Q2 2025 Recursion Pharmaceuticals Inc Earnings Call

Chris Gibson: Components from both Recursion and building new components of the OS in order to drive forward our mission. At Recursion, we base everything off of proprietary fit-for-purpose data, whether it is data we generate in-house or data that we pull from partners. We are not just generating data to help discover targets or to help translate programs or to help with clinical trials. We are building a true end-to-end capability from target discovery all the way through to clinical trial simulation. We are really, really excited about the way all of these pieces fit together and add to each other. Everything we do at Recursion is based on iterative cycles of learning. Much of our work is based on iterative cycles of dry lab predictions and wet lab validations.

uh, components from both extensia and recursion and building new components of the OS in order to drive forward our mission,

Chris Gibson: I want to talk about a few of the pieces of the Recursion OS that we really, really leaned into in the last quarter. I am going to start off with talking about BOLD2. This was a really exciting partnership with both MIT and NVIDIA, where we were able to help lead the field of protein folding and lead the field of protein ligand binding predictions with this work that we did with MIT. We were able to actually open source this project. To date, there have been almost 200,000 downloads and almost 50,000 unique users. What I think is most exciting, what has gotten the most traction about this work, is that we were able to actually make binding predictions that are approaching the level of efficiency and the level of efficacy of free energy perturbation calculations. We are able to do this with about 1,000-fold less compute.

Ever recursive, we base everything off of proprietary fit-for-purpose data, whether it's data we generate in-house or data that we pull from partners. And we're not just generating data to help discover targets or to help translate programs or to help with clinical trials. We're building a true end-to-end capability from target discovery all the way through to clinical trial simulation. We're really, really excited about the way all of these pieces fit together and add to each other. Everything we do at Recursion is based on iterative cycles of learning, much of our work based on iterative cycles of dry lab predictions and wet lab validations.

I want to talk about a few of the pieces of the recursion OS, that we really, really leaned into in the last quarter. And I'm going to start off with talking about bolts too. This was a really exciting, uh, partnership with both MIT and Nvidia where we were able to help lead the field of uh, protein folding and lead the field of protein. Uh Lian binding predictions. Uh with this work that we did with MIT and we were able to actually open source this project. And today there have been almost 200,000 downloads in all

Chris Gibson: That is really, really, really exciting. It means that a lot of the sort of real bespoke work that was done with physics-based computing can actually be done in a screening format. While there is more work to do in this space by us and many others, we are very excited about the way this tool and tools like this are going to be able to drive the field forward. What is more, we have already built this technology into the Recursion OS and even improvements on this technology into the Recursion OS. Another area we have been talking about for the last year has been our clinTech platform. This is something that we are now deploying against every single one of our programs at Recursion. There are multiple components to this. The first is our causal AI applied to human genomics. This is really exciting.

50,000 unique users. And what I think is most exciting. What's gotten the most traction about this work is that we were able to actually make binding predictions that are approaching the level of uh uh the level of uh efficiency and the level of efficacy of free energy perturbation calculations. But we're able to do this with about, with about a thousandfold less compute that is really, really, really exciting. It means that a lot of the uh, sort of real bespoke work that was done with physics. Based Computing could actually be done in a screening format and while there's more work to do in this space By Us and many others, we are very excited about the way this tool and tools. Like this are going to be able to drive the field for. And what's more, we've already built this technology into the recursion OS and even improvements on this technology into the recursion OS.

Another area we've been talking about for the last year has been our clintech platform.

Chris Gibson: We're taking patient data that we get from Helix and Tempus. We're combining that with our perturbation biology data and algorithms from Recursion to help to connect our platform to patients. This is enabling us to identify targets, to stratify patients, and even to do indication expansion. We've also started to design and simulate our clinical trials at Recursion using in-house software that we've been building. This is allowing us to potentially improve the optimal dose for 30% more patients. This is really, really exciting. Again, we are now deploying this against our programs at Recursion. Third, we're now using our AI not just to identify patients, not just to design our clinical trials, but actually to recruit and execute. The operation side of our clinical trials is really, really important as well.

And this is something that we are now deploying against every single one of our programs ever. There are multiple components to this. The first is our causal AI applied to human genomics, and this is really exciting. We're taking patient data that we get from Helix and Tempest, and we're combining that with our perturbation biology data and algorithms from Recursion to help connect our platform to patients. This is enabling us to identify targets to stratify patients and even to do indication expansion.

Chris Gibson: With the new software that we've built and the partnerships we've built in this space, we now have the potential for 50% faster enrollment projections at high-quality sites. This means we can activate trials up to two months faster. Again, this is the early days of our clinTech platform. What I'm most excited about is that we're already deploying these tools against the programs in our pipeline. We'll be deploying these against new programs in our pipeline soon. Najat Khan is going to be able to tell you more about that in a few minutes. We continue to advance a pipeline of both internal programs in oncology and rare disease, as well as a suite of R&D collaborations and programs with our partners of Roche, Sanofi, Bayer, and Merck KGA. We're really, really excited about all of these programs today.

We've also started to design and simulate, our clinical trials at recursion using in-house, uh, software that we've been building. This is allowing us to potentially, uh, improve the, the optimal dose for 30% more patients. This is really, really exciting. And again, we are now deploying this against our programs, at recursion, and third, we're now using our AI, not just to identify, uh, patients not just to design our clinical trials, but actually to recruit and execute the operation side of our clinical trials is really, really important as well. And with the new software that we've built and the Partnerships we've built in this space, we now have the potential for 50% faster, enrollment projections at high quality sites and this means we can activate trials up to 2 months faster. Again, this is the early days of our clintech platform but what I'm most excited about is that we're already deploying these tools against the programs in our Pipeline and we'll be deploying these against new programs in our pipeline soon. And as John's going to be able to tell you,

More about that in a few minutes.

Chris Gibson: What I think is most exciting isn't any one of the programs. It's the platform we're building and these leading indicators where we're demonstrating that we can bring medicines to the clinic faster and at lower cost. Ultimately, these leading indicators are things that we believe over time are going to continue to improve. We're going to be able to continue to raise a high bar of quality on our programs and drive them forward at real scale. To tell you more about the way we're building momentum, let me turn it over to our Chief R&D and Chief Commercial Officer, Najat Khan. Najat.

We continue to advance a pipeline of both internal programs and oncology, and rare disease, as well as a a suite of R&D, collaborations and programs with our partners of row sanofi. Bayer and Merc kga and we're really, really excited about all of these programs today. Well, what I think is most exciting, isn't any 1 of the programs, it's the platform we're building. And these leading indicators where we're demonstrating that we can bring medicines to the clinic.

Najat Khan: Thanks, Chris. Great to be here today. Let's dive into this. Chris mentioned the suite of partnerships and partner discovery programs and internal programs that we are progressing. A couple of things to note. On the internal side, you can see there are six or so programs that are going through really, really important inflection points, both across oncology and rare diseases. What I will do today is double-click a bit more on a couple of our more late-stage or later-stage oncology programs: CDK7, monotherapy dose escalation, as well as the initiation of our expansion cohort/combination arm, and RBM39. We will share a little bit more around the biomarker enriched, the solid tumors, the patient populations, et cetera, and how we leverage our platform insights in order to hone in on where we go. On the partnership front, I get this question a lot.

Faster and at lower cost and ultimately, these leading indicators are things that we believe over time are going to continue to improve. And we're going to be able to continue to raise a high bar of quality on our programs and drive them forward at real scale. And to tell you more about the way we're building momentum, let me turn it over to our chief R&D and chief. Commercial officer, John

Thanks Chris. Um, great to be here today. So let's dive into this Chris mentioned, you know, the suite of Partnerships and partner Discovery programs and internal programs that we are progressing.

Both across oncology and rare diseases. What I'll do today is double click a bit more on a couple of our more late stage or later stage oncology programs cdk7 monitor therapy dose escalation, as well as the initiation of our expansion cohort, combination arm and RBM 39. You know, we'll share a little bit more around the biomarker. Enriched the solid tumors, the patient population Etc and how we leverage our platform insights in order to hone in on where we go.

