Hello, everyone. Welcome to the third day of the H.C. Wainwright Conference here in New York. My name is Mitchell Kapoor. I am a Senior Biotech Analyst here at the firm. Today, I have the pleasure of welcoming Generate:Biomedicines for a fireside chat. From the company, I have Jason Silvers as the CFO. Jason, thank you so much for joining us.
Thanks, Mitchell. Great to be here.
I would like to start off the discussion for those who may not be familiar with the company or up to speed in the last couple of months. Maybe, Jason, you could start off with an overview of Generate and then talk about the lead programs, but also the broader platform context and the technology and the future of the company, how that could shape and evolve over time.
Sure. Generate:Biomedicines was founded eight years ago, before generative technology, generative capabilities were really even talked about, and well before ChatGPT and AlphaFold and some of those other technologies. Really what we were founded to do is use generative machine learning technology to ultimately discover innovative, differentiated, novel protein therapeutics for patients. Really trying to discover things that traditional drug discovery is unable to do, just given the ability of technologies to explore a much broader landscape of potential opportunities for proteins. What we did very early on at the company is started to understand what the technology could do, and one of the big concerns, or at least ideas that could have been concerning is are these novel therapeutics that are generated by AI or machine learning, are they immunogenic?
How would they actually be handled in the body relative because they're not formulated using the traditional technology or traditional techniques. We started very early with looking at low biology risk products, which is why TSLP, our lead asset, was even just talked about and we initiated on. Low biology risk, known pathways, safe molecule, but had some deficiencies in it that could be improved upon that could improve a patient's experience with a medicine that was very highly effective and safe. Tezepelumab was the first, or anti-TSLP molecule, was the first lens that we took as a company. What we did with that molecule is effectively used half-life extension technology, which a number of other companies are certainly using, but used our technology to change the molecule to get a much better binding affinity to the cytokine.
While we hit the same epitope as tezepelumab, we have tighter binding affinity by 20-fold, frankly, 100 femtomolar level of binding affinity. We think the critical nature of that molecule is not just the long half-life, which is a 98-day half-life, but also you need that tight binding affinity on the cytokine to ultimately get six-month dosing and not have waning efficacy over time. That's why we started with TSLP. Ultimately, we've done multiple partnerships with Amgen and Novartis as examples, who we would view as some of the greatest protein engineering companies out there, and they obviously have been extraordinarily successful at using traditional techniques and coming up with molecules.
What they did in our partnerships, Amgen we partnered with five years ago, Novartis we partnered with two years ago, is they're bespoke around individual targets where ultimately they gave us some of their most challenging, or most difficult challenges with protein engineering to come up with molecules or test biology. These are target-specific partnerships, but what it taught us, in addition to the great partners that we have, it taught us where the struggles that traditional techniques have in protein drug design. I'll get into some of that because it really gets to the platform and the next wave of products that we have. Ultimately, we've learned from that, and some of the new wave of things that we're working on are those innovative technologies.
One of the core things that differentiates us, and I'll come back to the platform, is we're not just a machine learning AI company that uses models and ultimately believes we're going to come up with the next wave of therapeutics based on the quality of our model. We think models are ultimately going to commoditize, are already commoditizing. Frankly, just having a better model, and even though we think we were first and probably have one of the best models out there, that's not enough. Biology is just such an unknown science, an unknown space. If you think about large language models and using the internet, if you ask ChatGPT to write you a paper, it can do an incredibly great job at writing you as long a paper as you want on almost any topic. Biology is just not known.
It doesn't have the breadth of knowledge. It's probably only 5% or 10%, maybe 15% known. It's not like you can use LLMs to come up with billions of hypotheses and know which one is actually going to be the right hypothesis. You need something to be able to test, an experimental wet lab capability to be able to test at scale these molecules. One of the core differentiators for Generate is while we've invested heavily on the models, we've invested as much, if not more, on the experimental side. While we can get billions of hypotheses, we actually, in the order of days or weeks, can test every single one of those hypotheses in bespoke assays to determine which are the ones that are going to be most promising for protein therapeutics. Happy to get more into that.
