Latest / What's Your Problem? / Mass-Producing Stem Cells to Cure Disease

Transcript

Mass-Producing Stem Cells to Cure Disease · What's Your Problem?

0:15
Speaker 1: Pushkin.
0:20
Speaker 2: There are these amazing cells in tiny human embryos. The
0:25
Speaker 2: cells are called pluripotent stem cells, and they're amazing because
0:29
Speaker 2: they can become any kind of human cell, a red
0:34
Speaker 2: blood cell, a skin cell, anything, any cell in your body.
0:38
Speaker 2: But pluripotent stem cells only exist for the first fourteen
0:43
Speaker 2: days of embryonic development. After that, they're gone forever. At
0:48
Speaker 2: least we used to think they were gone forever. And
0:51
Speaker 2: then about twenty years ago, researchers figured out how to
0:55
Speaker 2: take regular cells from adults, blood cells or skin cells
0:58
Speaker 2: or whatever. Take those cells, bring them into the lab,
1:02
Speaker 2: and then turn them back into pluripotent stem cells. These
1:07
Speaker 2: cells are called induced pluripotent stem cells, or ipsc's, and
1:12
Speaker 2: the possibilities they present for human health are both kind
1:16
Speaker 2: of obvious and awesome. If a person has a disease,
1:20
Speaker 2: you could use that person's own cells to grow any
1:24
Speaker 2: kind of new cells that they might need. You could
1:27
Speaker 2: grow new brain cells for Parkinson's disease, or new heart
1:30
Speaker 2: muscle cells for heart failure, or new bone marrow cells
1:33
Speaker 2: for leukemia patients. It has taken a long time to
1:38
Speaker 2: put that dream into practice, and in fact, it's not
1:40
Speaker 2: really solved yet, but researchers are getting close. A bunch
1:45
Speaker 2: of clinical trials are now underway using iPSCs to treat
1:49
Speaker 2: everything from Parkinson's disease to cancer to macular degeneration. But
1:54
Speaker 2: even if these clinical trials are successful, there will be
1:58
Speaker 2: another problem to solve. Turning a patient cells into iPSCs
2:03
Speaker 2: and then into whatever kind of cells they need takes
2:06
Speaker 2: months of work by highly trained science. It costs hundreds
2:10
Speaker 2: of thousands of dollars for each patient, and so even
2:14
Speaker 2: if those clinical trials are successful, the process of making
2:18
Speaker 2: the seals will still be too expensive and too labor
2:20
Speaker 2: intensive to ever benefit you know, millions of patients. So
2:25
Speaker 2: if the dream of IPSS is going to come true,
2:27
Speaker 2: somebody needs to figure out a faster, cheaper way to
2:31
Speaker 2: make them. I'm Jacob Goldstein and this is What's Your Problem,
2:40
Speaker 2: the show where I talk to people who are trying
2:42
Speaker 2: to make technological progress. My guest today is Nabiha si Client.
2:46
Speaker 2: She's the co founder and CEO of a company called Selino.
2:50
Speaker 2: Her problem is this, how can you make iPSC therapies
2:54
Speaker 2: quickly and cheaply? Before she got into the induced pluripotent
2:59
Speaker 2: stem cell business Nibiha was studying to be a physicist
3:03
Speaker 2: and she loved physics. Was going off to get a
3:05
Speaker 2: PhD in physics at Harvard, but just before she started school,
3:09
Speaker 2: her grandmother died, and she told me that had a
3:12
Speaker 2: really profound effect on how she thought about her research
3:15
Speaker 2: and her career.
3:17
Speaker 3: My grandma died due to severe diabetes that was not
3:21
Speaker 3: possible to control with insulin and other medications, and that
3:26
Speaker 3: just I felt really helpless. I felt helpless, and I
3:30
Speaker 3: felt this urge too. Okay, I don't feel comfortable going
3:35
Speaker 3: down this intellectual curiosity path of becoming a physicist, and like,
3:39
Speaker 3: what can I do to build better tools? There must
3:42
Speaker 3: be better tools that are necessary if my grandma died
3:47
Speaker 3: pretty odd, you know, due to diabetes, and there was
3:49
Speaker 3: nothing anyone could really do about it.
3:52
Speaker 2: So she started thinking about how to use physics to
3:55
Speaker 2: improve human health. For her graduate work, she figured out
3:58
Speaker 2: how to use lasers to make tiny holes in cell walls,
4:03
Speaker 2: and she started talking to all the researchers that she
4:06
Speaker 2: could to try and find useful applications for her research. Eventually,
4:11
Speaker 2: someone told her about induced pluralpotent stem cells, about iPSCs,
4:15
Speaker 2: and she realized that she might be able to use
4:17
Speaker 2: lasers to help automate the process of cultivating iPSCs.
4:22
Speaker 3: IPCs are extra complicated and special. I thought, I like
4:25
Speaker 3: to call them special because you actually have to go
4:28
Speaker 3: and like scrape bad cells away with a pipe pedant.
4:31
Speaker 4: It's super artisanal.
4:32
Speaker 3: So you're basically having these brilliant scientists looking under a microscope,
4:36
Speaker 3: holding cells in the dish, and then scraping with a
4:39
Speaker 3: pipe petter. And they're literally working ten ten hours a
4:44
Speaker 3: day scraping cells, not taking vacations, trying to get to
4:47
Speaker 3: work during the craziest snowstorms.