Najat Khan: I just wanted to step back for a second and share. Across our partnerships, there are two major areas of value creation. The first is really around what Chris mentioned in the beginning, proprietary fit-for-purpose data sets that we are co-developing with our partners. An example of this is, of course, the phenomap, the first neuronal phenomap, iPSC-derived with Roche Genentech. The other area of value creation is around partnered programs where we are designing using our AI modules on the chemistry side, very challenging first-in-class, best-in-class programs. Just recently, we achieved a fourth milestone in our Sanofi partnership. More to come on that. Going to the next slide, I am just going to take a second to do a quick snapshot on the overall programs that we have in our internal portfolio. Then I will go a bit more into CDK7 and RBM39.

On the partnership front, you know, I get this question a lot. So I just wanted to step back for a second and share.

Across our Partnerships. There's 2 major areas of value creation. The first is really around, what Chris mentioned in the beginning, proprietary fit, for purpose data sets that were co-developing with our partners. So an example of this is of course, the Phenom map, um the first neuronal Phenom map, ipsc derived with roast genetics.

And the other area of value creation is around partnered programs where we are designing using our AI, um, module from the chemistry side, very challenging first, in class, best-in-class programs. And just recently, uh, we achieved a fourth milestone in our senosi uh, partnership more to come on that.

Najat Khan: Just as a quick reminder, CDK7, really important target. The focus really is leveraging our AI-powered design module in our Recursion OS platform to optimize the therapeutic index. This is a target that has been tried by others before. So that is the area of focus. We should have more monotherapy dose escalation data by the end of this year. As I mentioned, combination initiated. RBM39, this is an example actually identified using our phenomaps where we identified a new MOA with synthetic lethal targeting opportunities in genomically unstable cancers. More on that. First half of 2026, we anticipate some initial data from our monotherapy dose escalation. You heard a little bit about the MEC1/2 in our FAP program.

So, just going to the next slide, I'm just going to take a second to do a quick snapshot of the overall programs that we have in our internal portfolio, and then I'll go a bit more into CD7 and RBM 39.

So, just as a quick, reminder, uh, cdk7 really. Important Target the focus really is leveraging. Our AI powered design, module in our recursion OS, platform to optimize the therapeutic index. This is a target that has been tried by others before, so that's the area of focus. Um, we should have more monotherapy dose escalation data by the end of this year and as I mentioned combination initiated

Our.

medium 39, this is an example, actually identified using our phenol Maps where we identified a new MOA with synthetic lethal targeting opportunities in genomically, unstable cancers, more on that first half of 2026, we anticipate some initial data from our monotherapy dose escalation,

Najat Khan: So I just want to highlight this is, again, another phenotypic insight where we actually derive the fact that there is a connection, an important relationship in an unbiased fashion between MEC1/2 and the relationship with MAP kinase pathway, signaling pathway, and APC and WN signaling pathway, which disease this is for FAP. So again, we should expect more data beyond the initial cut we shared earlier this year, second half of 2025, end of this year. MALT1, this is another program where now we are using and leveraging our AI-powered chemistry design portion of the Recursion OS platform, again, to lower the liability that is associated with UGT1A1 inhibition that is also in monotherapy dose escalation. To round it out, we also have a couple of preclinical programs here that are going through important inflection points in the development candidate/IND enabling phase.

Um, you heard a little bit about the mech, 1, 2, and, and our fap program. So I just want to highlight. This is again another phenotypic Insight where we actually derive, the fact that there's a connection and an important relationship in an unbiased fashion between

Mech, 1, 2, and then and the relationship with map. Tine pathway signaling pathway, and APC, and wind signaling pathway which disease. This is for fap. So, again, we should expect more data, uh, beyond the initial card we shared earlier this year, uh, uh, second half of 2025, and

Najat Khan: You know a lot of these programs, and we talked about this before, were really focused on the earlier versions of the Recursion OS platform. As we iterate and learn and add more components to our Recursion OS platforms, we expect the next wave of programs to be even more high potential and potential to do it in a more efficient way. I wanted to take you a little bit under the hood of what is actually in the Recursion OS, especially the 2.0 platform following the integration with Exscientia. If you just look to the left-hand side, we first start with the AI-powered biological insights. This is where we are actually deriving novel targets. This is from multi-omic data, whether it be phenomics, transcriptomics, et cetera, connecting that early on with the patient.

And most 1, this is another program where now we're using and leveraging, our AI powered chemistry design, portion of the recursion OS platform, again to lower the liability that's associated with. Ut1, A1 inhibition. That's also in monotherapy dose escalation and to round it out. We also have a couple of pre-clinical programs here that are going through important um inflection points in the development candidate enabling space.

But, you know, a lot of these programs and we talked about this before, we're really focused on the earlier, um, um, versions of the recursion OS platform and as we iterate and learn and add more components to our recursion OS platforms. We expect the next wave of programs to be even more high potential and and, and and potential to do it in a more efficient way. But I wanted to get take you a little bit under the hood of what's actually in the recursion, um, OS and specially the 2.0 platform following the integration with um, XI inia.

Najat Khan: This is the ML-based patient connectivity data layer that is really important for data sets such as from Tempus, Helix, and others, ensuring that we can actually take these biological insights and deconvolute the MOA and very early on do a screening approach around triaging what are some of the binding affinities early on. This is where approaches such as BOLD2 that Chris mentioned earlier is already being incorporated into our workflow. In addition to that, we are also developing proprietary algorithms in-house. As soon as we put this on a slide, I have to say it gets outdated because there is so much rapid iteration and work that is happening. In the middle, AI-enabled precision design, this is where we are designing our molecules, really optimizing both for novel scaffolds. This is where we use generative AI approaches and also active learning in order to optimize drug-like properties.

So, um, if you just look to the left hand side, we first start with the AI powered biological insights. This is where we are actually. Driving novel Targets. This is from multi-omic data, whether it be phenomic, transcriptomics, Etc. Connecting that early on, with the patient.

This is the ml-based patient connectivity data layer. That's really important to data sets such as from Tempest Helix and others,

Ensuring that we can actually take these biological insights into the Moa and very early on to a screening approach, um, around triaging. What are some of the binding affinities early on? So this is where approaches such as bolts too, that Chris mentioned earlier is already being incorporated into our workflow. In addition to that, we're also developing proprietary algorithms in house

Because there's so much rapid iteration and work that's happening in the middle. Um, AI enabled Precision Design. This is where we're designing. Our molecules really optimizing both for novel scaffolds. This is where we use generative, AI approaches and also active learning in order to optimize

Najat Khan: This also includes using QMMD approaches, which is a 3D protein and atomistic model. One important point here is the wet and dry lab integration that we have. This is where aspects around automated chemistry, automated biology, and automated ADMET become incredibly important. We can design out certain elements earlier, faster, to ensure that we have better molecules at its recovery. Last but certainly not the least, and one that is close to my heart, is ensuring that we do this also in clinical development. Chris touched on this in terms of some of the areas that we are building out. You will see some of the examples we are using in our current programs already around causal inference on patient stratification and also smarter trials and factory equipment.

Uh, drug-like properties. This also includes using qm MD approaches which is a 3D protein and atomistic models.

And 1 important Point here is the wet and dry lab integration that we have. So this is where aspects are on automated chemistry automated biology and automated admit becomes incredibly important. So we can design that certain elements earlier faster to ensure that we have better molecules out of discovery.

Najat Khan: As I go through each of the programs, I will actually highlight which area of the Recursion OS module and platform we are integrating and actually highlighted insights for our program. Let us start with RBM39. In this program, as I mentioned earlier, the focus was really around leveraging our maps of biology. Just as a reminder for everyone, starting on the left-hand side, we start with this really large maps of biology, whole genome CRISPR knockouts. Then we profile compounds that are proprietary to us in order to get a better understanding of the initial chemical substrates that might actually modulate the biological insight that we have identified. The example here is how we identified RBM39, which phenomimics CDK12.

