Transforming Cancer Diagnostics and Care with AI

Daniel Levine (00:00)

The Life Sciences DNA podcast is sponsored by Agilisium Labs, a collaborative space where Agilisium works with its clients to co-develop and incubate POCs, products, and solutions. To learn how Agilisium Labs can use the power of its generative AI for life sciences analytics, visit them at labs.agilisium.com. Amar, we've got Mohan Uttarwar on the show today. Who is Mohan? 

Amar Drawid

Mohan is a biotech entrepreneur who is the co-founder and CEO of 1Cell.AI. He's a repeat founder with deep experience in both diagnostics and therapeutics. And as an innovator and investor, he's got more than 30 years of experience in life sciences, precision diagnostics, and healthcare technology. 

Daniel Levine

And what is 1Cell.AI?

Amar Drawid

1Cell.AI is a precision oncology company that's using AI and single cell analytics to help pharmaceutical teams accelerate the next generation of cancer diagnostics and therapeutics. Its platform provides real-time tumor profile that can help drug developers make appropriate patient selection, accelerate development, and provide more nuanced understanding of a patient's response to therapy. But at the same time, this platform can be used to provide earlier diagnosis and guide personalized treatments by the oncologist. 

Daniel Levine

And what are you hoping to hear from Mohan today? 

Amar Drawid

I want to understand how 1Cell.AI 's platform works and the potential for real-time cell profiling to reshape clinical trials, drug development, and diagnostics. 

Daniel Levine

Before we begin, I want to remind our audience that they can stay up on the latest episodes of Life Sciences DNA by hitting the subscribe button. If you enjoy the content, be sure to hit the like button and let us know your thoughts in the comments section. And don't forget to listen to us on the go by downloading an audio only version of the show from your preferred podcast platform. With that, let's welcome Mohan to the show.

Amar Drawid

Mohan, thanks for joining us. We're going to talk today about how AI is transforming both cancer care and the development of new therapies, 1Cell.AI and how its liquid biopsy diagnostics are used by both clinicians and researchers. So let's start with the liquid biopsies. For audience members who may not be familiar with these, can you explain what they mean and how they work?

Mohan Uttarwar (02:28)

Thank you, Amar. Thank you for inviting me here. It's a pleasure and I appreciate an opportunity to talk a little bit about the field as well as what we do, why we are excited about what we do at 1Cell. Cancer is a deadly disease, we all know. One shoe doesn't fit all. So personalization of therapy is the only way cancer can be managed. This whole field has evolved into what they call precision oncology, which refers to personalization. Historically, what happens is somehow you find something, then the doctor tells you go into imaging, you do the radiologic scan, then radiology finds something, but then the pathology is ⁓ called for, which is the...process of taking a biopsy. Biopsy is the process of taking a small tissue sample from the area where you suspect that there is cancer and further analyzing it. It's sent to the lab, that tissue sample. It's called tissue biopsy. Tissue sample is sent to the lab. The lab does the processing of the sample. A glass slide is created. And the pathologist puts it under the microscope, does the reading, and based on the pattern he or she sees, they write a report and based on that report a treatment is given. This process is called tissue biopsy. Now tissue is an issue because it's a surgical procedure, it's ⁓ expensive and it's not an easy thing to do. It's invasive, it's interesting. As the field evolved and the science evolved, you know, the information that you get from tissue, similar information you can get it from blood, liquid. Okay. So that's why Dr. Klaus Pantel and Catherine Alix-Panabieres in Europe coined this term liquid biopsy. That means you take a simple blood draw, which is non-invasive or minimally invasive, and then you process it. Okay. And give a similar report. So that's the liquid biopsy aspect, right? From the sample of blood that you generate the reports using next generation sequencing.

Amar Drawid (04:49)

Now, when you're doing the liquid biopsy, is this circulating tumor cells or circulating tumor DNA? Are they available for pretty much most cancers or is that more prevalent in some cancers versus not? Or even the staging, maybe when it goes metastatic, it's more present. How does that work?

Mohan Uttarwar (05:11)

What happens is cells die, some natural death and tumor cells. So when they die, it spits out the DNA, that's the circulating DNA or cell-free DNA. Subset of the cell-free DNA from the dead cells, if it is a tumor cells, the death of a tumor cells which spits out the DNA, it's called ctDNA. Information that you generate from the ctDNA, circulating tumor DNA, is most relevant. But the problem with the liquid biopsy from the blood-based stuff is it's very difficult to figure out whether it was a cell-free DNA from a normal cell or versus the dead tumor cells. But now with the advent of AI and analysis, people have been able to figure out the difference. Okay. And it's a good biomarker. It tells you that more the ctDNA, more the prevalence of cancer. So you map it, right? And you have the hypothesis. 

