Latest / The BioHub - by Avetix / Episode 135 - Yerem Yeghiazarians - Co-Founder & CEO Soley Therapeutics

Transcript

Episode 135 - Yerem Yeghiazarians - Co-Founder & CEO Soley Therapeutics · The BioHub - by Avetix

• 0:05
  So welcome back to the episode of the Bio Hub.
• 0:08
  Today we're thrilled to welcome on Doctor Yaram Igirizarians, a
• 0:12
  physician, scientist, entrepreneur and the Co founder
• 0:15
  and CEO of Soleil Therapeutics. Yaram has built an extraordinary
• 0:19
  career at the intersection of medicine and innovation.
• 0:22
  A cardiologist by cardiologist by training and former professor
• 0:26
  of medicine at UCSF, he spent decades leading translational
• 0:29
  research and advancing our understanding understanding of
• 0:33
  cellular stress, cardiovascular disease, and regenerative
• 0:36
  medicine. Yarum's now leading.
• 0:38
  Soleil. Therapeutics who are science
• 0:40
  first tech enabled drug discovery and development
• 0:42
  company using cells as the world's most powerful sentences
• 0:46
  to uncover first in class medicines.
• 0:48
  So join us today as we'll talk through.
• 0:51
  The inspiration in Co. Founding Soleil, how they pulled
• 0:54
  off an incredible 200,000,000 series C round, as well as
• 0:57
  Soleil's platform and how it works.
• 1:00
  So yeah. And thanks so much for coming
• 1:01
  on. How are you?
• 1:02
  Good. Thank you so much for having me.
• 1:04
  It's a pleasure speaking with you.
• 1:05
  Look, it's a pleasure to have you on as well.
• 1:07
  I was looking forward to this. So let's just start off with a
• 1:10
  little bit about your journey through the field.
• 1:12
  So you've built a career spanning clinical medicine,
• 1:15
  academic research, and now company building.
• 1:18
  Can you give us a bit of a room for your your journey and and
• 1:21
  how you got to where you are today?
• 1:23
  So as you know, I'm a cardiologist and a professor of
• 1:26
  medicine, have been based at UCSF for the last 20-3 years.
• 1:31
  I for the last 20-30 years have been taking care of patients,
• 1:35
  doing surgeries, doing basic science research.
• 1:38
  I was the founder and director of the Translational Cardiac
• 1:41
  Stem Cell Program at UCSF for over 2 decades.
• 1:44
  My journey started that I'm an Armenian.
• 1:47
  As you can talk from my long difficult last name, I'm a
• 1:50
  descendant of the Armenian Genocide.
• 1:52
  I was born in Iran. We left Iran when I was a
• 1:56
  teenager after revolution and 4-5 years of war and bombings
• 2:01
  during the Iran Iraq war. Through lots of difficulties we
• 2:05
  made our way to the states. When I arrived here I didn't
• 2:08
  speak a word of English and we had no money when we arrived
• 2:12
  here. So a lot of challenges and a lot
• 2:14
  of difficulties and a long journey made it to a Brandeis
• 2:18
  University and I was a biology, biochemistry dual major.
• 2:23
  My English by then was getting better and I was fortunate to
• 2:25
  didn't go to Johns Hopkins School of Medicine and I
• 2:29
  graduated from medical school 30 years ago now in 1995.
• 2:33
  By then my whole family had immigrated to Boston and I
• 2:37
  wanted to go back home and I spent the next eight years at
• 2:40
  Harvard Medical School for all my additional training,
• 2:43
  internship, residency, fellowship.
• 2:45
  I was a chief resident, did the research and interventional
• 2:48
  cardiology training. And then in 2003, I was
• 2:51
  recruited to come to UCSF to be a clinician, a surgeon, and to
• 2:57
  to be the founder and director of the translational stem cell
• 3:00
  program in cardiology that I mentioned.
• 3:03
  And the research that was done in my lab over the last 20 plus
• 3:07
  years is what that was an inspiration to starting the
• 3:10
  company. So like therapeutics?
• 3:13
  And and just so you're route to being a CEOI guess is a little
• 3:17
  bit less traditional. When you look at CE OS, you
• 3:19
  probably look at like an ex chief business officer, chief
• 3:22
  commercial officer. How did you personally evolve
• 3:25
  from being a scientist and clip clinician into a CEO, and what
• 3:29
  are some of the lessons from that transition have stayed with
• 3:32
  you? Yes, that's a great question.