And last, but certainly not least, and close to my heart, is ensuring that we do this also in clinical development. Chris touched on this in terms of some of the areas that we're building out, and you'll see some of the examples we're using in our current programs already around causal inference on patient stratification, and also smarter trials and faster equipment.

So as I go through each of the programs, um, I will actually highlight which area of the um, recursion OS, module and platform. We are integrating and actually in uh highlighted um insights.

For our program. So let's start with RBM. Um, uh, 39

So in this program, as I mentioned earlier, the focus was really around.

Um, leveraging our maps of biology. So just as a reminder, for everyone starting, on the left hand side, we start with these really large maps of biology, whole genome crispr Knockouts, um, and then we profile compounds that are proprietary to us. In order to get better understanding of the initials chemical substrates, that might actually modulate the biological Insight that we have identified.

Najat Khan: CDK12, and this is to the panel to your right-hand side, has been an attractive target in oncology for its role in DDR modulation, but generally has suffered from challenges in selectivity because of how homologous CDK13 is. Leveraging our phenomaps, we actually identified that RBM39 is similar, phenotypically at least, to CDK12 and not to CDK13. That was the first insight. The second insight was the fact that we were actually able to develop molecular glues and degraders for RBM39, which you will see in a moment, that are also phenotypically mimic CDK12. This was our first inkling that this could potentially, RBM39 inhibitors or degraders could potentially provide a druggable potential analog.

so the example here is how we identify RBM 39, which phenotype phenomics, uh, cdk 12

So CDK 12, and this, to the panel to your right, has been an attractive target in oncology, right? For its role in DDR modulation.

But generally has been that has suffered from challenges in selectivity because of how homologous cdk13 is.

Leveraging. Our phenomena we actually identify that RBM. 39 is

Similar you know, typically at least to cdk 12 what we could and not to cdk 13 so that was the first Insight. The second Insight was the fact that we were actually developed, we're able to develop molecular glues and to graders for RBM 39, which you'll see in a moment that are also phenotypically. Mimic cdk12,

Najat Khan: I want to say something else that does not get talked about enough, which is if you look in the middle panel, we also look not just for CDK12 or CDK13, but we look more extensively across the map to see if there are well-established dependencies that are known of already biologically that are also being validated. An example here is a CDK12 and cyclin K similar phenomic readout. This is just a small detail in the entirety of the map that we look at. If you go to the next slide, this is another expansion of that same map. What we see here that is actually quite intriguing is in the center in the black box is what I was referring to in the earlier slide, which is the RBM39 and the degrader itself and some of the associations that we see with CDK12, CDK13, and so forth.

So this was our first inkling that this could potentially RBM 39 Inhibitors or degraders could potentially provide a druggable potential analog. And then I want to say something else that it doesn't get talked about.

Enough. If you look at the middle panel, we also look, not just for CDK 12 or CDK 13, but we look more extensively across the map to see if there are well-established dependencies that are known biologically and are also being validated. An example here is CDK 12 and cyclin E, cyclin K, with a similar phenotypic readout.

but this is just a small detail in the entirety of the map that we look at and if you go to the next slide,

Najat Khan: You look broader and you also see associations mechanistically in DNA damage repair, epigenetic regulation, cell cycle control, and transcription. This, when you look at it from an MOA perspective, which I will turn on next, actually intuitively makes sense. RBM39, if we go to the next slide, is focused, is important for splicing fidelity. Degradation of RBM39 leads to splicing defects. If you combine that with tumors that are already genomically unstable, whether it is because of DNA repair pathway vulnerabilities or transcriptional regulation, then that can actually increase the amount of instability leading to potential apoptosis and cell death. I just wanted to share with you how an insight is then triangulated with an understanding of the mechanism of action. That is not enough. So if you go to the next slide, in addition to that, we also looked at in vitro and in vivo work.

This is another expansion of that same map. And what we see here that’s actually quite intriguing is in the center in the black boxes. What I was referring to in the earlier slide, which is the RBM39 and the greater itself. And so some of the associations that we see with CDK12s that you get 13th, but you look broader and you also see associations making the next quickly in DNA damage repair, epigenetic regulation, cell cycle control, and transcription. And this, when you look at it from an MMOA perspective which I'll turn on next, actually intuitively makes sense.

RBM 39, if we go to the next slide is focused is is important for slicing Fidelity degradation of RBM 39 leads to splicing defects. Now, if you combine that with, uh, tumors that are already already genomically unstable, whether it's because of DNA repair pathway vulnerabilities or transcriptional regulation, then that can actually increase the amount of instability leading to potential apoptosis and cell death. So just want to share with you how an Insight is then uh triangulated with understanding of mechanism of action,

But that's not enough. So if we go to the next slide,

Najat Khan: Starting with, look, when we look at the broader patient population, just given the connectivity across the map that I noted, for replication stress, tumors that suffer from epigenetic dysregulation, cell cycle alterations, or oncogenic drivers are relevant, as well as those tumors that have DDR effects, so both of those. That spans several solid tumors from colorectal, breast, et cetera, along with some pretty clinically actionable alterations that we will be studying and looking into more, such as MSI high, MYC amplification, et cetera. We wanted to look at the in silico understanding and triangulate that with in vitro and in vivo work. So, if you look at the in vitro cell lines, you clearly see that RBM39 degrader, REC-1245 in this case, there is greater sensitivity in cell lines that have higher replication stress versus cell lines that do not have higher replication stress.

In addition to that, we also looked at in vitro and in Vivo work.

DDR effects. So so both of those and that spans several solid tumors from colorectal breasts, Etc, along with some pretty clinical actionable. Alterations that we'll be studying and looking into more such as MSI, High make, amplification Etc.

But we wanted to look at the encyclical, understanding and triangulate that with in vitro and in vivo work.

Najat Khan: This was a good early signal for us. If you go to the next slide, we see a similar trend hold in in vivo as well, where you see a reduction in tumor volume across different tumor types that actually have high replication stress signatures. This helps us to do things. Number one, better understand the importance of RBM39 as a first-in-class target in solid tumors. Second, also give us a better sense in terms of which patient population, tumor segments, et cetera, might be relevant for us to target. If you go to the next slide, we went a step further than that. We also wanted to look at the totality of it. So you have the Recursion OS inside, definitely the preclinical data that I mentioned, but also looking into mechanistic validation in the middle panel. We see two things here.

So, if you look at the in vitro cell lines and you clearly see that RBM, 39° greater. So Rec 1245, and this case there is greater sensitivity um, in cell lines that have higher replication stress versus the lines that don't have higher replication, stress.

so this was a good early signal for us and if you go to the next slide, we see a similar Trend hold

in in Vivo as well.

Where you see um, a reduction in tumor volume across different tumor types, that actually have high replication stress signatures so this helps us to do things. Number 1 better understand the importance of RBM 39 at the first and last Target in solid tumors.

Second also give us, give us a better sense in terms of which uh, patient population, tumor segments, Etc, might be relevant for us to Target.

and if you go to the next slide,

we went a step further than that. We also wanted to look at the totality of it. So you have the recursion um OS inside, definitely the pre-clinical data that I mentioned.

Najat Khan: First, the Dmax is approaching almost 100% in RBM39 degradation with quite potent D50 numbers as well. So rapid and potent RBM39 degradation. Now, we wanted to go even a step further. If you go to the next slide, which is, if you go to the slide before, please. Okay, that is okay. If you go to the next slide, this has actually helped us inform what our dose escalation and our combination arm is going to be. For RBM39, monotherapy dose escalation, but in terms of the cancers that we are looking after or going after is endometrial, ovarian, et cetera, cancers with high genomic instability. We will also be focusing on some of these biomarker-enriched populations such as MSI high. So again, first patient dose, patients are enrolling in this study.