Amar Drawid (06:21)

Okay. So it's like the higher stage, greatest stage you are, it's likely to have more ctDNA. DNA. And is it like in pretty much most cancers you see that or like some cancers more than the others?

Mohan Uttarwar (06:34)

Yeah, some cancers more than the others, but most cancer would have some DNA, ctDNA. Okay. And we're referring to tumor, i mean, the solid tumors, solid tumors. Yeah. Right. Yeah. So tissue biopsy, the next generation was liquid biopsy and liquid biopsy is referring to ctDNA. However, it is not a full representation of a tumor inside the body of a cancer patient. These are essentially DNA fragments coming out of the dead cells. So, what we are doing now is taking that industry forward to the third generation. We call cell biopsy, which is basically a next generation of liquid biopsy, but coming out of the circulating tumor cells. Now let me explain the CTC or circulating tumor cells. Gram of tumor, okay, sheds about a million cancer cells in the body, in the bloodstreams. So that may seem a lot, but we have trillions of cells in our body. So that means it's one in a billion circulating tumor cell. It's like a needle in the haystack. Okay, all right. Now, however, these are the real culprits. So, what happens is mostly 95 % of the cancer deaths happens because of the recurrence. The root cause of the recurrence is metastasis, a process where cancer spread from its origin. It might be breast cancer, but because of the circulating tumor cells, the cells that are shed, they go run around, most of them die, most of them are killed by our immune system, but some strong ones evade the immune system and they settle somewhere else. Okay, so they find the fertile ground, maybe it's lung, maybe it's brain, somewhere they go and settle and the secondary tumor grows. Okay, so these are like the there are fugitives on the run, but they are the microcosms of creating secondary tumor cells. And that's the root cause. So historically, it was very difficult to find those CTCs, those one in a billion circulating tumor cells. But now the new science, the ground-breaking science to capture that one in a billion circulating tumor cell, okay, at a very high degree of sensitivity, high degree of precision, the purity of capture,  and the high degree of simplicity and lower cost, okay. So why you are excited about this whole field is because 1Cell has this groundbreaking science and if I take these three axes order of magnitude higher sensitivity, order of magnitude higher purity of capture, order of magnitude lower cost, it's a thousand times better price performance than anything that existed before. 

Amar Drawid (10:02)

And it seems then that's going to be both from  the technical aspect as well as like the algorithmic or AIS. Are these both aspects going here?

Mohan Uttarwar (10:13)

Sure. Second generation of precision oncology also was about multi-dimensional data, multi-modal data, multi-omics data. Cancer is like an elephant and a  blind man touching it and describing what it is. A genomics is a science of genetics, right? It tells you something very important, but it doesn't give you a full picture. Just like a blind person touching the leg of an elephant, if you ask him to describe, he'll say, ⁓ elephant is like a leg. Another blind person touches, let's say, the tail and it says, it's like a snake. So unfortunately, the genomics, the transcriptomics, the proteomics, the methylomics, the metabolomics, these are all fields of science but they are looking at cancer into the silos with their own lenses. Unfortunately, cancer, everything, this has to be all integrated. So the first generation of precision oncology was driven by tissue biopsy and genomics data - like Foundation, they did very, very well. They established as the leader. But tissue is an issue. So second generation, the liquid biopsy, right, which is the blood-based stuff, right, you know, that came about. But what has been not fully equipped is, you know, again, that was really focusing again, you know, on the genomics and, you know, the transcriptomics. But DNAs, don't, you know, cannot get you the transcriptomics, or a little bit, but definitely not proteomics. So the third generation, which we call the cell biopsy, has the ability to do all three pieces together, the genomics, the transcriptomics, and the proteomics. Now what happens is multiomics, it's a big data problem. Cancer, as much as it's a disease, it's also a data problem and the data is overwhelming. So this is where AI comes in handy. Analyzing this multi-dimensional, multi-modal, multi-omics data, making sense out of it, correlating the data and predicting the outcome is the key challenge.

Amar Drawid (12:46)

So the challenge here I see is that usually when you do genomics, proteomics experiments, you have a normal tissue, you have a ⁓ disease tumor tissue, and you're looking at differences here. But then what you're collecting, majority of that is already normal anyway. So how do you then detect the specific cancer DNA or the cancer proteins from that? Because that's much higher level challenge than what people usually do.

