Latest / Zero Shot Podcast DEMO / Revolutionizing Cancer Diagnostics with OneCell.ai

Transcript

Revolutionizing Cancer Diagnostics with OneCell.ai · Zero Shot Podcast DEMO

• 0:03
  Mohan Utawar: Amr, we've got Mohan Utawar on the show today.
• 0:07
  Who is Mohan?
• 0:08
  Mohan is a biotech entrepreneur who is the co -founder and CEO of OneCell .ai.
• 0:14
  He's a repeat founder with deep experience in both diagnostics and therapeutics.
• 0:18
  And as an innovator and investor, he's got more than 30 years of experience in life sciences, precision diagnostics, and healthcare technology.
• 0:26
  And what is OneCell .ai?
• 0:28
  OneCell .ai is a precision oncology company that's using AI and single -cell analytics to help pharmaceutical teams
• 0:36
  accelerate the next generation of cancer diagnostics and therapeutics.
• 0:40
  Its platform provides real -time tumor profile that can help drug developers make appropriate patient selection, accelerate development,
• 0:48
  and provide more nuanced understanding of a patient's response to therapy.
• 0:58
  Interviewer: And what are you hoping to hear from Mohan today?
• 1:02
  I want to understand how OneCell .ai's platform works and the potential for real -time cell profiling to reshape clinical
• 1:10
  trials,
• 1:16
  speakers: OneCell. 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. Mohan emphasizes the importance of personalized therapy in cancer management, highlighting the evolution of precision oncology.
• 1:39
  Mohan Utawar: Thank you, Amur.
• 1:40
  Thank you for inviting me here.
• 1:42
  It's a pleasure and appreciate an opportunity to talk a little bit about the field as well as what we do, why we are
• 1:50
  excited about what we do at OneCell.
• 1:53
  Cancer is a deadly disease, we all know.
• 1:56
  One shoe doesn't fit all.
• 1:59
  So, personalization of therapy is the only way cancer can be managed.
• 2:05
  This whole field has evolved into what they call precision oncology, which refers to personalization.
• 2:13
  Historically, you know, what happens is somehow, you know, you find something, then the doctor tells you go
• 2:21
  into imaging,
• 2:28
  So, when they die, it spits out the DNA.
• 2:33
  That's the circulating DNA or cell -free DNA, okay?
• 2:38
  Subset of the cell -free DNA, right, from the dead cells, you know, if it is a tumor cells, the death of a tumor cells,
• 2:46
  which spits out the DNA, it's called CT DNA, okay?
• 2:51
  Okay.
• 2:52
  Information that you generate from the CT DNA, circulating tumor DNA, is most relevant,
• 2:59
  okay?
• 3:00
  But the problem with the liquid biopsy from the blood -based stuff is, it's very difficult to figure
• 3:08
  out whether it was a cell -free DNA from a normal cell or versus the dead tumor cells,
• 3:21
  Interviewer: right?
• 3:22
  CT DNA, okay.
• 3:24
  And is it, like, in pretty much most cancers, you see that, or, like, some cancers more than the others?
• 3:30
  Yeah.
• 3:30
  Some cancers more than the others, but most cancers would have some DNA, CT DNA, right?
• 3:36
  Okay.
• 3:36
  And we're referring to tumor, I mean, the solid tumors, solid tumors, right?
• 3:41
  Yeah.
• 3:42
  So, tissue biopsy, the next generation was liquid biopsy, and liquid biopsy is referring to CT DNA.
• 3:54
  okay?
• 3:55
  These are essentially DNA fragments coming out of the dead cells,
• 4:02
  okay?
• 4:02
  So, what we are doing now is taking that industry forward to the third generation, okay?
• 4:09
  We call cell biopsy, okay?
• 4:13
  Which is basically a next generation of liquid biopsy, but coming out of the circulating tumor
• 4:20
  cells.
• 4:21
  Now, let me explain the CTC, or circulating tumor cells.
• 4:26
  A gram of tumor, okay, sheds about a million cancer cells in the body,
• 4:33
  in the bloodstreams.
• 4:36
  So, that may seem a lot, but we have trillions of cells in our body.
• 4:40
  So, that means it's one in a billion circulating tumor cells.
• 4:48
  right, you do the radiologic scan, and then radiology finds something, but then the
• 4:56
  pathology is called for, which is the process of taking a biopsy.
• 5:03
  Biopsy is the process of taking a small tissue sample from the area where you suspect that there is cancer,
• 5:10
  and further analyzing it.
• 5:13
  It's sent to the lab, that tissue sample.
• 5:16
  It's called tissue biopsy.
• 5:17
  Tissue sample is sent to the lab.
• 5:19
  The lab does the processing of the sample.
• 5:23
  A glass slide is created,
• 5:24
  speakers: Liquid biopsies are less invasive and provide similar information to tissue biopsies. Circulating tumor cells are crucial for understanding cancer metastasis. Mohan highlights the invasive nature of traditional biopsies and the need for less invasive alternatives.
• 5:43
  Mohan Utawar: okay?
• 5:43
  And the pathologist puts it under the microscope, does the reading, and based on the pattern he or she sees, write a
• 5:51
  report.
• 5:52
  And based on that report, a treatment is given, okay?
• 5:56
  This process is called tissue biopsy, okay?
• 6:00
  Now, tissue is an issue because it's a surgical procedure.
• 6:04
  It's expensive, and it's not an easy thing to do.
• 6:08
  Yeah, and it's invasive, right?
• 6:10
  And it's invasive, right?
• 6:11
  It's invasive.
• 6:12
  It's invasive.
• 6:13
  As the field evolved and the science evolved,
• 6:21
  Interviewer: Okay.
• 6:21
  So, they find the fertile ground.
• 6:24
  Maybe it's lung, maybe it's brain.
• 6:26
  Somewhere they go in settled tune and the secondary tumor grows.
• 6:35
  you know, the information that you get from tissue, similar information, you can get it from blood, liquid,
• 6:43
  okay?
