Lantern Pharma Inc. (LTRN) Q2 2020 Earnings Report, Transcript and Summary

Good day, and welcome to Lantern Pharma's Second Quarter 2020 Earnings Conference Call. [Operator Instructions] I would now like to introduce your host for the conference call, Director of Investor Relations at Lantern Pharma, Marek Ciszewski. Please go ahead.

Thank you, Ashley, and thank you all for joining us for Lantern Pharma's Second Quarter 2020 Conference Call, our first as a publicly traded company. Our Q2 financial results and earnings press release was issued this morning and can be downloaded or viewed from the Investors section of our website. Also on this page, you will be able to find a slide deck with other financial and operational highlights that will be discussed on today's call. On the call today are Panna Sharma, Lantern's President and CEO; and David Margrave, Lantern's CFO. Following the safe harbor statement, Panna will provide an overview of our business, after which David will share our quarterly financial results. Panna will then offer concluding comments, after which we will open this call for questions. I would also like to remind everyone that our management will be making remarks and statements about future expectations, plans and prospects that constitute forward-looking statements for purposes of the safe harbor provisions under the Private Securities Litigation Reform Act of 1995. Lantern Pharma cautions that these forward-looking statements are subject to risks and uncertainties that may cause their actual results to differ materially from those indicated, including risks described in the company's filings with the SEC. These will include statements related to the potential advantages and development plans of our AI platform, our strategic plans, and plans to advance our collaborative and internal drug development programs, risk related to the COVID-19 pandemic, our expectations related to the use of our cash and cash equivalents, as well as our future operating expenses. These forward-looking statements reflect our current views about our plans, intentions, expectations, strategies and prospects, which are based on the information currently available to us and on assumptions we have made. Actual results may differ materially from those described in the forward-looking statements and are subject to a variety of assumptions, uncertainties, risks and factors that are beyond our control, including those risks detailed under the caption Risk Factors and Elsewhere in our most recent SEC filings and reports. Any forward-looking statements made on this conference call speak only as of today's date, Thursday, July 30, 2020, and Lantern Pharma does not intend to update any of these forward-looking statements to reflect events or circumstances that occur after today. A webcast replay of the conference call will be available on Lantern Pharma's website at lanternpharma.com. With that, I'd like to turn the call over to President and CEO, Panna Sharma. Please go ahead, Panna.