4:49
Speaker 4: Because if they don't show up, that run dies.
4:52
Speaker 2: Uh huh. And presumably, I mean if you think of
4:55
Speaker 2: actually getting it to the point where you can treat patients,
4:58
Speaker 2: it would be sort of impossibly expensive slash small scale, right,
5:03
Speaker 2: Like you could never do that for one hundred thousand
5:07
Speaker 2: people or something, right.
5:09
Speaker 4: Heart, we don't have enough scientists in the world.
5:11
Speaker 2: And of course that like highly skilled labor means like
5:15
Speaker 2: even more expensive than expensive drugs usually are.
5:17
Speaker 4: Right. Presumably that's right.
5:19
Speaker 3: And I think the cost estimates have gotten down over
5:22
Speaker 3: the past couple years because people have figured out how
5:24
Speaker 3: to do better biology but we're still in the hundreds
5:27
Speaker 3: of thousands of dollars.
5:29
Speaker 2: So you're setting out to solve this problem of how
5:33
Speaker 2: to grow iPSCs at scale, and in particular right this
5:37
Speaker 2: problem of getting rid of the bad cell colonies without
5:40
Speaker 2: disturbing the good ones. How do you figure out how
5:43
Speaker 2: to do that?
5:44
Speaker 3: So one of the things we did at the time
5:46
Speaker 3: was we spent quite a bit of time with biologists,
5:49
Speaker 3: so we were trying to understand their workflow. What do
5:51
Speaker 3: they do, what do they do in the lab, what
5:53
Speaker 3: are they looking for?
5:54
Speaker 4: How are they doing their hand gestures? And there's a
5:59
Speaker 4: lot of tilting, there's like tapping.
6:01
Speaker 2: This is the artisanal sort of separating the sales process exactly.
6:05
Speaker 3: The entire IPS manufacturing process can be on the order
6:08
Speaker 3: of three to four and there are many different parts
6:10
Speaker 3: to it. And certain scientists have certain features that they
6:14
Speaker 3: see by eye. So some will describe smiley faces, some
6:17
Speaker 3: will describe other features that they're seeing.
6:19
Speaker 2: Meaning like they look through the microscope to distinguish the
6:22
Speaker 2: good from the bad. That's right, and they sort of
6:24
Speaker 2: know it when they see it.
6:25
Speaker 4: That's right.
6:26
Speaker 3: And you have a whole range of how good our
6:28
Speaker 3: scientists are globally. So the best scientists are sitting at
6:33
Speaker 3: inside cleanrooms looking at these cells and trying to decipher
6:36
Speaker 3: the best cells. And the stakes are high because you
6:39
Speaker 3: don't really get in the way they're manufacturing their cells.
6:42
Speaker 3: They don't get to necessarily test the cells until you've
6:45
Speaker 3: done the entire process.
6:46
Speaker 2: Yeah. So, just to be clear, like this is a
6:48
Speaker 2: disaster for drug manufacturing, right, like not even for safety,
6:52
Speaker 2: but just like it's never going to work, right, It's
6:55
Speaker 2: never gonna work at scalesh Sure it could work for
6:58
Speaker 2: research for a while, but like you or somebody like
7:00
Speaker 2: you needs to come along to automate this, right.
7:03
Speaker 3: I'm so glad I never thought about how hard it
7:06
Speaker 3: was going to be and just went for it. If
7:09
Speaker 3: I know how hard it was going to be, like
7:12
Speaker 3: startups are hard, but I think we had this curiosity.
7:15
Speaker 3: We're a bunch of physicists, We had energy, we were passionate,
7:19
Speaker 3: and my co founder Marine and I we are very
7:21
Speaker 3: passionate about being in medicine and using our physics knowledge
7:25
Speaker 3: for medicine. So we were like, Okay, why don't we
7:27
Speaker 3: try why don't we figure out how to do it?
7:29
Speaker 3: And between twenty twenty and now, so many things have
7:35
Speaker 3: happened on the science and technology front at Seleno that
7:39
Speaker 3: I would label as impossible.
7:42
Speaker 4: I think there were at least the first few years.
7:44
Speaker 3: Of that phase, I was like, I don't know if
7:46
Speaker 3: any of this will work, and it was hard for
7:49
Speaker 3: me to come to terms with given that we had
7:52
Speaker 3: raised a big round.
7:53
Speaker 4: You know, a lot of people were talking about.
7:55
Speaker 3: This, but I also felt I kept telling my team,
7:58
Speaker 3: it's like, we have to give it our best shot,
8:00
Speaker 3: because if a team like ours isn't brave enough to
8:05
Speaker 3: try to go after this, this might not be resolved
8:08
Speaker 3: for a few decades. And what that means is we
8:12
Speaker 3: are at risk of falling into this pattern of pushing
8:16
Speaker 3: through complex manufacturing, of selling gene therapy products, even getting
8:21
Speaker 3: them through a phase through approval, but once they hit commercial,
8:25
Speaker 3: they're not meeting the patients.
8:28
Speaker 2: Meaning even if it works with the kind of technology
8:31
Speaker 2: that existed before you came along, even if it works therapeutically,
8:35
Speaker 2: it'll be so sort of bespoke and expensive that most
8:38
Speaker 2: people in the world aren't going to get it even
8:40
Speaker 2: if they need it. Is that what that means?