The last point I'll just mention, because there's a lot more, we've translated five molecules from our model into the clinic. We've shown they're not immunogenic. There's no more ADA formation, actually very low ADA formation. They're highly efficacious molecules. We have our lead assets are in phase III, which is the anti-TSLP. We have a couple oncology assets that are in phase I, which happy to talk about as well. That next generation of molecules and where we're focused now are on the things that China can't necessarily brute force their way into today, or traditional techniques really struggle to do. These are things like pH-dependent binding. Can you get 1,000-fold difference in a protein binder at a pH of 7.4 versus a pH of 6? Internalization.
We're working a lot with ADCs or other molecules where you have great targets, but very poor internalizers to be able to kill cancer cells, as an example. We've developed techniques that can get logarithmic fold improvement on internalization of these antibodies or other protein crossing barriers, blood-brain barriers, cellular barriers, gut barrier as another example. Using these types of techniques, we have a number of programs that are on the come, other than just the ones in clinical development, where we think we're more highly differentiated.
Excellent. That's a great overview, and I think it leads into a couple of questions here. One, can you talk about TSLP as a target and what it does in asthma? What Generate's design allows for two injections a year, what in that design is allowing for that? What can we take from what we expect will be positive data? If that is the case, how do we know that the platform is working, and that this can be extrapolated into the next selections and maybe even the rest of the pipeline, even though oncology would say, "Hey, even though this is I and I, we know that Generate's techniques to get there should be accretive to the rest of the pipeline versus just this readout.
Sure. TSLP is a known mechanism in asthma. TEZSPIRE has been on the market for five years. It is a biologic. Biologics in respiratory and asthma particularly are very low penetrated, so it is about 20% penetration in asthma. The great thing about the TSLP molecule, as has been shown through TEZSPIRE, is it is an all-comers of eos population in the asthma population. What you saw with the TEZSPIRE data is a 70% reduction in exacerbations in the high eos population above 300 eos, and about a 40% reduction in the low eos population below 300. Overall, the population, you saw a reduction of 56%. It is a monthly dosed medication in asthma, and so the benefit for our drug over that is it is a six monthly dosed drug. We hit the same epitope, as I mentioned before.
We have chosen our dose and moved from phase I to phase III, which I will talk about, and why we think we are very confident with that. In 300 mg, we are seeing 99.9% saturation of the target, which is the cytokine in this case, which is about the same as the approved dose in tezepelumab, the 210 mg also has 99% saturation. So there is no reason to believe there will be better efficacy in the clinical trial. We did show preclinically a 5x better potency, but again, if you are 99% saturating a target, that you are hitting the same target, the likelihood of seeing better efficacy is probably small. In the real world, however, what has been shown, and some data were presented at ERS last year, is that only about 20%, or it is suggested that only about 20% of patients on biologics in respiratory are adherent to their medicines.
If that is true, it is leading to a very significant cost to the system, but also a cost to these patients. Having an every six monthly dosed drug has a benefit, especially for asthmatics and frankly more so for COPD, which is the other indication that we are contemplating, of being commensurate with when patients are going to their physicians. If patients are more adherent to a six monthly dose, more convenient drug, you might ultimately see better efficacy over time, and a much better cost to the system. As far as the jump from phase I to phase III, which is a question we get a lot, this is not an unproven path. [inaudible] moved from phase I to phase III with a single dose and was approved by the FDA and EMA without any phase II or dose-finding data.
Glaxo, with their Aiolos molecule, has just announced they are going into six phase III trials with the TSLP molecule they bought from Aiolos. One of the indications is COPD, which we have not seen any data in COPD from that molecule, and moving directly to phase III. So it is a proven pathway, let us say. Again, I have mentioned multiple times we get the same epitope. Number three is we are seeing biomarker suppression out to, frankly, a year in the asthma data. We just presented data at ERS last week. So we are seeing for eos, FeNO, IL-5, and IL-13, deep suppression sustained out to a year in patients on a single injection. There is no difference between the 300 mg or statistically significant difference between 300 mg, 600 mg and above. Even the data we showed on our COPD trial also showed complete overlap between 300 and 600 mg.
