Daniel Chen, Founder and CEO at Synthetic Design Lab

Jesus Moreno (00:01.628)
Welcome back to Global Trials Accelerators, the podcast where we dismantle the barriers to clinical innovation and explore the strategies driving the next generation of life-saving therapies. My guest today has arguably lived both halves of that journey. Dr. Daniel Chan is a physician scientist who spent years at the bedside treating melanoma patients, then spent more than a decade at Hentec.

Leading the clinical development of Ats excuse me, Atesolisumba that's hard to pronounce. Ate Solisuma.

Daniel S Chen (00:41.634)
You can also call it T centric. T centric is its brand name. I don't know if you

Jesus Moreno (00:45.128)
Yeah, I think

Yes, I'm gonna go with that. Sorry. T-centric. Okay. Daniel Chen is a physician, scientist who spent years at the bedside. Sorry. Daniel Chen is a physician scientist who spent years at the bedside treating melanoma patients, then spent more than a decade at Gentech leading the clinical development of T centric, the first approved PDL1 inhibitor. From research all the way through

the approval around the world. He has he has co-authored the Cancer Immunology Cycle, one of the most cited conceptual frameworks in modern immunology oncology. And today he's the founder and CEO of Synthetic Design Lab, a company built excuse me. And today he's the founder and CEO of Synthetic Design Lab, a company

building what is called smart cancer drugs on an entirely new antibody drug conjecture architecture. Doctor Chen, it's a real pleasure to have you with us today. Welcome to the show.

Daniel S Chen (02:01.752)
Thanks so much for having me.

Jesus Moreno (02:05.864)
Doctor, I would like to start talking about your background and the arc of your career because it's unusually broad. Going from bedside oncology, big pharma development and now venture into creating a startup with with such a novel technology. The thread that really connects all those

moments in your career seems to be clinical trials. you started running the melanoma clinical at Stanford. How did treating patients directly shape the way you design a trial today?

Daniel S Chen (02:52.334)
So, you know, it's interesting. I've been I'm old enough now that I have a there are a lot of cycles in my la life that I get I have completed. I feel like some of them are are pretty early in my training. So I did my undergraduate work at MIT. I wasn't an engineer. All my friends were engineers. but that feels very relevant today. I did my physician scientist training at USC.

Obviously, I've lived a life that walks between the world of clinical medicine and science. And then finally, I did my internal medicine training, my medical oncology training, my postdoc in immunology at Stanford, and I stayed at Stanford where I treat treated patients with metastatic melanoma. When you're a scientist, but you're also a physician.

you certainly get to see a different side of the world we work in in terms of medicine. And as a particularly as a medical oncologist, you unfortunately see a lot of tragedies. You see young people, old people, husbands, wives, fathers, mothers, children that lose their battle with cancer. And it's really, really hard.

Those those stories, those people's stories have lived with me my entire career. And it's part of what drives you to try to be able to do something better because you know the kind of personal suffering that happens in patients trying to fight a disease like cancer.

Jesus Moreno (04:41.498)
Of course this is a very complex subject both technically and from the humanitarian perspective, the how it affects lives and and how difficult it it is to walk through this with a patient. And I'm curious to know if living both those worlds, the bedside and the bench the puzzle in the in at the bench.

it taught you anything about how to design or take into account the patient's experience when when approaching this type of clinical trial.

Daniel S Chen (05:26.452)
I mean, that's absolutely critical, right? it can be very easy when you're running large clinical trials to think about what you're doing all as data points. Data points that either tell you if a drug works or doesn't work or works in one patient or another. but when you s have spent time taking care of these patients, they're not data points. They're real people that when they have a side effect, they can really suffer with that side effect.

They have emotional ups and downs. And even with something like the immune system, the immune system is particularly interesting because the immune system is actually actually very susceptible to changes in how you are feeling. Whether you are ready to fight the disease or you're giving up. it can also be very susceptible to other changes in your life.

Whether you're getting you going outside and getting sunlight, how you eat, it is a very particularly complicated system. And when we are thinking about our clinical trials, we in particular in that cancer immunotherapy space, you really want to think broadly about how your patients are getting onto that trial, how they're doing with the treatment.

And who they are as people, because it really does make a difference, particularly in cancer immunotherapy.