8:43
Speaker 3: That is what that means, And you know iPSCs, it's
8:46
Speaker 3: still to be determined. We don't have any first approval,
8:49
Speaker 3: so let's see how that goes. But it is the
8:51
Speaker 3: most complex manufacturing process that I've seen so far. Other areas,
8:56
Speaker 3: other examples I can point to are cart therapies, Cancer
8:59
Speaker 3: therapy is curative, incredible.
9:01
Speaker 2: This is another cell therapy and the domain of like
9:04
Speaker 2: let's take cells and develop them and give them to
9:06
Speaker 2: the patient. Right therapy is the sort of the signal
9:11
Speaker 2: achievement of self therapy so far.
9:12
Speaker 4: Right, it was.
9:13
Speaker 3: Huge, and that was happening that approval was coming up
9:18
Speaker 3: when I was starting Seleno, so it actually was very
9:21
Speaker 3: motivating to see, Wow, now we can actually reach the
9:24
Speaker 3: point of curing previously in kurbal disease. But it's been
9:27
Speaker 3: interesting to see about the cart space. Every year, the
9:32
Speaker 3: maximum number of patients being dosed with a CARTI on
9:34
Speaker 3: the year is on average still ten thousand patients annually.
9:38
Speaker 2: Which is a small number. Which is a small number,
9:40
Speaker 2: what hundreds of thousands or millions who might benefit from
9:43
Speaker 2: the tree correct.
9:44
Speaker 3: And now the scope is expanding to solid tumors and autommunity,
9:47
Speaker 3: So like, why are we stuck? We're stuck in this number.
9:51
Speaker 3: There's an infrastructure problem.
9:52
Speaker 2: It's a scale problem. It's a lack of manufacturing at scale.
9:56
Speaker 3: That's correct, and so I do feel very strongly that
10:01
Speaker 3: it's important to push forward trials and build for scale
10:06
Speaker 3: from the get go. But it's hard because it's tempting
10:09
Speaker 3: to take shortcuts and like, oh, we could do this
10:12
Speaker 3: and this will be much faster. And the question I'm
10:14
Speaker 3: always asking my team is Okay, great, so let's take
10:17
Speaker 3: a step back, but how will this solution? Could this
10:21
Speaker 3: address a million patients annually?
10:23
Speaker 2: Yeah, because there are a bunch of sort of cluges
10:25
Speaker 2: where you could make a thing that works and it's
10:27
Speaker 2: more efficient than what people do today, but it's still
10:31
Speaker 2: kind of clue g and artisanal and not great to scale. Like,
10:33
Speaker 2: that's the trade off.
10:35
Speaker 3: That is the trade off, and that's an everyday trade off.
10:37
Speaker 3: And I feel very blessed that we've been at it
10:40
Speaker 3: for quite some time, building the different layers, and we're
10:43
Speaker 3: at this point now where we're building our closed system.
10:46
Speaker 3: It's called Nebula, Okay, and it's it's it's the next version.
10:51
Speaker 3: It's the version I never imagined even when we were
10:54
Speaker 3: building the laser based technology, which we call the optical bioprocess.
10:59
Speaker 3: But the idea is in order to ultimately scale down cost.
11:04
Speaker 3: You know, it's always great to run high precision manufacturing,
11:09
Speaker 3: so we have that down, but the cleanroom costs are still.
11:13
Speaker 2: High because again you're dealing with living cells and they
11:17
Speaker 2: can't get contaminated because that would be disastrous. So you
11:20
Speaker 2: have to have a crazy super sterile environment.
11:23
Speaker 3: And we're doing many patients, and you want to parallelize
11:27
Speaker 3: as much as possible, and you want to protect all
11:29
Speaker 3: the patient samples from each other. So what we're building now,
11:34
Speaker 3: which is even harder but exciting and we're making some
11:38
Speaker 3: great progress, is the closed version of this so building
11:43
Speaker 3: cassettes that could ultimately be the clean space that all
11:49
Speaker 3: the manufacturing happens. Is the size of your iPhone, which
11:52
Speaker 3: is very exciting, huh.
11:53
Speaker 2: So it's basically, the size of your iPhone is a
11:56
Speaker 2: tiny clean room where you are cultivating induced player potent
12:00
Speaker 2: stem cells. It all happens inside that little box.
12:04
Speaker 4: That is what's being designed.
12:05
Speaker 3: I just want to put lots of little stars next
12:08
Speaker 3: to it, because this is all in collaboration with the FDA.
12:12
Speaker 3: You know, the type of vision we're portraying is not
12:15
Speaker 3: how cell therapy manufacturing is happening today. So we're gonna
12:18
Speaker 3: work with the FDA and we're going to present data
12:21
Speaker 3: and we're going to work with our clinical collaborators. But yes,
12:23
Speaker 3: wouldn't that be awesome because then we can we have
12:27
Speaker 3: these autonomous systems with close cassettes. We don't need to
12:31
Speaker 3: establish high grade cleaner So you get a ton of
12:33
Speaker 3: flexibility on setting up manufacturing in places where you might
12:38
Speaker 3: not have clean room, you might not have academic centers
12:40
Speaker 3: of excellent, you might not have the workforce.
