Rebuilding Biopharma & Personalized Precision Medicine with Diego Rey Cofounder of Endpoint Health and YC Grad

What if you started a company like Roche (est. in 1896) from the ground up? How would you approach drug development differently given enabling technology available today? That's the question Diego Rey and the other founders of Endpoint Health asked. 

Diego Rey is a co-founder and Chief Scientific Office of Endpoint Health, which is flipping the traditional drug development model on its head with a precision-medicine approach. In the past, biopharma companies would start with a molecule and then see where it can be used. Endpoint thinks differently. They are using deep patient insight from the patient’s biology, molecules, digital patient data and the latest in AI technology to create precision-first therapies. Pretty cool and unique approach especially for those who have traditionally been overlooked by generic drugs. 

We’re excited to have Diego on to talk more about their approach, the future of precision medicine, and his inaugural work with Y Combinator’s life sciences startups. 

About Diego
Diego Rey, PhD, is a co-founder, board member, and Chief Scientific Officer of Endpoint Health, a Precision-First™ biopharma company where he employs his background in building multidisciplinary technical teams to create and develop the core technologies that enable Endpoint Health to deliver therapeutics and diagnostics to improve patient care.

Diego holds a PhD in Biomedical Engineering from Cornell University with minors in Biophysics and Applied Engineering Physics and a BS in Electrical Engineering from the University of California at Santa Barbara. Prior to Endpoint Health, during his PhD Diego co-founded GeneWEAVE Biosciences that was acquired by Roche where he was Head of Research for the Roche GeneWEAVE Division. After Roche Diego joined Y Combinator as YC’s first life sciences Visiting Partner. 

https://www.linkedin.com/in/diegorey/ 

About Endpoint
Endpoint Health is a precision-first™ therapeutics company that building a new kind of biopharma. By rewriting the molecule-first drug development model, Endpoint aims to deliver precision therapies that have the potential to improve outcomes for patients with immune-driven illnesses. Their vision is a world in which all patients get the best treatment possible for their unique biology and disease.

https://endpointhealth.com/ 

https://endpointhealth.com/pipeline/ 

Qualio Website

Previous episodes: https://www.qualio.com/from-lab-to-launch-podcast

Apply to be on the show: https://forms.gle/uUH2YtCFxJHrVGeL8

Music by keldez

Qualio website:
https://www.qualio.com/

Previous episodes:
https://www.qualio.com/from-lab-to-launch-podcast

Apply to be on the show:
https://forms.gle/uUH2YtCFxJHrVGeL8

Music by keldez

Transcript

Kelly Stanton: 0:17

Hey everyone. Thanks for joining us on From Lab to Launch today. I'm Kelly from Qualio and it's my pleasure to be your host and introduce you to these innovators in life sciences. If you haven't already please subscribe and give us a review on apple or Spotify. We'd love that. And if you want to be on the show, please see the application linked in the show notes. We've had a lot of people reach out and it's been our pleasure to connect. Today we have Diego Rey on the show. Diego is a co-founder and chief scientific officer of Endpoint Health, which is flipping the traditional drug development model on its head with a precision medicine approach. In the past biopharma companies would start with a molecule and then see where it can be used. Endpoint thinks differently. They're using deep patient insight from the patient's biology molecule. Digital patient data and the latest in AI technology to create precision first therapies, pretty cool and unique approach, especially for those who have traditionally been overlooked by generic drugs, more information on Diego and Endpoint in the show notes as well is in the show notes as well as a link to their current. We're excited to have Diego on, to talk more about their approach, the future of precision medicine and his inaugural work with Y Combinator, life sciences startups. Let's bring him in. Hi Diego. Thanks for joining us today.

Diego Rey: 1:36

It's been great to be here. Thanks. Thanks for having me.

Kelly Stanton: 1:39

Absolutely. We love hearing how people found their way into life sciences. Give us an overview of your path to where you are.