Thank you, Marek, and good morning to everyone on the call today. Thank you for joining us and taking the time to participate in our first quarterly call as a publicly traded company. I appreciate the time you all are taking to listen in to our conference call or our webcast, and I also want to take a moment early on to thank some of our frontline service workers, essential service and care staff, and of course, everyone in our health care and hospital systems. I know this is a particularly challenging time for many of us, especially as the global numbers for COVID have reached over 15 million. And I'm fully confident though that we'll be able to collaborate to conquer COVID-19, and also the multitude of issues it has exacerbated in our economy and society. Given all that though, today, we are experiencing and living in the beginnings of a golden age of artificial intelligence, an era where the availability of relevant data, computing power, cloud resources, on-demand sequencing, talent and the acceleration of AI and large-scale data analytics and algorithms, along with economic and investor demands have aligned to make large, data-driven, highly-responsive, machine-leveraged approaches to solving complex problems of reality. Every industry in almost every profession is experiencing the changes and benefits of this transformation. Drug development and drug discovery is one of the industry segments that is still in the early phases of this approach, and has the potential to be one of the largest manufacturers of this golden age of AI, as this approach can be used to massively increase the productivity of our efforts while significantly reducing the costs and risk in oncology drug development. Lantern is at the forefront of this model of AI-driven transformation in the area of targeted oncology drug development, which we believe will have the potential to yield improved outcomes for cancer patients globally. Our business model at Lantern is to leverage the power and potential of artificial intelligence to help us both rescue and develop drug candidates. We have 3 drug candidates in our portfolio today. And also, we are identifying new potential drug candidates or combination therapies that we can pursue as potential drugs that can be rescued and developed using our data-driven approach. In addition, the core RADR engine is able to help generate a very robust biomarker or genomic signature that can eventually be used as a companion diagnostic to help enroll, stratify and select patients that have the greatest potential to benefit from our therapy, both during late-stage clinical trials and eventually as a commercial diagnostic. We believe that by combining these leading AI and genomic capabilities, along with our highly experienced senior leadership team, all of whom have been focused purely in oncology for an average of 15-plus years, gives our company a very unique position to transform the cancer drug development process. It's an area that we all at Lantern feel very passionately about. Our team is half cancer researchers and biologists and half data scientists and AI professionals. It's a combination that we believe is uniquely assembled to solve the interdisciplinary problems of data-driven cancer drug therapy development. Shortly after our IPO closed on June 15, where we raised 26.3 million, we announced that our proprietary AI platform for precision oncology drug development, RADR, surpassed 450 million data points. That was roughly 6 months ahead of our previous plans. We've now crossed over 500 million and expect to cross the 1 billion mark in the next few quarters. Our current roadmap has us reaching 3 to -- over 3 billion on our current trajectory. All of this data is curated specifically for oncology drug development and drug response prediction. This data comes from a variety of sources. In the slides that were distributed earlier this morning and are available on our website, we detailed some of the sources. But these include open-source scientific and clinical data sets that get normalized and cleaned, data that we create and collaborative efforts with our research partners to look at drug sensitivity, to look at the genomics of cancer, to look at sequencing response. And then also our own proprietary studies from sequencing campaigns, drug sensitivity studies, cell assays and also from trials that we are pursuing. And finally, this data also comes from historical studies and trials in the relevant compounds or drug classes of interest to us. This can come again from a variety of sources, both from publications, but also from the companies from which we buy or acquire the therapeutic. It is important to note that nearly 2 years ago when I first joined the company, we were just approaching about 10 million data points, all from open source and only covering a handful of drug classes. Today, our platform has data spanning over 144 drug tumor interactions across over 95% of the known, approved compounds in oncology and has been significantly enriched in several areas where we are pursuing our own therapeutic development. Our team constantly seeks out experienced industry partners, top-notch collaborators that can help us further develop our AI platform, our models and further develop and validate our approaches and algorithms. These approaches and algorithms are critical since they provide the insight to the biomarker signature and insight that guides the accelerated drug development process that our company undertakes. Our goal today is to add an additional oncology development program each year through a partnership, collaboration or in-licensing of an additional compound. We believe that this constant, disciplined cycle of identifying, securing and developing a potential targeted therapy can create meaningful value for our investors while exploiting the full potential of our growing AI platform. Our pipeline today is small oncology -- small molecule oncology assets, includes new compounds that we have identified through our biomarker discovery efforts, as well as 2 compounds with extensive clinical experience that we acquired from after previous owners had abandoned development efforts following Phase III failures. Our RADR AI platform underpins all of these efforts. And as the quantity and quality of our AI data and algorithms grow, we are confident that so too will the value of our transformative business model. This data-driven, genomically-targeted and biomarker-guided approach allows us to pursue a transformational drug development strategy that identifies, rescues or develops drug candidates that we believe can be done at a fraction of the time and cost associated with traditional cancer drug development. Importantly, 2 of the drug candidates we are developing and that are in clinical stages have extensive clinical histories that we can leverage. These include data in safety, tolerability, history tolerability in patients, history of efficacy in certain patient groups and, of course, data from clinical trials. Unfortunately, these drugs did not meet the primary endpoints being pursued in the Phase III trials, but they did have notable improvement in outcome for certain patients. It was, however, unclear how to stratify for these patients. And in one case, an indication was pursued without full understanding, that a genomically defined subtype of that disease could have been more responsive. Again, these trials were conducted several years back and the knowledge about the genomics of cancer and the computational approaches have advanced significantly. More importantly, there's so much more data out there today that also has changed some of the regulatory environment to allow for these precision and, more importantly, personalized therapeutic trials. At the heart of all these problems, this is really a data analytics effort, the data problem, oftentimes an incomplete and overwhelmingly uncorrelated data sets. This is a perfect problem area for AI and a perfect problem area for cancer biologists that are computationally driven to help guide and supervise the AI. At the core, this