12:42
Speaker 2: Yeah, Like the dream is it happens inside a machine essentially,
12:46
Speaker 2: like you buy the machine and all the artisanal knowledge
12:49
Speaker 2: and the clean room and everything is in the machine
12:51
Speaker 2: is embedded.
12:51
Speaker 4: In the machine, intelligent machines that make your best them cells.
12:55
Speaker 2: Yep. So that so we've talked about the past, and
12:59
Speaker 2: now we've talked about the dream for the future. Let's
13:01
Speaker 2: talk about the present. I read Is it right that
13:03
Speaker 2: there's a Phase one trial in Parkinson's that you're involved in?
13:08
Speaker 2: What's with that?
13:10
Speaker 3: Yes, we had a very exciting year. We found our
13:14
Speaker 3: first clinical collaborator. It's the Parkinson's Cell Therapy team at
13:21
Speaker 3: mess General Brigham and it's been great to work with them.
13:26
Speaker 3: They have a phase one running where they're making the
13:30
Speaker 3: patient's own IPSS and their own neurons, and these neurons
13:34
Speaker 3: are being transplanted into the brain, okay, and we're working
13:38
Speaker 3: together to do the transfer of the manufacturing into our
13:42
Speaker 3: automated platform. And there's a lot of back and forth
13:44
Speaker 3: right now on getting that collaboration up and running.
13:48
Speaker 2: And so just to be clear, that trial exists now
13:51
Speaker 2: and they're currently doing it in the artisanal, old fashioned,
13:55
Speaker 2: hard and expensive way, and the hope is that you
13:58
Speaker 2: will come in and do it in your faster, cheaper way.
14:04
Speaker 4: That's exactly right.
14:05
Speaker 3: They're incredibly brave scientists and clinicians and they've put in
14:10
Speaker 3: the hard work over the past few decades to get
14:14
Speaker 3: this bioprocess up and running, invent new surgical techniques, design
14:19
Speaker 3: the clinical trial, and yeah, we want to support them
14:23
Speaker 3: to scale through the trial and then how does it
14:26
Speaker 3: get into commercial So it's been really exciting. And one
14:30
Speaker 3: of the things I love about this collaboration is we're
14:32
Speaker 3: geographically very close because we're in Cambridge and they're across
14:36
Speaker 3: the River Master. I think it's like a mile or
14:39
Speaker 3: two from us. So the ability to connect dots has
14:44
Speaker 3: been incredible because the manufacturing is happening inside the hospital.
14:50
Speaker 2: Interesting, like you're building a machine in the hospital.
14:53
Speaker 3: We will be deploying the machine in the hospital. Yes,
14:55
Speaker 3: the machines are being built at our headquarters.
14:57
Speaker 2: Now I shouldn't say built. Yeah, so you're going to
15:01
Speaker 2: drive put the machine in a truck. How big is
15:03
Speaker 2: the machine by the way, you know.
15:06
Speaker 3: Maybe like one or two refrigerators. Yeah, so that's how
15:10
Speaker 3: big they are. And the cassettes are about the size
15:12
Speaker 3: your iPhone. And initially we'll be deploying the machines to
15:17
Speaker 3: be doing making sales for one patient at a time,
15:19
Speaker 3: and then as we build more evidence, we'd love to
15:22
Speaker 3: make more and more patients on each machine.
15:25
Speaker 2: And will that be the first time your sales are
15:30
Speaker 2: going into patients.
15:31
Speaker 4: Yes, I believe.
15:32
Speaker 1: So.
15:33
Speaker 3: We do have two other amazing collaborators, one in South Korea.
15:37
Speaker 3: They're working on a peripheral artery disease. They also have
15:39
Speaker 3: a phase one trial. They're going to have a US
15:43
Speaker 3: expansion and then a spinal cord injury company as well.
15:48
Speaker 3: But yeah, the mass General team is doing great. We're
15:52
Speaker 3: also leaning into collaborating with the FDA We've had a
15:58
Speaker 3: very positive experience working with them. Earlier this year we
16:02
Speaker 3: were granted our Advanced Manufacturing Technology designation for iPSC generation
16:08
Speaker 3: and it's I think that maybe that's the biggest surprise
16:11
Speaker 3: of the year at how technology forward the FDA is
16:15
Speaker 3: and they've been paying attention. They've been asking great questions
16:18
Speaker 3: and all of our meetings. They have a full stack
16:21
Speaker 3: AI team that is fully tuned into how our models
16:26
Speaker 3: are being trained, like what's what's behind the hood. So
16:29
Speaker 3: it's really really compelling. Yeah, because I think the last
16:32
Speaker 3: ten years of selling gene therapies have been transformative in
16:36
Speaker 3: terms of curative medicines, but everybody is missing the impact of.
16:40
Speaker 4: Scale, like including the regulator.
16:42
Speaker 3: So they've now taken upon themselves to sort of help
16:47
Speaker 3: the field think about scale and work with technology companies
16:51
Speaker 3: like ourselves. So it's incredibly it's special and.
16:56
Speaker 2: Just briefly, like, from say the patient's point of view,
17:01
Speaker 2: how will it work? Simply?
17:04
Speaker 4: Yeah, I mean you know, we can take the mass
17:06
Speaker 4: General Brigham.
17:07
Speaker 2: Yeah, in that case, what will happen?