But also looking into mechanistic validation, and in the middle panel. And, you know, we see 2 things here. First, the D-Max is approaching Almost 100% in RBM, 39, degradation with quite potent. Um, D50, um, numbers as well.

So, rapid and potent are 39 degradation.

Now we wanted to go even a step further. If you go to the next slide, which is...

um, if you go on slide before, please,

Okay that's okay if we go to the next slide. So this is actually helped us inform what our dose escalation and our combination arm is is is going to be. So for RBM, uh, 39 monotherapy dose escalation but in terms of the cancers that we're looking after are going after is endometrial ovarian Etc with Cancers with high genomic instability and we will also be focusing on some of these biomarker enriched populations such as MSI High.

Najat Khan: We should have early safety and PK data from this monotherapy trial in the first half of 2026. Now, we will go to CDK7, which is our next program. Here, we actually leverage two components of our Recursion OS platform. First, focused on designing a molecule that can really optimize for the therapeutic index. Second, leveraging some of our clinTech approaches in order to hone in on which patient population and which combination arm we will hone in on. So let us go to the next slide. Okay. So just a quick reminder in terms of how the molecule was designed, a couple of things to note here. CDK7 has been an important target for some time as well. It is a master regulator, both cell cycle progression as well as transcription.

So, again, first patient dose, uh, patients are enrolling in the study. We should have early safety and PK data from on this monitor therapy trial in the first half of 2026,

Now, we'll go to cdk7, which is our next program.

Here, we actually leveraged two components of our recursion OS. The platform first focused on designing a molecule that can really optimize for the therapeutic index. Second, we leveraged some of our clintech approaches in order to hone in on which patient population and which combination arm we will focus on. So, let's go to the next slide.

Najat Khan: But one of the challenges that other compounds have seen so far is challenges with permeability, efflux, and not rapid absorption. We wanted to change that around. We used generative AI models to actually design new scaffolds. I think this part is really important, which is leveraging active learning and experimental ADMET data to quickly learn, iterate, and optimize the molecules to reduce the components that we wanted to design out, such as ensure that there's high permeability, rapid absorption, and low efflux. Similar to RBM39 degrader, which was done in a very short amount of time, 18 months from start to IND enabling, with about 200 compounds or so synthesized. In this case, you also see about 136 novel compounds synthesized and getting to candidate ID in less than 12 months.

Okay so just a quick reminder in terms of how the molecule was designed a couple of things to note here the cdk7 is it has been an important Target for some time as well. It is a master regulator both cell cycle progression, as well as transcription.

But 1 of the challenges that other compounds have seen so far is how you know, challenges with permeability um, e-lux and not rapid absorption. So we want to change that around.

We use generative, AI models to actually design new scaffolds. And I think this part is really important, which is leveraging active learning and experimental admit data to quickly, learn iterate and optimize, um, the molecule of to reduce the components that we wanted to design out such as ensure that there's High permeability rapid absorption and low efforts. And, um, similar to RBM, uh, 39 degree or which was done in a very short amount of time, 18 months from start to end enabling, um, with about 200 compounds or so synthesized. In this case, you also see about

Najat Khan: One of the components for designing high permeability, rapid absorption, and low efflux was to ensure that we would have sufficient exposures. You see that on the right-hand side panel, both 10 milligrams q.d., 20 milligrams q.d., clearing the IC80 line. When we actually look at versus some of the peers, it's an order of magnitude higher than the exposure that they're seeing. As of November/December 2024 data cutoff, the compound showed one confirmed PR in ovarian cancer, as well as multiple cases of stable disease, so far, with a favorable safety profile and no MTD reached. If you go to the next slide, what we have done since then is to really design which combination arm we will focus on. The one that we're going to focus on that we have announced today is second line plus platinum-resistant ovarian cancer. How did we get to that?

136 number compact synthesized and getting to candidate ID in less than 12 months. Now, 1 of the components for Designing High permeability rapid absorption and low efflux, was to ensure that we would have sufficient exposures and you see that on the right hand side panel, um, both 10 milligram QD, 20 milligram QD, clearing the IC 80, uh, line. And when we actually look at versus some of the peers, it's an order of magnitude higher than the exposure that they're seeing.

So as of November slash December 2024 data cut off, uh the compound showed 1 confirmed PR in ovarian cancer as well as multiple cases of stable disease.

So far with a favorable safety profile and no MTD reached.

if you go to the next slide, what we have done, since then it's really designed which, um, combination arm we will focus on

Najat Khan: First, we looked at preclinical data. Cell panels in vivo, you see in ovarian, both of them are sensitive to CDK17. There are multiple panels that were done. In addition to that, as part of our clinTech approach, we also use causal inference using some of this multi-omic and clinical data. This was very important to better understand the cause and effect factors here. What we see is that a higher expression of ovarian cancer based on this data is associated with lower overall or worse overall survival. This was based on about 32,000 patient records.

Yesterday, a second line plus Platinum resistant, ovarian cancer. How do we get to that?

So, first we looked at pre-clinical data, so cell panels in Vivo, you see in ovarian, both are of them, are sensitive to cdk 17. And there's, there are multiple panels that were done.

And then, in addition to that, as part of our clintech approach, we also use causal inference using some of this multi-omic and clinical data.

And this was very important to better understand the cause-and-effect factor here. What we see is that a higher expression of a variance cancer, based on this data, is associated with lower overall, or worse, overall survival.

Najat Khan: This gave the totality of the evidence from preclinical and also some of what we see in our early clinical data so far, combined with some of this causal inference work, gave us more confidence in terms of the first indication that we would go after, where there is significant unmet need in second line plus platinum-resistant ovarian cancer. If you go to the next slide, site selection and activation is in progress right now for the combination arm. The standard of care includes single-agent chemotherapy, BEVA, plus chemotherapy, and in some cases, PARP inhibitors. In addition to that, the monotherapy arm is ongoing. We anticipate more data from that later on this year. If you go to the next slide, I will also share a bit more about some of our partners' discovery programs. Next slide, please. Great.

This was based on about 32,000 patient records.

So, this gave the totality of the evidence from pre-clinical and also some of what we see in our early clinical data so far combined with some of this causal inference work. Um, it gave us more confidence in terms of the first indication that we would go after, where there is significant unmet need: second line plus platinum-resistant ovarian cancer.

So, if you go to the next slide, um, site selection and activation, um, is in progress right now. Um, the for the combination arm, the standard of care includes single agent chemotherapy Beva, plus chemotherapy and in some cases, Park Inhibitors. Um, in addition to that, the monotherapy arm is ongoing and we anticipate more data from that um, later on this year.

Go to the next slide.

So also share a bit more about some of our partners Discovery programs next, slide, please.

Najat Khan: If you look at Sanofi as an example, I just mentioned that we have our fourth program milestone achieved in the last 18 months. I just want to take a moment to say that some of these programs, both in immunology and oncology, first-in-class, best-in-class, some of the milestones that we are going through include important milestones in discovery lead series, development candidate, and so forth. We have several programs advancing to those milestones, including development candidate, in the next 12 to 15 months. This effort leverages what you saw in the Recursion OS platform, a lot of the AI-powered chemistry design module. In terms of Roche, five phenomaps built to date. You saw an example for RBM39 how we use some of our phenomaps. These are specific for the neuroscience and GI/onc space.

Great. So if you look at Sophie, as an example, um, just mentioned that we have our fourth program, Milestone achieved in the last 18 months. I just want to take a moment to say that some of these programs both in immunology and oncology first in class Best in Class. Some of the Milestones that we're going through include important milestones, in Discovery, we just need series development candidate and so forth. And we have several programs advancing, to those Milestones, including development candidate in the next 12 to 15 months,

This effort leverages what she saw in the recursion OS platform. A lot of the AI powered chemistry, uh, design module

Najat Khan: For the neuroscience one that we delivered last year, over a trillion iPSC-derived cells used, whole genome knockout, and also other perturbations in terms of overexpression. You are really getting a very holistic understanding of biological pathways. A lot of work in progress there in order to take those insights and translate them into novel programs. More to come on that. Also on the GI/onc indication, over four maps already developed there and already one program that has been optioned and more work happening. It is a real pleasure and honor to partner with partners such as Roche, Sanofi, Bayer, and Merck KGA where we bring the best of our capabilities, the Recursion OS, the Recursion expertise, and the platform tech expertise, along with the deep biology expertise and chemistry expertise in Genentech, Sanofi, and others.