Mohan Uttarwar (13:14)

Absolutely. Very, very good point. Excellent point. In liquid biopsy, I told you it's all about DNA and you have a challenge because you start with a noisy data. You don't know whether that DNA came from a normal cell, dead cells, or a circulating tumor, I mean the  DNA, right? And so when you start with the noisy data, again, you have to apply AI and deep analytics more resources to basically, you know, denoise that data. The next generation technologies, particularly the one that we have invented, are already starting with a cleaner data because you have figured out, we have figured out, capturing that one in a billion circulating tumor cells. ⁓ We already know that our starting point is a tumor cell.

Amar Drawid (14:10)

So you have the technology to then detect the tumor cell. Now does that like, does that depend on the kind of like surface markers there are on the tumor cells?

Mohan Uttarwar (14:24)

Very good point. So CTC is not new. It's been there 10 years ago. Unfortunately, what happened was the sensitivity wasn't there. And the endpoint was you capture the circulating tumor cells, you count and report them. So the clinical utility was limited. It told us that there is a problem. Your PET or CT scan or MRI might be clean. But if you find CTCs, that means, you know, there are some problems somewhere. Okay. So the scientists would say, we found the problem.  But the doctors would say, so what? My patient is happy because the PET is clean. And now you're telling me you found a CTC and you can't tell me what to do about it. Okay. So it's a very classic dilemma. Scientists get excited with what if. But the doctors are saying, so what? What if I found a CTC and the doctor is saying, so what? Unless you tell me what is the actionability? And the science stopped there in the past. But today with the advent of next generation sequencing and with AI, we are able to analyze the information in that single cell, okay, the genomic data, the transcriptomic data, the proteomic data and tell you and tell the doctor, hey, you know, it may be the cell coming from lung. You did a PET on basic breast, which was the origin stuff, right? So without AI analyzing the cell information that is hidden in that circulating tumor cell, we would not enable the doctor to take those critical clinical decisions. So it's really the integration of information from the biology of the cell, the science part, and the AI working on analyzing the genomic data, the transcriptomic data, the proteomic data, The surface marker. We know historically that if it's, let's say, HER2 marker, on surface of the cell, very likely that cell must be coming from breast cancer site. If it's an EGFR, very likely, again no guarantees, but very likely it's coming from a lung cancer, right? Also the way morphology of those cells look is very unique. So we use AI to analyze how the cell looks, the morphology, the size, the shape, the density, the contrast.

Amar Drawid (17:12)

There's imaging as well then.

Mohan Uttarwar (17:14)

Image analysis of the cell that we capture. Right.

Amar Drawid (17:18)

Okay, so in addition to the multi-omics, you're also doing the image analytics.

Mohan Uttarwar (17:22)

Absolutely. Before we do multiomics, we do the analysis of these cells. We do the characterization using our AI algorithms and we give enough information. Now, one other fact that is actually very revealing is that many times the CTCs are individual CTCs, but many times you have this, what we call the the combinations, right? You know, have the group of cells hanging together. Now the risk profile of those patients, prognostic is much, much different. It's much higher risk.  it reveals those kinds of things. Okay. You know, so there's interesting stuff, right? Now, how do we capture these circulating tumor cells, right?  The CTCs - there are two methods for capturing. One is size based, right? So tumor cells are usually larger in size and there are techniques, you know, micro filtration, there are techniques to really do the nanofluidics to capture those cells. That's one method. The other method is called affinity based. So tumor cells have certain types of proteins on the surface of the cells. EpCAM being one very popular protein that is on all solid tumors that are epithelial in nature, transferring in another protein that is expressed, okay? So what happens in the size-based capture, the cells go through a lot, you know, pushing and pulling. Nanofluidics, you know, you're forcing this, you know, nano filtration, you're pushing it. As is when cell leaves the tumor, it was in a very comfortable position sitting in the home and now it has to fight the whole battle. Immune system really is the aggressor which is trying to kill it. So only a few remain, they avoid all the forces against them and so they are, but they go through a lot of fights, they go through a lot of transitions, transformation, pressure, right. So as a result, size-based capture has not yielded great results. Affinity capture, relatively, is less stressful on the cells. So that's been historic perspective. The groundbreaking science that we have, but again, capture and count, doesn't tell you the whole story. So where 1Cell comes in is a ground breaking science to isolate the captured cell into a live single cell. Traditional circulating to the CTC, the end point was capture and count and give the report. For us, this is not an end point, this is the starting point. We begin with this captured and isolated live single cell and we do the imaging modality on it, we do the NGS on it, we do the multi-omics analysis on it. And so we have  much deeper insights that enable the doctors to say what's really going on. Is the therapy working? If it is working, why it's working? If it is not working, why it is not working? And what could you do potentially to change the course of the therapy? Can we add, you know, can we increase the dose? Can we add the combination therapy? Can we change something? Or if nothing, if it is working, can I reduce the dose level? Can I give those chemo holidays? Can I do the de-escalation? All these questions are unanswered in the minds of the oncologist. Provide AI assistant to the oncologist based on this scientific data that is presented, multiomics, you know, data that is presented for a given patient at a given time point, to be able to provide them meaningful, actionable information so that they change the course of the treatment, personalize the treatment for a given patient, which will affect the outcome.

