? You know, 1 of the things is, we asked about lower quality candidates. This is where if you can actually simulate more predict which compounds would actually have better versus worse admed properties, but this is where Active Learning and the multi-parameter optimization that complexity that we can do it in a very the industry can do in a very sequential way. We do it in a much more efficient way exterminate online and only supervised for compounds that we have confidence in that's where you see some of the numbers shifted pretty dramatically.

You know, um, cycle times becoming half and then also 90% less compounds synthesized. So that's just 1 example as to how we track it. The other thing I would say on the biology side,

Speaker #3: Maybe I'll take one more question. So I want to take as many. I know we're a little bit over time. From Gail and Sean on partnership strategy.

Look, we the maps of biology, give you a lot of hypotheses in terms of potential knowledge.

Najat Khan: From Gail and Sean on partnership strategy. Any expected guidance for potential clinical opt-in from partners? Will we receive an update on this? Actually, Ben, do you want to share on that one?

To hear that.

Speaker #3: Any expected guidance for a potential clinical opt-in from partners? Well, will we receive an update on this? So actually, Ben, do you want to share?

Really robust.

Do both that allows us to look at Targets and no, 1 has looked at support.

Speaker #2: Sure. Happy to. So as we continue to advance the programs along with Sanofi and begin to move to different programs from Roche into the design phase, we absolutely expect to see some of those five programs that have hit their early discovery milestones move into the opt-in.

Ben Taylor: Sure. Happy to. As we continue to advance the programs along with Sanofi and begin to move different programs from Roche into the design phase, we absolutely expect to see some of those five programs that have hit their early discovery milestones move into the opt-in, and we're working very closely with Sanofi to make that happen as quickly as possible. I think there's also a broader point that's really important around the partnerships. If you take a step back, and we get a lot of questions on what's our partnership strategy, where do we plan to go in the future, if you take a step back to what we do, part of our mandate is how do you create a risk-diversified model for being able to be an investor in the biotech space?

Because we're not the biology is coming from. What we always tear that with regards, experimentation. And that's where the lab the what and by lab is incredibly important to us because we can do it with speed. We can learn fast.

All that data is captured to make our models better.

So, we are a continuous and rapid learning organization.

Speaker #2: And we're working very closely with Sanofi to make that happen as quickly as possible. I think there's also a broader point that's really important.

Um, and I will say the integration with the expansion has really helped that, right? Because now you have both the biology and the chemistry side sitting side by side.

And we iterate on.

Speaker #2: Around the partnerships, if you take a step back and we get a lot of questions on what's our partnership strategy, where do we plan to go in the future, if you take a step back to what we do, part of our mandate is how do you create a risk-diversified model for being able to be an investor in the biotech space?

Data generation models. Is this question?

From 1 of our leaders, AI leaders in the company. I'm just kidding.

Speaker #2: And so we obviously have transformative potential medicines that are coming up through our internal pipeline. But you also have to look at our partnership business and see how we've been able to advance programs and do it in a capital-efficient way and really diversify that risk and of that are.

Ben Taylor: We obviously have transformative potential medicines that are coming up through our internal pipeline, but you also have to look at our partnership business and see how we've been able to advance programs and do it in a capital-efficient way and really diversify that risk and diversify what the long-term benefits of that are. We will absolutely continue to drive that partnership forward along with our internal pipeline, and we'll balance out how we're getting the upfront payments while also still maintaining a lot of that downstream economics.

And that platform needs to remain differentiated, so we're strictly in an industrial area of that matter.

As an example.

Of a clinical development side. We've seen the investment.

To make a better product. So how do we recruit faster? How do we pick the right patient?

Speaker #2: So we will absolutely continue to drive that partnership forward along with our internal pipeline. And we'll balance out how we're getting the upfront payments while also still maintaining a lot of that downstream economics.

In our chemistry and design platform work on continuously, evolving, and iterating on our models, and we'll share more in due time. And in, in our biology platform, you've seen the Investments we're making in.