• 3:34
  I am a first time CEO indeed and there are a lot of similarities
• 3:38
  and some differences of course being in academia, doing a
• 3:42
  clinical care, surgeries, research and now becoming the
• 3:45
  CEO of the company. However, there are a lot of
• 3:47
  similarities as well. And I would say staying
• 3:50
  organized, paying attention to details as you would for your
• 3:53
  patients and for every surgery that I do, listening to advice.
• 3:58
  This is not a one person show, it's a team effort, knowing your
• 4:02
  own limitations and having no ego.
• 4:05
  Working as a team is the most important thing in my mind and
• 4:09
  and all of these skill sets are applicable both in academic
• 4:12
  medicine as well as not in industry.
• 4:14
  And becoming the CEO of a company and for me naturally was
• 4:18
  a natural progression for the research that we're doing in my
• 4:21
  lab. We worked on it for over a
• 4:23
  decade with my Co founder Kuru Shamari.
• 4:26
  And you know, after 10 years, he and I probably know all the
• 4:30
  details about the platform. And it was just natural
• 4:32
  progression to spin up the company with this amazingly
• 4:36
  transformative platform and to try to discover new drugs in
• 4:41
  industry as opposed to validating a platform with
• 4:46
  repurposed drugs. Like just talk us through when
• 4:50
  you were sort of thinking about setting up so like what what was
• 4:53
  the original scientific insight that led to the founding of the
• 4:56
  company and and how long did that idea to take to mature into
• 5:00
  something that you believed could actually become a company?
• 5:04
  And good question. So the origin of the company,
• 5:06
  Tom, started over 16 years ago. So even though the company is
• 5:10
  only five years and the research that led to the starting of the
• 5:14
  company is decades old, and we started with a scientific
• 5:20
  question. And the question was how do
• 5:22
  cells determine their fate? And by that I mean why is it
• 5:27
  that cancer cells survive the harsh tumor microenvironment,
• 5:31
  which is low oxygen and low nutrients and cancer some has
• 5:34
  adapted to that environment and the cells survive and
• 5:36
  proliferate and metastasize. Whereas it takes just a few
• 5:41
  minutes of the same harsh environment of heart attack and
• 5:44
  stroke for heart muscle cells and brain cells to die in a low
• 5:48
  oxygen, low nutrient environment.
• 5:51
  So as you know, I come from a cardiology, cardiovascular
• 5:53
  research background and stem cell background.
• 5:55
  And my Co founder, Kuruj Ameri is a cancer molecular biologist.
• 6:01
  And at the time that we met around 2010, my laboratory had
• 6:04
  discovered stem cell secretive proteins that were rescuing
• 6:08
  dying heart muscle cells and brain cells from the harsh
• 6:12
  environment of low oxygen and low nutrients.
• 6:14
  And we're trying to figure out how do these proteins work.
• 6:18
  So when I met Kuroch, I was fascinated with his background
• 6:21
  because for 1520 years prior to coming to UCSF from Oxford
• 6:25
  University, 5-6 years there, then Stanford University 5-6
• 6:29
  years there, what his focus was was on the fields of hypoxia,
• 6:33
  anoxia, and cancer biology, specifically oxygen sensing and
• 6:38
  cellular behavior in a harsh environment.
• 6:42
  So we saw an opportunity to work closely together and he in fact
• 6:46
  joined my lab in 2010 and we started a whole cardio oncology
• 6:50
  unit to try to understand how do cells determine their fate
• 6:54
  towards survival or death. So as you know, biology is
• 6:58
  complex, but we figured that it's not magical and we reasoned
• 7:01
  that there must be some flow of information within the cell that
• 7:04
  dictates eventual cell fate. And if if anyone can figure this
• 7:08
  out, then you can potentially automate the system and use it
• 7:12
  for high throughput screening to discover drugs that selectively.
• 7:16
  And the keyword is selectively increase the stress level in a
• 7:19
  cell to kill it. If your intent is discover
• 7:21
  cancer drugs or antimicrobials or to actually reverse the
• 7:26
  health of a cell, make it work better, live longer, which would
• 7:29
  be applicable to a number of other non oncology conditions.
• 7:33
  It took us about 10 years, Tom, and this work was done in my lab
• 7:37
  at UCSF. When the platform was fully
• 7:40
  validated, we then licensed technology out to isolate
• 7:44
  therapeutics and we started a company and that that's how
• 7:47
  we've been doing the the rapid discoveries over the last five
• 7:50
  years. Like starting any business is
• 7:53
  obviously risks, risks that come with that.