Diego Rey: 1:47

Sure. Yeah. So, I'll go way back to my undergrad days, I studied extra electrical engineering so that, and the life sciences originally it started off as an engineer and I was at UC Santa Barbara. And while I was at UC SB, I did some summer research. At Cornell that landed me in the Cornell nanofabrication facility. And so, one of the things that was happening at the time, these are the days where nanotech was all the rage, I think, just coming coming about. And then the um, you know, when you're building things that those small scales you can interact with biological systems at that scale. And so that's a, that was my, my entry into the life sciences was that link between engineering. And using the tools that we're building to interact with biological systems, so cells, molecules, and so on. And then fast forward, I ended up applying to a PhD program in biomedical engineering. So I made the switch from the he used to say the hard sciences to the squishy sciences life sciences in my PhD. So I ended up at Cornell doing a PhD in biomedical engineering. Got a master's and PhD there, the minor in biophysics and another one in applied engineering physics. So the really combination of the engineering side of things, and then the life sciences. And so that's how I got into the.

Kelly Stanton: 3:02

So walk us through how Endpoint's patient first approach works.

Diego Rey: 3:06

Yeah. So, our precision first approach the way. So the way that this works is that we, you know, when we started the company we decided as you described in the intro to take a patient data first approach, as opposed to a molecule first approach. And so what what we what we mean by that is that rather than starting with a molecule and seeing what diseases we may, we may be able to develop that molecule in. We start with no molecule and only start with the patient data within a given disease with a key hypothesis that by better understanding the patient biology within the disease, we may find unique therapeutic needs. Within subgroups within that disease where we may expect a better outcomes in the patients, essentially. And so we work with gene expression, data from peripheral, whole blood as well as electronic health record data. And in both of those cases, we take an approach where we first start with just looking at that data in and of itself not taking into account any biological information or clinical information, and just look for patterns in that data. So this is an unsupervised machine learning technique where we look for groups of patients that may look similar. Just in terms of, for example, their gene expression or their electronic health record variables. And then once we find those groups that pattern the group together, then we ask the question of what are the biological characteristics of each of those groups. And do they have clinical utility? And in taking that approach, what we've found is. Within syndromes and diseases. We, we do indeed see these clusters of patients that are biologically distinct from each other. And just looking at the, those biological characteristics. It seems very clear to us that they need different therapeutic approaches in order to address the, the, their particular need. And and so that's what then leads us to the right molecules. And we use that information. Develop molecules and part of our model is that although we can use that information to develop new molecules from scratch, we actually have found several candidate therapies that are already developed that we've actually worked to inland license. And with this approach, hopefully get these therapies to patients much more.

Kelly Stanton: 5:17

That's fascinating. How does that, you know, a typical clinical trial approach you know, the, the enrollment can be kind of staggered. So in, in this case then Is there an impact, I guess, on the trial from, from, because you would want to have lots of patients enrolled upfront, I would think to gather those bits of information and do the data aggregation as you've described, does that change the clinical trial timelines

Diego Rey: 5:43

then it does. Yeah. It actually has a pretty dramatic effect. Once we've actually identified these subgroups prior to running the trial. When we run the trial, we use a diagnostic test that identify as this specific subgroup to enroll those specific patients. And so it's although it's a sub set of the overall patient population, you would have enrolled. What we found is that the improvement in the, in the outcome, the effect size is dramatically high. Then it would be in that and stratified cohort. And so the net effect is actually shorter, faster and less expensive trials because we need to power the trial to show a much larger effect than we would otherwise. And so even though we're enrolling fewer patients technically, or a subset of the patients with using a diagnostic to identify the patients the trial actually is, is, is shorter. And with fewer patients at the end of.

Kelly Stanton: 6:39

Nice. Nice. Yeah. And that would definitely when you're trying to figure out this work for some and not for others. If you don't take those things into account, that's not, as it's not visible, you, you kinda, right. Like you wouldn't see some of that cohort grouping or sub cohort grouping, you would have back those groups out and reanalyze your data. I guess if things aren't meeting Endpoints and that that's, that's really powerful information to have up front.

Diego Rey: 7:05

Wow. Yeah.

Kelly Stanton: 7:07

Nice Endpoints pipeline page mentions. Addressing the unmet need in immune driven illnesses. What's the size of the unmet need your you're focusing on?

