AI and Microbiomes 101 with Jona (EP 128)
The Harry Glorikian Show
Harry Glorikian: Hello. Welcome to The Harry Glorikian Show, where we dive into the tech-driven future of healthcare.
Now, here’s a fact that still blows me away every time I hear it. There are about 30 trillion human cells in your body. But there are about 38 trillion bacterial cells, mostly hanging out in your large intestine. And that’s not even counting all the viruses, fungi, protists, and other microbial cells that live on your skin, in your bloodstream, and all around your body.
So in effect, what you think of as you is not really you. You’re actually a walking colony of many different organisms. All of which cooperate peacefully, for the most part. Unless the balance goes awry, and then you can get very sick, very fast.
Of course I’m talking about the microbiome, which has been getting more and more attention from researchers and doctors now that we’re starting to have the tools we need to identify and measure all those microbes and see what they’re up to.
My guest today is a serial healthcare and AI entrepreneur Leo Grady, and he’s started a company called Jona whose mission is to help patients and physicians keep up with the skyrocketing amount of scientific literature about the microbiome and try to translate it into real steps people can take to improve their health.
If you’re a Jona customer, you start by sending in a fecal sample. Then the company uses a large-scale gene sequencing technique called shotgun metagenomics to get a profile of all the microbes in your GI tract.
Since everyone’s microbiome contains a different mix of microbes, the next step is to use large language models to sift through the published science about the AI and microbiome and find the studies that relate to the specific bugs in your microbiome.
Then the company gives patients and their doctors a report that parses out whether their microbiome makeup might be contributing to their health problems, and whether there might be any health or nutritional interventions that would help.
It’s all in the early stages. And right now Jona’s test is mostly available through concierge medical services, executive health clinics, and other offices that do a lot of cash-pay tests.
But Leo thinks that over the long term the service has the potential to turn the AI and microbiome from a former black box into something closer to what he calls an “organ of data.” Meaning, a part of the body that doctors can, in a sense, visualize and analyze in the same way we can use MRI and other forms of imaging to scan our other organs.
If you’re a longtime listener to the show you may remember that I spoke with Leo back in 2021 about a previous company he headed called Paige, which was applying AI to digital pathology. Before jumping into Jona’s technology, I asked Leo to catch me up on how that company is doing.
So here’s our full conversation.
Harry Glorikian: Leo. Normally I would say welcome to the show to most people, but for you I have to say welcome back to the show. And I think the first time we talked was about two years ago. You were leading a company called Paige, which was just to remind everybody, if you haven’t listened to that episode, is it’s an AI platform to help pathologists reach the right diagnosis when they’re reviewing digital pathology images. And I think it might be the first time I’ve had someone back on the show, but to talk about a different company. So it’s a…
Leo Grady: Pleasure to be here, Harry.
Harry Glorikian: Yeah. No. It’s so great to have you on the show again. We were talking before I hit the record button, like, you’re a man on a mission to drive AI into health care. So, I mean, it’s you’re speaking directly to me in in many different ways. So, um, but listen, before we even jump to talk about the new company, Jonah, um, any thoughts on Paige? Is, you know, is digital pathology still a hot field? I mean, I’m sure you’re still very aware of, you know, how things are going in that space.
Harry Glorikian: Well, it’s funny because I don’t want to date myself, but I remember when I started my career, I was, you know, maybe 24, 25 years old. I was in immunohistochemistry and we were talking about digital pathology back then. And so it has been it’s it’s been a few years, let’s say, between then and now for, for the field to really get going. So I mean, when people say, you know, medicine doesn’t necessarily adapt quickly, if that’s not a really good example, I don’t know what is. I mean, you have to get the right technologies to come into place to cause that, that, that movement. And as you said, reimbursement workflow, all these other things have to go into play. But I want to, you know, let’s let’s flip now and talk about your new company, Jonah. You’re using AI to help people optimize their health by optimizing their microbiome. Right? So I just want to step back for people who aren’t necessarily familiar with the AI and microbiome and start by talking about, you know, the microbiome itself, the state of AI and microbiome sciences. Some people call the microbiome a new organ, right? The argument being that it that it’s just as important as your liver or your kidneys or anything else, and it can have its own unique disorders and deserves to be studied as sort of a integrated thing. And so maybe you could sort of prime people and share some of your learnings.