Jesus Moreno (07:01.208)
Absolutely. And I I would imagine that was of great relevance when you were working at a Gentech carrying the tricentric from research through IND and then everywhere in in clinical phases to approval around the world and and having to spearhead that that effort of you know moving through those

very different stages and yet having to impact the lives of so many patients that are putting their trust the trust of their well-being in you i'm i'm curious to learn and and for those in the audience that might be you know familiar with this type of situations what did the program teach you about

where trials actually slow down and where the real bottlenecks are, both from the patient perspective as well from the development of the of the drug.

Daniel S Chen (08:11.302)
Yeah, so when you think about developing a new drug, I think you do need to be really thoughtful. and in each stage of clinical development, it's a little bit different. So you think about those first in human studies, those are generally going into patients who are at their last line of treatment. They've run out of any standard of care. And when we're doing dose escalation, they may not be getting.

The active doses of your drug or very active doses of your drug because the clinical trial is designed to test that. You really need to take that into account in those early trials, the way you design it. So there are things you can do. Can you build into your trial ways so that patients who are getting those really low doses can go on to get higher doses as you clear other cohorts? are there ways to to

Rethink those early trials so that you get the data you need, but you still protect the patients so that they're getting active treatment. Those are really important to think about. The other thing that is interesting about the early space, the very first inhuman studies of novel agents, is I feel like every patient matters. You need to know every story.

Because you don't have the big numbers to run statistics on. And that's the setting where you're really looking for hints of either your drug is working or not working, or side effects that you might need to be able to address before they become more problematic. And so for me, when I was running those early studies for T centric in our initial phase one dose escalation, I wanted to hear.

everything about that patient's journey. We would often joke you would want to know what they had for breakfast. You would want to know what time they had their infusion. You want to know how they're feeling and of course you'd ultimately want to know if they're feeling better and if they're having radiologic responses. So there there is a particular, I think, art but in that early phase of clinical study where

Daniel S Chen (10:39.084)
You want to know every single thing about that patient and how they're doing on your novel treatment.

Jesus Moreno (10:46.594)
Yes, in particular when the the rule book per se doesn't apply since it's such a novel novel therapy. and what what would you say were the key strategic decisions you made along that journey from research all the way to worldwide approval that made this

made the development and the clinical trials around this therapy successful. And and how did that differ from the more traditional way of running a clinical trial where where the the therapy is is better understood or or more widely understood.

Daniel S Chen (11:39.276)
Yeah, so I would say there are three with there were three major things that were really important in terms of decisions along the way for those that early clinical development. And I would suggest that they are indication, dose and schedule, and biomarkers and patient identification. So let's talk about each of those. So number one, indication. PD1, PDL1 inhibitors.

Unlike many drugs, work across a lot of patients with cancer. Not every type of cancer, but many types of cancer. But we didn't know that at the start. We had a sense that these drugs would work well in traditionally immune-sensitive diseases. So diseases like melanoma and renal cell carcinoma. But you had to open up

At some point, and start to explore additional diseases to better understand your drug. And we did that very early. And certainly we saw very early hints of activity already, even at low doses in diseases like lung cancer, which was not considered a traditional immunologic responsive drug. But we also made some smart bets. So one of the big things that

That I had seen was at the time a presentation on the spectrum of mutational burden in different cancer patients. And when I looked at that chart, that chart looked a lot to me like the chart of diseases with that we think of as potentially being responsive to immunotherapy. It also made

Sense F to me as a scientist, because when you have a high tumor mutation burden, you have more chances for that cancer cell to look foreign to your immune system. And for us, that led to an early exploration of a disease that was not considered immune-sensitive, that was bladder cancer. And bladder cancer w was a terrible disease with very few treatments at the time. immunotherapy works very well in that particular disease.

Daniel S Chen (14:02.494)
And it allowed us to get actually our first accelerated approval for T-centric. So that was a really important choice. the second, dose and schedule. Dose and schedule is one of the most important decisions you make coming out of your phase one study. For a biologic, T-centric is a IgG antibody-based therapeutic.

That's a therapy that g generally has a very wide window. You can dose high, you can dose more modest or medium dose and schedule, or you can or you can go much lower. And it's hard to know in those early studies what the right dose and schedule is. We decided to go on the higher end, and there were a number of reasons for that. A, there it was well tolerated across a wide range of doses.

it also maybe you one could imagine the possibility of of higher responses, but it was not you could definitely could not say that statistically. But to me, one of the biggest reasons is because when you go to a higher dose and schedule, it allows you to push out the time window that a patient is exposed to. That means if

They take a treatment holiday, or if they come off study, they actually still have ongoing immunologic active activation, really. It's for for T-centric, it's taking away the breaks. So it allows the immune system to fight the cancer. And and for cancer immunotherapy, that's important because the the actual responses that you get

While they can be seen with responses and durable responses, they have a much wider range of presentations. And so going to those high doses, I think, really protected patients for in terms of getting their best response. Now, the final one was one that is really important to the field and was particularly tricky for the entire field over a very long period of development. And that is.