17:09
Speaker 3: In that case, they'll be they'll see a physician and
17:13
Speaker 3: they'll get a diagnosis for their disease. And in this
17:16
Speaker 3: case it's Parkinson's. Then they'll get a prescription that says
17:21
Speaker 3: you're going to get an atologous cell therapy.
17:25
Speaker 2: And meaning your own cells.
17:27
Speaker 3: Yes, yes, exactly, personalize your own match with your DNA.
17:32
Speaker 3: And then they'll show up to or maybe it's the
17:35
Speaker 3: same day they get the prescription and maybe they're at
17:37
Speaker 3: their doctor's office, but they will have to either provide
17:43
Speaker 3: blood draw or a skin biopsy. I can imagine really
17:47
Speaker 3: far into the future. It could be hair cells, it
17:49
Speaker 3: could be saliva.
17:50
Speaker 2: But for this one, yeah, they take a little bit
17:53
Speaker 2: of your blood or a little bit of your skin
17:55
Speaker 2: and then.
17:56
Speaker 3: And then they say, okay, we'll schedule your surgery and
18:01
Speaker 3: come back in a couple months and.
18:02
Speaker 4: We'll be ready to go.
18:04
Speaker 2: Essentially, you're starting with the patient's cells, their skin cells
18:07
Speaker 2: or their blood cells. You're ending up with brain cells
18:10
Speaker 2: that match their own brain cells. What part of that
18:13
Speaker 2: transition happens inside your machine automatically.
18:16
Speaker 3: Yes, So the getting to really high quality iPSCs is
18:23
Speaker 3: the first product we've established.
18:25
Speaker 4: We're establishing end to end, Like.
18:27
Speaker 2: You put the whatever the blood cell or the skin
18:30
Speaker 2: sell in the machine and out the other end comes
18:32
Speaker 2: a high quality ips is it really like that.
18:37
Speaker 3: It's lots of AI and lots of biology and lots
18:40
Speaker 3: of fluidages, but it is kind of like that.
18:41
Speaker 2: Yeah, okay, it's true that part is automated. That's really
18:44
Speaker 2: what I'm asking, Like.
18:46
Speaker 3: We're working on it. Yeah, it's and it's going to
18:49
Speaker 3: be automated. There will be human human experts in loop
18:53
Speaker 3: as always, and there will be end QC. But the
18:56
Speaker 3: day to day operations, I mean, you know right now,
18:58
Speaker 3: like Exeleno, things here are running automated and they run
19:03
Speaker 3: pretty much twenty four hours a day, so they're like,
19:07
Speaker 3: you know, proming imaging, fluids, laser processing because the cells
19:14
Speaker 3: need different actions at different time points, so a lot
19:17
Speaker 3: of those things we've established to be algorithmic.
19:20
Speaker 4: Yeah, it is automated.
19:21
Speaker 3: You know, we have a we have a very small
19:24
Speaker 3: and mighty team of bio engineers, but we definitely do
19:27
Speaker 3: the work.
19:27
Speaker 4: Of ten fifty x more.
19:31
Speaker 2: I would say, yeah, through automation, through.
19:34
Speaker 4: Automation, that's right.
19:35
Speaker 1: Yeah, we'll be back in just a minute.
19:51
Speaker 2: One quick note before we get back to the interview.
19:54
Speaker 2: Near the end of the conversation, you will hear Nabiha
19:57
Speaker 2: mentioned something called allogeneic therapies. Those are therapies where ipsc's
20:04
Speaker 2: induced player potent stem cells are developed based on generic
20:08
Speaker 2: cells rather than based on a patient's own cells. Those
20:13
Speaker 2: are easier to cultivate, but in many cases they have
20:15
Speaker 2: drawbacks similar to organ transplants, because patient's own immune systems
20:20
Speaker 2: tend to reject those cells. So I just wanted to
20:22
Speaker 2: clarify that in advance. Okay, back to the interview. How
20:26
Speaker 2: are you using machine learning or AI in your automated process.
20:31
Speaker 3: The way we use machine learning and AI is we
20:34
Speaker 3: take a lot of photos of all the cells every day.
20:37
Speaker 4: How are they doing.
20:38
Speaker 3: We've trained a bunch of algorithms in Google Cloud that
20:41
Speaker 3: tell you, oh, this is a good stem cell, this
20:44
Speaker 3: is not a good stem cell, this is good density,
20:46
Speaker 3: this is not good density. And then those algorithms feed
20:50
Speaker 3: into other algorithms that make decisions on what to do
20:53
Speaker 3: with the cells. So that your expert scientists don't have
20:56
Speaker 3: to sit and make all these decisions, and it's hard
20:59
Speaker 3: to make when it's at this massive of a scale.
21:02
Speaker 3: So they can review what the algorithms are doing, they
21:05
Speaker 3: can intervene it whenever they want to. I think like now,
21:08
Speaker 3: a very timely a similar field would be self driving cars.
21:11
Speaker 3: You know, there's just a lot of imaging that's being used,
21:14
Speaker 3: and then the car can make its own decisions. And
21:17
Speaker 3: at least in a tesla you have you have a
21:20
Speaker 3: driver and they can override any time. Wimos are running autonomous.
21:24
Speaker 4: So that's what we do.
21:25
Speaker 3: We use imaging to help with all the decision making
21:28
Speaker 3: your manufacturing.