• 6:44
  So that's why Dr.
• 6:46
  Klaus Pantel and Katrina Penebrez in Europe, they coined this term liquid biopsy.
• 6:53
  That means you take a simple blood draw, which is non -invasive or minimally invasive, and then you process it, okay,
• 7:01
  in the lab, and give a similar report.
• 7:04
  So that's the liquid biopsy aspect, right?
• 7:10
  speakers: Mohan highlights the importance of detecting circulating tumor cells. The significance of metastasis in cancer progression.
• 7:20
  Mohan Utawar: Okay.
• 7:21
  Okay.
• 7:22
  So, these are like the fugitives on the run.
• 7:25
  But they are the microcosms of creating secondary tumor cells.
• 7:33
  Okay.
• 7:33
  And that's the root cause.
• 7:36
  Okay.
• 7:37
  So, historically, you know, it was very difficult to find those CTCs, those one in a billion
• 7:44
  circulating tumor cells.
• 7:46
  Okay.
• 7:47
  You know, and so, you know, but now the new science, the groundbreaking science to
• 7:55
  capture that one in a billion circulating tumor cells.
• 7:59
  Okay.
• 8:00
  At a very high degree of sensitivity,
• 8:06
  Interviewer: high degree of precision, the purity of capture.
• 8:10
  Okay.
• 8:11
  And the high degree of simplicity and lower cost.
• 8:15
  Okay.
• 8:16
  So, why you are excited about this whole field is because one cell has this groundbreaking
• 8:23
  science.
• 8:24
  And if I take this three axis, order of magnitude, higher sensitivity,
• 8:32
  speakers: The integration of multi-omics data can lead to better cancer treatment decisions. The groundbreaking advancements in the purity and cost of capturing circulating tumor cells.
• 8:43
  Mohan Utawar: order of magnitude, higher purity of capture, order of magnitude, lower cost, it's a thousand times better price
• 8:51
  performance than anything that existed before.
• 8:59
  speakers: The need for integrating various scientific fields to improve cancer diagnostics.
• 9:05
  Mohan Utawar: multimodal data, multiomics data.
• 9:08
  Cancer is like an elephant and a six blind man touching it and describing what it is.
• 9:15
  A genomics is a science of genetics, right?
• 9:20
  It tells you something very important, but it doesn't give you a full picture.
• 9:25
  Just like a blind person touching, you know, the leg of an elephant.
• 9:30
  If you ask him to describe, you'll say, oh, elephant is like a leg.
• 9:36
  Interviewer: Another blind person touches, you know, let's say the tail and it says, oh, it's like a snake.
• 9:41
  You know, so unfortunately, the genomics, the transcriptomics, the proteomics, the methylomics,
• 9:50
  the metabolomics, these are all fields of science.
• 9:53
  But they are looking at cancer into the silos with their own lenses.
• 9:59
  Unfortunately, cancer, everything, this has to be all integrated.
• 10:04
  Mohan Utawar: So the first generation of precision oncology was driven by tissue biopsy and genomics
• 10:12
  data.
• 10:13
  Companies like Foundation, they did very, very well.
• 10:16
  They established as the leader.
• 10:19
  But tissue is an issue.
• 10:20
  So second generation, the liquid biopsy, right, which is the blood -based stuff, right?
• 10:26
  You know, that came about.
• 10:28
  But what has been not fully equipped is, you know, again, that
• 10:35
  was really focusing again, you know, on the genomics and, you know, the
• 10:42
  transcriptomics.
• 10:43
  But DNAs, they don't, you know, cannot get you the transcriptomics or a little bit, but
• 10:51
  definitely not proteomics.
• 10:53
  Interviewer: You know, so the third generation, which we call the cell biopsy, you know, has the ability to do all three
• 11:01
  pieces together.
• 11:02
  The genomics, the transcriptomics, and the proteomics.
• 11:07
  Now, what happens is multiomics, you know, it's a big data problem.
• 11:12
  Cancer, as much as it's a disease, it's also a data problem.
• 11:17
  And the data is overwhelming.
• 11:19
  So this is where AI comes in handy.
• 11:22
  In analyzing this multidimensional, multimodal, multiomics data, making
• 11:29
  sense out of it,
• 11:31
  Mohan Utawar: okay, correlating the data and predicting the outcome is the key challenge.
• 11:37
  Right?
• 11:38
  So the challenge here I see is that, like, usually, like, when you do, like, genomics, proteomics experiments, right, like, you have, like, a normal tissue, you have
• 11:46
  a disease, tumor tissue, right?
• 11:48
  And you're looking at, like, differences here.
• 11:49
  But then what you're collecting, that has, like, majority of that is already normal anyway.
• 11:56
  So how do you then detect the specific cancer DNA or the cancer proteins from that?
• 12:02
  Because that's a much higher level challenge than what people usually do, right?
• 12:07
  Absolutely.
• 12:07
  So how do you do that with AI?
• 12:10
  Yeah.
• 12:10
  Very, very good point.
• 12:12
  Excellent point.
• 12:13
  In liquid biopsy, I told you it's all about DNA.
• 12:17
  And you have a challenge because you start with a noisy data.
• 12:21
  You don't know whether that DNA came from a normal cell, dead cells, or a circulating tumor.
• 12:28
  I mean, the, the CT DNA, right?
• 12:31
  Yeah.
• 12:31
  And so when you start with the noisy data, again, you have to apply AI and deep analytics, more resources to basically,
• 12:39
  you know, denoise that data.
• 12:42
  Okay.
• 12:42
  The next generation technologies, particularly the one that we have invented, you are already clean,
• 12:50
  you're starting with a cleaner data because you have figured out, we have figured out, capturing that one in a billion circulating
• 12:58
  tumor cells.
• 12:59
  Okay.
• 13:00
  We already know that our starting point is a tumor cell.
• 13:05
  Oh, okay.
• 13:06
  Okay.
• 13:06
  So you're, so you have the technology to then detect the tumor cell specifically.
• 13:12
  Correct.
• 13:13
  Okay.