Amar Drawid (21:58)

And cancer sometimes changes as well, right? So you have the mutations, some mutations take over versus the other, right? So in that sense, if it is growing,  you know, you can detect  okay, what is the new mutation that's coming up, right? And then the oncologist can then change the treatment accordingly as well.

Mohan Uttarwar (22:15)

It evolves. Yes. You know, and so many successful companies, you know, and I'll give you one example, Natera. It does the issue at this baseline at the starting point. It hones in on an information about 16 gene panel and it only monitors those 16 genes longitudinally. So one of the most successful company, one of the most successful test. But it does not address the evolution of cancer. You cannot take a snapshot. It's like I've taken, before leaving my home, going to the office, if I take, let's say, Google Maps, and I take a snapshot and I start driving, and if there is an accident and I have to do the stuff, I can't just, it cannot be a static thing. Cancer evolves. You have to - the testing has to kind of adapt to the evolution of the cancer. I think the newer sciences, newer tests, newer diagostics is really more reflective of the evolution of cancer, more adaptive to the evolution of cancer and provide the tools to the oncologist, you know, that reflects the changes that happen. That's how the outcomes are better.

Amar Drawid (23:36)

Yeah. So this accords to where you described as the clinical diagnostic. So it's a clear lab model. Can you talk a bit about that? How did you get certified and what would that entail?

Mohan Uttarwar (23:48)

Yeah, good question. There are two ways a diagnostic company can offer the new innovation. More traditional way is basically your invention, you go through the IP protection, and you go through regulatory pathways, which is the 510K for an FDA clearance - a predicative device, some similar test that has already been approved by FDA and you establish that your test is as good if not better. You do that. Now, that takes a long time, two, four years and many tens of millions of dollars before you see your first revenues, etc. The other way is a provision called LDT, lab developed test. So if you have a lab that is CLIA and CAP certified, CLIA is a regulatory body that does the inspection of the labs, ensuring that they follow proper protocols. It is run by a very qualified board certified pathologist. And if you establish and prove that you have developed a test that has a good science backing it up, good publication, you have done a good scientific experiments, quality control and all of that stuff, then on a limited basis for a limited target, you could offer this lab. So, we have adopted a two-prong approach, a two-phase strategy. We have a CLIA CAP certified lab in Foster City here in Bay Area where we could take the samples from the patients. We process the sample and produce the results and the reports and give it back to the oncologist based on which they can basically take the actions. Our initial focus is not commercial diagnostics. Our initial focus is to provide these services to pharma and biotech companies that are doing clinical studies, clinical trials. Pharma companies are always pushing the envelope. They want newer technology. They want new science to work. And so it's a shorter path. Helping them accelerate their translation research, their clinical trials, gives us a shorter path to revenue and gives us an add-on confidence that our test now then can become a companion diagnostic test and eventually a commercial diagnostic test.

Amar Drawid (26:29)

Okay. And so tell us about the information that you provide to clinicians or to the clinical trial coordinators, right? Is that about, okay, well, there's these mutations or like what kind of information are you providing to them?

Mohan Uttarwar (26:45)