Daniel S Chen (16:26.392)
Patient identification and biomarkers. So we knew early on that PDL1 was a good biomarker for this field, but it was not a perfect biomarker. it also was a biomarker that seemed to be different in different diseases. So the PDL one biomarker in lung cancer was very different than the way the PDL one biomarker behaved in

Breast cancer, or many other diseases. And so one of the things that has been incredibly important for the field was really to figure out was this the right biomarker for what diseases, what tests to use? And that was a journey that was a long journey across many different efforts to try to hone in on.

On what the right approach was. And ultimately, at the end of the day, it was based on data, it was based on science, but there was also a philosophical component because while the biomarker could select for patients that had better responses to the drug, it the negative patients, patients that didn't express PDL1, still had a few patients that did very well on treatment.

And so you can imagine, depending on how you view that data, you might say, no, it's absolutely important to treat those patients because where else are they going to get the kind of benefit of immunotherapy? Or you say, no, we don't treat those patients. The toxicities, the opportunity cost is just too high to be dosing someone when they don't have a strong likelihood of benefit or a weaker benefit.

And so you can see how why that kind of situation led to a prolonged struggle for the field to figure out where the biomarker work was most important in terms of selecting patients for treatment.

Jesus Moreno (18:40.23)
That's that's very insightful doctor. And and I wonder if that realization had something to do with that co-authoring of the cancer immunity cycle and the cancer immune set point. because those are two very different intellectual activities. So it's it's an intellectual shift going from running a clinical trial to to authoring

you know, and a framework for understanding how cancer and immune and the immune and the immune system react to each other. So was was that process of let's say philosophical research in in trying to understand and create a scaffold that described how all this

this components fit together from a biophysical standpoint, help you make better d decisions in terms of how to plan and execute the trial.

Daniel S Chen (19:50.69)
Yeah, so I think you're referring to the cancer immunity cycle and the cancer immune set point. Those are what I hope are landmark papers that Ira Melman and myself wrote during that 10-year journey into cancer immunotherapy. I'll say that for me, look, I was I was trained as a physician scientist. I did my postdoc in Mark Davis's lab. He's a world-famous immunologist. And

Not only did I treat patients at Stanford f with metastatic melanoma, I was a translational oncologist, meaning I was simultaneously studying how patients' immune responses interacted with their disease, their melanoma. And at the time when I was at Stanford, we didn't have good therapies. So my work really focused around why didn't the immune res system

respond more actively to cancer. So I would say that the concepts that are there, some of the fundamental concepts of the cancer immunity cycle and the cancer immune set point, at least for me, started very early. They had their inception all the way back to when I was at Stanford treating patients and studying the human immune system. And but there are also many concepts in those papers

That were reflective of what we were seeing. And I think for both Ira and I, we have our scientific hypotheses based on how we believe the immune system works in both animals, but more importantly, in humans. And when we look at clinical data, we're trying to understand which of those concepts the data supports.

And which of those concepts the data refutes. And so when you do that, you're looking at the data in a very specific way, right? It's not random. It is fully the intersection between a deep appreciation for science and human biology and the data you're seeing. And so for us, I would say that's the where the inspiration and and

Daniel S Chen (22:17.464)
Fundamental concepts for the cancer immunity cycle and the cancer immune set point came from. And does it affect how we think about the field, how we treat patients, how we run clinical trials? Absolutely. They still do today. I think they are more relevant than ever. and the reason for that is they describe fundamental biology, in this case, cancer immunity, and

How we believe it works in humans. And they don't just describe how it works or why it works when it does, they also describe why it fails when it fails. And what we've seen in the last, you know, now, maybe over the last seven or so years is that it's been very difficult to

Find other approaches in endogenous cancer immunity that work as effectively as PD1 and PDL1 inhibitors. And if you go back to the cancer immunity cycle and you go back to the cancer immune set point, I think we have the scientific many of the scientific concepts that are present that describe why that is. And I think a large piece of it is the

PD1 PDL1 plays an outsized role in the regulation of immunity. So when you look at other checkpoints, they're biologically active, but it's like a drop in the ocean next to PD1 PDL1 inhibition. And when you have small effects added to big effects, those can be very hard to appreciate in clinical trials. Doesn't mean those targets aren't active.