21:29
Speaker 2: So it's largely pattern matching, right, which is essentially what
21:32
Speaker 2: the expert scientists are doing. As you said, some of
21:35
Speaker 2: them talk about whatever a smiley faces something, it's just
21:37
Speaker 2: because the individuals have seen whatever thousands have done it
21:41
Speaker 2: thousands of times, and it's a it seems like a
21:44
Speaker 2: good thing to use AI for, right, like a classic like,
21:47
Speaker 2: here's lots and lots of good ones and lots of
21:49
Speaker 2: lots of bad ones. Now here's a new one. Pickwa
21:51
Speaker 2: are the good ones and one of the bad ones?
21:53
Speaker 4: It's that you're absolutely right. So what's great about it.
21:56
Speaker 3: Usually if humans can see something by eye, we're able
21:59
Speaker 3: to trend an algorithm to do that.
22:00
Speaker 4: So that's real number one.
22:01
Speaker 3: And then the second thing that's very exciting about what
22:03
Speaker 3: we do is this time series data. This is really
22:09
Speaker 3: important because you can really start to draw patterns through
22:12
Speaker 3: time and even figure out predictions. You can go back
22:16
Speaker 3: in time and predict the future. And our algorithms have
22:20
Speaker 3: been able to because we've fed in a lot of
22:22
Speaker 3: time series data, and we've fed in also genetic data
22:27
Speaker 3: of how these cells look.
22:28
Speaker 4: At the end, these algorithms can go.
22:31
Speaker 3: Back into the early stages of the process say actually,
22:34
Speaker 3: this one is this cell or this colony is going
22:38
Speaker 3: to be bad, so you might want to eliminate that.
22:41
Speaker 2: So, just to be clear, time series data is like
22:44
Speaker 2: we can think of it like a time lapse video
22:46
Speaker 2: of the life of a cell colony, and so then
22:50
Speaker 2: you learn patterns of like if it is evolving in
22:53
Speaker 2: a certain way or developing, I should say in a
22:55
Speaker 2: certain way, it's going to be good, or if it's
22:56
Speaker 2: developing in this other way, it's going to be bad
22:58
Speaker 2: based on the past. Is that what you mean?
23:00
Speaker 4: That's exactly right. You just made me think of like Netflix.
23:03
Speaker 3: I don't know why, but you know, like different movies,
23:06
Speaker 3: like I know what I'm going to get when I'm
23:07
Speaker 3: watching a rom com or I want to watch a
23:09
Speaker 3: murder mystery. So you have the but you know, not
23:12
Speaker 3: every rom CAMM is the same, but I know how
23:14
Speaker 3: the story should flow.
23:15
Speaker 4: And I'm making my choices.
23:17
Speaker 3: Yes, so it can start to make those kinds of
23:20
Speaker 3: look in the crystal ball and it just increases the
23:23
Speaker 3: efficiency and we still do the end processing is the same,
23:27
Speaker 3: and the more data we see it in, the better
23:29
Speaker 3: they get.
23:30
Speaker 4: So it's exciting. Data is important.
23:32
Speaker 3: Data is important for everything in AI right now, and
23:34
Speaker 3: it's no different for us. And I should add the
23:37
Speaker 3: data that we generate a lot of our friends are
23:39
Speaker 3: generating in biotechnology companies.
23:42
Speaker 4: It's very expensive data.
23:44
Speaker 3: So we do a lot of hacking to figure out
23:47
Speaker 3: what is like the optimum data said that we can
23:50
Speaker 3: take that it's cost effective and like timegated and like
23:54
Speaker 3: we're not losing any resources. We don't have access to
23:57
Speaker 3: infinite amounts of data.
23:59
Speaker 2: So okay, So that's that's where you are as a company.
24:03
Speaker 2: You talked a little bit before about iPSC therapies more generally, right,
24:09
Speaker 2: but let's return to that now for a second. So, like,
24:11
Speaker 2: have any iPSC therapies been approved by the FDA?
24:16
Speaker 4: Not yet?
24:17
Speaker 3: Okay, The first approvals are going to be conditional approvals
24:22
Speaker 3: are going to be in Japan, okay, And you know,
24:24
Speaker 3: I think Japan is a very passionate about iPSCs, given
24:29
Speaker 3: that they want to know about price, so they've been
24:32
Speaker 3: working hard at it when other nations and countries.
24:35
Speaker 4: Maybe slowed down. I started a little bit, you know,
24:38
Speaker 4: just being like, you know, not.
24:40
Speaker 2: Sure what are those therapies going to be.
24:43
Speaker 3: Yeah, Parkinson's, there's heart disease. Those are the two that
24:46
Speaker 3: I think will be up first. And then there's just
24:50
Speaker 3: incredible trials running all over the world around vision laws.
24:56
Speaker 3: I mentioned spinal cordanentry diabetes. Yeah, there's some really interesting
24:59
Speaker 3: programs out of China where it was an autologous patient
25:05
Speaker 3: derived pancreatic cell transplant that they carried through, which was
25:11
Speaker 3: quite incredible.
25:12
Speaker 4: Yeah.
25:12
Speaker 3: So I do think the volume picks up and sort
25:16
Speaker 3: of creates even greater urgency to start putting all the
25:19
Speaker 3: pieces together and getting to scale.
25:22
Speaker 2: Urgency, because once people start figuring out therapies that work,
25:27
Speaker 2: there will be a need to actually make the cells,
25:31
Speaker 2: which is where you come in.