is what our company does. Additionally, we are using these drug candidates because they have a substantial body of data that can be mined to illuminate potential mechanisms of action that can aid in efficiently driving our biomarker discovery studies to pinpoint the cancers and the subtypes of patients where these drugs can be best focused. These insights then help guide targeted clinical trials in stratified patient groups that can hopefully demonstrate statistically meaningful results. Our dual approach to both develop de novo biomarker-guided drug candidates and rescue historical drug candidates by leveraging the data sets in our platform along with the continuous advances in genomics, computational biology and cloud computing is emblematic of a new era in drug discovery and development, one that we are very excited to be participating in and pioneering. Leveraging our AI platform-based approach to potentially derisk, focus and accelerate the drug discovery and development process is a central value proposition for investors and one that will help both our current portfolio but also future compounds that we have the opportunity to collaborate or in-license. In this context, we are focused on building a portfolio of targeted potentially high-value oncology drug candidates, each of which has the potential to be a partner for pivotal registration trials in later phases, providing a defined path for potential significant value creation for our investors and more importantly, for cancer patients. Turning to our [ current ] compounds in active development across 4 programs. The first LP-100, the most mature, also known as Irofulven, is in an active Phase II trial that is using a genomic signature, measuring gene expression and a targeted set of genes to guide enrollment in a prostate cancer trial. LP-100 is a drug candidate that exploits cancer cells' deficiency and DNA repair mechanisms, and the trial is being managed and sponsored by our out-licensing partner, Oncology Venture, a European biotech based in Denmark. LP-100 is in an active Phase II trial for metastatic hormone refractory prostate cancer. We expect that results from the ongoing Phase II trial will be available for us to report in the first half of 2021. LP-300, formerly known as Tavocept, is being prepared to enter a Phase II trial for non-small cell lung cancer in never-smokers, which many researchers today have characterized as a hidden but rising disease. The incidence of lung cancer, and non-small cell lung cancer, in particular, is rising among never-smokers and also is a significant clinical need, especially among women and in certain Asian populations. Our review of the data and literature shows that nearly 20% of the global cases of non-small cell lung cancer, NSCLC, are now occurring in never-smokers. It is important to note that nontobacco-based lung cancer and NSCLC in particular has a very different molecular and mutational profile as compared to lung cancer and smokers. We believe that this was partly one of the reasons that the primary endpoints were not achieved in historical clinical trials. So we are planning on initiating a Phase II clinical trial with key research centers and KOLs to look at this drug in this population as a combination agent with chemotherapy in patients that do not qualify for other targeted therapies or have become unresponsive to prior treatment regimens. It is important to note that based on retrospective analysis from both prior Phase III and Phase II studies, certain subsets of patients, including nonsmokers, showed a significant increase in both progression-free and overall survival. But those trials were not focused on these subsets of patients or indications, and therefore, the drug was not advanced in a more targeted fashion. Today, we have a better appreciation of the genomics of lung cancer, of non-small cell lung cancer, the variety of biological pathways and proteins that are involved in all the subtypes of cancer -- lung cancer. And then we can now devise a biomarker-driven approach that can help stratify these patients into a potentially more responsive and nuanced group. And we believe that would be a statistically meaningful group and more importantly, help these patients survive longer and derive benefit from this therapy. Our third molecule, LP-184, is an active development in 2 programs. LP-184 is a highly potent DNA damaging agent in the acylfulvene class of compounds. And now we believe this works very selectively in certain solid tumors that overexpress PTGR-1 or have a certain genomic profile. And it also works in certain CNS cancers. The first program is focused on site-agnostic solid tumors. So this is based on the tumor occurring anywhere in the body, but as long as it has the genomic profile that matches, so this would be a targeted, genomically-driven drug or biomarker-driven drug, much like many of the new small molecules that have been approved over the last several years. So we're leveraging our RADR AI platform to study and clarify the signature of response prediction across several solid tumors. This is a preclinical program. We have published posters of both ASCO and AACR. These are available on our website, describing some of the signature details and results, and also some of the preliminary studies that show this highly-potent, in fact, nano-molar potency, targeted efficacy in these certain solid tumors. We also have published a signature that we believe correlates with response. LP-184 belongs to the folding class of compounds and has already demonstrated increased plasma stability, reduced total body clearance, significantly longer half-life and potentially greater tumor regression than other known folding based compounds across a number of preclinical studies. Importantly, LP-184 has demonstrated high nano-molar potency and the ability to cross the blood-brain barrier. This opens up a potentially high value and important opportunity to help patients with certain glioblastomas. Approximately half of all glioblastoma patients today currently fail existing standard of care therapy. We are currently conducting numerous preclinical studies of LP-184 and preparing for launching IND-enabling studies in 2021, which we anticipate will lead to the start of the Phase I/II trial in 2022. Further work on these biomarkers, both in clinical and in preclinical studies, will help establish a genomic signature that may accelerate our time to a clinical trial to also derisk and focus our development efforts and ultimately help guide patient selection and bring this drug where it's needed, which is to patients with certain genomically defined cancers. We believe the market for our drug candidates, LP-100; LP-300; and LP-184 as focused small molecule oncology therapies, could be several billion U.S. dollars per year in the top 10 medicine markets alone. As the studies and trials develop further and get increasingly focused and mature, we will provide updates to investors and to press about these efforts. After completing our IPO, we've also been developing our AI, data science and biology and development teams, but plan on keeping our efforts very focused and leverage partnerships and the high-quality on-demand services from select labs, CROs and CMOs, Establishing and managing these partnerships and networks will be an essential part of our growth model, and we will provide investors updates from time to time on how these efforts are progressing and how they help in our mission of getting the right cancer treatment to the right patients faster and with reduced economic burden and higher investor yield. By bringing together our current portfolio of drug candidates and our RADR AI platform, Lantern provides the potential for multiple shareholder value-enhancing milestones over the coming quarters and years, and also significant upside in potential future deals as a result of our platform-centric approach to identifying and developing new compounds for development. Now I'll hand the call over to our CFO, David Margrave, for a review of our second quarter results. David?

