We were very excited to establish a scientific advisory board that is joined by experts such as Doctors Mitchel Berger at UCSF, Doctor Lisa DeAngelis at Memorial Sloan Kettering, and Doctors Stuart Grossman and John Laterra at Johns Hopkins, all four of which have deep subject matter expertise, accomplished scientific experts, and leaders in Neuro-Oncology. In fact, two of them are actually lifetime achievement award winners at the Society for Neuro-Oncology, and they're able to now help us shape the development and path for STAR-001. Remind you, Starlight is 100% owned by Lantern. We'll have the potential for this to be a very positive impact on our investors as we monetize this unique asset, the patents, the insights, and its ability to work in certain brain cancers. The dosage and safety data in Phase I Trial will be used to advance the indications for the 1B Phase II Trial, which Lantern, as a wholly owned subsidiary, will sponsor. We think the market potential for both this drug as STAR-001 and as LP-184 will exceed $14 billion, consisting of about $4 billion plus in CNS cancers, both pediatric and adult, and about $9 billion-$10 billion for other solid tumors. We believe this has the potential to be a blockbuster drug across a number of indications. Now, to support a lot of this, we actually were working quite a bit on trying to understand how do we predict the blood-brain barrier permeability. Our team did a fantastic job at our patent pending blood-brain barrier permeability predictive algorithm. It represents what we believe is a computational breakthrough of exceptional significance. With five of the top 11 rankings in the Therapeutic Data Commons Leaderboard and the ability now to be a very high performing algorithm, we can do maybe 100,000 molecules an hour. You know, that translated can mean a million molecules or more in a workday. So we've developed an AI system that outperforms industry standards in terms of accuracy and throughput for CNS drug therapeutic development. This will also be, in fact, one of the first agentic AIs that we make publicly available for drug developers. We're going to open this up and partner this with precision medicine groups to help guide their development and also potentially for therapy selection in patients. We're in fairly advanced discussions now with a number of institutions and a brain tumor group to actually use this algorithm as part of their work. Now, this technological advantage has profound implications for accelerating CNS Drug Discovery, a notoriously challenging domain where over 98% of small molecules fail to effectively penetrate the blood-brain barrier, and where some of the traditional algorithms have been kind of in the two thirds to 70%-75% accuracy. Now we're seeing a whole new generation of algorithms, including ours, which have taken that up into the low to high 90%. This unprecedented accuracy allows us to identify promising CNS penetrant compounds with extraordinary efficiency. I also mentioned ours is also high performing. We have taken some very unique engineering steps to actually decrease the amount of time required. The computational capability does not merely enhance our existing programs. It actually opens up entirely new therapeutic possibilities across multiple neurological indications for not only us, but also for other drug development teams. Now, our AI powered antibody drug conjugate development module also represents a fundamental reinvention of traditionally resource intensive high risk development process. Our AI module for ADC development identified 82 very promising targets and over 290 target indication combinations. Many of these are actually validated because some of them are already in preclinical and clinical trials. This is one of oncology's most rapidly growing therapeutic modalities. The technical implications for this ADC module for using AI is pretty substantial. Traditional ADC development requires a lot of iterative testing of antibodies, nanobodies, any kind of maybe bispecific, and then the linkers and various payloads, and a process that can take years and millions or maybe even tens of millions of dollars just in early stage work. Our computational approach reduces these timelines, we believe, by a third to half, and preclinical costs by even more than half, while simultaneously enhancing the target selection process. This efficiency advantage positions us to rapidly advance multiple ADC candidates with exceptional selectivity profiles and potential for superior therapeutic windows, and enables us to allow others to take advantage of this AI. This will be one of the many AI modules we place into what we call an agentic framework, which is really the kind of the vanguard of AI work today. Once we put it into an agentic framework, we can allow it to be used by collaborators and partners. I'll talk more about this later in today's call. The RADR Platform expansion beyond 100 billion Oncology specific data points represents a computational resource of unprecedented scale and specificity in precision Oncology. The vast repository of molecular, clinical, pharmacological data enables increasingly sophisticated analysis that traditional approaches simply cannot match, but very importantly, do not have the underlying data and curation already that