And in terms of Rosh, you know, 5, female Labs built to date. So, you saw an example, for RBM 39, how we use some of our phenomena Maps? These are specific in for the neuroscience and ghee on space. I mean, for the Neuroscience 1, that we delivered last year, over a trillion ipsc, derived cells used whole genome knockout and also other perturbations in terms of overexpression. So you're really getting a very holistic understanding of, um, biological Pathways and a lot of work in progress there. In order to take those insights and translate them into novel programs. So more to come on that.

Najat Khan: When it comes to Bayer and Merck KGA, similarly, the second area of value creation that I mentioned earlier, which is challenging targets, developing molecules for them using our chemistry platform, or actually highlighting and nominating novel or undruggable targets from our maps of biology. With the potential here, a lot of work ongoing for over $100 million in partnership milestones by the end of 2026. With that, I am going to hand it over to Ben Taylor, our CFO and President of UK, to tell us a little bit more about our financial update. Ben.

And then also on the GI, um, an indication over four maps already, um, developed there and already one program, um, that has been optioned and more work happening. And I think one point to note here, it's a real pleasure and honor to partner with partners such as Bayer and More KGA, where we bring the best of our capabilities, you know, the Recursion OS, the Recursion, you know, uh, Drug Hunter expertise and the platform tech expertise along with the deep biology expertise in chemistry, expertise in genetics, and OP and others. And then when it comes to Bayer and More KGA, similarly, you know, the second area of value creation that I mentioned earlier, which is challenging targets, developing molecules, uh, for them using our chemistry platform or actually highlighting and nominating novel or undruggable targets for our maps of biology with potential here. A lot of work ongoing for over $100 million in partnership milestones by the end of 2022.

Ben Taylor: Terrific. Thanks, Najat. We had a good quarter and ended with a strong cash balance, as we go to the next slide, showing $533 million in cash at the end of the quarter. That was based on not only managing our expenses. At the time of the merger, we made a commitment to our shareholders that we would not only drive a lot of the growth and the programs and the technology that Chris and Najat talked about, but also manage our expenses. You have seen us go from a pro forma burn in 2024 to an expected cash burn in 2026 that is 35% less. That is really our commitment as a management team to making sure that we are doing this as efficiently as possible. We had some great cash inflows over the quarter.

So with that, I'm going to hand it over to Ben Taylor our CFO and president of UK. Uh to tell us a little bit more about our financial updates been

Terrific. Thanks Ma

So we had a good quarter and ended with a strong cash balance as we go to the next slide uh showing uh 533 uh million in cash, at the end of the quarter.

Um, that was based on, uh, not only managing our expenses. So at the time of the merger, we made a commitment to our shareholders. That we would not only drive a lot of the growth and the programs and the technology uh, that Chris and I got talked about but also manage our expenses. And so you've seen us go from a ProForm of burn in 2024 to a expected cash burn in 2026. That's 35% less.

Uh, and that's really our commitment as a management team to making sure that we're doing this as sufficiently as possible.

Ben Taylor: In addition to the Sanofi milestone payment, we also had a $29 million R&D tax credit. This is a U.K. tax credit. We will continue to receive this in the future, although it will be smaller as the legislation around it has changed. Our guidance has not changed. We continue to project over $100 million in partnership inflows by the end of 2026 and managing our burn below $390 million in 2026, next year. All of that comes together with an expected cash runway through the fourth quarter of 2027. That cash burn number that I gave you does not include any partner inflows or other financing or inflows that would come in. With that, I will turn it back over to Chris.

29 million R&D tax credit. This is a UK tax credit. Uh we will continue to receive this uh in the future, although it will be smaller uh as the legislation around, it has changed

Our guidance has not changed and we continue to uh project over 100 million in Partnership inflows, by the end of 2026 and managing our burn below, 390 million, uh, in 2026. So next year,

uh all of that comes together with an expected cash Runway through the fourth quarter of 2027, um that cash burn number that I gave, you does not include any partner inflows or other financing uh or enclosures that would come in.

Chris Gibson: Thanks, Ben. I just want to end by talking a little bit about how we are looking ahead at the future of Recursion. It has been an incredible last nine months post the business combination with Exscientia. We really feel like we have pulled together the best elements of both companies' platforms into the Recursion OS 2.0, as both myself and Najat talked about earlier. Going forward, I think you are going to begin to see us, while maintaining an extraordinarily high bar for quality, bringing unique biological insights identified with our multimodal maps across many different cell types. We are going to see us bring new ideas, new targets, new chemistry. We are going to use our MOA and target deconvolution systems, tools like BOLD2, our QMMD systems, and even CRISPR screens to help prosecute those exciting targets.

Uh, and with that, I will turn it back over to Chris.

Thanks Ben. Yeah, I just want to end by talking a little bit about how we're looking ahead at the future of recursion. It's been an incredible last 9 months post the business combination with extensia. We really feel like we've pulled together. The best elements of both companies platforms into the recursion OS 2.0 as both myself and the gene talked about earlier and going forward, I think you're going to begin to see us while maintaining an extraordinarily High bar for Quality bringing unique biological insights identified with our multimodal Maps. Across many different, uh, cell types. We're going to see us bring new ideas. New targets, new chemistry. We're going to use our MOA and Target deconvolution systems tools like bolts 2 rqm systems.

Chris Gibson: Then we are going to continue to deploy this clinTech platform to help translate the models and the programs that we are developing at Recursion with real-world evidence into programs that can move towards the clinic. Again, we are focused on differentiated, high-quality programs that are going to go where others cannot. We are excited for the Recursion 2.0 platform to start to show you some of those programs that are really bringing together all of the elements from target discovery all the way through to clinTech in the coming quarters and years. Over the next 18 months, we have a catalyst-packed calendar. The second half of this year is looking really exciting, multiple readouts, including FAP and CDK7, as Najat spoke to earlier. In the first half of next year, we will be talking about our RBM39 program with early safety and PK from the monotherapy trial.

Crispr screens to help, uh, prosecute, those exciting targets, and then we're going to continue to deploy this clintech platform to help translate, uh, the models and the, and the programs that we're developing at recursion with real world evidence into programs that can move towards the clinic. And again, we are focused on differentiated high-quality programs that are going to go where others can't and we're excited for the recursion 2.0. Platform to start to show you some of those uh programs that are really bringing together all of the elements from Target Discovery. All the way through to Clint in the coming quarters and years.

Chris Gibson: Then rolling into the second half of next year, we are going to be looking at both MALT1 and initiating our eNPP1 program, which we were able to bring in recently from our JV with RallyBio. In addition to what you see here from our internal pipeline, we are going to be delivering across all of our partnerships with the potential for additional phenomap options, the potential for new project initiations, and the potential for programs being optioned by our partners. Again, Recursion continuing to deliver across both our internal and partner pipeline, while also building the future drug discovery platform that we think is going to help to improve the probability of success, the time, the cost, and the potential of the medicines that we are advancing. With that, we are going to move over to the Q&A portion.

But over the next 18 months, we have a catalyst packed calendar, the second half of this year, looking really exciting. Multiple readouts, including fap and cdk7 as in John spoke to earlier. In the first half of next year, we'll be talking about our RBM 39 program with early safety and pique from the monotherapy trial and then rolling into the second half of next year, we're going to be looking at both malt 1 and initiating, our enpp1 program, which we were able to bring in uh recently in in from our JV with rally. Bayou, in addition to what you see here from our internal pipeline, we're going to be delivering across all of our Partnerships with the potential for additional Phenom, map options. Uh, the potential for new project initiations and the potential for programs being optioned by our partners. So again, recursion continuing to deliver across both our internal and partnered pipeline while also building the future.