Thank you, Panna, and good morning, everyone. I'd like to welcome all of those that are new to Lantern as investors and also welcome our pre-IPO investors that are listening in to our progress. The second quarter of 2020 was our first quarter as a public company, although the time we were public during the quarter was only for the last 2 weeks. Please bear in mind that we'll be making comparisons year-over-year to the second quarter of 2019, during which time, we were still a private company. During the second quarter of 2020, we reported a net loss of $833,422 versus a net loss of $629,393 in the second quarter of 2019. General and administrative expenses during the quarter increased $408,279 from $268,120 for the 3 months ended June 30, 2019, to $676,399 for the 3 months ended June 30, 2020. The increase was primarily attributable to increases in labor expense and costs associated with transitioning to and becoming a public company. Research and development expenses decreased $204,250 or 57% from $361,273 for the 3 months ended June 30, 2019 to $157,023 for the 3 months ended June 30, 2020. The decrease was primarily attributable to reductions in product candidate manufacturing-related expenses, reflecting completion of process development and scale-up studies conducted in the prior year period. We expect that our research and development expenses will increase as we plan for and commence our clinical trials of LP-300 and LP-184, and as we develop our AI and our cancer biology teams. As of June 30, 2020, we had cash of approximately $23.8 million, driven by the net proceeds of our IPO that closed on June 15, 2020. We issued 1.75 million shares at the IPO at a price of $15 per share. And after underwriting discounts, commissions and other expenses, Lantern netted 23.4 million in proceeds from the IPO. In regards to some of the key housekeeping items about Lantern Pharma, we currently have 7,370,199 shares outstanding on a fully diluted basis inclusive of warrants and options. Included in that total are warrants outstanding to purchase 332,014 shares of common stock, the majority of which are from historical financings as a private company and options outstanding to purchase 820,608 shares of common stock that have been issued to company employees, management and directors. Currently, we have 10 employees distributed across multiple disciplines, including data science and AI, drug discovery and clinical development and finance and administrative. I look forward to your questions and to providing you information on how we are managing our business and financials as we grow our impact on personalizing cancer treatment and transforming the paradigm of drug development. I'll now hand the call back to Panna. Panna?