• 13:13
  Okay.
• 13:13
  Okay.
• 13:14
  Now, does that like, does that depend on like the kind of like surface markers there are on like the tumor cell or?
• 13:21
  Very good point.
• 13:22
  So CTC is not new.
• 13:24
  It's been there 10 years ago.
• 13:26
  Okay.
• 13:28
  Unfortunately, what happened was the sensitivity wasn't there.
• 13:33
  And the endpoint was you capture the circulating tumor cells, you count and report them.
• 13:40
  Okay.
• 13:40
  Okay.
• 13:41
  So the clinical utility was limited.
• 13:45
  You know, it told us that there is a problem.
• 13:48
  Okay.
• 13:49
  Your pet or CT scan or MRI might be
• 13:53
  Interviewer: clean.
• 13:53
  But if you find CTCs, that means, you know, there are some problems somewhere.
• 14:00
  Okay.
• 14:01
  So the scientist would say, oh, we found the problem.
• 14:04
  Okay.
• 14:05
  Okay.
• 14:05
  But the doctors would say, so what?
• 14:07
  My patient is happy because the pet is clean.
• 14:11
  And now you're telling me you found a CTC and you can't tell me what to do about it.
• 14:17
  Okay.
• 14:18
  So it's a very classic dilemma.
• 14:20
  Scientists get excited with what if.
• 14:23
  Okay.
• 14:24
  But the doctors are saying, so what?
• 14:27
  What if I found a CTC and the doctor is saying, so what?
• 14:31
  Unless you tell me, what is the actionability?
• 14:34
  And the science stopped there in the past.
• 14:39
  But today with the advent of next generation sequencing and with AI, okay, we are able to analyze
• 14:47
  the information in that single cell.
• 14:49
  Okay.
• 14:51
  Okay.
• 14:51
  The genomic data, the transcriptomic data, the proteomic data, and tell you and tell the doctor, hey,
• 15:00
  you know, it may be the cell coming from lung.
• 15:03
  You need a pet on basic breast, which was the original stuff, right?
• 15:09
  So without AI analyzing the cell information that is hidden in that circulating tumor cell,
• 15:16
  we would not enable the doctor to take those critical clinical decisions.
• 15:23
  Okay.
• 15:23
  So it's really the integration of information from the biology of the cell, the
• 15:31
  science part, and the AI working on analyzing the genomic data, the transcriptomic data,
• 15:39
  the proteomic data, right?
• 15:41
  So like you said, cell surface marker.
• 15:43
  You know, we know historically that if it's, let's say, HER2 marker on the surface of the cell,
• 15:51
  very likely that cell must be coming from breast cancer site.
• 15:56
  If it's an EGFR, very likely, again, no guarantees, but very likely it's coming from a lung cancer, right?
• 16:05
  Also, the way morphology of those cells look is very unique.
• 16:09
  So we use AI to analyze, you know, how the cell looks, the morphology, you know, the size,
• 16:17
  the shape, the density, the contrast, right?
• 16:21
  So there's a lot of imaging as well, then.
• 16:23
  Image analysis of the cell that we capture, right?
• 16:27
  Okay.
• 16:27
  So in addition to the multiomics, you're also doing the image analytics.
• 16:31
  Absolutely.
• 16:32
  Absolutely.
• 16:32
  Got you.
• 16:32
  Even before we do multiomics, we do the analysis of these cells, right?
• 16:38
  Okay.
• 16:38
  We do the characterization using our AI algorithms.
• 16:42
  And we give enough information.
• 16:45
  Now, one other, you know, fact that is actually very revealing is that many times the CTCs are
• 16:53
  individual CTCs.
• 16:54
  But many times you have this, you know, what we call the combinations, right?
• 17:02
  You know, you have the, you know, group of cells hanging together.
• 17:07
  Okay.
• 17:08
  Now, the risk profile of those patients, prognostic is much, much different.
• 17:13
  It's much higher risk.
• 17:14
  Okay.
• 17:15
  Again, imaging reveals those kind of things.
• 17:19
  Okay.
• 17:20
  You know, so, so there's interesting stuff, right?
• 17:22
  Now, how do we capture these circulating tumor cells, right?
• 17:27
  The CTCs, there are two methods for capturing.
• 17:30
  One is size -based, right?
• 17:32
  So, tumor cells are usually larger in size.
• 17:36
  And there are techniques, you know, micro filtration.
• 17:40
  There are techniques to really do the nano fluidics to capture those cells.
• 17:45
  That's one method.
• 17:47
  The other method is called affinity -based.
• 17:50
  So, tumor cells have certain
• 17:53
  types of proteins on the surface of cells.
• 17:55
  So, Kepcam being one very popular protein that is on all solid tumors that are epithelial in
• 18:03
  nature.
• 18:04
  Okay.
• 18:05
  You know, a transferrin in another protein that is expressed.
• 18:10
  Okay.
• 18:10
  So, what happens in the size -based capture, the cells go through a lot of, you know, pushing
• 18:18
  and pulling.
• 18:19
  Nano fluidics, you know, you're forcing this.
• 18:23
  You know, nano filtration, you're pushing it.
• 18:27
  As is, when cell leaves the tumor, okay, you know, it's in a, it was in a
• 18:35
  very comfortable position sitting in the home.
• 18:38
  And now, it has to fight the whole battle, right?
• 18:42
  Immune system really is, you know, the aggressor which is trying to kill it.
• 18:47
  So, only a few remain.
• 18:51
  They, you know, avoid all the forces against them, you know, and so they are, right?
• 18:56
  But they go through a lot of, you know, fights.
• 18:59
  They go through a lot of transitions, transformation, right?
• 19:02
  Pressure, right?
• 19:03
  So, as a result, size -based capture has not yielded great results.
• 19:09
  Okay.
• 19:10
  Affinity capture, relatively, is less stressful on the cells.
• 19:16
  Okay.
• 19:17
  You know, so that's been historic perspective.
• 19:21
  The groundbreaking science that we have, but again, capture and count doesn't tell you the whole story.