Our OncoInsytes , which is the name of our assay, is an LDT. So we get two tubes of 10 ml blood each. We provide a collection kit. They are available at the doctor's office. A phlebotomist goes with the patient, we draw the sample and those samples come to us. It's a one day turnaround time. It might take two days depending on the location, etc., and then we do the processing of these samples. So what do we do? It's a two track. The first track is we extract the DNA from the blood sample. And we have developed part of OncoIncytes is a ctDNA section of the test where we have developed a very novel 1080 gene panel that works on the liquid biopsy, produces the results, tells, what are the genes, what are the mutations, you know, indels, fusions, very comprehensive stuff that we provide. It also provides the meaningful interpretation, not just the analysis of what genes and mutations are present, but we have created a backend informatics, a comprehensive knowledge base, which allows us to provide actionable reporting. And so we characterize based on NCCN guidelines what is the level one evidence, level two evidence, level three evidence. So very comprehensive stuff that has the actionability because of the presence of these genes or these mutations or these translocations or these things, we are able to say that most likely this is the recommendation of these drugs will work, these drugs won't work etc. It's a very actionable report that oncologists can use it as a reference. Ultimate call is made by the oncologist. We only analyze and interpret and present the data. Based on that data oncologist will make a call and do the stuff. So the owners, that responsibility is with the oncologist. We are merely the tools to provide the information to the oncologist. The second tube, sorry, please go ahead. So this is the DNA side of the story. The second tube then we extract, we capture the circulating tumor cells. And then we extract the DNA and the RNA and the proteins. And then we run our single cell assay and get the full analysis of what are the DNAs on each single cell. And usually a 10 ml blood will give us somewhere between 5 to 15 circulating tumor cells. That's one in a billion, right? And so we are now honing around somewhere 10 cells, right? So if we get 10 cells, each single cell, okay, we do the whole genome, the whole transcriptome and a targeted proteome, some 20 proteins. And we provide a very comprehensive report of what genes, what mutations, what translocations, what fusions, what proteins, all of that stuff. Now, this in conjunction with the ctDNA, our OncoInsytes, we are not saying CTC is better than ctDNA or ctDNA is better than CTCs. What we are saying is that when you combine the two and give an integrated report that is much better than any individual technology. Historically, ctDNA or Selfie DNA based tests have shown that 18 to 19 % of the time, you have NMDs, no mutation detected. So even if the best companies, the Guardant, the Natera, the Foundation, the Tempests of the world, this is an industry average. So when you combine that with the CTC together, that thing, the sensitivity goes from 70, 80% to high 90s. Because what is found in ctDNA or what is missed in ctDNA, CTCs capture it.

Amar Drawid (31:20)

Yes. Usually, we're trying to do this multi-omics, right? Because you have different parts of the overall cellular capturing, but now you're adding another very new angle on top of the multi-omics. You're adding the CTC angle as well. Okay. Yeah, that's great. And so this rich information that you're providing. So let's talk about both settings, right? Like the one is more like the commercial setting and then the other one is in the clinical trial setting. In the clinical trial setting, there's a lot going on right now. So based on this, what kind of decisions can be made about the clinical trial? Because this patient is there to get a specific therapy. So now you come up with this. Now what changes? Because either the patient is taking that therapy or they're not, right? So how does this...

Mohan Uttarwar (32:11)

Very good point. There are two separate tracks here. One is the clinical diagnostics which we are doing it in India. Where the doctor wants to know what is the right therapy for a right patient at the right time point and the right dose. So we provide them a full comprehensive report to help him or her make those decisions. That's one. The second part of that workflow, the clinical workflow is okay, you have given the drug. Now is the drug working? Response monitoring is another aspect of it. And there are two pieces to it. One is the MRD, the minimum residual disease. 95 % of the time you have taken care of, but that little 5%, that becomes a problem down the road. How to handle that, right? So MRD and the therapy response monitoring, that's the clinical side. Now you ask me the second question, how is this OncoInsyte assay helpful in the clinical trial setting for the pharma? So I would say three or four key points that we address. First and foremost, when you're doing the screening for patient recruitment, is this the right patient?

Mohan Uttarwar (33:34)

Usually you have inclusion criteria, but most of the inclusion criteria are very high level. Breast cancer patient, women between the age of this and this.

Amar Drawid (33:46)

It's not going at the molecular level at all, right? the cellular. 

Mohan Uttarwar (33:50)

Yeah. So that's why even when you recruit patients, you know, they don't perform very well. Right? So by leveraging assays, tests like OncoIncytes , a molecular level, you have a much better fit. So patient selection is a very interesting area where we can help the clinical trials be successful by recruiting the right patients. Equally important, patient deselection. How not to recruit the wrong patients? Because one bad apple messes up the whole fruit basket. And so again, when you integrate the ctDNA and CTCs, you have a much richer set. So we could basically find better patients, recruit the right patient. Okay. And deselect the wrong patients. So that's one, you know, clear value proposition to the pharma companies that are doing biomarker based chemical trials. Okay. And we know biomarker based trials have at least two times higher probability of success from the FDA clearance. Okay. But typical biomarkers that were based on tissue was very hard, right? Because then you have to have tissue biopsy, you know. So cell biopsy or a liquid biopsy is relatively easy because you just take the blood sample. So it costs less and it's much easier to monitor and manage, right? So that's one.