• 7:55
  But in the earlier days, what were the biggest risks you were
• 7:58
  taking from scientifically, financially or from a personal
• 8:02
  perspective and how did you manage that, that uncertainty?
• 8:05
  Yeah. That's a great question.
• 8:07
  You know, so obviously starting any business, especially in
• 8:10
  biotech, is a risky business. There's a lot of chances that
• 8:14
  one has to take. So coming from academia to
• 8:17
  industry, clearly there's a big jump.
• 8:20
  For me personally, I had a stable job for over 2 decades
• 8:24
  seeing patients, doing surgeries, running a stem cell
• 8:28
  lab, extremely well funded laboratory that I had, doing
• 8:32
  lots of publications. I had a doctor of medicine.
• 8:35
  I gave up all of that. And about four years ago, I came
• 8:38
  out to be the CEO of the company because I truly believe in the
• 8:42
  transformative technology that we have.
• 8:45
  And so it was a lot of chances to be take.
• 8:47
  It was risky personally and also from a a business perspective.
• 8:53
  But if I were to do it again, I would do it over again.
• 8:55
  Despite having a young family, two young children, everybody
• 8:59
  thinks I'm crazy for doing what I've done after I leaving
• 9:02
  everything behind at UCSF. But I think, you know, we're
• 9:05
  making great progress and I'm extremely confident that that
• 9:09
  the the platform that we have will be very fruitful and
• 9:13
  discovering and developing numerous drugs in the near
• 9:16
  future. Yeah.
• 9:17
  Look, congratulations on what you're building.
• 9:18
  We can get into some of the details later on, on on what you
• 9:22
  guys have achieved, but just to go into the platform a little
• 9:25
  bit more. So it's built around using
• 9:27
  living human cells as biosenses. Can you walk us through, I guess
• 9:32
  at a high and practical level, how the platform works, what
• 9:35
  kind of data it generates? And how does this approach
• 9:38
  change the way you identify novel mechanisms or first in
• 9:42
  class opportunities compared to more conventional discovery
• 9:45
  methods that are out there? So it turns out that when a cell
• 9:50
  is exposed to a drug, the self senses this information, it
• 9:55
  reacts to it, and it responds to the drug that it's sensing.
• 10:00
  This cellular response is translated into flow of
• 10:04
  information within a cell, and we have learned to translate
• 10:07
  this cellular flow of information into understandable
• 10:11
  alphabet of human language. The way we do this is very
• 10:14
  different than any other technology that is out there.
• 10:19
  It's very different than other phenotypic screening
• 10:22
  technologies, very different than cell painting, for example.
• 10:25
  We track hundreds of dynamic features, if not thousands, and
• 10:30
  we track hundreds of protein expressions, aggregation
• 10:34
  confirmation, protein movement and transport, protein local
• 10:38
  localization and clearance, in addition to DNA damage
• 10:41
  responses, unfolded protein responses, mitochondrial stress
• 10:46
  responses, autophagy, self innocence, and numerous other
• 10:50
  features. And we use AIML to extract this
• 10:54
  information from the cell. And in fact, just a few weeks
• 10:57
  ago, we had our first AIML published in the peer review
• 11:01
  literature. So essentially, Tom, the cells
• 11:04
  are talking once they're exposed to a drug and we have uncovered
• 11:08
  how to listen and decode the cellular language.
• 11:12
  And it turns out every drug results in a unique flow of
• 11:15
  information that we call Soleimap.
• 11:18
  You can even take drugs that bind the same upstream target.
• 11:21
  They're in the same class of drugs.
• 11:23
  And it turns out the flow of information is very different
• 11:26
  amongst those drugs that supposedly bind the same
• 11:29
  upstream target. So we can cluster drugs
• 11:32
  together, we can decluster drugs together.
• 11:34
  And through these flow of information, we can predict
• 11:38
  druggable features versus toxic features for a drug that for
• 11:43
  example kills a cell cancer cell for that example.
• 11:46
  So the platform is very unique and it's fully automated.
• 11:49
  We now can screen over 100,000 drugs on a weekly basis.
• 11:53
  And all the inventory management system, everything from a
• 11:58
  workflow perspective is novel, is in house built and we're very
• 12:02
  efficiently able to screen and discover drugs very rapidly.