• 19:28
  So, where one cell comes in is a groundbreaking science to isolate the captured
• 19:36
  cell into a live single cell.
• 19:40
  Okay.
• 19:41
  So, traditional circulating tumor cell CTC, the end point was capture and count and give the
• 19:49
  report.
• 19:50
  For us, this is not an end point.
• 19:53
  This is the starting point.
• 19:56
  Okay.
• 19:56
  We begin with this captured and isolated live single cell.
• 20:02
  And we do the imaging modality on it.
• 20:06
  We do the NGS on it.
• 20:08
  We do the multi -omics analysis on it.
• 20:11
  Right?
• 20:12
  And so, we have a much deeper insights that enable the doctors to say what's really going on.
• 20:20
  Is the therapy working?
• 20:22
  If it is working, why it's working?
• 20:25
  If it is not working, why it is not working?
• 20:29
  And what could you do potentially to change the course of the therapy?
• 20:33
  Can we add, you know, can we increase the dose?
• 20:38
  Can we add the combination therapy?
• 20:41
  Can we change something?
• 20:42
  Or if nothing, if it is working, can I reduce the dose level?
• 20:47
  Can I give those chemo holidays?
• 20:49
  Can I, you know, do the de -escalation?
• 20:52
  Right?
• 20:53
  So, all these questions are unanswered in the minds of the oncologist.
• 20:59
  Okay?
• 21:00
  We provide AI assistant to the oncologist.
• 21:04
  Okay?
• 21:05
  Based on this scientific data that is presented, multi -omics, you know, data that is presented for a given patient
• 21:13
  at a given time point, to be able to provide them meaningful, actionable information
• 21:21
  so that they change the course of the treatment.
• 21:25
  Personalize the treatment for a given patient, which will improve the outcome.
• 21:29
  Yes.
• 21:30
  And cancer sometimes changes as well, right?
• 21:32
  So, you have the mutations, some mutations take over versus the other, right?
• 21:36
  So, in that sense, like, if it is growing, like, you know, you can detect, like, okay, what is the new mutation
• 21:44
  that's coming up, right?
• 21:45
  And then the ecologist can then change the treatment accordingly as well.
• 21:49
  It evolves.
• 21:50
  Okay?
• 21:50
  Yes.
• 21:51
  You know, and so many successful companies, you know, and I'll give you one example, Natera.
• 21:56
  It does the tissue at the baseline, at the starting point.
• 22:01
  It hones in on an information about 16 -gene PAL, and it only monitors those 16 genes
• 22:09
  longitudinally.
• 22:11
  One of the most successful companies, one of the most successful tests.
• 22:15
  But it does not address the evolution of cancer.
• 22:21
  Okay?
• 22:22
  You cannot take a snapshot.
• 22:23
  You know, it's like, you know, I've taken, you know, before leaving my home, going to the office, if I take, let's say, you know, Google Maps,
• 22:32
  right?
• 22:33
  And I take a snapshot, and I start driving, and if there is an accident, and, you know, I have to do the stuff.
• 22:39
  I can't just, you know, it cannot be a static thing.
• 22:45
  Cancer evolves.
• 22:46
  So you have to, the testing has to kind of adapt to the evolution of the cancer, you know.
• 22:53
  And I think the newer sciences, newer tests, newer diagnostics is really more reflective of the evolution
• 23:01
  of cancer, more adaptive to the evolution of cancer, and provide the tools to the oncologist, you know, that
• 23:09
  reflects the changes that happen.
• 23:11
  And that's how the outcomes are better.
• 23:14
  Yeah.
• 23:14
  So this uncoincides, right, what you described as the clinical diagnostics.
• 23:19
  So it's a clear lab model.
• 23:21
  Can you talk a bit about that?
• 23:23
  Sure.
• 23:23
  How did you get, like, certified, and what does that entail?
• 23:26
  Yeah.
• 23:27
  Good question.
• 23:28
  There are two ways a diagnostic company can offer, you know, the new innovation.
• 23:33
  Okay.
• 23:34
  More traditional way is basically, you know, your invention, you know, you go through the
• 23:42
  IP protection, and you go through a regulatory pathways, which is the 510K for an FDA
• 23:50
  clearance, right?
• 23:51
  So you find a predicate device, some similar test that has already been approved by FDA,
• 23:58
  and you establish that your test is as good, if not better, right?
• 24:04
  You know, and you do that.
• 24:06
  Now, that takes a long time, you know, two, four years, and many tens of millions of dollars before you see your
• 24:13
  first, you know, revenues, etc.
• 24:17
  The other way is a provision called LDT, lab developed test.
• 24:25
  So if you have a lab that is CLIA and CAP certified, you know,
• 24:33
  CLIA is a regulatory body, you know, that does the inspection of the labs, ensuring that they follow
• 24:40
  proper protocols.
• 24:41
  It is run by a very qualified, board certified pathologist.
• 24:48
  Okay.
• 24:49
  And if you establish and prove that you have developed a test that has a good science
• 24:57
  backing it up, good publication, you have done a good, you know, scientific experiments, quality control, and all
• 25:05
  of that stuff.
• 25:05
  Then, you know, on a limited basis for a limited target, you could offer this, you know, lab.
• 25:14
  Okay.
• 25:14
  So we have adopted a two -prong approach, a two -phase strategy.
• 25:19
  We have a CLIA CAP certified lab in Foster City here in Bay Area, okay, where we could take the samples
• 25:27
  from the patients.
• 25:28
  We process the sample and produce the results and the reports and give it back to the oncologist
• 25:35
  based on which they can basically, you know, take the actions.
• 25:41
  Our initial focus is not commercial diagnostics.
• 25:45
  Our initial focus is to provide these services to pharma and biotech companies that are doing
• 25:54
  speakers: The future of cancer diagnostics and the role of OneCell. ai in shaping this future.
• 26:02
  clinical studies, clinical trials.
• 26:05
  Okay.
• 26:06
  Okay.