Amar Drawid (35:25)

Yeah, and it's also faster, most probably.

Mohan Uttarwar (35:28)

Much faster, right, that's one. The second thing is okay you have now recruited the patient, you started, you have dosed the patient right. Is it working or not working? In the today's point, right? Let's say if you're doing immune cancer therapy. Whether my therapy is working or not working, I have to wait for three to four months and I have to go expose the patient to either a CT scan or an MRI or a PET. And then I would know using what they call it as a resist criteria, okay? Whether the tumor is shrinking, whether it is not shrinking or whether it is growing. But look at the timeframe now for every patient under study, I have to wait for three, four months before I know whether my therapy is working or not working. Okay. Let's say you're targeting the drug with herceptin, HER2. Okay. And you've given the drug and now you have to wait. Now, instead of that, you know, three to four months wait, within a matter of couple of weeks, if I could tell you whether the drug is working or not working, wouldn't that be a great value?

Amar Drawid (36:47)

Yeah.

Mohan Uttarwar (36:48)

How do we do today?  By capturing circulating tumor cells. Right. First of all, if the drug is really working, the tumor cells should really go down. Yes. The ctDNA should really go down.  Okay. But you have an 18, 19 % NMDs in ctDNA. Right. So you miss out those 20%. Right. But if I can capture CTCs, right. And if I say, I have CTCs where HER2 is still expressed on the surface of the CTCs. That means my therapy is not quite working. Okay. And then by doing this multiomics analytics, if I could say what is the reason why it is not working. Okay. And again, I am making it up, but there was a marker, let's say EGFR. So if there was an EGFR positive marker, then you know historically that HER2 will not work. You don't have to wait for three, four months, you can make those critical decisions now. And you say based on multiomics profile, okay, what else combination therapy or can we switch over? Can we change something, right? Or can we add something to it, right? You know, a combination therapy to have a resistance prediction, right? If you can predict the resistance, then actionable information will help you add some combo therapy, anticipating the resistance so that the outcomes would be better. So you see the combination of information, multiomics data from a CTCs or a single cell coupled with AI to do the prediction is going to transform this field and make the clinical trials much more successful. Okay. Because you're taking actions proactively. You're not waiting for three months, then realizing that, my drug didn't work. That's a lot of time and loss of money.

Amar Drawid (39:01)

Yeah, and it's also that the tumor has progressed by that time.

Mohan Uttarwar (39:05)

By that time, tumor has progressed, right?

Amar Drawid

And so this early detection of the tumor increasing or tumor changing, right? This will be adding a lot of value. So how are you thinking about how can this be commercialized? We talked about the clinical trial study, but in terms of the clinicians using that in the US and in terms of how you are thinking about commercializing, would there be any-like peer barriers or so. So, what is your plan around that?

Mohan Uttarwar (39:33)

Currently, where we are taking is help the biopharma companies and if they use our assay to accelerate their translation research, then one path would be this assay becomes a companion diagnostics. That with that drug, right? So that's one path we are pursuing. Parallel we have initiated a number of chemical studies, specific utilities, okay? And once we get the 510K , for instance,  then we'll do the MolDX route to get the reimbursement, right. Once we get the reimbursement, then we'll make this commercially available. Okay. And we will, we have two choices. Either we build our own, you know, sales force and the whole operation, or we partner with larger established labs who already have the partnerships in place. Okay, and currently what our interest is, our focus is going to be we are the R &D. We can come up with the new assays and our intent is to leverage strategic partnerships for commercialization of our assays. You know, in the commercial setting, we'll probably strategically partner with other larger lab setups.

Amar Drawid (40:47)

Yes, that makes total sense. in terms of like we talked about the fantastic science and technology around it. How do you measure the sensitivity and is there like a lot of variation? Can you talk a bit about that?