Diego Rey: 7:17

Yeah. So we focus in two areas broadly in immunology. Whenever the immune system is the culprit, essentially, and that's in critical care as well as chronic inflammatory diseases and in critical care even before the pen down. A syndrome like sepsis, which is a body's dysregulated immune response due to an infection uh, responsible, responsible for one in five deaths globally uh, and, during the pandemic. And unfortunately, a lot of the patients who died with COVID had about 90% of them had ARDS and sepsis as well. So it really highlighted the particular needs for these addressing these syndromes and today there are really no therapies approved that are targeting that dysregulated immune response. And we believe it's because of this heterogeneity uh, and these patients that you need to actually stratify the patients into these different biologically defined groups in order to target specific therapies for each of the specific needs. So that's in critical care and in chronic inflammatory disease. In many cases, less than 50% of the patients who received the therapies are responding to those therapies. And then we have a similar hypothesis that because there's this biological heterogeneity. And so we can address that maybe we can expect a better response to these therapies.

Kelly Stanton: 8:31

I love the idea of really cleaning up and targeting the therapies to, you know, I think people have this sort of broad expectation that any drug I take is going to work no matter what. And then they're incredibly disappointed when it doesn't, but you know, biology is not right. Right. It's biology. And so I love that you call it squishy science because it absolutely is. Yeah. With so much unmet need out there. Though, how are you guys deciding on what treatments to focus on first?

Diego Rey: 9:00

Yeah. So it's a combination of that need. And also where we think this approach will have the biggest impact. So, it, it, the approach, I think shines when the it's a difficult area to develop therapies in. And when there is that heterogeneity, right? And so, sepsis is a prime example of that, right? That's a, it's a area with very limited clinical trial success in the past. And in the chronic inflammatory diseases, that is also areas where we think that there may be more or less heterogeneity. So I think it's a combination of those two things. It's where's it needed most. And so therefore we're where it could be a make an impact. And and where, where would this approach, particularly with B particularly B well suited.

Kelly Stanton: 9:41

How do you see Endpoint and this technology evolving in the coming years?

Diego Rey: 9:45

Yeah. So, so right now, we're, we've very recently in licensed a our first molecule antithrombin three from a company called Grifols. Uh, This is uh, we're taking it directly into a phase two trial, given its history. In the past and in this patient population. So we're in the midst of our clinical development program but presuming clinical success in the, in the future. What we envision is a situation where even after commercializing the therapies and getting these to patients that will continue to learn in the process and we'll be able to gain new insights into into patient biology. In the use of these therapies and may be able to identify maybe further subgroups and refine the groups of patients that we're identifying in order to achieve either better response rates perhaps. And so we're, we're envisioning this a future where the, the therapies are are developed and we continue to actually learn more and more about patient biology and in order to develop even maybe new therapies. For, for additional groups that we might, and we might encounter in the real world that maybe our own therapies aren't actually addressing very well. And that will be the source of new cohorts for, for new therapeutics development.

Kelly Stanton: 10:55

We have a lot of startup founders who follow our show. What lessons did you learn from working with the folks at Y Combinator that might be useful for other founders?

Diego Rey: 11:03

Yeah, sure. So, at YC I came in as the Y Combinator's first life sciences visiting partner. But you know, even, even before joining Y Combinator by the time I showed up. They already had over 140 life sciences companies in their portfolio. And they had a really great set of folks who with life sciences experience that was helping YC as part-time partners and, and mentoring founders in the process. And so I came in to, to help in, in that, in that effort. And one of the things that, you know, really noticed is that you know, this day and age and this is one of the motivations for starting Endpoint as well, is that there's so many enabling technologies out there that have matured over the years in being able to generate data from, from patient specimens and better understanding biology, making sense of the data with machine learning techniques and even be able to utilize diagnostics approaches that again, have matured in, are more off the shelf now and can be translated into, into practice more readily. And so putting this altogether, I think it really lowers the barrier to that entry to do new work in these fields. I think it opens a door for for potential founders who maybe didn't come from a life sciences background or at least the life sciences industry industry background into the field. And I think it's a source of diversity really in, in our field that when you, when you combine those new perspectives with the well-established best practices and expertise that's been developed over the year, that combination of the two I think is is really powerful. And so, and it's going to lead to a lot of innovations and at the end of the day better options for patients. And so the the, the long story short for me is that I think more people should be starting companies. It's a, good thing for the world.