Leo Grady: Yeah, you’re absolutely right, Harry. So what is microbiome? The microbiome is the collection of all the organisms that live in your body and on your body. That’s bacteria, fungus, viruses, protists, archaea, all these different organisms, and particularly in your gut, in your colon in particular, these organisms have been shown to have a very profound effect on your health. And think, you know, what’s happened if you look back in history is, you know, for a long time, people didn’t even realize that that germs were dangerous. You had the germ theory and cholera and all these things and and really that created this backlash. We need to eradicate them all. And antibiotics came on and and, you know, we’ve had just wonderful successes in curing a lot of diseases with, with these medications. And I think over time, it’s become increasingly recognized that actually many of these organisms serve really important functions in your metabolism and your digestion and really affect your health. And that’s what really launched this probiotics industry. And people are getting more and more interested in this. And we’re learning more from a science standpoint. And it’s complicated. What we do know is that the human microbiome is tightly linked with your immune system. It’s linked with your with basically every GI disorder, autoimmune conditions, liver disease, obesity, metabolic disorders, cancer, drug efficacy, even Parkinson’s, Alzheimer’s and mental health, depression and anxiety have all been linked with the microbiome, and we don’t fully understand exactly what’s causing what in all of these circumstances.
Leo Grady: But the state of AI and microbiome science has been growing exponentially, particularly in the last five years. And it’s because of the drive down in the cost of sequencing machines. So for a long time, the only way you could study the AI and microbiome was by culturing them. But then you needed to isolate them. You needed to have the right medium. You had to have the right environment for them to grow. And what we found is that many of the organisms that are in your gut, we just don’t have that capability to culture them effectively, but we can sequence them. And now that sequencing has allowed us to identify them down to strain level and really study how they’re impacting your health. And just to give you a metric, the literature is growing at a rate of about 2000 papers every month in PubMed. There are papers on the microbiome, and that’s really broadly based. But no human being can read all of these papers. And so we built a large language model that can. And I believe that AI is really the perfect technology for understanding the microbiome because of the complexity. It’s the complexity of all of these organisms and how they interact with your body, and also the complexity of the literature. So we started by solving the second problem first and building this large language model to read the the literature and then be able to summarize all of those learnings to interpret somebody’s AI and microbiome test results.
Harry Glorikian: Interesting. Interesting. Yeah. Well, it’s funny because I can’t even remember if you and I talked about the large language model we ended up creating more for investing to read the literature, but not for diagnosing or identifying linkages of a disease or anything like that. Right. So, so different use of of a model. But. Just stepping back though. So if I was a skeptic, I’d say, yeah, the microbiome is important, but we’re still at the early stages of understanding it. So there’s I mean, there’s so many different species of microbes that can live in our guts, in so many different combinations. And we don’t necessarily have a good sense of what constitutes healthy or unhealthy microbiome. Right? On top of that, I think you mentioned sequencing, but. I want to say cheap and easy is not actually always available either, as you mentioned.
Leo Grady: Right.
Harry Glorikian: So obviously you believe in this because you’re you’re doing it. But is this field ready to be exploited by commercial pharma therapeutic industry. How do you think about that argument that would be made by someone in the field? Because I know someone’s making that argument somewhere.
Leo Grady: Well, the science is at a certain point, right? And the science is growing, as I mentioned, more than 2000 papers every month in PubMed. Now that science is only going to go in one direction and get better and we’re going to learn more. It’s certainly true that today we we do know some things, and it’s also true that a lot of people are very interested in their microbiome, and many people are struggling with health issues. And maybe they’ve taken tests and, and gone to see a doctor. And they they’re still looking for answers and they want to know, is there anything in my microbiome that’s been linked in the literature to something that can point me in a direction where I might be able to figure it out? And so we offer that service for people. It’s not a diagnostic test, but we can say, look, we ship a kit to your house and it’s a stool sample. And basically you ship it back. And the we do deep shotgun metagenomic sequencing, find all the bacteria, the fungus, the viruses down to a strain level in your microbiome. And then the AI takes that and scours the literature and says, here are all the diseases, here are all the conditions, here are all the symptoms, here are all the allergies, everything that’s been linked to a microbiome that looks like yours. And we cite all the studies and we say, you know, your microbiome has been linked with fatigue or with abdominal pain. Here are the studies that have described a microbiome like yours in people with these conditions. And we also try to provide some level of, of evidence to say they’re big studies, great journals, smaller studies, lower journals, to give somebody a sense of of what’s actually known today. And so at the end of the day, they can judge for themselves, and their doctors can judge for themselves on whether this state of knowledge is useful for any given situation.