• 12:06
  And I've seen first time the facility and it's, it's amazing
• 12:09
  just what you build and it's, it's super impressive.
• 12:12
  I've not seen anything like that before.
• 12:14
  Yeah. Thank you for visiting us.
• 12:15
  It is first in class as you state, you cannot go out and buy
• 12:18
  this equipment. In fact, we've put 2025
• 12:21
  different equipment together to create the first ever fully
• 12:25
  integrated, fully automated high throughput robotic drug
• 12:28
  discovery platforms. And you know, in addition to the
• 12:33
  scientific insights, the automation insights and the
• 12:36
  level of QA that we have, the quality assurance, we're able to
• 12:40
  generate very, very clean, reproducible data that has great
• 12:45
  scientific depth and information for a drug discovery process.
• 12:49
  And all the AIML work that we're, we're doing because we're
• 12:52
  generating our own data, we're not tapping into any outpatient
• 12:56
  public data sets that are incomplete, biased, sometimes
• 12:59
  not even reproducible. So we train our own models with
• 13:03
  our own data and that that's what we're very confident with
• 13:06
  the our AIML approaches. I never like to use the word
• 13:10
  competitors because I think ultimately what you guys are
• 13:12
  doing is for the patients, but who are the companies that you
• 13:15
  look at that may be doing something similar to you guys?
• 13:18
  Or is this just like a completely uncharted field that
• 13:21
  you you work in it? Yeah, to the best of our
• 13:23
  knowledge. And nobody's doing drug
• 13:25
  discovery the way we're doing it.
• 13:26
  And our discovery approach is very orthogonal and very
• 13:31
  different than traditional methods of drug discovery.
• 13:34
  Typically the way drug discovery happens is people think of a
• 13:37
  disease upfront, they do decades of research into what the
• 13:41
  ideology or cause of diseases, and then they try to figure out
• 13:45
  a target within that understanding of the biology of
• 13:48
  disease. And then they spend a long time
• 13:50
  trying to come up with a drug that they bind that target.
• 13:53
  There are a lot of companies in AIML using AIML to bind the
• 13:57
  target more efficiently, better, and then they start doing the
• 14:00
  downstream experiment. So it starts with disease, a
• 14:04
  hypothesis about a target, finding a drug that binds that
• 14:07
  target and then a downstream experiments for simple monogenic
• 14:11
  diseases, this works amazingly well.
• 14:14
  And as a physician, Tom, I'm the beneficiary of using many of
• 14:17
  these drugs in my patients. For example, cholesterol
• 14:19
  lowering with H&G KOA reductase inhibitors, they work incredibly
• 14:23
  well. So we essentially have flipped
• 14:25
  the whole drug discovery paradigm 180°.
• 14:28
  Instead of starting with disease and target and then the
• 14:31
  downstream experiments, we start to find drugs that at a global
• 14:36
  cellular level, not just a target at a global cellular
• 14:39
  level, give rise to these desired Soleil features.
• 14:43
  Once we find drugs like that which they exist, and these are
• 14:46
  all small molecules, we do target agnostic medicinal
• 14:49
  chemistry to make sure the drug is druggable in patients.
• 14:52
  They pass the target product profile.
• 14:55
  Then we've put in place completely novel scientific
• 14:58
  methods to figure out how the drug is working, and that's
• 15:01
  usually the Achilles heels for other phenotypic platforms.
• 15:05
  People then don't know how the drug is working.
• 15:07
  We've overcome that challenge. We can tell you how the drug is
• 15:11
  working at a global cellular level.
• 15:13
  Once we have a drug that we know is working well, shows good
• 15:18
  tolerability and efficacy in our animal models, then we say what
• 15:23
  disease should we treat? So we let the drug determine its
• 15:26
  own fate and we put a completely novel bioinformatic process in
• 15:30
  place that we identified disease selection and which patients
• 15:34
  with that disease to include in our upcoming clinical trial.
• 15:37
  And just in the last two to three years, we have discovered
• 15:40
  over 10 new cancer drugs. We have 3 outstanding programs
• 15:45
  in non oncology including neurodegeneration, Parkinson's
• 15:49
  for obesity as well as hair regeneration.
• 15:51
  And each one of these programs is progressing extremely
• 15:54
  efficiently and we're headed to clinic with two of our drugs for
• 15:58
  our clinical trials. That's amazing and.