Kelly Stanton: 12:48

Definitely, definitely. Well, and I, I love your your, your story where, you know, you started in electrical mechanical engineering types and have moved over to life sciences. You know, I've been in life sciences now, myself over 20 years and I've worked with people from the variety of backgrounds. And I just think the variety of perspectives is what makes it makes it so dynamic. Yeah, we didn't ask you about how Endpoint got started, can you tell us the founding story behind Endpoint then?

Diego Rey: 13:15

Sure. Yeah, so, I mentioned I was the UCS B undergrad than PhD in biomedical engineering at Cornell. And maybe a, the, the story that led to the story of Endpoints. So while at Cornell. A two along with two other co-founders Jason Springs and Leonardo Teixera has a lab mate of mine and Jason was doing his MBA. We started our first company called GeneWEAVE bio-sciences and so we uh, grew that company up uh, with a classic venture path of series seed a and B rounds of financing. There, we were developing tests for detecting and identifying bacteria and guiding antibiotic therapy in hospitalized patients, that company was acquired by Roche in 2015. And then I joined Roche as head of research for our division in the gene weave division of Roche. And it's the, and then the company, many of its employees and technology uh, still at Roche and being developed. Our first product has since gone through FDA authorization and it's now part of the Roche Cobas product line. And so, but an after Roche w what led to Endpoint health was we got the, the same co-founders from GeneWeave got back together. And um, and one of the insights that we had was that we were, we were thinking essentially a bit of a thought experiment of, you know, what have we started a company like Roche from scratch, what might we do differently? And they get back actually to your question about about Y Combinator and send us some of the lessons learned. You know, the, the, the key insight that we had was that, well, the world is very different today than it was when in 1896, when a company like Roche was started. And as an example you know, these enabling technologies again are, are one of those key differences. And so if we started a company like Roche today, that was going to be developing therapies and commercializing them we would start with data first as opposed to the molecule approach. And we meet, we covered that earlier. And and so the that's what that, that thought experiment is what led to, to, to Endpoint health and and where we're at.

Kelly Stanton: 15:09

Um, On a more personal note, if you could go back and tell yourself something at the start of your career, what would that be?

Diego Rey: 15:16

Yeah, I think, you know, the biggest difference this is this, you know, so second time around have the, you know, fortunate to have the experience of going through building a first company, GeneWeave even now and Enpoint as a, as a second company, and the biggest difference between then and now is actually a psychological one. It's a, it's one that you know, both times are hard. It maybe even a, you know, just as hard or even harder now, the second time around, because our vision is actually so much bigger. And with that with Endpoint health but the and so it was less about kind of the the, the work involved and the challenges and, and the, the biggest lesson learned is more about what realizing what's important. And what's maybe less important what to worry about when not to worry about so much. And, and the effect of that is really actually that one of a, of a psychological effect that allows you to focus more on what really matters and what's important and not so much on, on what might not be. So that was, that's been one of the, one of the biggest lessons. The, I think that at the same time we do go through a lot of challenges. And so, one of the things that I think it, it was a lesson learned, but actually I wouldn't, I wouldn't go back and tell myself this lesson, which is what those challenges were, you know, going into it kind of, with, you know, a lot of optimism and with a, you know, kind of point of view that we're, there's going to be challenges no matter what, and we're going to address them when they'd come to them. I think. It maybe almost maybe helped back then to not know what we were getting ourselves into in that regard, just to dive right in with a, you know, kind of a fresh point of view and address, address the challenges as the, as they came along. But we, I think, I think the biggest, the biggest lesson was, was one of'em, you know, what, what to focus on and what to not, not to focus.

Kelly Stanton: 16:58

Yeah, I guess when you don't know any better at all feels important. Right? Well, where can people go to learn more follow along and connect with you?

Diego Rey: 17:08

Yeah, so the main places endpointhealth.com, our website we have a great news and update section there. You can keep up to date on our latest press releases and scientific publications and so on. And for me personally@diegoarey is my my hashtag there at or at my handle there at a, a Twitter. And so feel free to, to send me a message there or follow me. And, and we also post a lot about one health on my, on my account there.

Kelly Stanton: 17:33

Nice. Thank you so much for joining us today, Diego. We appreciate your time.

Diego Rey: 17:38

Hey, likewise, pleasure being here and thanks for having me