Mohan Uttarwar (41:04)

We go through what we call the analytical validation study, okay, where the sensitivity, the specificity, the repeatability, all those factors are well covered. We have on our team member, our VP of, you know, clinical development comes with years of experience doing it with the drug companies. So very regimented, very strict, very stringent, you know, criteria that we have brought into our practice. So we do the analytical validation, then we do the clinical validation before the assay is ready for putting it into the production stuff, right, where we do that. We also do it independently with third party, independent labs. So we were very fortunate to have a collaborator like the University of Augusta, Dr. Kohle, who has been doing these kinds of stuff for companies such as Agilent, Illumina and many other well established companies have taken their help to do the analytical validation. We did one study where we compared our assay with an FDA cleared assay. It's called PGDX, the company which has been acquired by LabCorp. It's one of the very popular, successful, well-established assays. I'm very happy to report to you that we showed 99.8 % equivalency, equivalent to an FDA-cleared assay, done completely independently at a lab which is the University of Augusta. That paper will be published very soon. Manuscript is ready. We're working through the final details. That gives us the confidence that independent lab was able to conduct an independent study with an FDA cleared assay and we showed substantial equivalency. So that becomes interesting.

Amar Drawid (43:04)

That's amazing. Congratulations on that.

Mohan Uttarwar (43:07)

Thank you.

Amar Drawid (43:08)

And so now as we talked about, you know, talked about this third generation, right? Where is this field going? Like let's say three, four, five years later, you're, the ongoing, so that will be on the market. What will be next? Like where is this field going? What do you see as  the next, like the fourth generation in this area?

Mohan Uttarwar (43:29)

Great question and that's the reason why we are excited. Our mission is to democratize precision oncology, making it actionable, making it accessible, so easily accessible across the country and around the world and making it affordable. So that's our vision, that's our mission. And we believe that cell biopsy coupled with AI is the transformer. Okay. Our ultimate goal is  can this be a simple assay with a simple blood draw, be able to detect way early and I wouldn't say displace completely, but significantly reduce the need to wait for three, four months. Okay. And look at the sensitivity of CT scan. Unless the secondary tumor grows to 9 to 10 millimeter, you can't detect it. A 9 millimeter tumor means billions of cells. And here I am looking at single cell. So if we could utilize good AI to analyze the data and show the equivalence, substantial equivalency, don't have to wait for three, four months, don't have to spend thousands of dollars. It will transform the care. And particularly for survivors, cancer survivors, the people in the remission, where they have to go through once a year, twice a year, once a quarter, and go through the agonies and the pains, spend a lot of money, don't have the sensitivity. So the celebration that my PET is clean is not very long lasting, right? Because it didn't get detected because your tumor wasn't quite nine millimeter. But within a month after you celebrate your cleanliness, you might come back again. Okay. So early prediction of a recurrence, if I could do through cell biopsy, then I think we have conquered the big time. 90 % of the canc er deaths happens because of the recurrence. Right? And recurrence, the root cause of it is the CTC, right? Because of metastasis, right? And if we can capture early and create a sensitive specific assay, which is not, which is minimally invasive, a simple blood drop, I think it will change the field. And that's our mission. And our goal in life is to impact at least a million cancer patients lives across the country and around the world.

Amar Drawid (46:19)

That is fantastic. all our best wishes to you about those. Mohan Uttarwar, co-founder and CEO of 1Cell.AI. Mohan, thank you very much for your time today.

Mohan Uttarwar (46:31)

Thank you very much, Amar and the team.

Daniel Levine (46:33)

Well, that was a great conversation. What did you think? 

Amar Drawid 

It was fascinating to learn about the progress being made in this area of diagnostics, liquid biopsies. So we've been living through this when it was tissue biopsies and then liquid biopsies came in and now it's liquid biopsies, but only single cell and the precision that we can have now from scientific and technological point of view of really focusing on one cell and then really figuring out from there what could be what's happening with the tumor. It's just fascinating how we're rapidly advancing the science and technology, which is really at the forefront of healthcare at this point. It must be 20 years now that liquid biopsies kind of first emerged on the scene. there was a lot of excitement early on about their potential, The impact has been limited so far. To what extent do you think what one cell is doing addresses the existing limitations of liquid biopsies? So they are not only using just the liquid biopsy and then doing some regular experiments. They are doing a lot of the multiomics on this. 

Daniel Levine

He talked about genomics, transcriptomics, proteomics, as well as a lot of stuff about  understanding the morphology of cell. 