Leo Grady: So you’re right, there’s a lot left to know in the AI and microbiome field, but we actually do know a lot already, and we view ourselves as using the AI to really help people understand what’s known today. Now we do a second thing too, which is if you want to change your microbiome in a certain direction, the AI also looks through the literature and says, here are all the dietary choices. Here are the lifestyle choices that you can make to be able to move your microbiome in a direction that might be better for you. But again citing all the studies citing the level of evidence. There are also studies that have looked at at drug interactions with the machine learning microbiome, and which drugs are going to be more effective for which people. Our AI is reading that, but we’re not presenting that to consumer. But in the future, we do plan to open up some interface for doctors to be able to access that information.
Harry Glorikian: Yeah, I mean, I always I’ve always had this theory about antibiotics, but but we can talk about that a little bit later. But so look, you were in…Paige is in pathology and Jonah is about the AI and microbiome. The common theme is AI. You and I talked about that earlier, but. How did you get interested in the AI and microbiome field? I mean, and what convinced you now’s a great time to start?
Leo Grady: Well, you know, my father was a virologist, so he he was actually a leading virology for New York State Health Department. And so I grew up around microbiology, going to the lab with him. And, you know, my path took me into ultimately doing my PhD in AI and entering health care from that angle. But I’ve had several loved ones in my family who have Crohn’s disease, who have colitis, who have celiac disease. My son has undiagnosed GI disorders. He’s 14, and I’ve seen all of them struggle in many cases for years to get a diagnosis and to really understand what’s going on. And then even when they have a diagnosis, they don’t get a lot of guidance on what they can eat, how how they can adjust their lifestyle to reduce symptoms. And yet they find that the choices they make there really affect how they feel. But they really it’s all trial and error to figure it out. And so I’ve I’ve seen all of these individuals, you know, these loved ones struggle to try to understand what’s going on. And often they end up in functional medicine or integrated medicine and, and where they get some sort of guidance on nutrition and food that has helped them in many cases, even as they, you know, continue to work with their doctors and get regular scopes and all of those things. So I’ve certainly seen that on the personal side and the struggle that that many people go to go through.
Leo Grady: But, you know, specifically with the AI and microbiome field, just following the literature over the years, it’s pretty amazing. I mean, some of the things that have been discovered, you know, fecal transplants can in some cases really almost cure somebody of certain diseases. And yet in other cases, they don’t do anything, or in other cases they can even be dangerous.
Leo Grady: And what it says to me is that if we really understood what we were doing here and we really understood which microbes to put in and which ones to take out, and we had the ability to do that, that it opens up opportunities for new therapeutics and ultimately even, you know, potentially curing some of these diseases. So so those those studies have really inspired me. I think there was studies also on the impact of the microbiome and behavior and how in certain mouse studies, the presence or absence of different microbes could completely change their behavior. And I found that so counterintuitive and yet really fascinating. And so all of these different things came from different angles to highlight to me that the microbiome was really important and super complex, and that we really need to figure out how it was interacting with your health. And me personally, I don’t have any health issues, but I’m, you know, a bit of a biohacker. I try to stay healthy. And so I got personally, I did a bunch of AI and microbiome tests. In fact, I think I did all of the AI and microbiome tests, and I was just really disappointed. You know, most of them were really geared towards selling probiotics or supplements. And all of this amazing literature that I could go read on PubMed myself were just not reflected in anything that was being shown. And I felt that we could do better by using AI to be able to read the literature and provide that summary for someone.