Thank you, David. I think it would be useful to talk about our future plans in regard to our platform and portfolio, so we can provide some context for investors, especially before we open up for Q&A. So as a summary, our core business model is one that we believe is scalable across many more compounds and that the RADR platform is a foundational element upon which the value of our franchise can continue to be built. We are focusing on several multibillion-dollar therapeutic opportunities in oncology and will continue to remain focused in cancer. We have developed RADR and continue to perpetually refine it as the wealth and quality of our data sets grow. We believe that the power of the platform will be unique. RADR was developed and refined over the last few years and now integrates more than 0.5 billion data points, over 145 drug classes that are immediately relevant for oncology drug development and patient response prediction. We're currently using state-of-the-art convolutional and artificial neural network technology as well as other AI and proprietary machine learning algorithms to identify the best route for development and for disease prediction. By identifying the clinical candidates together with relevant genomic and phenotypic data, we believe our approach will help us design more efficient preclinical studies and more targeted clinical trials, thereby accelerating our drug candidates' time to approval and eventually to patients. We believe that this data-driven, targeted approach has the ability to reduce the cost and time to bring oncology drug candidates to specifically targeted patient groups. Looking forward, there are 4 key areas that we believe are likely to drive enduring value for shareholders. One, our AI platform. RADR is unique, timely and an industry-defining asset and is still rapidly growing. We are focused on having this becoming the largest, AI-enabled oncology drug development platform. Two, our existing portfolio of therapies. Our existing 3 compounds are in various stages of active clinical development and are in areas representative of several billion dollars of global therapy sales, many of which do not have adequate therapeutic options today. Three, future drug development initiatives. As mentioned in the call earlier, we are generating many meaningful and targeted insights into areas where rescue and accelerated development efforts should be used or can be used with certain failed or stalled compounds, and we believe that we can in-license and explore at least one additional opportunity per year. Our potential for -- and fourth, our potential for future collaborations with pharma and biotech partners. Since we've gone public, we've had increased interest from pharma and biotech about our approach and also now have an improved team and infrastructure to pursue many of these joint potential initiatives. If we are able to finalize and collaborate these initiatives with another company, it can drive significant additional financial resources and also potential upside in milestones and economic rights to additional drug programs. As I stated in the beginning of this call, this is really the beginning of the golden age of AI, especially in drug development. We believe that entire industries will be transformed, some more rapidly than others, but they will all be changed by an approach that is increasingly driven by data, near-time analytics and a major compression of the traditional value creation cycle. Massive new value can be created, in our case, for oncology patients and the health care system, as well as those that invest and participate in these efforts. And with that, I'd like to open up the call for questions. Ashley, can you please open the line for questions?