Those data, plus the fact that if anyone studied the tezepelumab data in phase II, where they studied an eightfold difference in dose, 70 mg every four weeks, 210 mg every four weeks, and 280 mg every two weeks, that eightfold difference showed zero statistical significant difference in exacerbation reduction, and they chose 210 mg. You put all the totality of that together, the probability that our drug will work at 300 mg, we believe is extraordinarily high. That is what we have done. We have moved directly to phase III. As far as the competitive landscape, which you touched on a little bit, we are the first long-acting molecule in phase III. We started the trial back in December, and we believe we will have full enrollment on the trial. It is about a two-year enrollment, so by the end of next year.
It is a 52-week follow-up, and data we think will be by the late 2028, early 2029. Then, as I mentioned, we did study it in COPD, and we presented those data recently. Very similar. It is a 98-day half-life. We are seeing deep suppression out to six months in our COPD patient population, and overlap between the 300 and 600 mg. So right now we are contemplating what we do with that and whether we move directly into phase III as well. The other question you answered, sorry.
No, this is great.
I am trying to answer all your questions without boring everybody here, because hearing me talk is a lot. How do you validate the platform? Number one is it is a 98-day half-life. On a YTE half-life extension, typically you would expect something in the 70- 90 days. So this is a longer half-life. Does that potentially have some impact from the fact that we are binding tighter to the cytokine? Potentially. We have seen some other examples of long half-life extended molecules that don't have binding affinity improvement, have waning efficacy out at the tail end of that. Our binding affinity, which again is the 106 femtomolar binding affinity level, has such a tight binding to the cytokine that we believe it is not being released out at that six-month period. Therefore, we think the efficacy will last for that six-month period.
That was designed by the platform, right? I mean, to actually take a picomolar level molecule and make it a femtomolar level binding affinity is not something that others have shown able to do using traditional techniques. Our second set of molecules which are in the clinic on the oncology front also we think will validate in part our technology. The second asset, which is in phase I, is an oncology asset. It is an MMAE neutralizing antibody. For those familiar with an antibody-drug conjugate, all the Seattle Genetics antibody-drug conjugates, PADCEV is one example, have MMAE-based payloads.
One of the big issues with those is when the payload, the MMAE, gets cleaved and freely circulates, it causes significant toxicities, peripheral neuropathy, skin toxicities, neutropenia, which in the clinical trial for PADCEV showed 2/3 of patients ended up getting peripheral neuropathy, 20% of those patients end up off drug or reducing dose or having dose holidays. It is a significant liability to the drug, even though it is an amazing drug for urothelial cancer patients, given the response rates you are seeing. We designed through the platform an antibody that binds only to the region on the free MMAE, which is a small molecule, the MMAE, that is only exposed when it is off the linker. That takes technology to do that.
It is not simply using techniques where you immunize a mouse, a llama, a human to try to come up with a range of antibodies. You are actually designing this specific for a region so that you don't impact the intact ADC, so it can go to the tumor and kill the tumor cells, but you can limit, bind, and clear the free payload that is causing the toxicities.
That is in phase I right now. We will have proof of concept data at the end of the year. Happy to talk about. What the trial design is. I want to give you a chance to ask more questions.
I'm just piling the questions up because this is great.
Those are the types of things that will continue to show the technology, and again, what I mentioned upfront, the new wave of things. We're looking at extracellular target protein degradation. Using our platform, we've shown that we can do great things with selectivity and specificity. We've now shown our ability to do pH-dependent binding differences up to, frankly, a thousandfold difference in binding at a pH of 7.4 versus 6. We've shown internalization. For extracellular target protein degradation, you need to bind a target extracellularly, bring it to a cell, get it endocytosed into an endosome, where the pH is lower, and then recycle your drug so that you can go and do the same for additional targets.