• 16:01
  It is that the potential of see this oncology neurodegenerative
• 16:06
  obesity like it's the potential to go in other therapeutic areas
• 16:09
  as well and I guess at least just the selected ones that
• 16:12
  you've chosen. Yeah, absolutely.
• 16:14
  So we are not A1 drug, one target, one disease company and
• 16:17
  frankly the platform is applicable to both oncology
• 16:20
  discoveries and many other non oncology discoveries.
• 16:23
  But to stay focused, our focus right now is cancer, get 2 drugs
• 16:28
  to clinic, do our own phase one clinical trials with the funds
• 16:31
  that we have raised and then advance these three non oncology
• 16:35
  programs. But frankly that non oncology
• 16:39
  program is very applicable to many, many other conditions
• 16:42
  including Alzheimer's, completely new approaches, Lou
• 16:45
  Gehrig's, Huntington's disease and many other conditions.
• 16:48
  We're trying to stay focused, get our drugs to clinic from a
• 16:52
  cancer perspective and advance these three programs.
• 16:55
  But that this is just the beginning.
• 16:56
  I think a platform can be applicable to a broad range of
• 16:59
  different diseases. It's amazing, so impressive just
• 17:02
  to listen and just to go into another milestone that you guys
• 17:06
  achieved fairly recently, you know, announced a 200,000,000
• 17:10
  series C round, which is a major milestone for any biotech,
• 17:13
  particularly given how the markets have been recently as
• 17:16
  well. Just talk us through like what
• 17:18
  did it take behind the scenes to, to raise that amount of
• 17:21
  money and to get to the the company to a point where that
• 17:25
  was possible? And how does that, having that
• 17:28
  level of capital, change your strategic ambition, both in
• 17:31
  terms of speed and ambition? Yeah, excellent.
• 17:34
  All great points. So let me start with what the
• 17:36
  goals are of our Series C fundraise.
• 17:38
  In total or last five years, we raised $290,000,000 including
• 17:42
  the 200,000,000 Series C that you mentioned.
• 17:45
  And the goal of the Series C, we have a lot of different cancer
• 17:48
  drugs. We're going to take two of them
• 17:51
  and bring them to complete two different phase one clinical
• 17:54
  trials in oncology. One will be in liquid tumor and
• 17:58
  1:00 will be in solid tumor. And that work is progressing
• 18:00
  exceptionally well. We're going to continue to grow
• 18:05
  our very rapidly growing oncology portfolio.
• 18:09
  As I mentioned, we have over 10 different assets and we're going
• 18:12
  to bring them all to an Ind stage.
• 18:16
  We're going to advance our non oncology programs and continue
• 18:19
  to advance our AIML programs in computer vision, chemistry and
• 18:23
  data integration. Regarding the fundraising, the
• 18:28
  fundraising, the investors are very excited with our orthogonal
• 18:32
  differentiate approach. Our precrimble data is
• 18:35
  outstanding, is very solid and we have within the last two
• 18:39
  years of doing all this three years, we already have drugs
• 18:42
  that were taken to clinic. Our platform is able to discover
• 18:47
  and develop the drugs that we bring forward.
• 18:49
  We don't have a platform and a clinical program that are
• 18:52
  disjointed from each other. We do not in license drugs from
• 18:55
  anywhere else. Every single drug, every single
• 18:59
  product is in house, developed and brought forward.
• 19:02
  So our platform has the power to become this exceptional
• 19:05
  efficient engine for continuous drug discovery.
• 19:08
  And we're looking forward to taking our first two developing
• 19:11
  candidates to clinic and test them in patients and see how
• 19:15
  they work in patients. But once we show the first one,
• 19:18
  the second one is working in clinic, then the whole platform
• 19:21
  from A-Z will be validated. That means the chance of every
• 19:25
  other asset that we have both in cancer and non cancer, the
• 19:29
  chances of them also being successful in crime trials is
• 19:32
  much, much higher. So we're very excited with where
• 19:35
  we are or very excited with a fundraising.
• 19:37
  We're excited to have our own drugs headed to clinic and we're
• 19:40
  right on time and right on our milestones and we're very
• 19:43
  excited to treat our patients because this could be a
• 19:46
  transformative approach for a very efficient drug discovery.
• 19:50
  That's so exciting. And just like as you guys move
• 19:52
  towards the clinic, what CC is the most critical upcoming
• 19:56
  inflection points for the company and how do you think
• 19:58
  about balancing platform innovation with the very
• 20:01
  execution heavy work of of clinical development?