Chris Gibson: I am going to go to the first question, which comes from multiple parties, which is about our BOLD2 project. The question is, is BOLD2 the initiative with a major partner on foundational protein structure modeling that I mentioned at JPM earlier this year? The answer is yes. This is the partnership that we alluded to at JPMorgan. One of the questions here is, why open source versus keeping it internal? We believe that discovering and developing medicines is really, really challenging. Biology is really complex. Chemistry is really complex. There are places where we believe we have a very differentiated advantage, such as with our large-scale phenomics platform and our design platform. These are places where we are going to keep those tools internal.

Chris Gibson: There are other places where we need to be on the forefront, but we believe there are many competitive partners or groups working in the space. In those areas, rather than try to keep something internal that others have available to them, we actually think it is best to help commoditize that particular technology. That is exactly what we are doing with BOLD2. We are commoditizing our complement, making sure that everyone has access to the kinds of tools that many groups are using, and then keeping proprietary those tools that we think nobody else really has. The second question is, are you still building proprietary models? The answer is absolutely. We were leveraging the BOLD2 models before they were public. We also have large-scale internal data sets.

Drug Discovery platform that we think is going to help to improve the probability of success. The time, the cost, and the potential of the medicines that were advancing. And with that, we're going to move over to the Q&A portion. And I'm going to go to the first question, which comes from multiple parties, uh, which is about our bolts 2 projects. So, uh, the question is, is bolts to the initiative with a major partner on foundational. Protein structure modeling that I mentioned at JPM earlier this year. And the answer is yes, this is the, this is the partnership that we alluded to at JP Morgan, um, and 1 of the questions here is why open source versus keeping it internal. So we believe that, uh, you know, discovering developing medicines is really, really challenging. Biology is really complex, chemistry is really complex. And there are places where we believe we have a very differentiated Advantage such as with our large scale, phenomics platform and our design platform. These are places where we're going to keep those tools. Internal, there are other places where we need to be on the Forefront, but we believe there are many

Competitive, uh, uh, Partners or groups working in the space and in those areas rather than try to keep something internal that others have available to them. We actually think it best to help commoditize, that particular, uh, technology. And that's exactly what we're doing with bolts too. So we're commoditizing our compliments. Making sure that uh, that everyone has access to the kinds of tools, uh, that many groups are using and then keeping proprietary, those tools that we think nobody else really has

Chris Gibson: One could imagine that we could take the same kind of architectures, the same kinds of models that have been built in BOLD2, and training them across much larger proprietary data sets to give us an internal advantage. The second question, I am going to go to Najat. The question is from Dennis at Jeffries. Dennis asked for the CDK7 combo expansion cohort in ovarian cancer. What standard of care are you allowing in the trial? Remind us the level of efficacy they showed in terms of OR and PFS. Najat, I will come to the part two after you answer the first one.

The second question is, are you still building proprietary models? And the answer is absolutely. So we were leveraging, the bolts 2 models before the they were public. We also have large scale, internal data sets and 1 could imagine that, we could take the same kind of uh uh architectures. The same kinds of models that have been built in bolts 2 and training them across much larger, proprietary data sets to give us an internal advantage.

Najat Khan: Thanks, Chris. Thanks, Dennis, for the question. Great question. The standard of care, as I mentioned during the presentation, will be single-agent chemo plus BEVA as well. The last that I've seen for that combination, the median PFS was about 6.7 months. The median OS was about 14 to 22 months. For us, for the combination, we definitely want to see meaningful improvement to the standard of care. This is a patient population with very significant unmet need. The team will look through in terms of what other points might be more critical as well, for instance, the proportion of patients that reach a certain scan by a certain period of time and so forth. A lot of conversations ongoing there. We definitely want to see meaningful improvement from the standard of care for PFS.

And the question is from Dennis at Jeffrey and Dennis asked for the cdk7 combo expansion cohort in ovarian cancer what standard of care are you allowing in the trial and remind us the level of efficacy? They showed in terms of oh and PFS and then n will come to the part 2 after you answer the first 1.

Great. Um, thanks. Dennis for

Chris Gibson: Thanks, Najat. You hit part two there. So I will move on to the next question, which is Brendan from Cowen and Alec from BFA asked, you mentioned the multi-omic profiling that is ongoing for REC-1245, that is our RBM39 program. Do you expect the data from this analysis will in part dictate which patients you enroll in future studies? What data from this analysis would you be able to leverage when targeting or enrolling future patients? Finally, can you point to the differentiation of RBM39 compared to other CDK targeting assets?

Uh, Beva as well. Um, the last that I've seen for that combination, the median PFS was about 6.7 months and then median OS was about 14 to 22 months and look for us. Um, you know, for the combination we definitely want to see meaningful Improvement to the standard of care. This is a patient population with very significant unmet need and, you know, the team will look through in terms of what other points might be more, uh, critical as well. For instance, the proportion of patients that reaches certain scan by a certain period of time and so forth. So a lot of conversations on go ongoing there but we definitely want to see, meaningful improvements from the standard of care for PFS.

Thanks and you hit part 2 there. So I'll move on to the next question which is Brandon from Cohen and Alec from BFA asks you mentioned the multi profiling that's ongoing for rec 1245. That's our RBM 39 program. Do you expect the data from this analysis? Will in part dictate, which patients you enroll in future studies and what data from this analysis? Would you be able to leverage when targeting or enrolling future patients? And then finally, can you point to the differentiation?

Najat Khan: Great. Lots of questions. Thank you, Brendan. Thank you, Alec. I will start with the first couple of questions, which is the data from this analysis dictating the data from this analysis dictating the patients that we will go into and then also future patients. As I mentioned during the presentation today, the beauty of the maps of biology, the phenomaps, the multi-omic approach, and so forth, is instead of having a single screen in a certain area for a certain target, you saw the holistic nature of how you can see the target being important and interesting across different pathways. That was really important for us to understand that for various forms of replication stress, which can be epigenetic, which can be other areas as well, and DNA repair vulnerabilities are both very important for RBM39 as a target. That was step one.

Najat Khan: That is actually what helped us for our monotherapy dose escalation to select patients in those areas, as you saw in our press release this morning. The other thing I will also say is the monotherapy dose escalation is going to be important. We are going to see patients with certain biomarkers recruited and enrolled and so forth. We will make more of the honing in of where we go based on data that we receive. This is a great way of actually using some of this data, not just for a novel target discovery, but something I have said before, but also while you are in discovery to have a better hypothesis of which patients you might actually want to go forward with. 100,000 patients plus.

Of RB, M39 compared to other cdk targeting assets. Great, lots of questions. Thank you, Brandon. And thank you, Alec. I'll start with the first couple of questions, which is the data from this analysis, dictating the data from this analysis, dictating, the patients that will go into and then also, um, future questions because I mentioned during the presentation today, you know, really instead of having, I think the beauty of the maps of biology, the phenomena of the multaq approach. And so forth is instead of having like a single screen in a certain area for certain targets, you saw the holistic nature of how you can see the target being important, uh, and interesting across different Pathways, that was really important for us to understand that. Look for various forms of replication stress which can be epigenetic, which can be, you know, other areas as well and DNA repair vulnerabilities are both very important for RBM 39 as a Target that was Step 1 and that's actually what helped us um for our monotherapy dose escalation.

And to select patients in those areas, right? Um, as you saw in our in our, in our uh press release this morning. The other thing I'll also say is look the monetary therapy. Does the issue is going to be important. We're going to see patients with certain biomarkers recruited and enrolled and so forth and we'll make more of the honing in of where we go Based on data that we received. But this is a great way of actually using some of the data not just for a novel Target Discovery, but something I've said before but also while you're in Discovery, Discovery to have a better

Najat Khan: The expansion is because it actually targets a broad, has the potential, I should say, to target a broad set of tumor types that are genomically unstable.