Those are the types of things that you're going to start to see emerge because we've now directed our technology to the more innovative side of things and really where traditional techniques, and again, Chinese companies have not shown their ability yet to go after these more novel areas.
Very interesting. Okay. Maybe I start with, the MMAE, whenever it is cleaved and it is free, I am curious, how do you make sure your drug doesn't get into the tumor, and then whenever the payload is cleaved, the MMAE payload is cleaved, it is kind of a counter effect on the ADC that is supposed to be treating the tumor? It is very interesting.
Yeah. No, the bystander effect we think is really important. You can't clear 100% of the free MMAE, otherwise, we do think you will impact tumor killing. In our preclinical studies where we studied in mice and non-human primates, we actually showed if you get up to 80% clearance of free MMAE, you don't impact the tumor killing, but you do get a significant reduction in skin toxicities and neutropenia in mice and non-human primates. Again, in humans, we are going to be studying peripheral neuropathy. But when you get to 85% reduction, you actually do start to impact the tumor killing. The design of our phase I trial, which we are in right now, the first portion of it is a dose escalation portion, where we are looking for what is the dose of our antibody that will reduce free MMAE by 50%.
The FDA gave us fast track designation for this product. We're in first-line treatment for urothelial cancer patients. They've told us that we can go up to 80% reduction, but we want to be careful getting too close to that impact on tumor killing. We know at a 50% reduction of free MMAE, you're getting a substantial benefit for patients in terms of reducing the toxicities.
We've already dosed the first cohort of patients in that trial. We believe by early 2027, we'll have the dose of our drug that reduces the free MMAE by 50%. Then we'll do an expansion cohort in the phase I in 2027, where we'll look at patients who have already developed peripheral neuropathy, urothelial cancer patients. They're on PADCEV and KEYTRUDA, and now can we give in each cycle our drug with PADCEV and KEYTRUDA for those patients and stop, slow, or reverse the progression from grade 1 to grade 2 neuropathy?
If you can do that, you've shown your proof of concept, and then our discussions with the FDA to date have been we potentially could do a registrational trial with safety endpoint. Obviously, we'd have to have that discussion in more detail once we have the phase I data. Ultimately, we would think we'll need to do either non-inferiority study or something that shows you're not impacting the tumor killing. In reality, there are three huge benefits for this. Number one, you're obviously dealing with patient side effects and treating significant toxicities. It's a huge benefit for patients. Number two, at ASCO, what was recently shown is the longer patients are on PADCEV, the more complete responses you get.
If you can improve, increase either the dose or the longevity in which patients are taking PADCEV, which our drug we believe can do, you might actually have a better impact on tumor killing and complete responses. Number three, one of the challenges in the community where you're only seeing about 50% of urothelial cancer patients get PADCEV is physicians, many of which have challenges dealing with the side effects. If this drug is successful, then you could see a huge uptake in the community where the drug is not getting to patients at the level which it should.
Very interesting. Okay, the design of the phase I, is it patients who are exhibiting peripheral neuropathy, and you're now trying to show a reversal in that? Or is it all patients and they're prone to peripheral neuropathy, and you're just trying to see if you can prevent it?
Well, the first part, again, is dose finding. It's all patients who have urothelial cancer, first- line therapy, getting PADCEV and KEYTRUDA. They'll get their first cycle without our drug, so you can actually get a baseline MMAE, free MMAE level.
Then at the second cycle and beyond, we'll give our drug, so you can measure the impact of the reduction of free MMAE. So that's number one. The second portion of that will be urothelial cancer patients who already have developed peripheral neuropathy. If you can imagine, we were a little bit surprised at how quickly the first cohort enrolled, because imagine being a urothelial cancer patient, and you don't know if the drug you're getting with a great drug of PADCEV and KEYTRUDA is ultimately going to impact your tumor.
Yet enrolled incredibly fast. Now you think about that expansion cohort. These are patients who already have grade 1 peripheral neuropathy.