• 20:05
  Yeah. So as I mentioned, our main goal
• 20:07
  for the Series C is to get two of our drugs in cancer and
• 20:12
  execute two phase one Clinger trials, one in liquid tumor, one
• 20:16
  in solid tumor. And these drugs are by the way
• 20:18
  effective against the different cancers as well.
• 20:21
  But the first one as we've published is going to be acute
• 20:24
  myeloid leukemia, but the drug is also effective against
• 20:27
  different liquid and different solid tumors.
• 20:30
  All of the drugs that we discover at this time are small
• 20:33
  molecules, even though the platform is applicable to
• 20:35
  discovering non small molecules as well or right now our focus
• 20:38
  is on small molecules. So from a inflection point that
• 20:42
  of course this year is a busy year for us.
• 20:44
  We're gonna meet with the FDA. We're gonna tell them about our
• 20:48
  plans about our first upcoming clinical trial and the second
• 20:52
  one as well. So it's gonna be a busy year
• 20:54
  dealing with the FDA. We're looking forward to that
• 20:57
  because we're excited to see what their thoughts are about
• 21:00
  our orthogonal approach to drug discovery.
• 21:03
  The data is very solid. So I'm actually very hopeful
• 21:05
  that it will go just fine and then we'll get to start the
• 21:08
  clinical trials after the Ind approval to get going with that
• 21:13
  trials. So those are the main goals from
• 21:16
  a clinical perspective as well as growing the other programs in
• 21:20
  oncology, non oncology. And we're continuously improving
• 21:24
  the platform and because we're generating all of our internal
• 21:27
  data, Tom, we're creating all these foundational models from
• 21:31
  an AIML perspective. And these models are all
• 21:34
  continuously being tested and they're getting better and
• 21:36
  better and better with our data input for better output.
• 21:40
  So we're very hopeful that from a computer vision, chemistry,
• 21:43
  data innovation, we can speed things up over the upcoming few
• 21:47
  years throughout the process of everything that we're doing now,
• 21:50
  it's important to point out, as you stated earlier, we're a
• 21:53
  science first company. We're not an AIML company that
• 21:58
  is trying to crack the complexity of biology.
• 22:00
  I don't think us or anyone is ready for that today in 2026.
• 22:05
  Our scientific foundation has not changed one bit or the last
• 22:08
  16 years that Koresh and I have been working together.
• 22:11
  And we use AIML to complement our science and to accelerate
• 22:15
  our science from a computer vision perspective, automation
• 22:18
  perspective, chemistry perspective and integrating all
• 22:21
  this data you can imagine. If you're able to screen over
• 22:24
  100,000 drugs on a weekly basis, there is a lot of data that gets
• 22:28
  generated and that's where AIML can accelerate your work and
• 22:33
  compute power can accelerate your work.
• 22:35
  But the scientific input and the scientific questions are the
• 22:39
  driving force of everything we do in a company, including our
• 22:43
  AIML to accelerate all his work. And I guess it's a separate
• 22:47
  question just related to culture, like what, what type of
• 22:50
  culture are you trying to build a a Soleil?
• 22:54
  And it's often talked about the the often hard to define
• 22:57
  culture. But what were you trying to
• 22:58
  build on a on a culture perspective?
• 23:01
  So first I have to say that that the success that we've had so
• 23:05
  far is all because of the T. We have an outstanding T and we
• 23:09
  have 39 full time employees. We have scientists, engineers,
• 23:15
  AIML experts, automation experts and we all work very, very
• 23:19
  closely together. You can put the best AIM experts
• 23:23
  in the room with the best data, but some of them don't know what
• 23:27
  the actual scientific questions are that are important and
• 23:30
  meaningful. You can put the best scientist
• 23:32
  in the room and they don't know what how AIML can actually help
• 23:37
  them with their work. So it's it's extremely important
• 23:41
  for all of these groups with their domain expertise to really
• 23:45
  work as a team and understand how they can help each other.
• 23:49
  And that frankly, is one of the hardest jobs at the company
• 23:52
  because we may have to repeat the same thing multiple times to
• 23:55
  make sure we're on the same page.
• 23:56
  And once we're on the same page, then you see everybody is like,
• 23:59
  wow, this could be really powerful.
• 24:01
  So that's why we're going to grow so late.
• 24:03
  Therapeutics very carefully, not over hard too quickly.