Harry Glorikian: Yeah, well, you sort of like. I was going to ask you that question of like, you know, what do you not want the business to be? And I have, you know, my own opinion about all these probiotics that are out there. And do they even make it to where they need to get to so that they can be efficacious in any way? But, you know, let’s dig into the products, services or even the you know, I don’t know where you guys are thinking long term therapies, you’re developing at Jonah Health. You had a blog post where you describe Jonah Health has the MRI for microbiome. And so what do you mean by that? Let’s start there.
Leo Grady: So I’ll just point out one quick note. The company is just Jonah, not Jonah health. We only we only use Jonah Health as our URL, but the company. Okay. Um, what do I mean by that? Well, you know, as you mentioned, I was working in pathology. Before pathology, I worked at Heartflow, where we built cardiovascular diagnostic tests for coronary disease using AI. And before that I was at Siemens building, you know, I products for radiology for MRI machines and CT. And I think what was really amazing to me is watching doctor look at an image like this, like a cardiac CT, for example. And there are 512 by 512 pixels, you know, by however many slices, maybe 400 slices, a lot of data in there. And these doctors would jump into an image. They would, you know, zoom in, zoom out, pan through the slides, rotate them, do some special views, curved MPs, and in five minutes they would have a diagnosis. They would have a report. They would also find the the bone fracture and the lung nodule. And they would have consumed all of that data visually. Right. And it was incredible just to see how they could take so much data and visually interpret it and, and make sense of it. And I saw the same thing in pathology. You have these incredibly detailed quarter micron resolution images of tissue. And there’s so much going on in these in these tissue samples.
Leo Grady: And if you watch a trained pathologist, they they zoom in, they zoom out, they pan, they look at different views. They and again, very quickly they can get to a diagnosis and, and also see all of the funny bits there that you know, can be helpful in understanding the person’s health. But it’s because these are visual environments that were built for these doctors, because they’re trained in using these visual environments, and they have the tools to create the visualizations that are going to help them interrogate the data and understand it. And so I look at this and I say, now, the microbiome. Um, okay. So if we want to say it’s a new organ, well, it’s not an organ like a heart. It’s not an organ like tissue. It’s not an organ like a kidney. There is no MRI that you can take of the microbiome. So I really see the microbiome as an organ of data. And if it’s an organ of data then how do we build the equivalent of that? An MRI workstation or CT workstation, or that pathology workstation where we can have a trained doctor of the future. Look at this data and interrogate it. Visualize it in different ways. Zoom in, zoom out, and really not only use it to get a diagnosis, but ultimately also see all the other knock on effects in somebody’s health.
Harry Glorikian: So you showed me the kit or you held the kit up for anybody that’s watching this on YouTube. But. Is the company consumer facing facing, you know, direct to patient? Or is it the kind of thing where they’re going to have to go to their physician and have it ordered through their physician?
Leo Grady: So it’s not a diagnostic and it’s not a medical device. This is a product for information only and is not reimbursed by insurance, although it does qualify for HSA, FSA. We are making it available through providers who do primarily cash pay tests. So not your typical PCP or academic medical center. So what are doctors who do cash pay tests? Concierge clinics, functional medicine, integrated medicine, holistic medicine, executive health. Oftentimes also obesity clinics. Even medical spas will do cash pay testing. We also do make it available direct to consumer. But that’s not really the primary way in which we’re reaching people. But it’s important for us as a value to make it as accessible as possible. So if somebody is not able to access some of these other doctors and they want to be able to take health into their own hands, we make it available for them to be able to do that.
Harry Glorikian: Excellent. Well, I was going to say, because I’m not going to call my doctor. If I wanted to take this, I would just want to call up and and speak to a physician who would then let me get access to it so I could make sense of the data myself. But, you know, speaking of data. What kind of data do you guys collect about the microbiome from the customers? I mean, I was looking at the the technology page and it says deep sequencing protocol that includes shotgun metagenomics. And it’s. So could you explain to people maybe one level deeper. You know, What is shotgun metagenomics?