Chris Gibson: Thanks, Najat.

Najat Khan: The other.

Hypothesis of which patients you might actually want to go uh forward with 100,000 patients plus and the expansion is because it actually targets abroad has a potential I should say to Target abroad set of of tumor tests with that are genomically unstable.

Chris Gibson: Oh, go ahead.

Najat Khan: I didn't answer the CDK acid question. Just wanted to make sure I answered that. The point of differentiation in RBM39 and CDK acid, look, RBM39 is not a kinase, right? A lot of the kinases, for instance, as I mentioned, CDK12 has always been for a long time an important oncogenic target. But the homology with CDK13 just makes it challenging to really get that selectivity that you're looking for. So for us, it was born out of that inspiration of selectivity for a target that's important for DDR modulation, but went beyond much more when we looked at the broader map. And trust me, the map I even showed you today just for DDR pathways, it's a big, beautiful map. It's much broader than that. So at some point, I'd love to be able to show you more and what you see there.

Thanks Mr. John and then the other go ahead. I didn't ask.

Just wanted to make sure.

Uh, the point of difference.

Chris Gibson: Thanks, Najat. OK, next question. Brendan from Cowen and Sean from Morgan Stanley asked, for the upcoming FAP data, where do you see the threshold for success in that readout that would give you confidence in the path forward? Given the high unmet need in FAP, do you think the magnitude of polyproduction you've seen to date would support approval and uptake in this patient population if replicated in Phase 3?

Are being 39 is not a kinase, right? And a lot of the kinases, for instance, as I mentioned so you get 12 has always been for a long time and important oncogenic Target. But the homology with CK 13 just makes it challenging to really get that selectivity that you're looking for. So for us it was born out of that inspiration of selectivity for a Target that's important for DDR modulation but went beyond much more when we looked at the broader map and trust me the map. I even showed you today just for DDR Pathways. It's it's a big beautiful map. It's much broader than that. Uh so at some point I'd love to be able to show you more and what we see there

Najat Khan: Thank you, Chris. And thank you, Brendan and Sean from Morgan Stanley, for the question. Look, for FAP, the standard of care, there is no therapeutic that has been approved for FAP. Let me just back up by saying that. Celecoxib and others are used off-label, polyburden reduction about 20% to 30% or so forth. We are definitely looking for a meaningful improvement in the polyburden reduction. And some of the initial data has been promising. However, what is going to be really important for us is to look at the data later on this year where we will have a broader patient population. The second question around support for approval and uptake, following the data that we see later this year, of course, it is going to be important to have conversations with regulators.

Thanks a lot. Okay, next question. Um, Brendan from Cohen and Sean from Morgan Stanley, ask for the upcoming fap data. Where do you see the threshold for success? In that read out? That would give you confidence in the path forward and given the high on that need the fap. Do you think that magnitude of Polo production you've seen today would support approval and uptake in this patient population? If replicated in Phase 3. Thank you Chris. Uh, and thank you. Um, Brandon and Sean, um,

Najat Khan: Once we do, happy to follow up and share more in terms of what is going to take from an approval perspective.

Chris Gibson: Thanks, Najat. Next, we have partnership questions coming from Gil at Needham and Sean at Morgan Stanley. Najat, I am going to send the first one over to you, which is, for the $7 million milestone achieved under the Sanofi collaboration, one of the latest in many milestones we have earned from that collaboration, can you go into more detail as to what exactly was achieved to merit this milestone?

Um, and the second question around support for approval and uptake, you know, following the data that we see later this year. Of course, it's going to be important to have conversations with regulators. Once we do, happy to follow up and share more in terms of what's going to take from an approval perspective.

Najat Khan: Great. The programs that we have, and again, up to 15 programs as part of this partnership, I cannot disclose exactly, of course, the target. But I can say that this was a challenging target in the immunology space. What we do see is the milestone is focused on lead series, right? Actually being able to successfully accomplish that next upcoming milestone would be development candidate. I think the point that is important to note is, look, these are all very, very challenging first-in-class, best-in-class targets. To design them is hard. It is not how you do it traditionally. The fact that we have been able to get four out of four so far, knock on wood, somewhere, I think is an important testament to how new approaches can help us and augment what we could do before. More to come over the next 12 to 15 months.

Thanks DJ. And next, we have partnership questions coming from Gil at nem and Sean at Morgan Stanley is out. I'm gonna send the first 1 over to you which is for the 7 million. Milestone achieved under the Santa Fe collaboration uh 1 of the latest and many Milestones we've earned from that collaboration. Can you go into more detail as to what exactly was achieved to Merit this Milestone. Great. So, um, the programs that we have and again up to 15 programs as part of this partnership. Um, we, I can't disclose exactly. Of course the Target. But I can say that this was a, uh, challenging, uh, Target in the Immunology space. And what we do see is the Milestone is focused on Lead Series, right? Actually being able to successfully accomplish that, uh, next upcoming Milestones would be development candidate. I think the point that's important to note is look. Um, these are all very, very challenging. First, in class, best-in-class targets and to design them is hard. It's not how you do a traditionally and the fact that we've been able to get 4 out of 4 so far, knock on wood somewhere. Um,

Chris Gibson: I think this is one of the interesting things about the tech biospace, Najat and Dennis, or I should say Gil and Sean, is that a lot of the companies in this space that are partnering with large pharma are working on some of the very hardest targets that were not amenable to more traditional approaches. So progress by us and others on these milestones is pretty exciting. Ben, I am going to turn it over to you now. What visibility, if any, do you have on the potential $100 million in milestones by 2026? Are any assumed in the cash runway calculations? Again, this comes from Gil at Needham and Sean at Morgan Stanley.

Ben Taylor: Sure. Thanks, Gil and Sean. So in a way, we have a lot of visibility in the sense that guidance is only based on the existing partnerships and existing programs in those partnerships. Now, of course, we do not have certainty that those milestones will be accomplished. What we do is we actually look at all of the programs that we know and we probability weight them. This is a probability weighted number, not the full amount. If we were to take the absolute number, it would be higher than this. We do not include any potential new business development or additional expansion on programs that are not yet identified. Those are two areas where we could grow potential milestones in the future. This is our best estimate that we felt safe in given the existing business.

I think is an important Testament to how new approaches can help us and augment what we could do before, but more to come, um, over the next 12 to 15 months. I think this is 1 of the interesting things about the tech biospace nijad and, and Dennis, or I should say Gil and Sean is that, you know, a lot of the, um, a lot of the companies in this space that are partnering with large Pharma are working on some of the very hardest targets that, uh, we're not amenable to more traditional approaches, so progress by us and others on these Milestones is pretty exciting been. I'm going to turn it over to you now. Um what visibility if any do you have on the potential 100 million in Milestones by 2026? Are any assumed in the cash Runway calculations? And again this comes from Gil at Native and Sean and Morgan students. Sure thanks skill and Sean so uh in a way we have a lot of visibility in the sense of that guidance is only based on existing Partnerships and existing programs in those Partnerships.

Chris Gibson: Thank you, Ben. Next, we are going to go to Dennis from Jeffries and Monty from LERINC, who are both asking questions about our cash runway and how we get to our guidance of Q4 2027 cash out.

Now, of course, we don't have certainty that those milestones will be accomplished. And so, what we do is we actually look at all of the programs that we know and we probability weight them. And so, this is a probability-weighted number, not the full amount. If we were to take the absolute number, it would be higher than this. And we don't include any potential new business development or additional expansion on programs that are not yet identified. So those are two areas where we could grow potential milestones in the future. But this is our best estimate that we felt safe in, given the existing business.