It means that are not active enough to get the kind of clinical benefits that we want as physicians or andor the clinical benefit that we can see as statisticians. And so that has been a problem for the field. And we need better approaches. Well, the cancer immunity cycle and the cancer immune set point also define some of the things that we think may be problems that we haven't been able to find or develop.

Daniel S Chen (24:41.826)
Better therapies for yet. So things like immune exclusion is difficult to break. It's likely driven by things like TGF beta biology, but TGF beta, unlike PDL1 and PD1, is not an on-off switch. And when you don't have an on-off switch, the modulation of that biology can be very difficult. I think it's one of the reasons why some immunotherapy.

That has not worked in the later line setting or the metastatic setting does seem to work in the adjuvant setting, in the earlier setting. And I would argue one of the reasons for that are that some of these more difficult, more problematic immune suppressive mechanisms like immune exclusion and TGF beta really come on later in the disease process, not and may not be as present in those patients with early stage disease.

Similar for immune deserts. Immune deserts, these are tumors that exhibit essentially no infiltration of immune cells into that into the tumor microenvironment. So there's nothing to to activate there because they're not even there. And they're not there for probably some for some pretty big reasons. Those tumors tend to be v have very hostile tumor microenvironments. There's a lot of

lipid and metabolic derangements in that microenvironment. And so as we think about drug research and drug development, I think we can still use that type of scientific framework to think about what it is we need to do next. And from my perspective, it's one of the reasons I have focused so much of my career over the last 10 years in this space of

engineered therapeutics because I think engineering has the ability to open doors into how we modulate complex biology in a more powerful way and we just may need that to to break through the next barrier in terms of enhancing cancer immunity and other approaches to cancer therapy.

Jesus Moreno (27:01.532)
Finding the right drug for the right patient, as you have stated previously. And I'm curious, is that why you chose to

Take this different kind of risk of starting a company, having reached the top of clinical development and research, being the VP of Global Head of Cancer Immunotherapy development and and stepping away from that and and focusing on and creating your own company. that seems like a a risky move. So I'm I'm curious to know if this

relentless pursuit of understanding the disease and understanding how to align the drug and the disease. was that the primary driver for that decision?

Daniel S Chen (28:00.972)
Yeah, so you bring up two interesting things. right drug for the right patient, and why someone who had been doing incredibly well in the clinical development space would change course in what they spent their career and time working on. For me, I don't view it as a risk. I don't honestly, I generally I'm I wouldn't say I'm afraid of risk.

I would say I'm more drawn to what I think is important and where the field needs to go. Now, whether that one person considers that risky or not is dependent on completely on one's own philosophy. but for me, I feel I feel like I've seen enough to have a sense of where the field needs to go. And then it just makes me feel like it's my responsibility to do my part.

To help that happen. I felt like that was true. I did my part as part of a bigger orchestra for cancer immunotherapy. And I feel like I'm doing that now for the field of engineered protein-based biologics. and so I I can't, I don't feel like I have time to be afraid of things. I need to do what I think is important.

And I think we need engineered therapeutics today more than ever, because we understand biology better than ever. and also because single-targeted therapies, which we've spent most of our lives on, T-centric is a single-target therapy, right? It just blocks PD1, PDL1 interaction. That I feel like is mostly played out.

Not to say we'll never have more great drugs like that, but many of those super important targets that work great because you just block it, we've already discovered and we've already made drugs out of. So, really, in many ways, the next frontier is this marriage of a deeper understanding of biology and engineering tools that will allow us to build more powerful.

Daniel S Chen (30:24.566)
medicines. And for us at Synthetic Design Lab, our focus is around what we consider smart medicines. Drugs that are no longer passive blockers of a target, but actually active drugs. Drugs that we can program almost like they're simple computers. We can give them molecular switches essentially that when designed properly are multi-tiered logic gates. So that the drug

Can sense a specific environment or situation in a patient's cancer, process that information to change the way it's behaving, and also adapt when the cancer adapts. And so that really creates a very different paradigm for thinking about how to use drugs, how we create drugs, and what drugs can do. And that brings me back to your final comment around.