25:32
Speaker 3: Yes, make the cells, scale them, and give therapy developers
25:35
Speaker 3: options because right now a lot of them are budget limited,
25:39
Speaker 3: resource limited and can only dose one patient every two years.
25:43
Speaker 2: Wow, just because it's so expensive to essentially make the cells.
25:47
Speaker 3: And high failure rate, it's not a high yield rate,
25:51
Speaker 3: and they don't They're understaffed, there's been budget cuts, there's
25:55
Speaker 3: just a lot of problems. So it would be great
25:59
Speaker 3: to have even more trials running. You know, I think
26:02
Speaker 3: until Phase three trials happen, it's really hard to know
26:06
Speaker 3: how the trial's going to go. We just don't have
26:08
Speaker 3: enough volume right now to have enough shots on goal.
26:11
Speaker 2: Well, and to run a phase three trial, you kind
26:14
Speaker 2: of need the automation, right, I mean Phase three trials
26:16
Speaker 2: tend to be quite large, a lot of patients, and
26:18
Speaker 2: if you have to have scientists making sales by hand,
26:20
Speaker 2: it's going to be hard to run a phase three trial, right.
26:23
Speaker 3: That's exactly right, which is why we haven't seen any
26:25
Speaker 3: ATOLL news programs get that far yet. But the ALO
26:28
Speaker 3: ones are getting there, which is exciting because it builds
26:31
Speaker 3: evidence for the mechanism of action.
26:33
Speaker 2: So it's easier to make sort of generic cells at
26:37
Speaker 2: scale as opposed to sort of bespoke sales for each patient.
26:40
Speaker 2: That's right, That's why the alloy So Okay, if things
26:43
Speaker 2: go well, what for you and the field, I guess
26:48
Speaker 2: you want you need both right, people need to find
26:51
Speaker 2: therapies at work, and you need to be able to
26:53
Speaker 2: sort of implement those therapies at scale. Like what will
26:56
Speaker 2: the world look like in what is the right amount
26:59
Speaker 2: of time to say ten years? It's five enough. Will
27:02
Speaker 2: the world look different in five years?
27:04
Speaker 3: In five years, I do think the world look will
27:07
Speaker 3: look quite different for Parkinson's pace And that's incredible because
27:11
Speaker 3: it is a pretty horrible disease that leads to lack
27:15
Speaker 3: of independence. Just it's just sad to see what patients
27:20
Speaker 3: have to go through and have lots of family members
27:22
Speaker 3: on our team who.
27:24
Speaker 4: Have Parkinson's.
27:26
Speaker 3: So yeah, you're going to go to your doctrin and
27:28
Speaker 3: say I want this this therapy and that will be
27:31
Speaker 3: an option.
27:32
Speaker 4: And I think we will see more of those. In
27:34
Speaker 4: ten years.
27:36
Speaker 3: I think we'll see at least five more diseases where
27:39
Speaker 3: there is one allogenetic therapy that's available and a lot
27:44
Speaker 3: of the autologous trials are getting into phase three in
27:48
Speaker 3: a scalable way. And what's what I'm hopeful for in
27:52
Speaker 3: the next five years. My mom just turned sixty, and
27:56
Speaker 3: in the next five or ten years, I don't want
27:59
Speaker 3: to have to worry about her diabetes all the time,
28:02
Speaker 3: and I would love to have the option of having
28:05
Speaker 3: her own cell replacement to manage her diabetes.
28:09
Speaker 4: That would be incredible, and.
28:12
Speaker 3: I think that that is happening, and I think the
28:15
Speaker 3: questions around how scalable will it be and where will
28:19
Speaker 3: we get it and who's.
28:20
Speaker 4: Going to make it?
28:20
Speaker 3: I mean, I think people are going to figure this out.
28:24
Speaker 3: Even this year. This year was not happier for biotech
28:27
Speaker 3: and biopharma. The markets were down. There's a lot of
28:34
Speaker 3: concerns around scale and investor returns. But I still find
28:39
Speaker 3: it incredible that gene cell therapy regard of medicine, companies
28:45
Speaker 3: and scientists are still chugging away. We're still getting into
28:49
Speaker 3: trials and brute forcing it because everybody is so passionate.
28:53
Speaker 3: I think the passion really comes from creating a paradigm
28:56
Speaker 3: shift from treating symptoms or accepting the status quo of
29:00
Speaker 3: a disease trajectory to wow, can we reverse disease? Can
29:05
Speaker 3: we get to curative medicines? And that collective will pay
29:09
Speaker 3: is incredible And I think a lot of us have
29:12
Speaker 3: experiences around aging and loss in our families, so it's
29:17
Speaker 3: driving this movement. And I think in the next couple
29:21
Speaker 3: of decades, we'll have lots of humans on Earth. We're
29:23
Speaker 3: going to be above sixty five and getting into eighty.
29:27
Speaker 3: So this does become an economic concern as well. So
29:31
Speaker 3: how do we keep everybody healthier for longer and using
29:35
Speaker 3: everybody's own regeneration, their own cell tissue and even organ replacements.
29:41
Speaker 4: I'm very up. I just tend to always be optimistic.