Leo Grady: So there are multiple ways of doing sequencing in the microbiome. So the classical way of of assessing your microbiome was through culturing. As I mentioned, once you start to get into sequencing there was a technique that was developed called 16S, which is a way of understanding the bacteria in the microbiome. And 16S is a preserved part of the genetic code for bacteria that allows you to always find this, this piece of code and to be able to identify the the organism down to a certain resolution of taxonomy. So it’s very difficult to get strain level resolution and sometimes even species level resolution with 16S. Um, it’s is something similar, but it’s for fungus rather than bacteria. And with shotgun metagenomics it’s a very different approach what you do. So the problem with 16S or ITS is that you don’t get that strain level. Um, you don’t often you don’t actually get the DNA of these organisms. And you also are not going to be able to find anything that’s not bacteria or not fungus, depending on whether you’re doing 16A or it’s shotgun metagenomics, it takes a very different approach.
Leo Grady: Basically, it molecularly cuts up the DNA into little strands. Each of those strands gets sequenced and then computationally, they get reassembled into DNA that gets matched against a database to find that organism. And so the way it gets described often is like, you take a you take a book and or you take, you know, ten copies of the same book and you rip them up differently. And then you try to reassemble the one copy of the book from all the different shreds of these ten copies. But because you shred them differently at different places, you can kind of match them up, so that you can reconstruct the, the full book. And so shotgun genomics, the advantage of it, it’s more expensive. But the advantage of it is that you do get the full DNA of the sequence of the organisms, and you’re not limited to only. And you can get down to a strain level, and you’re not limited to just bacteria or fungus. You also can sequence protists or archaea or or viruses as well.
Harry Glorikian: So that brings me to the question of. How is the testing part of your business maybe differentiated from the normal competitive set of microbiome companies out there? Are you collecting more or better data than many of the other existing entities out there?
Leo Grady: Most of them are doing 16S because it’s cheap and because they they really, at the end of the day, just want to sell probiotics or supplements. And so they do something that is relatively cheap, relatively well understood. And and from a consumer standpoint, it’s really hard to know what what type of sequencing is being done. Many of the companies are not particularly transparent about it either. The advantage of shotgun is that if you really want to take advantage of the full literature, then you do want to know down to a species level or strain level. There are many circumstances where we know that different strains can behave differently in the gut and are associated with different things, and so if you can’t distinguish between these different strains, then it makes it hard to leverage any of the literature that’s on those on those organisms. Additionally, we know we’re learning more and more about the the microbiome component that’s not bacteria. And showing that some of the other elements of the microbiome can also have very profound effect on your health. I mean, if you think about it, historically, penicillin was derived from a fungus. Rapamycin was derived from a fungus. You know, these other organisms have a very strong impact on your health as well. And so we don’t want to limit ourselves, especially as the literature is emerging on these others.
Harry Glorikian: So that’s maybe a good segue to how AI plays a role in your product. I mean, we talked about, you know, you you’re applying a large language model trained on medical and scientific literature about the microbiome. I mean, let’s talk a little more about that. I mean, once you have some data about the composition of an individual patient’s microbiome, does that, you know, is that the input then for the queries for the large language model? Because I’m trying to understand how the microbiome data interacts with your generative AI in actionable advice or, say, treatment for a specific patient.
Leo Grady: So you can think of our technology in really three parts. So the first part is a large language model that consumes the literature and goes through and reads all of these scientific studies, and that that large language model will say, here’s a study that was 500 people. It was conducted in this part of the world. It had this composition of men and women. They were, you know, this, these ages. And the study found that in people with Crohn’s disease versus healthy controls, that there was more E coli and less saccaromyces. Right. And so the AI will extract all that information out of that one paper and then go to the next paper. And maybe that paper is on Crohn’s disease. Different study, different patient population, different findings in the microbiome and so on and so on. Right. And so reads all of these papers and extracts that information out. So that’s the first part of our our large language model, our technology. The second part says, okay, now we’ve got 400 studies on Crohn’s disease. And they were all on slightly different patient populations. They all had slightly different findings. How do we aggregate all of that together. And look at Harry’s microbiome and say, do you fit the profile that’s been observed, you know, broadly in aggregate across all of these different papers? And, you know, the way in which we do that is effectively going paper by paper and saying, does Harry’s microbiome match the profile in paper, one that was observed for Crohn’s? Does it match it in paper two and paper three and paper four.