Right drug for the right patient. As you know, I spent most of my career championing right drug for the right patient. But in a provocative manner, I would I like to say now that with as smart drugs become the next wave, and that's what I believe will happen, it will blow up the paradigm for right drug for right patient. Because

These smart drugs can essentially change the way they behave to adjust to each of the biomarkers that we currently use. And that is a very powerful concept. But when I say that, I'm really being provocative because what I really believe is not that we will no longer have the right drug for the right patient, but the biomarker and patient selection will have to bump up a level.

Jesus Moreno (32:02.098)
Mm-hmm.

Jesus Moreno (32:12.357)
Mm-hmm.

Daniel S Chen (32:23.84)
Rather than being focused on whether a patient has the target we're going after, this will force us to start to develop biomarkers that are more sophisticated and test fundamental things about the cancer that are not just about whether they have the target, but how those cancers behave. And as a nice example of that, if you think about something like

An antibody drug conjugate, right? A lot of antibody drug conjugate work that uses a biomarker. When they use a biomarker, it's generally the biomarker of the target that the antibody drug conjugate or ADC is binding to. In a world of smart drugs, you won't need to do that anymore because your smart drug will react and adjust to the configuration of different targets that are present in that cancer.

But you will still need to know whether that cancer actually is sensitive to the payload that you're delivering to it. If it's completely resistant to the payload of that ADC, that's probably not the right patient for your ADC. And so, in such a way, I think the emergence of smart drugs will actually force us to push to identify those patients that have more fundamental.

functional characteristics that make sense for a given drug.

Jesus Moreno (33:59.813)
It will it would be the right drug for all patients, if if you want to be even more provocative with that statement, thinking about a drug that adapts to the conditions of the patient and delivers the right therapy based on those those factors. but you mentioned antibody drug conjectures, Doctor, and it's it's one of the most

active areas in all of oncology currently. But the science is still wrestling with some hard limits. from your perspective, with a space that is quote unquote crowded at the moment, where do you see the trials most often run into trouble? What are the bottlenecks that that are slowing down the progress of both ADCs and

smart smart drug development.

Daniel S Chen (35:01.294)
Well, I think it's great that there's so much work going on in antibody drug conjugates. And there's a couple of reasons why I feel that way. Number one, and HER2 to me is the North Star for the field. And HER2 is such a powerful drug. In fact, if you look at it from a complete l response rate and durability of response rate, these are measures that we often use in the best responses for something like cancer immunotherapy.

And HER2's data for in HER2 high breast cancer patients really rivals that of the best cancer drugs of any class, including cancer immunotherapy. That's how powerful it can be. The problem, the struggle for the field, has been that HER2 is a kind of a unique target for solid tumor ADCs. It is not only very cancer specific.

And internalize as well, so you get good payload delivery. It's also expressed at a 10 to 100 times higher levels than other ADC targets. And so when we look at solid tumor ADCs, you just don't see the kind of activity that NHER2 has shown NHER2 high patients for these other ADCs. That doesn't mean there aren't a lot of great ADC drugs coming, but they're not getting to.

The kind of benefit that we see within HER2 in HER2 high patients. And that's to me where the field needs to focus. There will be a wave of approved ADCs that help patients, but I'm a strong believer, and it's one of the reasons why I found it to be important to create the technology and the company with my co-founder, Ramesh Balaga, at Synthetic Design Lab, because I feel like

Yes, we can make advances in ADCs and we can change payloads and linkers and do all sorts of amazing things. There's so many of those to come because we don't just have to limit ourselves to cytotoxic payloads. There are many other types of payloads that can help patients. But fundamentally, what are we going to do about the fact that there are no more HER2 targets out there? And

Daniel S Chen (37:26.198)
Are we just okay with living with suboptimal targets? I mean, that's fundamental to the field. And so again, for Synthetic Design Lab, our focus is around being able to synthetically recreate targets that behave like her too high, using using technology, using engineering, using multi-tiered log logic gates to create essentially what is a smart.

Daniel S Chen (38:00.428)
I think you are mute.

Jesus Moreno (38:04.018)
Sorry, Doctor. I was thinking about that novel mechanism and how when there's this element of unknown territory, the regulatory side of things gets even more complicated. What do you think sponsors must understand when they're taking something truly first of kind into a first in human, whether it be within the US or globally?

How do you see the regulatory bodies adapting to this new proposed therapies?