• 26:07
  Okay.
• 26:07
  So, you know, pharma companies are always pushing the envelope.
• 26:11
  They want newer technology.
• 26:12
  They want new science to work.
• 26:14
  Right.
• 26:15
  And so it's a shorter path, helping them accelerate their translation research, their
• 26:23
  clinical trials, gives us a shorter path to revenue and gives us an add -on confidence that our
• 26:30
  test now then can become a companion diagnostic.
• 26:34
  Yes.
• 26:35
  And eventually a commercial diagnostic test.
• 26:38
  Okay.
• 26:39
  Okay.
• 26:40
  And so tell us about, like, the information that you provide to the clinicians or to the clinical trial
• 26:47
  coordinators, right?
• 26:50
  Is that about, okay, well, there's these mutations or, like, what kind of information are you providing to them?
• 26:56
  Our OncoInsight, which is the name of our assay, is an LDT, right?
• 27:01
  So we get two tubes of 10 ml blood each.
• 27:06
  We provide the collection kits.
• 27:09
  They are available at the doctor's office.
• 27:12
  Okay.
• 27:13
  A phlobotomist goes, you know, with the patient.
• 27:15
  We draw the sample and those samples come to us.
• 27:19
  Okay.
• 27:20
  It's a one -day turnaround time.
• 27:23
  It might take two days depending on the location, etc.
• 27:26
  And then we do the processing of these samples, right?
• 27:30
  You know.
• 27:31
  So what do we do?
• 27:32
  It's a two -track.
• 27:33
  You know, the first track is we extract the DNA, you know, from the blood sample.
• 27:38
  And we have developed part of OncoInsights is a CT -DNA section of the test where we have
• 27:46
  developed a very novel 1080 gene panel that works on the liquid biopsy.
• 27:54
  And it produces the results.
• 27:56
  It tells, okay, what are the, you know, what are the genes?
• 27:59
  What are the mutations?
• 28:01
  You know, indels, fusions, very comprehensive stuff that we provide.
• 28:06
  It also provides the meaningful interpretation, not just the analysis of what genes and mutations are
• 28:14
  present.
• 28:15
  But we have created a back -end informatics comprehensive knowledge base.
• 28:21
  Okay.
• 28:22
  Which allows us to provide actionable reporting.
• 28:28
  Okay.
• 28:28
  And so we characterize based on NCCN guidelines.
• 28:33
  Okay.
• 28:34
  That what is the level 1 evidence, level 2 evidence, level 3 evidence.
• 28:38
  Right.
• 28:38
  So very comprehensive stuff that has actionability.
• 28:41
  Because of the presence of these genes or these mutations or these translocations or these things,
• 28:49
  we are able to say that most likely this is the recommendation of these drugs will work, these drugs won't
• 28:57
  work, etc.
• 28:58
  It's a very actionable report that oncologists can use it as a reference.
• 29:04
  Ultimate call is made by the oncologist.
• 29:08
  We only analyze and interpret and present the data.
• 29:13
  Based on that data, oncologists will make a call and do the stuff.
• 29:18
  Right.
• 29:18
  So the onus, that responsibility is with the oncologist.
• 29:22
  We are merely the tools to provide the information to the oncologist.
• 29:26
  The second tube.
• 29:29
  The second tube.
• 29:29
  Sorry.
• 29:29
  Please go ahead.
• 29:30
  Okay.
• 29:31
  So this is the DNA side of the story.
• 29:34
  The second tube then we extract, we capture the circulating tumor cells.
• 29:41
  Okay.
• 29:42
  Okay.
• 29:43
  And then we extract the DNA and the RNA.
• 29:46
  Okay.
• 29:47
  And the proteins.
• 29:48
  And then we run our single cell assay.
• 29:52
  And get the full analysis of what are the DNAs on each single cell.
• 29:57
  And usually a 10 ml blood will give us somewhere between
• 30:04
  The importance of integrating AI into cancer diagnostics to enhance patient care.
• 30:10
  Interviewer: 5 to 15 circulating tumor cells.
• 30:14
  That's 1 in a billion.
• 30:15
  Right.
• 30:16
  And so we are now honing around somewhere 10 cells.
• 30:20
  Right.
• 30:20
  So if we get 10 cells.
• 30:21
  Each single cell.
• 30:24
  Okay.
• 30:25
  We do the whole genome.
• 30:27
  The whole transcriptome.
• 30:29
  And a targeted proteome.
• 30:31
  So about 20 proteins.
• 30:33
  Right.
• 30:33
  And we provide a very comprehensive report of what genes, what mutations,
• 30:42
  what translocation, what fusions, what proteins.
• 30:47
  Right.
• 30:47
  You know, all of that stuff.
• 30:49
  Now, this in conjunction with the ctDNA.
• 30:53
  Right.
• 30:54
  So our Onco insights, we are not saying ctc is better than ctDNA.
• 30:58
  Or ctDNA is better than ctCs.
• 31:01
  What we are saying is that when you combine the two and give an integrated
• 31:08
  report, that is much better than any individual, you know, technology.
• 31:15
  Historically, ctDNA or selfie DNA based tests have shown that 18 to
• 31:23
  19 % of the time you have NMDs, no mutations detected.
• 31:28
  Okay.
• 31:30
  Okay.
• 31:30
  So even if the best companies, the garden, the Natera, the foundation, the tempest of the world, this
• 31:38
  is an industry average.
• 31:40
  Okay.
• 31:40
  So when you combine that with the ctC together, that thing, you know, the sensitivity goes from,
• 31:48
  you know, 70, 80 % to high 90s.
• 31:54
  Oh, wow.
• 31:54
  Okay.
• 31:55
  Because what is found in ctDNA or what is missed in ctDNA, ctCs capture it.
• 32:00
  Yes.
• 32:02
  And this is like more like usually we try and do like, you know, this multi -omics, right?
• 32:07
  Because you have different parts of the overall cell you're capturing.
• 32:13
  But now you're adding another very new angle on top of the multi -omics.