29:43
Speaker 3: That's what gets me up every day to work on
29:46
Speaker 3: these hard problems. So I'm quite excited, and I think
29:50
Speaker 3: what I'm encouraging myself, my team, and my friends, like,
29:53
Speaker 3: let's keep the optimism high. Let's problem solve together.
29:56
Speaker 4: We don't have to do this alone.
30:02
Speaker 2: They'll be back in a minute with the lightning round.
30:15
Speaker 2: I want to finish now with a lightning round. Okay,
30:20
Speaker 2: were you aware when you chose the name of your
30:22
Speaker 2: company that there is a personal injury lawyer who advertises
30:26
Speaker 2: a lot whose name is Seleno? Yes?
30:29
Speaker 4: Ish, not really so Yeah.
30:32
Speaker 3: I think when I named the company, I wasn't clear
30:36
Speaker 3: that anybody was going to care about us, honestly, Like,
30:39
Speaker 3: we didn't have a website, we just incorporated. We had
30:42
Speaker 3: a terrible logo that I made on PowerPoint, so it
30:47
Speaker 3: became more obvious a lot later. But I knew it
30:50
Speaker 3: was an Italian last name when we put that way,
30:52
Speaker 3: So I did know then, and I think Seleno and
30:54
Speaker 3: Barnes that person is an Italian last thing too, Cellino.
31:00
Speaker 2: Did anybody ever call your company?
31:03
Speaker 3: I did, like happen like maybe two percent of the time.
31:05
Speaker 3: But the way I got to the name was cell
31:07
Speaker 3: and Innovation Selena and it is also a star in
31:10
Speaker 3: the Pleiades star cluster and says it's.
31:13
Speaker 4: A nod to my astronomy. Love.
31:16
Speaker 2: You called your mother's approval of your curry a proud moment,
31:20
Speaker 2: and so I'm curious, like, what is the secret to
31:24
Speaker 2: making a curry? Your mother approves.
31:26
Speaker 3: Of being very focused on the taste and the smell. Uh,
31:32
Speaker 3: it's always experience.
31:34
Speaker 2: That's not a secret. Of course, it should taste good
31:37
Speaker 2: and smell good.
31:38
Speaker 3: It's not a secret, you know. It's interesting. Yeah, my
31:41
Speaker 3: mom is an excellent shift. She's excellent and many things,
31:45
Speaker 3: and her curry just taste a certain way. So I'm
31:47
Speaker 3: always trying to get as close as I can, and
31:51
Speaker 3: when it matches that she makes the best Bengali food
31:54
Speaker 3: in the hut, So like that's my measure.
31:57
Speaker 2: I know in my wife's family, there's a tradition where
31:59
Speaker 2: if someone asks you for the secret to your recipe,
32:02
Speaker 2: you mislead them, you don't actually tell them the secret.
32:05
Speaker 2: And I feel like that's what's happening here. I feel
32:07
Speaker 2: like I haven't got any information out of you on
32:09
Speaker 2: making a great curry.
32:11
Speaker 3: Okay, so let me maybe just general notes about Bangladeshi curries.
32:14
Speaker 3: Like it's a lot of turmeric, garlic and ginger paste.
32:18
Speaker 3: We like whole spices like cardamom and bay leaves and things,
32:23
Speaker 3: but it's.
32:23
Speaker 4: Turmeric, cuman chili.
32:26
Speaker 3: It's not very complicated, but the ratio is different than
32:30
Speaker 3: other regions of South Asia. So turn it up on
32:35
Speaker 3: the turmeric and then you'll get to Bangladesh.
32:37
Speaker 2: Good. Are lasers overrated or underrated?
32:44
Speaker 4: Underrated?
32:46
Speaker 2: What is one underrated thing about lasers?
32:53
Speaker 3: They are so incredibly precise and thanks to optics light
32:58
Speaker 3: based manufacturing, we have all like all semiconductors. That's why
33:02
Speaker 3: you and I get to have this conversation online through
33:06
Speaker 3: through a laptop and the internet.
33:08
Speaker 4: Yeah.
33:09
Speaker 3: So the precision and the scale that they've delivered, it's incredible.
33:13
Speaker 3: Light is incredible. I mean I just I just find
33:15
Speaker 3: it remarkable that can be a wave and a particle
33:18
Speaker 3: at the same time. Actually, my dog is named Photon.
33:21
Speaker 2: Oh great, I like that is your dog full of energy?
33:26
Speaker 4: Incredible? And she is a particle and a wave at once.
33:30
Speaker 2: We all are I guess if I understand correctly, she's.
33:33
Speaker 4: Very high energy.
33:34
Speaker 3: Yeah, we kept My husband and I are both physicists,
33:36
Speaker 3: so we went with Photon because we both use a
33:39
Speaker 3: lot of lasers in grad school. And then our daughter
33:42
Speaker 3: is Kiara and that also means light in Italian. Oh.
33:46
Speaker 2: I love that. Nabihas the client is the co founder
33:56
Speaker 2: and CEO of Seleno. Please email us at problem at
34:00
Speaker 2: pushkin dot fm. We are always looking for new guests
34:04
Speaker 2: for the show. Today's show was produced by Trinamnino and
34:08
Speaker 2: Gabriel Hunter Chang. It was edited by Alexander Garriton and
34:12
Speaker 2: engineered by Sarah Bruguer. I'm Jacob Goldstein and we'll be
34:15
Speaker 2: back next week with another episode of What's Your Problem.