[Operator Instructions] We will take our first question from Kyle Bauser with Colliers Securities.

Maybe I'll just start off with the orphan drug designation for LP-300. I think you already submitted that. Can you just remind us when that took place and kind of when you expect to get an answer and hear back from them?

So we are -- we have applied for orphan drug designation for LP-300 in the never-smoker population. We don't have a time line. We are in active dialogue with the orphan designation group about our approach. And how never-smokers can be defined as a targeted population. So we don't have a time line on that. We are in active dialogue. I think that would definitely help some of the exclusivity in terms of the commercial rights, but we plan on pursuing the target of never-smokers or genomically-defined never-smokers in a trial regardless of the timing on the orphan designation. I think of that largely as kind of a bonus if we can achieve that. And bear in mind that the never-smokers have not ever been defined as a separate and distinct group. So we're working through that as well.

Got it. Okay. That makes sense. And how about for LP-184 for pancreatic and glioblastoma? I think you're going to be applying for the designation there. Any sort of timing segmentation?

Those -- I think those should be relatively much more straightforward since, as you mentioned, Kyle, glioblastoma and pancreatic are already orphan indications so that should be, I think, a lot easier. What we're doing now is compiling some of our preclinical data, and we expect to do at least one of those this year and probably the other one early next year. Those are kind of back-to-back in our queue right now to submit. And then on both of those I mentioned, I think it should be -- those should be much more straightforward since those indications have already been reviewed by the orphan designation groups.

Okay, okay. And can you talk a little bit more about what steps need to take place for you to begin the Phase II LP-300 trial? Just kind of the final remaining things that you need to kind of accomplish before you can initiate that.

Sure. There are 3 things that we plan on achieving with the 4. But one, we have started and we've already issued a press release on which was the GMP manufacturing of the compound. So that's begun. So that's kind of on our list. We believe that will be done in the next several months. The second is the finalization of the signature, which we're actively looking at now, and we should finalize before the close of this year. The third is agreement with sites, and we'll be providing an update to investors on the sites and the KOLs that we're working with. We're in active dialogue with all of them. We probably have 1 lead site, which we're very far along with, but I don't want to steal news from future opportunities. So we'll be talking about that probably in the next 2 -- less than -- probably sometime in late Q3. And so our goal is really to launch the trial by mid-next year. So we think of get everything queued up in the remainder of this year and then Q1 allows to get the sites going and operational and then start enrolling in Q2.

Okay, okay, that's helpful. Yes. And maybe just one last one, if I may. I know the $2 million to $3 million of the recent raise has been kind of earmarked to explore additional in-licensing compounds. And now with over 500 million data points, I imagine RADR's already kicked out quite a few ideas for new assets to in-license. And you mentioned in your remarks that you hope to in-license about 1 asset per year, I think. But do you have a pretty active list of potential compounds that RADR has already kicked out? I'm just kind of curious how many assets you're actively exploring at a given time.

Yes. So that's a great question. It almost seems like at times, that there could be a whole business, but we probably have several compounds that we are very interested in. There are actually 1 or 2 that we're actually doing some testing in. And there are probably over half a dozen that have come to us from biotech and pharma for potential partnership or collaboration or savings or some kind of discussion. And we're in various phases of looking at the data or getting information or having initial calls or assigning the NDAs to get a peek at the data that they have. So the opportunities come to us both ways, both from insights that RADR might generate because we're looking at a certain class of compounds or because we're looking at a certain disease and we come across papers or data or target. And then more importantly, also from inbound, biotechs and pharmas of various sizes and indications that are interested. And we write -- that's definitely an area we can spend a lot more time on. And as you mentioned, now that we're at 0.5 billion data points, and more importantly, looking at more and more cancer categories, we definitely have probably more than another 10 to 12 ideas that are -- that we should be looking at more aggressively. So it's -- this is a great -- it's a great problem to have, but we have to remain focused on advancing our current portfolio at the same time. So with a team of 10, maybe growing to 12 or 15, it's still a lot more than we can handle currently. But I think as we scale up, we'll be selectively picking 1 or 2 choice assets to continue developing future development efforts.

[Operator Instructions] We'll take our next question from John Vandermosten with Zacks.

Panna, David, congratulations on going public last month. Let's start with just a chat about some of the inputs that go into optimizing the target population. You've talked about that pretty generally, but I'm just wondering what specific categories are used to identify a drug that might work in a targeted population.