Daniel S Chen (38:40.482)
You know, that's a incredibly interesting question. when I was a younger drug developer, when I was just starting, I often felt like regulators were almost like our adversaries. That cancer immunotherapy really helped me better understand where regulators sit in the world of innovation. They're not the adversaries.

The regulators are there to help and protect the patient population. And the way they interact with drug developers changes dramatically based upon the clinical benefit the drugs delivered. And again, I saw that in spades with the development of PD1, PDL1 inhibitors. And I also we've seen it with the development of CAR T.

Cancer immunotherapy and CAR T are not without side effects. And they had complicated questions around biomarker and patient selection. They have complicated questions around dose and schedule and how long you treat with, and what do you do with some of the more severe side effects? But the second, it was appreciated just how powerful an impact they could make.

Daniel S Chen (40:08.075)
These drugs could make with patients with what should have been terminal diseases in some cases and became treatable and became durable responses, you could see that that switch flip. And the regulators, in my experience, really became more clear to me as partners. How do you best figure out the questions that are

still unknown about your drug while making sure that patients had access to these transformative medicines. So I think that when you ask me a question about regulators, I think it's important for us as clinical drug developers to remember that these are our partners. They're there to make sure that great drugs get to patients, that

Drugs that maybe don't have the right benefit to risk ratio are more or limited or don't get to patients. And for us as drug developers, it's our job to work with them to make sure that we're developing drugs the right way to the getting them to the right patients so that the clinical benefit profile makes sense.

Jesus Moreno (41:30.562)
Absolutely. It's it's important to remember that because as you say, sometimes that relationship becomes adversarial where it should be a collaboration aimed at at protecting the patient from negative side effects. but doctor, I I have to ask about the bus word nowadays and that's

in regards to the promise of AI and decentralized trials as a way of collapsing the timeline for the execution of this type of of novel therapy clinical trial from your perspective you think this this promises are real or are we still just talking about you know a slight point in in a presentation is it

Something that seems to be tangible when running a trial.

Daniel S Chen (42:36.544)
So I I obviously I think this is an incredibly interesting area. I will start by saying that I believe that AI is going to change everything in our world. so I'm a strong believer about the impact, both positive and negative, of AI on on human beings as a species, on civilization. it will touch every part of life. However, it will touch every part of life at different rates.

Some things, AI, LLMs, machine learning are really powerful today already, and you can see those. Some things it will make an impact, but it won't be for three to five years. And for other things, it might be five to twenty years before it makes a big impact. I think to me, the way to think about this is current AI, which is really

LLM. This is not general artificial intelligence, right? These are not the AI we're talking about today is not itself alive and conscious, but it's very good at learning from humans and behaving like humans. And it in that way, it can do many things very powerfully by learning from humans. But it requires massive amounts of data to be good at it.

And when you start to think about its application to our field, biotechnology, medicine, pharmaceuticals, you have to think about it, where it works now, where it works later, what it's good at now, what it needs more data for. And I would argue that in the space of decentralized studies, I think decentralized studies already have a place in drug development.

I think that position is an ancillary one. It's a supportive one. I think that to really fulfill the true promise of decentralized studies, we need a ton more data. Because the reason why clinical studies work, why big randomized studies work, is because they cut through.

Jesus Moreno (44:53.17)
Hmm.

Daniel S Chen (45:01.72)
The massive number of variables that are out there. And in particular, they cut through the variables that we don't even understand. It's not even the variables we understand, it's the variables that we don't understand. That we don't know are variables. And so to make the full promise of of decentralized trials really drive.

drug development and clinical development, I just think we need a lot more data so that we do understand, so we have enough data to cut through all of those variables, known and unknown.

Jesus Moreno (45:48.105)
Speaking about data, at the AACR this year you made your first public data disclosure. what did the readout tell you about both the promise and the current limits of of the platform?

Daniel S Chen (46:05.038)
Yeah. So I think what you're talking about are is our synth body platform at Synthetic Design Lab. This is this multi-tiered logic-gated controlled biologic therapeutic. It's protein-based. I'll start with what it taught us about the limitations. Just like the we just talked about variables for decentralized trials, when you make a powerful complicated pattern.

platform like SynthBody, which has between six and twelve active domains, all designed and around the way the domains l live in 3D space with each other and how they behave, there are a lot of variables, a lot more variables than we're used to with a more traditional biologic therapeutic approach like an IgG antibody.