• 24:07
  Because when you bring in too many people too fast, then the
• 24:09
  right hand doesn't know what the left hand is doing.
• 24:12
  And close collaboration amongst all of these team members is
• 24:16
  exceedingly important for ultimate success.
• 24:19
  So it, it's, that's the type of culture, teamwork, respecting
• 24:23
  each other's backgrounds. We all come from different
• 24:25
  backgrounds. I learned constantly from our
• 24:27
  engineers, automation experts and, and AIML experts.
• 24:30
  And hopefully we contribute from a scientific perspective.
• 24:34
  And between myself and Kuroch, we have a lot of in depth basic
• 24:38
  science know how and we have the clinical know how.
• 24:41
  So we covered the whole basic science to clinical and and we
• 24:45
  complement that with the an outstanding team to help us
• 24:48
  accelerate our work. And just to finish this off, and
• 24:52
  this is a question that we always finish with with on the
• 24:54
  podcast, if you were to sit down with with any free people past
• 24:59
  or present, who would you go for and why?
• 25:01
  Yeah, there are a lot of people I can name probably that will
• 25:03
  take the whole podcast hour. But the first one I want to
• 25:07
  mention would honestly be my dad.
• 25:09
  He passed away about 10 years ago.
• 25:11
  And he did not come from a scientific background.
• 25:15
  And he was always asking me and questioning me.
• 25:17
  Hey, Aaron, what are you doing? What is this research about?
• 25:20
  What are you trying to do? So I would have loved for him to
• 25:23
  have been around to see the progress we've made to actually
• 25:26
  have drugs now that are head to clinic to treat patients.
• 25:29
  And that would have been something I would have hoped
• 25:32
  that he would have seen. But he passed away a decade ago.
• 25:36
  Another pair of folks I would love to have met in my life
• 25:40
  were, frankly, my both of my grandfathers.
• 25:43
  Both of them died before I was born.
• 25:45
  In fact, I got my name after my dad's father, and I always
• 25:49
  wanted to have met them. And the stories that I've heard
• 25:53
  from family about each one of them are incredible people,
• 25:57
  incredibly generous, incredibly respected.
• 26:00
  In fact, one of my grandfathers started that, one of the first
• 26:02
  Armenian schools in Tehran, in Iran, and I would have loved to
• 26:06
  have met them and learn about them and our generations and the
• 26:10
  struggles that they frankly had to escape the Armenian genocide
• 26:13
  and to make it beat another person.
• 26:16
  You know, I'm a big athlete. I love sports, you know, and I'm
• 26:21
  a big Boston sports fan, Boston Celtics fan, but we always
• 26:24
  compete against the Lakers and 1.
• 26:27
  And I didn't like the Lakers, but one individual I liked was
• 26:30
  Kobe Bryant. And it would not, it would have
• 26:33
  been nice to sit down with him to see what motivated him to be
• 26:36
  so great and how he handled pressure and then how he became
• 26:39
  this amazing basketball player that he was.
• 26:43
  There are, of course, many, many other people I can name from
• 26:46
  politics, from religion, from other successful businesses,
• 26:51
  including Steve Jobs and Elon Musk and Jensen Huang, and the
• 26:55
  list goes on. And you can learn so much from
• 26:58
  these people and to make yourself better, to see what
• 27:02
  that their struggles have been and how they overcame and how
• 27:04
  they created all these successful, amazing companies.
• 27:07
  So I'm always happy to learn. I'm always happy to get feedback
• 27:11
  and it's a it's and I listen to a lot of podcast by the way,
• 27:15
  too, Tom, because you pick up a lot of great pointers from
• 27:18
  people and you're like, hey, that's a good point.
• 27:20
  I can apply that to how I do XYZ and maybe I can become a better
• 27:24
  leader and a person along the way.
• 27:27
  Nice, amazing. Well look, 3 great answers
• 27:29
  there. And yeah, I think what you
• 27:32
  builded at Soleil is, is super impressive.
• 27:35
  I'm looking forward to seeing how the next inflection points
• 27:38
  come, which I'm I'm sure will. Will will go.
• 27:40
  Well, and yeah, sounds so exciting what you're building.
• 27:44
  So thanks again for coming on and helping us out with this.
• 27:46
  It was a it was a pleasure. Thank you so much.
• 27:48
  It was a pleasure speaking with you.
• 27:50
  Thank you for the great questions and definitely stay in
• 27:52
  touch and come visit again.