we have done. Now, the technical sophistication of RADR enables multidimensional analysis that identify non-obvious relationships between genomic features, drug responses, and potential combination strategies. This capability has directly enabled our biomarker discovery initiatives, including PTGR1 signature mechanisms, underlying synergistic combinations such as checkpoint inhibitors or spironolactone with 184 or even Rituximab with 284. As we continue to refine the methodologies and feed data from studies back into the platform, RADR evolves from just an analytical platform to a predictive engine capable of identifying promising therapeutic approaches with unprecedented efficiency and precision, and ultimately in the next generation with its own level of automation. Through the integration of advanced AI, computational biology, and precision medicine approaches, we're systematically addressing some of oncology's most challenging domains with an unprecedented level of efficiency and scientific rigor. Our burn rate is a fraction of that of other companies, yet our advancements across multiple molecules, putting them into patients and advancing the platform is something I'm quite excited about. Financially, we closed the year with $24 million in cash, cash equivalents, and marketable securities, which I believe will give us runway to execute in our business this year and take our programs to inflection points with data and outcomes. David Margrave, our CFO, will discuss this in more detail in a moment. Our continued execution across these clinical trials and with our precision oncology programs positions us for multiple value creating milestones throughout this year and with the potential to deliver transformative therapies for patients with limited treatment options. Now I'll turn the call over to David Margrave. We'll talk about our financials and other key metrics. David. Thank you, Panna. And good afternoon, everyone. I'll now share some financial highlights from our fourth quarter and full year ended December 31, 2024. I'll start with a review of the fourth quarter. Our general and administrative expenses were approximately $1.6 million for the fourth quarter of 2024, up from approximately $1.3 million in the prior year period. R&D expenses were approximately $4.3 million for the fourth quarter of 2024, up from approximately $3.6 million in the fourth quarter of 2023. We recorded a net loss of approximately $5.9 million for the fourth quarter of 2024, or $0.54 per share, compared to a net loss of approximately $4.2 million, or $0.39 per share for the fourth quarter of 2023. For the full year of 2024, our R&D expenses were approximately $16.1 million, up from approximately $11.9 million for 2023. This increase was primarily attributable to increases in research studies of approximately $2.95 million relating to the conduct and support of our clinical trials, as well as increases in research and development payroll expenses of approximately $897,000 and increases in consulting expenses of approximately $376,000. Our general and administrative expenses for 2024 were approximately $6.1 million, up slightly from approximately $6 million for 2023. The increase was primarily attributable to increases in other professional fees. Our R&D expenses continue to exceed our G&A expenses by a strong margin, reflecting our focus on advancing our product candidates and pipeline. Net loss for the full year 2024 was approximately $20.8 million, or $1.93 per share, compared to approximately $16 million, or $1.47 per share for 2023. Our loss from operations in the 2024 calendar year was partially offset by interest income and other income net, totaling approximately $1.4 million. Our cash position, which includes cash equivalents and marketable securities, was approximately $24 million as of December 31, 2024. Based on our currently anticipated expenditures and capital commitments, we believe that our existing cash, cash equivalents, and marketable securities as of December 31, 2024, will enable us to fund our operating expenses and capital expenditure requirements for at least 12 months from today's date. We expect that we will need substantial additional funding in the near future, and one of our key objectives for the remainder of 2025 will be to pursue additional funding opportunities. As of December 31, 2024, we had 10,784,725 shares of common stock outstanding, outstanding warrants to purchase 70,000 shares, and outstanding options to purchase 1,245,694 shares. These warrants and options, combined with our outstanding shares of common stock, give us a total fully diluted shares outstanding of approximately 12.1 million shares as of December 31, 2024. Our team continues to be very productive under a hybrid operating model. We currently have 24 employees focused primarily on leading and advancing our research and drug development efforts. I will now turn the call back over to Panna for an update on some of our development programs. Panna. Thank you, David. Our leadership and the innovative use of AI and machine learning, in many ways AI for good, to transform costs and timelines in the development of precision oncology therapies has allowed us to have a pretty exciting pipeline. It's allowed us to bring three molecules to market, with teams, costs, and