From the -- I can say each -- basically each drug or opportunity probably starts in different places. Oftentimes, the starting point may be the results of a Phase II or a Phase III trial where efficacy or signal of efficacy was seen in certain patients. But it wasn't seen in enough patients. That's oftentimes a very important starting point. Another important starting point might be where they see a very good signal of efficacy in Phase II, but it's unclear if there's 1 mechanism or multiple mechanisms. Another good signal oftentimes we see is actually from approved drugs. We're actually getting -- we're looking at some improved therapeutics that got approved for a certain indication, and the researchers and company thought that another cancer based on the site of the tumor would be ideal. But for some reason, that mechanism didn't seem to work there, and so it failed in another site. And those are also places that oftentimes we look at. So I think it really depends on the stage of the drug and where it's been pointed. But we really try to start with figuring out, is there a signal that we can determine based on response in a certain group and lack of response or an incomplete response in another group, and that to us is kind of a starting point. And a lot of that data is driven by RNA gene expression data and sometimes also genomic data. So those are the 2 starting points. We then add to that data about drug sensitivity. And then we'll supplement it with specific cell-based assays that look at certain functions or certain end points. And those are typically in proprietary studies that we do with CROs or with collaborators. And so then that also feeds into our data pool. We then -- if we do find these differing RNA signatures or potential RNA signatures, we then conduct proprietary sequencing campaigns either in biopsy that we obtain under IRB or in xenograft models or organoids, sometimes cell lines, but typically higher up in the value chain, to look at -- do we see a potential of RNA signature change and the potential responsive versus nonresponsive group. And again, every cancer is a little bit different, whether there's available off-the-shelf models is always the question, the quality of that model, do we need to create a new model. So each time it's a little bit different, but it really starts on can we get a nuanced understanding of the responder versus nonresponder groups based on biological networks and that network of activity before and after dosing or other events and it could be genomic, could be transcriptomic, could be enzymatic, could be protein-based, all of the above. And in fact, that's a good question. We actually wanted -- a big push for our platform next year is to move more and more into larger immunomic- and antigen-based response identification. So that's an area we have kind of on our checklist to look at and start integrating beyond just RNA.

Okay, great. Good summary. So a lot of your drugs are -- there's a lot of data available for it. Obviously, they've already gone through trials. So how does happening all that previous data affect the trial design going forward in your focus area, in your indication and cost going forward? I mean, obviously, there's a benefit there. What are some of the specific benefits that you're able to get with that historical data available?

Yes. So the historical data, and again, this goes in the data quality measure. I think historical data is a good starting point to understand what issues were looked at by the prior researchers. But it depends on was that data finalized in 2007, 2014, 2018, because the quality of sequencing has changed so much, as you know, John, over the past decade. The machines have gone through multiple generations, the number of studies have gone and increased significantly. So a lot of that gives us an idea, but it doesn't give us a complete answer. And so we try to go back and use that only as a starting point. And oftentimes, these -- there will be targeted biomarker studies or there will be targeted structural studies, there will be targeted binding studies. So all those we take into account, and then we figure out, okay, where are the big holes, were there questions about data quality or data value, were there questions about sequencing depth or sequencing capabilities that we need to redo. And so yes, the historical data is a great starting point. And ultimately, the most important historical data, if we get it, is the response in trials. And we probably like to look at that as closely as possible. And sometimes it's shared, but typically, that involves a lot of later-stage dialogue under NDA to get out that data.

Okay. Helpful. And I want to extend an...

And just to answer the second part of the question. The great thing about using a trial or a drug that had failed or has been abandoned, is that you can save several years of work, 2 to 3 years of work easily, sometimes more because you don't have to go through the IND-enabling and Phase I/II study. So you save millions of dollars and several years. And so we think that is why we like to look at some of those efforts because there's literally thousands of trials that have failed over the last decade, and several hundred of those, we think could be very promising compounds. And we just have to find -- again, this is a real data problem. Where do those compounds work best? And is there a sufficient population that's in need of that? And so that's really what we try to accomplish. And that to us is the data problem. But you don't always have all the data. So we try to replicate that data using proprietary methods, whether it be through collaborators, partnerships, sequencing campaigns, sensitivity studies, cell-based assays that are looking at specific functional aspects that we think are involved in the mechanism. And so those are all things that we try to enrich for. And the more of that data we feed, we can save years or months of effort of traditional bioinformatic analysis or statistical analysis. And we can do some of these things like literally within days instead of months. And so that's why it allows us the platform to ask and answer questions more rapidly, and therefore, guide our work. And so rather than spending several hundred thousand or several million and saying, this doesn't really pan out, we can do it in a much more targeted way. So I think going after a rescue compound, we can save years, and millions of dollars upfront, but then more importantly, the process itself will be more efficient, and we can save millions of dollars as we reenter into pivotal trials.