Amar Drawid

So they're bringing in a lot of different types of analytics together using AI, using analytics. And also he talked about gene assay, right, over a thousand genes in that. So it's really going deep into quite a bit understanding much more about the cell, much more about the DNA, but also about the proteins. So it provides a lot more information. It's also a good thing about, I mean, what he talked about was the report that they generate, which is not just about, okay, well, this gene here, but then they are using NCCN guidelines to then connect this to the drug therapies. And then really talking about, okay, well, what are really the actionable mutations that we can see because that's the biggest problem, right? Okay. There are some mutations that you can detect in any DNA, but so what? What do you do with that? There is no drug for that. So now detecting these actionable mutations, we're also tying them to the therapeutic options. I think that's going to be great. And then it's also as we get more and therapies, this is going to even get to be more and more, right? Because they're going to be able to say, okay, well, these were mutations that were not necessarily actionable before, but they will be now, right? So I think that's definitely very good. And also, to me, the big thing is to be able to detect early, right? I mean, like three, he talked about three to four months. That's huge amount of time in the cancer patient's life after diagnosis. So getting any of this information before you see that, like the tissue growing or so, think that will be definitely a big step forward in terms of changing the therapies for the patients. And it should result in better lifespan, higher quality of life in the long run for the patients. 

Daniel Levine

Mohan said this combination of applying a multiomics approach and cell analysis to circulating tumor cells wouldn't be possible without AI. Is this a good example for the...potential of AI to change clinical practice and allow us to finally realize the long-held vision of personalized and precision care? 

Amar Drawid

Anytime you're using omics, you have to use AI because the omics data is huge. You talk about a single genome, that's huge. You're about proteomics. You're looking at all the proteins in the cell, right? So you definitely need AI and advanced analytics to process any omics data. And then as you're looking at combining those data, combining different types of omics, but also combining a lot of this cell data, you need the AI to glue all of that together. So yeah, you have to have it. And of course, in diagnostics, I definitely think that AI has a big usage in diagnostics because you're trying to figure out what's happening in this cell and the cell has way too many components that you do need AI to do the analysis for that. 

Daniel Levine

The initial focus of 1Cell.AI is on helping biopharma companies use the technology to improve their drug development efforts and help build a case for its test as a companion diagnostic. What do you think of that strategy? 

Amar Drawid

That's a good strategy. I think they are following both strategies, right? Like going with the 510k route as well as this over here. I would say definitely this gives them a lot of experience about like how it works in the clinical trial setting with how the clinicians will use this information. But also, I would say the big advantage there is to be able to have it as companion diagnostic. If they can get approved as companion diagnostic for any drug, then the test needs to be used, has to be used whenever that drug is to be prescribed. So that, I think, will be fantastic for them commercially. And that also is just going to help in getting the general usage application. I mean, they will be generating a lot of data that will be helping with those applications as well. 

Daniel Levine

As you think about the various stakeholders around clinical practice, providers, payers, regulators, drug companies, and patients, what do you think about the potential for AI to become integrated into care and what will it take to win acceptance for doing so with these different stakeholders? 

Amar Drawid

The way I think is that the physicians and patients are always very interested in understanding what is happening. Regulators, it's going to be more about, well, they're doing the trials. It's about the insurance, right? They have to make the decision to include this in their formulary or so. I want to repeat that. It's about the insurers and whether they are going to reimburse this or not. I would say one of the things is going to be, whenever you talk about AI, how expensive is it? Like when you talk about next generation sequencing, doing a lot of the proteomics analysis, it's going to take some ⁓ money to do all of that. But then what they have to think about is the benefits from here, right? So, at the level for the patients, but also at the population level, is this going to really then help prevent the patient from recurring? Is that going to help? Is it going to help in increasing the quantity of life, but also the quality of life? Is that going to help in maybe less therapies later on because you're able to do, and the wrong therapies later on, right? Because you're detecting very early on what should be the right therapies. I think those are some of the advantages that the payers will take into account and then they will do the analysis. But I would say that it's going to, I mean, there's definitely the potential to have this in clinical practice. I think at some point we have to get there. We have to have these diagnostics, the early diagnostics to be able to detect cancer early on or the changes in cancer. I always think about diagnosis is much better than cure. You're always much better off with diagnosis  than cure. And something like diagnostics like that is going to require AI because there are so many genes that can be potentially involved in cancer that you need to have analytics. It's not going to be just one test that is going to be able to detect what the molecular mutation is. You are going to need analytics and AI to be able to detect holistically for the right therapy. 

Daniel Levine

It was exciting to hear and a great example of how AI can not only change drug development but clinical practice. So Amar, thanks as always. Thank you.

Thanks again to our sponsor, Agilisium Labs. Life Sciences DNA is a bi-monthly podcast produced by the Levine Media Group with production support from Fullview Media. Be sure to follow us on your preferred podcast platform. Music for this podcast is provided courtesy of the Jonah Levine Collective. We'd love to hear from you. Pop us a note at danny at levinemediagroup.com. Life Sciences DNA, I'm Daniel Levine.

Thanks for joining us.