efficiency that continues to make massive year over year improvements. We have LP-300 in Phase II. We plan on having another readout during the second quarter. We've accelerated enrollment because of our expansion into Japan and Taiwan. Specifically there, the disease occurs in never smokers at about a 2X to 3X higher rate. This is particularly important because we'll also use that to leverage the Phase II data to look at partnerships, perhaps geographic partnerships as well, which we've already begun having conversations with. Our Phase I trials for LP-184 and LP-284, both really potent synthetic lethal agents, one for solid tumors, has advanced to over 50 patients. We expect to enroll about 60 patients. We're getting very close to what we believe will be the completion of the trial. LP-284, slightly different dosing schedule, but similar cohort structure, is a few months behind, and we think we'll be able to have that 30 patients enrolled later this year. All three trials will have data, but very importantly, we also expect to have great ideas on how to pinpoint the use of these molecules in specific therapeutic areas. This is why we have over 11 orphan, rare pediatric, and fast track designations. It's very important to note. For a small company, we have 12 designations across 11 different programs, ATRT having both orphan and rare pediatric. That's really almost, we have for every headcount, we almost have a half a designation. In fact, it's the only molecule that I know that actually has four designations for a rare pediatric. Pinpointing how a molecule will work is really one of the most challenging things. This is really about not only understanding your molecule, but also actually knowing where and how to use it. We've achieved this in a very, very short period of time. Remember, LP-284 did not even exist when we raised money to go public. LP-184 wasn't in the clinic. LP-300 was just beginning to peel the onion in terms of its mechanistic potential. During 2024, we achieved our goal of reaching 100 billion data points, growing that cancer focused data more in one year than we had in the prior three years. More of this data growth and data ingestion campaigns will be automated, freeing up our team to focus on intelligent curation and analysis of data, and also on creating upstream engineered data sets to solve more specific problems. These problems, we think, can start making use of certain types of generative AI, AI that'll transform our analytic capabilities to actually autonomous agents. Today, I'd like to share with you our vision for the next evolution of our RADR Platform, a future where agentic AI and autonomous intelligence dramatically accelerates our ability to transform oncology drug development, not only at Lantern, but also for other drug companies. At Lantern, we've consistently demonstrated how our proprietary platform has revolutionized our approach, but we believe also traditional Oncology Drug Development Paradigms. As we've shared in our previous quarters, our AI-guided approach has enabled us to advance all these candidates into the clinic at a fraction of the traditional costs and actually have more pinpointed and more precise trials. It takes us an average of about $2 million -$2.5 million per program from scratch to get it into a trial, whereas the industry standard is somewhere in the range of $10 million-$15 million. Now we're entering a transformative phase where RADR will leverage the agentic, we're going to start leveraging agentic AI capabilities. Autonomous systems capable of making complex decisions, analyzing intricate biological data sets, and executing sophisticated workflows without constant human supervision. Our enhanced RADR Platform will feature autonomous intelligence and will modularize these into agents. These agents will continuously monitor and integrate real-time data from relevant biomarker and cancer studies and publications, enabling dynamic protocol insight that can be used in real trials and to make precision medicine decisions. They'll autonomously identify potential combination regimens by analyzing billions of unique molecular interactions across multiple therapeutic modalities, similar to our recent significant insights on 184 and checkpoint inhibitors that demonstrate a transformation of an immunologically cold tumor into a hot tumor, but with a totally different level of scale. Imagine being able to do thousands of these molecules in a week. It will also deploy advanced reinforcement learning algorithms that will optimize lead compound selection or elucidate target characterization across for antibody drug conjugate development or peptide or drug-drug conjugate development. Again, we've already identified 82 promising targets and over 290 target indications, many of which are already validated in the clinic from other companies. Now, this next generation of our platform represents a fundamental shift in drug development methodology, moving from human-limited analytics and reactive to proactive continuously self-learning systems capable of identifying non-obvious patterns and opportunities and benchmarking those across multiple therapeutic dimensions. For us, though, it is we have certain dimensions, specifically in oncology or specific in Neuro-Oncology. While our current