• 32:18
  You're adding the ctc angle as well.
• 32:21
  So, okay.
• 32:22
  Yeah, that's great.
• 32:24
  Right.
• 32:24
  And so this rich information that you're providing.
• 32:28
  So let's talk about like both the settings, right?
• 32:31
  Like the one is a more like the commercial setting.
• 32:33
  And then the other one is in the clinical trial setting.
• 32:36
  I said clinical trial setting, there's a lot going on right now.
• 32:38
  So how like, so based on this, what kind of decisions can be made about the clinical trial, right?
• 32:45
  Because this patient is there to get a specific therapy.
• 32:48
  So now you come up with this.
• 32:50
  So now what changes?
• 32:52
  Because either the patient is taking that therapy or they're not, right?
• 32:54
  So how does this change?
• 32:56
  Very good point.
• 32:57
  There are two separate tracks here, right?
• 32:59
  One is the clinical diagnostics, which we are doing it in India.
• 33:03
  Okay.
• 33:04
  Where the doctor wants to know what is the right therapy for a right patient at the right time point and the right dose.
• 33:12
  Right?
• 33:12
  So we provide them a full comprehensive report to help her make those decisions.
• 33:19
  Okay?
• 33:19
  That's one.
• 33:20
  The second part of that workflow, the clinical workflow is, okay, you have given the drug.
• 33:29
  Okay.
• 33:30
  Now, is the drug working?
• 33:32
  So therapy response monitoring is another aspect of it, right?
• 33:38
  And there are two pieces to it.
• 33:40
  One is the MRD, the minimum residual disease, right?
• 33:44
  95 % of the time you have taken care of.
• 33:47
  But that little 5%, right?
• 33:50
  That becomes a problem down the road, right?
• 33:53
  And so how to handle that, right?
• 33:56
  So MRD and the therapy response monitoring.
• 33:59
  That's the clinical side.
• 34:01
  Now, you ask me the second question.
• 34:03
  How is this OncoInsight assay helpful in the clinical trial setting for the pharma?
• 34:10
  Okay?
• 34:10
  speakers: Mohan reflects on the conversation and the advancements in cancer diagnostics.
• 34:16
  Interviewer: So I would say three or four key points that we address.
• 34:21
  First and foremost, when you are doing the screening for patient recruitment, is this the
• 34:29
  right patient?
• 34:31
  Usually, you have inclusion criteria.
• 34:34
  But most of the inclusion criteria are very high level.
• 34:38
  Yeah.
• 34:38
  Breast cancer patient, women between the age of this and this.
• 34:43
  You know.
• 34:43
  Yeah.
• 34:44
  It's not going at the molecular level at all, right?
• 34:46
  Or the cellular level.
• 34:47
  Yeah.
• 34:48
  Right?
• 34:48
  Yeah.
• 34:48
  So that's why even when you recruit patients, you know, they don't perform very well.
• 34:55
  Right?
• 34:56
  So by leveraging assays, tests like OncoInsights, a molecular level,
• 35:04
  you have a much better fit.
• 35:06
  So patient selection is a very interesting area where we can help the clinical trials be successful by
• 35:13
  recruiting the right patients.
• 35:16
  Equally important, patient deselection.
• 35:21
  Okay?
• 35:21
  How not to recruit the wrong patients?
• 35:25
  Because one bad apple messes up the whole fruit basket.
• 35:30
  Okay?
• 35:31
  Right?
• 35:32
  And so, again, when you integrate the CT DNA and CTCs, you have a much richer set.
• 35:39
  So we could basically find better patients, you know, recruit the right patient, okay?
• 35:47
  And deselect the wrong patients.
• 35:49
  So that's one, you know, clear value proposition to the pharma companies that are doing biomarker -based chemical
• 35:56
  trials.
• 35:57
  Okay?
• 35:58
  And we know biomarker -based trials have at least two times higher probability of success from the
• 36:06
  FDA clearance.
• 36:07
  Okay?
• 36:08
  But typical biomarkers that were based on tissue was very hard, right?
• 36:13
  Because then you have to have tissue biopsy.
• 36:15
  You know, so cell biopsy or a liquid biopsy is relatively easy because you just take the blood sample.
• 36:22
  So it costs less and it's much easier to monitor and manage, right?
• 36:28
  So that's one.
• 36:29
  Yeah.
• 36:29
  And it's also faster most probably, right?
• 36:31
  It's much faster, right?
• 36:33
  Much, much faster, right?
• 36:34
  That's one.
• 36:35
  The second thing is, okay, you have now recruited the patient.
• 36:39
  You started, you have dosed the patient, right?
• 36:44
  Is it working or not working?
• 36:47
  In the today's point, right?
• 36:49
  Let's say if you're doing immunocancer therapy, whether my therapy is working or not working, I have to wait for three to four
• 36:57
  months and I have to go expose the patient to either a CT scan or an MRI or a PET.
• 37:04
  And then I would know using what they call it as a racist criteria, okay, whether the tumor
• 37:12
  is shrinking, whether it is not shrinking or whether it is growing.
• 37:17
  But look at the time frame now for every patient under study.
• 37:22
  I have to wait for three, four months before I know whether my therapy is working or not working, okay?
• 37:29
  Let's say you're targeting the drug with Herceptin, HER2, okay?
• 37:34
  And, you know, you've given the drug and now you have to wait.
• 37:38
  Now, instead of that, you know, three to four months wait, within a matter of couple of weeks,
• 37:45
  okay, if I could tell you whether the drug is working or not working, wouldn't that be a great value?
• 37:53
  Yeah.
• 37:54
  Right?
• 37:55
  How do we do that today?
• 37:57
  Okay.
• 37:58
  By capturing circulating tumor cells, right?
• 38:02
  First of all, if the drug is really working, the tumor cells should really go down.
• 38:06
  Yes.
• 38:07
  The CT DNA should really go down.
• 38:09
  Yes.
• 38:09
  Right?
• 38:10
  Okay.
• 38:11
  But you have an 18 -19 % of NMDs in CT DNA, right?