And have the promise of a drug that can be dosed to prevent the progression. We will really be looking at if 50%+ of patients are progressing from grade 1 to grade 2 peripheral neuropathy in the literature, if our drug can reduce that by 25%, 20%, 50%, whatever the right number is, that would have a huge impact on these patients, and that is what we will be looking for in this expansion cohort.
Yeah, absolutely. Interesting. How do you see that being used? Let us say the ideal situation. Is it where patients are taking this in anticipation of developing it, or would you see it more as a situation where they develop the peripheral neuropathy and then they are-
I think you would want. So 2/3 of the patients in the clinical trial of PADCEV develop peripheral neuropathy, and once it becomes irreversible or grade 2, it is irreversible. We would envision that all patients would get this drug.
Very interesting. Great. Okay.
Starting at cycle 1. Peripheral neuropathy is an accumulated side effect, so typically around cycle 3 or 4, and ultimately it accumulates over time and gets worse for patients. If you start it at the beginning, as long as you're not impacting the tumor, we believe that you can maybe prevent even the progression to grade 1 neuropathy and certainly to irreversible neuropathy.
Great. Okay. One other thing you mentioned earlier that was quite interesting is the target coverage you're seeing with your TSLP is high enough that you don't expect the efficacy to be better, but the durability is obviously the value driver here. When you look at expansion of your platform and potentially going after other targets, is there a situation where a drug might not have as high target coverage, like 99%, like TEZSPIRE does, that you could potentially improve upon and show not only a durability benefit, but maybe an efficacy benefit as well?
Yeah, absolutely. One great example, we did an IL-13 study, a phase I study, with an incredible molecule. Probably I would say one of the best, if not the best profiles out there. What we showed, even relative to the Apogee molecule, is we had twice the bioavailability with our molecule. So over 100-day half-life. But bioavailability that showed at an equivalent dose, we had twice the bioavailability. So their 600 mg dose is our 300 mg dose in terms of PK profile. We actually believe that our technology can show better efficacy on various drugs out there that have liabilities. Again, where we focus the technology, and right now the biggest issue is our platform has capability to do a lot more than we could possibly afford, right? It's very productive.
Where we focus the platform now are on some of the more challenging, maybe more. They don't have to be biologically high risk. We could still choose biologically low risk targets, but ones that traditional techniques have struggled to actually either hit or address.
Wonderful. Okay. Finally, I like to close discussions by just giving a preview. We talked about a lot of different areas of Generate, but just give us a preview of the next 12- 18 months, the key catalysts to watch. Specifically for your lead program, what should we expect in terms of what we could see at the data, and set up the inflection point for us?
Yeah. I guess the first thing is we're well underway enrolling the TSLP molecule in asthma. We have regulatory approval in 39 of 42 countries. We're across six continents, and so that's well underway. We'll have that enrolled, we believe, over the next 12- 15 months, by the end of 2027. Number two is the other indications. COPD, we just revealed data in the last couple of weeks on that. We think it's very strong. There may be a path to move that also into registrational trials. That market opportunity, that's probably 1% penetrated in biologics, and has a huge market opportunity. We didn't have time to talk about tozo and what the implications for TSLP, but we think even based on the tozo data, there's a huge opportunity for the TSLP asset, and particularly one that's six months long.
That's a decision we'll make in the near- term. The oncology assets will play out over the next course of the year, and I think both in our CAR T, which we didn't talk about, as well as the MMAE neutralizer, we'll have proof of concept data over the course of the next 12 months or so, by the end of 2027 in both of those. I think we have done some great partnerships to date. Now that we're getting to the end of those partnerships, we have a lot more capacity to do more partnerships. You will see us do additional partnerships similar to ones we've done in the past, and potentially licensing other interesting innovative technologies as they emerge.
That we think you'll see, and then I think as I mentioned, now that we've directed our platform and technology to some of these novel differentiated areas, I think over the course of the next 12, 18 months, you will see some of these new proprietary products emerge. Many of which we will keep ourselves, and some of which we might either spin out as new companies or license out.
Excellent. Thank you so much, Jason, and thank you to the Generate team. I'd like to thank everybody in the audience as well for joining us for this fireside chat.
Thank you.