Leo Grady: And then we do a weighted sum of all of these papers where we weight each study, each paper by the the quality of the study. So larger cohort sizes, higher quality journals get a higher weight, smaller cohort sizes lower. You know, lower quality journals get a lower weight. We put it all together and present that to you. But we cite all those studies. Then the third part is the generative part where once we’ve done that, that matching between the literature is to actually summarize it for you and say, Harry, here’s what what we found that that you can pay attention to for your microbiome. And when you sign up, you put in, you’re asked what you’re looking for. Like what? What are your goals? And you may say, my goal is to, you know, screen myself and just be healthy. You may say, like, I’m suffering from abdominal pain. I’m trying to see, is there any link with abdominal pain in my microbiome? In the literature you may say, like I’m trying to lose weight or whatever it is. And so based on what you tell us, your intention is that third part, that generative part is going to package the information in a way that tries to help you leverage what was found to achieve your goal.
Harry Glorikian: So how do you guys manage for you know, what everybody will call a hallucination or, you know, is it just quality control before it goes to the patient to make sure that what it’s, you know, what it’s saying makes sense or. You know, is it so tightly trained that it’s not going to, you know, identify some, make up something that it’s going to throw into the summary or all of the above? How are you managing for that?
Leo Grady: So if you think about those three parts, right. The only part that could be potentially subject to hallucination is the third part. Right? And the first part, when the AI is reading these papers and saying, this is a study about Crohn’s disease and had this cohort size, etcetera, we do have a human in the loop that validates that the AI extracted the information correctly and says, okay, this paper was properly, you know, interpreted by the AI. And then once that the human signs off on it, it goes into the knowledge base. And we know that that we can leverage that paper, that we interpreted what it said correctly. And so then when it comes to the third part, you know, this is not a chat bot. So you’re not going to say, like, write me a poem on my microbiome in the style of Emily Dickinson. This is, you know, it’s not going to just create things out of whole cloth, right? So it’s really designed to be able to answer the, you know, pre-specified queries that you can put into it when you sign up and create the the summary for you in a way that really matches what you’re looking for. And it’s, it’s structured in how it does that so that we can really, you know, ensure that that all, everything it’s telling you is backed by by true studies.
Harry Glorikian: So, you know, if you’re phenomenal gastroenterologist — your product, does this up their game? Does this you know, if you had the best of the best, are you going to get the same answer? How would you think about that?
Leo Grady: You have to understand. Top gastroenterologists received very little training when they went through med school on the microbiome, because there wasn’t all that much that was known until recently. And even today, if you go to the big GI meetings, go to DDW, you see a lot of work, a lot of presentations on the microbiome. The GI community is very interested and very excited about the opportunities with the microbiome. The AGA, the American Gastroenterological Association has a study committee on the microbiome. They’re very engaged. At the same time, no GI doc has read 2000 papers a month. That’s just not possible. And they all have, you know, a job treating patients, right. So they stay up with the literature as best they can and they’re all very interested, but they really appreciate. And I would say many of them are skeptical of some tests or probiotics or claims that get made, you know, in different supplements and, you know, have seen a lot that they are not comfortable with out there in the market. When we’ve worked with GI docs and we have just an incredible clinical advisory board. They really appreciate what we’re doing because they they can see all the linkages that between the microbiome and what’s in the literature, and we tell them where all of these linkages are coming from. We link them out to the papers. If they want to go read them and we tell them, like, is this more preliminary evidence or is this been verified? And, you know, multiple larger studies. And so they really appreciate the way that we’re approaching it and the information they’re getting. So it’s not like there’d never be a head to head go ahead and interpret this microbiome, because GI docs are just not capable of reading all of these papers and then integrate integrating them together. So they really appreciate what we’re doing is as a information source for them to help treat their patients.
Harry Glorikian: You know, I was just thinking about it, though. So you do your microbiome, you run it through the system. It gives you an answer. But next month there’s 2000 more papers, and the month after that, there’s 2000, right? Does the system then potentially give people the opportunity to sort of get updated?
Leo Grady: Yeah. So as as these new papers come out in the I goes through them and reads them. Then we provide updates to your report. And so this is something that, you know, we’re still working out exactly what the right frequency is. We don’t want to bother people and just, you know, update them every day. But at the same time, we do want them to be able to take advantage of the latest literature. Now, after a certain point, because your microbiome can change if you test your microbiome a year ago, you know, even if there are new papers that are related to your microbiome from a year ago, it may not be as relevant to you today. So it’s something you may want to continue to monitor by by getting fresh data on yourself. But but we do really want to keep people up to date on what gets learned even after they’ve taken a test.