That's the goal. And just an extension on the orphan topic we were discussing earlier. Because you have these very focused populations and subsets of populations, do you anticipate future products will be in that targeted area? I mean, obviously, there are benefits to having an orphan drug. And it seems like the approach that you're using would identify those kinds of populations more likely. Is that kind of a goal that you see going forward? Or is it a beneficial by-product in some cases like NSCLC.

I think as I mentioned, it's a plus. It's definitely a beneficial by-product. I think by large part, most oncology therapies that are getting approved today, go after narrower and narrower populations that are genomically defined. And if we can get an orphan designation for that genomic definition, that I think increases the value and gives us some additional commercial rights, but it's not necessary, not necessarily required. But I think that is a plus today. We definitely don't need it to move forward, and that's part of the value of having these companion diagnostics, is that you can identify that population in a fairly robust way and that allows you to ensure that you're going to have a higher likelihood of response. So either way, we think populations will be more narrowcast. And that's definitely part of the opportunity with RADR to do that faster and better. But the other opportunity that we're also seeing beyond just the narrow definition is something that we'll be talking about more as the -- during the latter part of this year is combination programs. So many of the cancers develop resistance over time. And one of the biggest things that has come out from all the advances in computational virology -- and by the way, our COVID efforts wouldn't be as advanced as they are today if it weren't for a computational virology. But one of the things that we've learned in virology and antiviral and some immunology is that combination drugs and combinations can be very, very powerful because you can go after multiple modalities and you can go after multiple points where the cancer can evade or evolve to move away from the therapy. And so instead of -- it's almost like a metaphor, right? Instead of just hitting with 1 thing, if you hit something with 2 or 3 things at the same time, the likelihood of it not being able to revive or come back is much higher. So how do we find these combinations and how do we test them? That becomes an even more complex problem than just solving for a single agent. So what -- again, this becomes a data problem, and a testing problem. So part of the value of RADR that we're focusing now, also we're looking at algorithms and we're looking at models where we can actually start doing combinations more with greater precision so that we can suggest combinations to pharma partners, we can look at combinations for our existing drugs or we can find drugs that have failed prior combinations and then reenergize those efforts. So that's an area of functionality that we'll be talking about as the year progresses and definitely into next year with combination programs.

And one last one for me, just on the FDA's openness to allowing an orphan designation. I mean, we may have a specific population that's numerically defined as an orphan indication. But do they push back on that? I mean, I think you have NSCLC that is never-smokers, but I mean, do they allow -- what's the pushback, I guess, that they give, if any, on defining things like that? Because you can identify that, that's a different population, but what's the regulatory agency doing when you present that to them?

We're still in the early phases of that, so I don't know. I mean, I think the pushback is really to clarify how you're -- if it's not already defined, it becomes definitely more challenging. So I think as Kyle earlier pointed out, there are certain areas like glioblastoma [indiscernible] which are very, very clearly have been orphan designated as a result of the -- just the historical data that's collected based on the site of the tumor. And so I think now as they move toward basing an orphan designation based on a signature or based on some kind of other unique thing, that becomes a back and forth, that becomes more of a dialogue to prove to them, this is, in fact, unique population. So that's really the core of it, is proving that it's a unique population. And that, that unique population will have a different response.

[Operator Instructions] It appears that there are no further questions at this time. I'll turn the call back over to the presenters for any closing remarks.

Great, Ashley, thank you for the Q&A. So we look forward to having discussions with many of you, and we hope that you continue to follow and watch Lantern as we progress. And we will be providing periodic updates and press releases about our progress, and we hope to be talking with many of you very soon. Thank you all for joining our first quarterly call.

Thank you. And this does conclude your program. Thank you for your participation. You may disconnect at any time.