And so, what I think we've learned over the last couple of years in working on this technology is that there are a lot of variables we don't understand yet. And really, the best way to build these today is to have a high-throughput engine, something that allows you to create enough variations that the variables are captured, and then you can select.

For the feature set that you want in these smart drugs. So the way we do this is we design it intellectually up front. We use everything we know about human biology and the disease that we're going into. We apply certain AI-based lenses to look at everything we know about the targets and the biology of these diseases. But then all of that gets

essentially captured within a very large set of variations that we then can screen in high throughput. So I would say, like decentralized studies, today we use that high-throughput screening as a way to to design and optimize a lot of the drugs that we're creating in the smart drug category. But in the future, I think there will be enough data.

Daniel S Chen (48:29.322)
So that AI can help us design these better, faster, more powerfully, because it will now be powered by a data set that tells it w all the different variables that exist. On the positive side, I think we we've seen that we can actually build these things. You know, when we started Synthetic Design Lab, this was all a hypothesis and what I would call science fiction.

Rather than science, right? We believed we might be able to do something and it was would be important. But I think today in 2026, we know we can make these things now. We know we can make these smart drugs. We know we can make them like IgGs at scale, with drug like properties, with IgG like PK. We can tune the PK to whatever longer, shorter. But the most powerful part of it is we've seen.

That you can actually design these things with logic gates. And we've done the experiments to show that it responds to those logic gates.

Jesus Moreno (49:39.357)
Dr. Chen, one last question before I let you go, and this is a big picture question. Five years from now, what does success look like for a synthetic design lab, both from the perspective of the patient as well as from the perspective of the whole industry thinking about designing a drug?

Daniel S Chen (50:03.126)
Yeah, so that's a great question. And obviously I have a hot lot of hopes and dreams around this, not only for the company, but for what we can do in with medicines and with patients. So from my perspective, if this company is successful the way I hope and believe it will actually be, it will change how we think about medicine. And it will change how what we can do for patients. And that's where it has to start.

There are so many diseases for which we have medicines that are just okay. And we like to think of them as great medicines, but it's only because they're great medicines because we can't figure out how to do better. Right? So in the field of medical oncology, we often think about wins as: hey, we were able to help you live a little bit longer. We were able to help you feel a little better.

bit better while you were alive. We might be able to put you into remission for a while.

But when you think about medicine and human health and human suffering with diseases like cancer, you realize very quickly: if you're a patient, all those things are niceties. You kind of just want your disease to go away. You want to not have cancer. And so one of the powerful things of cancer immunotherapy was we feel like we were actually able to do that. We were able to give patients who had terminal cancer.

Their lives back. But it was still a very small percentage of patients that we could do that to today. And so what are what do I want to see for the field? Well, in the future, I want to see us be able to take away some of these diseases. I want to be able to see us move the most advanced therapies well beyond just cancer and move it into spaces like Alzheimer's disease.

Daniel S Chen (52:07.436)
That impacts a lot of people. I want it to affect the field of obedicity and medicine. We've seen huge impacts with drugs like GLP1 and now multifunctional triple G versions of that field. But I think we can do still better because there are ways to change how the human body not only cuts back on caloric intake, but what it does once calories come into the body.

I think we can do better for autoimmune disease. I think we can do better for cardiology. And so these are fields that I think we can really impact a lot of patients. And in terms of drug development, again, my hopes and dreams and beliefs here are that within three to five years, we won't even remember what it was like when we had drugs that weren't smart drugs.

And we will think about biology and drug design very differently. It will no longer focus on can we find the next drug target like HER2 or PD1 or PDL1 or VEGF or GLP1? It will be more holistic. It will be about we understand human biology, and there are a lot of different factors that play into that disease. How would we best design a smart drug using

What approximates if then statements to solve that problem?

Jesus Moreno (53:43.508)
Dr. Daniel Chen, this has been generally a fascinating conversation. A tour from melanoma clinic to a molecular description of of the disease and how new therapies that behave like logic circuits might be the answer for this and many other challenges in healthcare. Thank you for sharing both the science and the strategies with us today.

Daniel S Chen (54:14.008)
Well, thanks so much for having me on. I really enjoyed the chance to interact here and I hope we have a chance all together as a scientific and medical community to do much better for patients.

Jesus Moreno (54:29.064)
Thank you, Doctor. And to all our audience listening today, until next time, keep accelerating.