• 38:16
  So you miss out those 20%, right?
• 38:20
  But if I can capture CTCs, right?
• 38:23
  And if I say, oh, I have CTCs where HER2 is still expressed on the surface of the CTCs,
• 38:31
  that means my therapy is not quite working.
• 38:34
  Okay.
• 38:37
  Okay.
• 38:37
  And then, by doing this multi -omics analytics, if I could say, what is the reason why it is not working?
• 38:45
  Okay.
• 38:46
  And again, I am making it up, but there was a marker, let's say EGFR.
• 38:51
  So if there is an EGFR positive marker, then we know historically that HER2 will not work.
• 39:00
  Okay.
• 39:01
  You know, so you don't have to wait for three, four months.
• 39:05
  You can make those critical decisions now.
• 39:09
  And you say, based on multi -omics profile, okay, what ails combination therapy?
• 39:15
  Or can we switch over?
• 39:16
  Can we change something?
• 39:18
  Right?
• 39:18
  Or can we add something to it?
• 39:21
  Right?
• 39:22
  You know, a combination therapy to have a resistance prediction.
• 39:26
  Right?
• 39:27
  If you can predict the resistance, then actionable information will help you add some combo therapy,
• 39:34
  okay, anticipating the resistance, so that the outcomes would be better.
• 39:40
  So, you see, the combination of information, multi -omics data from a CTCs or a single cell,
• 39:48
  coupled with AI to do the prediction, is going to transform this field and make the
• 39:56
  clinical trials much more successful.
• 40:00
  Okay?
• 40:01
  Because you are taking actions proactively.
• 40:03
  You are not waiting for three months, then realizing that, oh, my drug didn't work.
• 40:08
  Okay.
• 40:09
  That's a loss of time and loss of money.
• 40:13
  Yeah.
• 40:13
  And it's also, the tumor has progressed by that time, right?
• 40:16
  By that time, tumor has progressed.
• 40:18
  Right?
• 40:19
  Yeah.
• 40:19
  And so, you're, like, this early detection of, like, the tumor increasing or tumor changing, right?
• 40:25
  So, this is, yeah, this is, I mean, this will be adding a lot of value.
• 40:29
  So, how are you thinking about, like, how can this be commercialized?
• 40:34
  Like, we talked about the clinical trial study.
• 40:36
  But in terms of, like, the clinicians using that in the U .S.
• 40:40
  And in terms of how you are thinking about commercializing, would there be any, like, pair barriers or so?
• 40:47
  So, what is your plan around that?
• 40:49
  Right.
• 40:49
  Currently, the way we are taking is help the biopharma companies.
• 40:54
  And if they use our assay to accelerate their translation research, then one path would be this assay becomes a companion
• 41:02
  diagnostics.
• 41:04
  So, that, with that, right?
• 41:06
  So, that's one path we are pursuing.
• 41:07
  Okay.
• 41:08
  Parallelly, we have initiated a number of clinical studies, you know, specific utilities.
• 41:15
  Okay?
• 41:15
  Okay.
• 41:16
  And once we get the 510ks, for instance, right, then we'll do the MALDX route.
• 41:23
  Okay.
• 41:24
  To get the reimbursement, right?
• 41:26
  Once we get the reimbursement, then we'll make this commercially available.
• 41:32
  Okay.
• 41:33
  And we will, we have two choices.
• 41:35
  Either we build our own, you know, Salesforce and the whole operation.
• 41:39
  Or we partner with larger established labs who already have the partnerships in place.
• 41:46
  Okay.
• 41:47
  And currently, what our interest is, our focus is going to be, we are the R &D.
• 41:53
  We can come up with the new assets.
• 41:55
  And we, we, our intent is to leverage strategic partnerships for commercialization of our assets.
• 42:04
  You know, in the commercial setting, we will probably strategically partner with other larger lab setters.
• 42:10
  Yes.
• 42:11
  That, that makes total sense.
• 42:12
  And now, in terms of, like, we, we talked about the, the, the fantastic science and, and technology around it.
• 42:18
  So, how, like, how do you measure the sensitivity?
• 42:22
  And, and is there, like, a lot of variation?
• 42:24
  Like, how have you, can you talk a bit about that?
• 42:27
  We go through what we call the analytical validation study.
• 42:32
  Okay.
• 42:33
  Where the sensitivity, the specificity, the repeatability, all those factors are well covered.
• 42:41
  Okay.
• 42:41
  We have on our team member, our VP of, you know, clinical development,
• 42:48
  comes with years of experience doing it with the drug companies.
• 42:54
  So, very, very regimented, very strict, very stringent, you know, criterias that we have brought into
• 43:01
  our practice.
• 43:02
  So, we do the analytical validation, then we do the clinical validation before the assay is ready for putting it
• 43:10
  into the, or shrink stuff, right, where we do that.
• 43:13
  We also do it independently with third party, independent labs.
• 43:18
  So, we were very fortunate to have a collaborator like the University of Augusta, Dr.
• 43:25
  Kohli, who has been doing this kind of stuff for companies such as Agilent, Illumina,
• 43:32
  and many other well -established companies have, you know, taken their help to do the analytical validation.
• 43:41
  We did one study where we compared our assay with an FDA -cleared assay, you know,
• 43:49
  it's called PGDX, the company which has been acquired by LabCorp.
• 43:55
  Okay.
• 43:55
  It's one of the very popular, successful, well -established assay.
• 43:59
  And I'm very happy to report to you that we showed 99 .8 % equivalency, you
• 44:07
  know, equivalent to an FDA -cleared assay done completely independently, you know, at a lab, which is the
• 44:15
  University of Augusta.
• 44:16
  And that paper will be published very soon.
• 44:20
  Manuscript is ready.
• 44:21
  We're working through the final details.
• 44:23
  But that gives us the confidence that independent lab was able to conduct an independent study with an FDA
• 44:31
  -cleared assay and we show a substantial equivalency.
• 44:36
  You know, so that becomes interesting.