Harry Glorikian: You went through a whole series of health problems earlier in the in the discussion that you think that Jonah’s technology can help. I mean, I think when I was looking at the website, there’s some things that might be, say, low hanging fruit like digestive health or weight management, but some of the ones down on the list that you mentioned cancer, neurodegenerative, mental health, longevity. How do you think or explain how Jona’s technology might help in some of those later areas.
Leo Grady: Well, you know, if you take cancer, for example, right? Cancer is obviously something that’s very scary and life threatening, and it is something that we worked on at Paige. And Paige is still engaged with, um, and there is no diagnostic test for cancer that looks at your microbiome. However, you know, if you were to say something like smoking is associated with lung cancer, that would be true. Even though just because somebody is smoking doesn’t mean they’ve got lung cancer. Right. And if we say, you know, this profile, this change in your microbiome has been associated with colon cancer, that is not a diagnosis of colon cancer. But if it’s something that you’re worried about, maybe you should go talk to your doctor and, you know, get your annual colonoscopy.
Harry Glorikian: Yeah, I was thinking about it more of like, you know, in immunooncology trying to match up. You know, we know that certain microbiome profiles seem to have a better reaction to when you, when you’re on an immunooncology therapy than, say, others. And I think people are still trying to figure out, yeah, which way is up. I mean.
Leo Grady: So about a third of people don’t respond to immunooncology, and actually a third of people even can have adverse effects. And the current methods for determining who’s going to do well and who doesn’t with Pd-l1 is not great as a predictor. Um, and as you’ve pointed out, there are numerous studies at this point that have shown that the state of your microbiome can impact or it can be predictive at least of how well you do on immunooncology. Um, no one has validated that to the point that it can be a companion diagnostic. Not yet. Right. Um, but certainly there’s evidence to suggest that that could be done. Um, at the same time, there’s another element to oncology that gets discussed less, which is when people take antibiotics. When people go through chemotherapy, they often develop GI issues afterward. Um, because and it’s thought that it’s because your microbiome gets so wiped out that you can actually acquire problems. So for example, with my sister, you know, she went through a breast cancer fight and she came out the other side of it. Um, but even after she came out of the other side of it, she developed colitis, and she’d never had colitis, you know, her whole life. And she was, you know, in her 50s at that point. So you’d think you would see it before. Before then. Um, but, you know, it’s not uncommon that this happens. And we don’t know, for example, that this was the result of the chemo or the antibiotics or whatever. But she’s not alone in incidence of GI issues after going through cancer treatment.
Harry Glorikian: And it’s interesting because I was just thinking about like, as you’re going through this, you. You could almost have a group that could say, guys, the next study you should do might look like this from the data that we’re seeing because you’re sort of looking at all the studies that are moving in a particular direction, and you start to see maybe breadcrumbs of what should be done next.
Leo Grady: Yes.
Harry Glorikian: Interesting. So. How do you see all this coming together sort of as a growth business? Because you are a venture backed company. So you’ve got to you’ve got to drive this thing towards growth. I saw I think it was the test costs $485 and I think it’s for the holidays. You guys have discounted it to $385. Is that the main source of revenue? Is it? You know, I think you guys are also doing nutritional coaching. I mean. What are you going to be? Your your main drivers. You think?
Leo Grady: At this stage. Yes that is that is our, our main focus. And a lot of companies will, you know, try to offer some sort of testing at a lower price and then sell you probiotics or foods or all sorts of other things where they, they actually make money. And we’ve taken a different approach, um, where we are just loyal to the person and the information that we’re able to give them, and we’re not. Trying to sell supplements or anything else to that individual. So that means that we have to to really provide them a lot of value and really service them very well. And so at this point, with this initial launch, we are working through, as I mentioned, concierge medicine, executive health clinics, obesity clinics, functional medicine, holistic medicine, as well as some private docs. And also, you know, offering it directly to consumer. Ultimately, over time, my view is that once we’re able to get enough data and sequence enough microbiomes that we will be able to to improve the drug development process, the drug usage process for determining who’s going to do well on on certain medications. And we’ll be able to build new clinical diagnostics and therapeutics by going through clinical trials and FDA and everything that’s required to do that. But for for now, this is the focus of the business.