Speaker #3: What suffice to say, Gail and Sean, as a working actively on this and, of course, will share updates, and in the next two months.

Najat Khan: Suffice to say, Gail and Sean, we're working actively on this, and of course, we'll share updates in the next few months. Last question. You've generated over $500 million in partner-related payments to date. How should we think about the forward trajectory of platform monetization, particularly the balance between near-term milestones and retaining long-term economics and wholly-owned programs? I think it's very similar to what Ben said. You know, our platform is focused on generating better products. That's what we focus on, whether we do it internally or with partners. You know, we create optionality in terms of our wholly-owned programs. Some of the programs, you know, again, we're data-driven in our approaches in terms of could be wholly owned, could be partnered, could be out-licensed, and same goes for some of our partner programs as well.

Speaker #3: Last question. You've generated over $500 million in partner-related payments to date. How should we think about the forward trajectory of platform monetization, particularly the balance between near-term milestones and retaining long-term economics and wholly owned programs?

State-of-the-art transcripts only models. So that's but again, they're all with the purpose. How do we improve the targets that we're putting into our program around the compounds that are high quality and ensuring that we execute our programs?

Um, small as execution clinically, but then also take the right patients in, in favor.

Speaker #3: I think it's very similar to what Ben said. You know, our platform is focused on generating better products. That's what we focus on, whether we do it internally or with partners.

Um, maybe I'll take 1 more question so I want to take as many. I know we're a little bit over time from Gail and Sean on partnership strategies.

Speaker #3: And you know, we create optionality in terms of our wholly owned programs. Some of the programs you know, again, we're data-driven in our approaches.

Speaker #3: In terms of could be wholly owned, could be partnered, could be out-licensed. And same goes for some of our partner programs as well. So you know, with that, I'll just close by saying thank you so much for your time and attention.

Any expected guidance for a potential clinical opt-in from Partners? Well, will we receive an update on this? So um, actually that do you want to share?

Sure.

Najat Khan: You know, with that, I'll just close by saying thank you so much for your time and attention. Thank you for all of the questions. We have a lot of momentum, a lot of important work ahead, and we continue to move that forward and excited to share more updates in the coming months and years for some. Thank you again.

Speaker #3: Thank you for all of the questions. We have a lot of momentum, a lot of important work ahead. And we continue to move that forward.

So, uh, as we continue to advance the programs along with seni and and we can move, uh, different programs from roshi to the design phase.

Uh, we absolutely expect to see some of those 5 programs that have hit the early Discovery. Milestones to move into the opt-in and uh, we're working very closely with

Make that happen as quickly as possible. I think there's also a broader point that's really important around the partnerships. If you take a step back—and we get a lot of questions—

And strategy.

To take a step back to what we do part of our mandate is how do you create a risk Diversified model for being able?

To be an investor in the biotech.

And so we obviously have transformative potential medicines that are coming up through our internal pipeline.

but you also have to look at our partnership business and see

how we've been able to advance the programs and do it in a capital efficient way. And really diversify that risk and diversify, uh, what the long-term benefits of that are. So we will absolutely continue to drive that partnership forward along with our internal Pipeline. And we'll balance out how we're getting the outcome payment as well. Also still maintaining a lot of that concentration

Which suffice to say Gail and Sean have been working actively on this. And of course, they share updates, um, and what?

Else last question, you've generated over 500 million in partner related payments today? How should we think about the forward trajectory of platform? Monetization, particularly the balance between near-term milestones and retaining long-term economics and wholly owned program? I think it's very similar to what, um, been said. You know, our platform is focused on generating better products.

And whether we do it internally or with partners and you know, we create optionality in terms of our fully owned program, some of the programs, you know, again your data driven and our approaches in terms of could be wholly owned, could be partnered, could be out licensed and and same goes for some of our partners.

So you know with that I'll just close by saying thank you so much for your time and attention. Thank you for all the questions. We have a lot of momentum. A lot of important work ahead and we continue to move that forward and excited to share more updates.

coming months and

thank you again.