• 44:38
  That's amazing.
• 44:39
  Congratulations on that.
• 44:41
  Thank you.
• 44:42
  Okay.
• 44:43
  And so now, as we talked about, you know, you talked about this third generation, right?
• 44:48
  Where is this field going?
• 44:50
  Like, let's say three, four, five years later, you're, yeah, on Queen's side, that will be on
• 44:58
  the market.
• 44:59
  What will be next?
• 45:00
  Like, where is this field going?
• 45:01
  What do you see as, like, the next, like, the fourth generation in this area?
• 45:05
  Great question.
• 45:06
  And that's the reason why we are excited.
• 45:08
  I have, our mission is to democratize precision oncology, making it actionable, making it accessible,
• 45:16
  so easily accessible across the country and around the world, and making it affordable.
• 45:23
  Okay.
• 45:24
  So, that's our vision.
• 45:26
  That's our mission.
• 45:27
  And we believe that cell biopsy coupled with AI is the transformer.
• 45:39
  speakers: Mohan thanks the audience and reflects on the importance of the conversation.
• 45:44
  Thank you very much, Amr and the team.
• 45:48
  Well, that was a great conversation.
• 45:52
  What did you think?
• 45:53
  Yeah, it was fascinating to learn about the progress being done in this area of diagnostics,
• 46:00
  liquid biopsies.
• 46:02
  Right?
• 46:02
  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
• 46:09
  cell.
• 46:10
  And the precision that we can have now from scientific and technology point of view, really focusing on one cell
• 46:17
  and then really figuring out from there what could be the, what's happening with the tumor.
• 46:25
  It's just fascinating how we're rapidly advancing the science and technology and, you know, which is really at the
• 46:33
  forefront of healthcare at this point.
• 46:35
  You know, it must be 20 years now that liquid biopsies kind of first emerged on the scene.
• 46:42
  And there was a lot of excitement early on about their potential, but the impact has been limited so far.
• 46:49
  To what extent do you think what one cell is doing addresses the existing limitations of liquid
• 46:56
  biopsies?
• 46:57
  So they are not only using just the liquid biopsy and then doing some
• 47:04
  regular experiments.
• 47:09
  I mean, they are doing a lot of the multiomics on this.
• 47:11
  So you talked about genomics, transcriptomics, proteomics, as well as a lot of stuff about understanding the morphology of the cell.
• 47:19
  So they're bringing in a lot of different types of analytics together using AI, using analytics.
• 47:27
  So, and there also, he talked about gene assay, right?
• 47:31
  About over a thousand genes in that.
• 47:33
  So it's really going deep into quite a bit of understanding much more about the cell, much more about the
• 47:41
  DNA, but also about the protein.
• 47:43
  So it provides a lot more information.
• 47:46
  It's also, we have to think about, I mean, what he talked about was the report that they generate, which is not just about, okay, well, this gene here and then,
• 47:54
  but then they are using NCCN guidelines to then connect this to the drug therapies.
• 48:00
  And then really talking about, okay, well, what are really the actionable mutations that we can see?
• 48:06
  Because that's the biggest problem, right?
• 48:07
  Okay, there's some mutations that you can detect in any DNA, but so what?
• 48:12
  What do you do with that?
• 48:13
  There is no drug for that, right?
• 48:14
  So now detecting these actionable mutations, but also tying them to the therapeutic options, I think that's going to be great.
• 48:21
  And then it's also, as we get more and more therapies, this is going to even, going to be more, right?
• 48:26
  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?
• 48:32
  So I think that's definitely very good.
• 48:35
  And also, I mean, to me, the big thing is to be able to detect early, right?
• 48:39
  I mean, like three, he talked about three to four months.
• 48:43
  That's a huge amount of time in a cancer patient's life after diagnosis.
• 48:47
  So getting any of this information before you see that, like the tissue growing or so, I think that will be
• 48:54
  definitely a big step forward in terms of changing the therapies for the patients.
• 49:00
  And it should result in a better lifespan, higher quality of life in the long run for the patients.
• 49:06
  Mohan said this combination of applying a multi -omics approach and cell analysis to circulating
• 49:14
  tumor cells wouldn't be possible without AI.
• 49:18
  Is this a good example for the potential of AI to change clinical practice and allow us to finally
• 49:25
  realize a long -held vision of personalized and precision care?
• 49:29
  I mean, anytime you're using omics, you have to use AI because the omics data is huge.
• 49:35
  You talk about a single genome, that's huge.
• 49:38
  You're talking about proteomics.
• 49:40
  You know, you're looking at like all the proteins in the cell, right?
• 49:42
  So
• 49:44
  definitely need AI and advanced analytics to process any omics data.
• 49:50
  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
• 49:58
  AI to glue all of that together.
• 50:01
  So, yeah, you have to have it.
• 50:03
  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
• 50:11
  in this cell, and the cell has way too many components that you do need AI to do the analysis for that.
• 50:19
  The initial focus of one cell is on helping biopharm companies use the technology to improve their drug development
• 50:27
  efforts and help build a case for its test as a companion diagnostic.
• 50:32
  What do you think of that strategy?
• 50:34
  It's a good strategy.
• 50:35
  I think they are following both strategies, right, like going with the 510K route as well as this.
• 50:42
  But here, I would say definitely this gives them a lot of experience about like how it works
• 50:50
  in the clinical trial setting with how the clinicians will use this information.
• 50:54
  But also the big, I would say the big advantage there is to be able to have it as companion diagnostic.
• 51:00
  So, if they can get approved as companion diagnostic for any drug, then the test needs to be used, has to be used
• 51:08
  whenever that drug is to be prescribed, right?
• 51:13
  So, that I think will be fantastic for them commercially.
• 51:17
  And that also is just going to help in getting the general usage application.
• 51:23
  I mean, they will be generating a lot of data that will be helping with those applications as well.
• 51:30
  As you think about the various stakeholders around clinical practice, providers, payers, regulators,
• 51:38
  drug companies, and patients, what do you think about the potential for AI to become