Ben Taylor: Sure, sure, absolutely. A couple of important notes here. One, it is really important to always focus on the cash flows when we are thinking about cash runway. If you look at our P&L statement, our operating expenses or our net income actually include a lot of non-cash expenses in it. It is really important to go to that cash flow statement and look down at what is flowing through there. Secondly, all of our guidance that we gave, the $450 million this year, the $390 million next year, is cash-based operating expense and CapEx, not including any partner inflows or new business development or finance. What we do is we then look, what are all the scenarios that could take us forward and get us to 2027? Actually, what we found is there are many different ways that we get to the fourth quarter of 2027.

Thank you, Ben. And next, we're going to go to Dennis from Jeffrey's and Monty from lying, uh, who are both asking questions about our cash Runway. And how we get to our guidance of Q4 2027, uh cash app. Sure sure, absolutely. So, um, couple important notes Here 1. Uh, it's really important to always focus on, uh, the cash flows when we were thinking about cash Runway. So if you look at our, uh, pnl statement, uh, our operating expenses are net income. Actually include a lot of 9 cash.

Ben Taylor: What we felt comfortable with is even just looking at our existing partnerships, like I was just talking about with the milestones, we felt comfortable that operating in a smart way that we are right now and trying to be as efficient as possible with our expenses, trying to really execute on our existing partnerships, and following the same sort of strategy that we have on other cash inflows, including financing, we felt very comfortable we could get to the fourth quarter of 2027. We will continue to move forward. As time goes forward, we will look to optimize as best we can around those different variables.

Expenses in it. So it's really important to go to that cash flow statement and and look down at at what is flowing through there. Secondly, all of our guidance that we gave the 450 million this year, the 390 million. Uh, next year is Cash based, uh, operating expense and capex, not including any partner inflows or new business development or financing. And so what, uh, what we do is we then look what are all the scenarios that could take us forward and get us to 2027. And, actually, what we found is, there are many different ways, uh, that we get to the fourth quarter of 2027. What we felt comfortable with is even just looking at our, uh, existing Partnerships. Uh, like I was just talking about with the, the milestones,

Chris Gibson: Thanks, Ben. Final question here from John, who asks or says, "We've seen companies like xAI making bold moves, such as investing heavily in compute with millions of chips to accelerate their vision. Can you share how Recursion is similarly tripling down? What ambitious or transformative initiatives are you planning that reflect your next level of thinking?" John, thanks. Great question, I think, to end in. First, I would just say, if you have looked at the State of AI report that Nathan Benyouk puts out, you will actually see that Recursion is, I believe, one of the only biopharma companies that is actually listed as the top 20 private or public companies in the world, non-governmental companies in terms of the scale of our compute. We are nowhere near Tesla, xAI, or any of those companies.

We felt comfortable that, um, operating in a, uh, smart way that we are right now and trying to be as efficient as possible with our expenses. Trying to really execute on our existing Partnerships and uh following the same sort of uh strategy that we have uh on other cash inflows including financing. Uh we felt very comfortable, we could get to the fourth quarter 27, um and so we will continue to uh, move forward and as uh, time goes forward, we'll look to optimize as best we can around uh, those different variables.

Chris Gibson: But we really are driving one of the most sophisticated, large-scale compute initiatives in the whole of biopharma. I think that speaks to the kind of ambition that we have for how technology is going to drive this field forward. In terms of other initiatives, I have spoken at prior events, including JPMorgan, about our belief in this field racing towards what we call a virtual cell. This is essentially a computational model of cellular biology that would allow you to predict what would happen to a cell, many different kinds of cells, if you acted on them in any way. You add a protein. You change the effect of a gene or the expression level of a gene. You add a small molecule or multiple small molecules.

Li tripling down, what, ambitious or transformative initiatives? Are you planning that reflect your next level of thinking? John thanks, great question, I think to end it. First, I'll just say, if you've looked at the state of AI reports that Nathan Beno puts out, um, you'll actually see the recursion is, I believe 1 of the only biofarma companies, uh that's actually listed uh as the top 20 private or public companies in the world non-governmental companies in terms of the scale of our compute. Now we're nowhere near Tesla xai or any of those companies but we really are driving 1 of the most sophisticated, uh, large scale compute initiatives in the whole of of biofarma. And I think that speaks to the kind of ambition that we have for how technology is going to drive this, this field forward. But in terms of other initiatives, you know, I've spoken at prior, uh, events, including JP Morgan about our belief, in this field racing towards what we call a virtual cell.

Chris Gibson: We believe that building a reliable and robust virtual cell is going to require not just having really good protein folding data, not just having really good atomistic and physics modeling, and not just having good patient data or pathway data. It is going to require having all of those different data layers and being on the frontier of all of those. I think Recursion today, through our partnerships with companies like Tempus and Helix, really driving the patient layer through our own work at Recursion, building the pathway data with genome-scale knockout maps across more than a dozen different human cell types. As you heard today, with our BOLD modeling and some of our QMMD modeling, we are able to really work at the protein folding and the atomistic modeling layer.

And this is essentially a computational model of cellular biology that would allow you to predict what would happen to a cell many different kinds of cells. If you acted on them in any way you add a protein, you add you change the effect of a of a gene or or the expression level of of a gene. You add a small molecule or multiple small molecules

Chris Gibson: I think being able to operate across all those layers is going to be a real advantage as we race towards the virtual cell and deploy early versions of that internally. What's more, we have a team at Recursion Pharmaceuticals called the Frontier Research Group. The Frontier Research Group is a dedicated group of folks who are working at the very frontier in high-risk but high-reward areas. While this virtual cell is a part of the work that that group is doing, some of the work you heard about today, including the causal AI modeling using Tempus data, actually started in this Frontier Research Group and now has gone into production across the Recursion OS. These are the bets we make in high-risk, high-reward areas that then get deployed, in some cases, just six or nine months later.

Uh, and we believe that building a reliable and robust virtual cell is going to require, not just having really good protein folding data. Not just having really good atomistic and physics modeling and not just having good patient data or pathway data. It's going to require having all of those different data layers and being on the frontier of all of those. And I think recursion today through our Partnerships with companies like Tempest and Helix really driving the patient layer, uh, through our own work at recursion, uh, building the pathway data with both genome. Scale, knockout Maps across more than a dozen different human cell types. And then, as you heard heard today, with our bolt modeling, and some of our qmd modeling, we're able to really work at the protein folding of the atomistic modeling layer. And I think being able to operate across all those layers is going to be a real Advantage as we race towards the virtual cell and deploy early versions of that internally. What's more? We have a team at recursion called the frontier research group and the frontier research group,

Chris Gibson: I cannot tell you about all the things we are doing in that group. I will say one of the areas we think is super interesting, we are watching very closely, is the use of agents to automate the way we discover things and to automate the way we might discover medicines. That is certainly an area that we are working to stay really close to as well. Lots of exciting work happening at Recursion Pharmaceuticals and across the whole field. It feels like a very, very exciting area to watch for the next half decade or so. I want to thank everybody for joining us today. We really appreciate having you. Really appreciate the questions. We look forward to seeing you at the next earnings call or perhaps sometime before then. Thanks, everybody.

Is a dedicated group of folks who are working at the very Frontier in high-risk but high-reward areas. And while this virtual cell is a part of the work that that group is doing some of the work you heard about today, including the causal, AI modeling using Tempest data actually started in this Frontier research group and now has gone into production across the recursion OS. And these are the bets we make in high-risk, high-reward, areas that then get deployed in some cases, just 6 or 9 months later. I can't tell you about all the things we're doing in that group but I will,

Say 1 of the areas we think is super interesting. We're watching very closely is the use of agents to automate the way we discover things. And to automate we the way we might discover medicines and that's certainly an area that we're working uh, to to stay really close to, as well. So, lots of exciting work happening at recursion and across the whole field. It feels like a very, very exciting area, uh, to watch for the next half decade or so. So I want to thank everybody for joining us today. Uh, we really appreciate having you really appreciate the questions and we look forward to seeing you at the next earnings call or perhaps sometime before. Then, thanks everybody.