Harry Glorikian: Yeah, that was going to be my next question, which was, you know, because we’ve been in this business long enough is like, when do when do you get pharma involved? Do you work with hospitals? Do you talk to the insurers? You know, how do you get there? But you know, right now I guess you guys are trying to accumulate enough data so that you can pick a certain place and then go from there.
Leo Grady: I mean, this initial product is a wellness product. It’s informational. It’s reading the literature and just reflecting it to somebody. It’s not a diagnostic, it’s not a medical product, and it’s going to stay that way in the future. We will build medical products and diagnostics and those will be different. They’ll go through a different pathway and they’ll be offered through hospitals and Medicare and all of these things. But this product is a wellness product, and it’s just reflecting the literature for an individual already that provides a tremendous amount of value. And we’ve had incredible feedback from everyone that we’ve been working with. And we’ll we’ll keep that this product outside of the the diagnostic and medical device realm.
Harry Glorikian: So, have I missed anything? Have I have I not hit a nail that that is important to talk about regarding the product or the company or what you guys are trying to do?
Leo Grady: No, I think we really covered a lot of ground, Harry. Um, I think one thing I’ll say is that the microbiome is such an interesting point in culture and in, in medicine, because every doctor that I’ve spoken to is convinced that the microbiome is essential, that it’s important that it will be very impactful on on patient care. And the only question is not if. It’s when. Some doctors think it’s going to be sooner and others will think it’s going to be longer. But nobody disputes that the microbiome is really important and essential. Um, or at least nobody I’ve talked to. And on the consumer side, there’s this tremendous interest as well. People are taking probiotics. They’re they’re getting fermented drinks and kombucha and kefir and, and yogurt and all these different things and, and, you know, and me among them. Right. And and so there’s this, this really strong interest on both sides of consumers wanting to control their health and be healthier and doctors that are really excited about the field. And I think that’s created a situation which some people have tried to take advantage of that interest. And, and, you know, make claims before things were ready to back those up. But at the end of the day, the science is real and the science is growing. And I’m really convinced and excited that the microbiome will someday be its own branch of medicine with its own doctors.
Harry Glorikian: Oh, yeah, I fully agree with you. I mean, I think that there’s a lot to still understand because of its level of complexity. It’s trying to actually, you know, access the samples. If you were saying, let me see something that’s higher up before it gets down to the bottom. And if you want to actually make a change to the microbiome. I mean, it’s a well-fortified space that doesn’t lend itself to changing very easily. I mean, if you try to change your microbiome and you’re trying to do it through food, it could take you years to potentially affect change.
Leo Grady: Yeah, I think that’s one of the most fascinating aspects of it is like it’s it’s both stable and malleable and changeable. You know, if you think about other ecosystems, like if you were to go to, to Yellowstone National Park and take a census of all the organisms there, all the chipmunks and the bugs and the birds and and the beavers, and you were to take that census every single day, you would find that it would change a bit, you know, as certain organisms were, were born and died, but it would be fairly stable and there’d be some seasonal variation to all these different species, but it would be more or less a stable ecosystem, but at the same time, like it can change quite suddenly if, you know, the the water supply got disrupted, if the, the environment changed, if an invasive species came in, if there was, you know, change to the temperature or the rainfall, there was a drought. Um, all these different things could change it and could change it permanently. Um, and yet so it’s, it’s on one hand stable and on the other hand, um, vulnerable. But also on the bright side, you you can affect change there. And I think as we really learn how to understand the current state of things and move it, engineer it to move it in the state that we want it to, that will unlock tremendous potential in health care.
Harry Glorikian: I couldn’t agree more. Leo, it’s been great having you on the show again. You know, I’m looking forward to either, you know, hearing how the company is doing, maybe taking the test at some point, just to ground myself. But, you know, I wish you guys incredible success. I think the area is incredibly fascinating.
Leo Grady: Thank you so much, Harry. It’s been fun.