platform is already proven exceptional with over 100 billion data points oncology-focused, by deploying agentic architecture and interfaces on top of very specific modules, we will have the potential to create systems that reduce key development decision timelines and compress complex data gathering and analytics, creating unprecedented efficiency advantages. Rapid biomarker identification and validation, in our case, PTGR1 and others, autonomous design and optimization of combination regimens, instantaneous evaluation and molecular libraries. The financial implications for this are pretty substantial, potentially reducing preclinical development costs by 60%, 70%, and 80%, while simultaneously increasing successful transition rates in early development and perhaps later development phases. We are strategically positioning our agentic architecture with RADR Platform to not only drive our internal pipeline, but also as a valuable collaborative asset for biopharma partners seeking to overcome drug development bottlenecks. We've had very successful collaborations with Oregon Therapeutics and Actuate Therapeutics, both collaborations where we offer targeted RADR modules for these partners. We believe we'll generate some near-term commercial traction as a result of that. We anticipate launching our first agentic AI around the blood-brain barrier permeability prediction algorithm. That's now being commercialized as a module that will be publicly upcoming, and it'll leverage our unprecedented performance metrics and also have the algorithm hopefully guide actual treatment decisions being made in a number of trials. Additionally, our ADC development module, which has already demonstrated capabilities as compared to traditional approaches, will also become more broadly available later this year, along with another project that will be publicly facing, probably in early summer, called Project Zeta. Now, all three of these will be leveraging agentic architectures, why some wildly very different, but they'll put into the public face the ability to actually start thinking about drug development at a level of scale and data access that's usually unheard of. The golden age of AI in medicine isn't just beginnings. It's accelerating exponentially. By integrating agentic capabilities, we believe our AI RADR will transform from an analytical platform to a true development partner, one that is awake 24 hours a day, one that's capable of operating continuously at a scale that's unprecedented across multiple research dimensions and constantly grows, connecting insights across previously siloed areas of cancer biology and ultimately helping us deliver life-changing therapies to patients faster. We aren't just building better tools. We're actually fundamentally reimagining what's possible in precision oncology. As we continue this journey, our agentic RADR Platform positions us at the forefront of an entirely new paradigm in drug development, one in which AI doesn't merely assist human researchers, but actively participates alongside through autonomous continuous learning and insights that can be tested and recursed back into the system and hopefully deployed into the clinic faster. This golden age is actually accelerating, and it's being driven by large-scale, highly available computing power, incredibly massive data storage, and also great people. At the end of the day, you have to have great imaginations and wonderfully dedicated people, to be able to deliver this, ultimately for patients and to improve human life. We're at levels of quality and data that have never been imagined before. Companies that harness these capabilities are really the future of the tech bio industry, and I believe will become long-term leaders that create massive value for patients and investors. We think, of course, industries go through their cycles and ups and downs, but I've never been more bullish on the potential for AI to really transform and change outcomes for patients. Also, it'll make our medicines faster, cheaper, and with increased precision. I think it'll help us change the direction of R&D productivity and output in the pharma industry. We believe our approach is the future of developing cancer therapies where data can be used to accelerate programs, de-risk identification, identify combinations and patient populations faster, and get life-changing medicines into actual trials. I want to express our deep, my deep gratitude to our team, our partners, our stakeholders for their unwavering support, and especially to our clinical trial sites and to the patients participating in our trials. I think together we're lighting a way towards a brighter future in Oncology and solving real-world problems that enable rapid development of precision therapies that can alter the cost and timelines in drug discovery, and very importantly, place Lantern at the forefront of a new era of unprecedented insights. Now, with that, I'd like to now open the call to any questions or clarifications, but also, as we do so, I'd like to take a quick moment to thank our team for helping us to prepare for these calls and to prepare for our quarterly filings. Again, let's go ahead and take questions from our audience. I ask you to do so in one of two ways. You can type your question directly into the QA tool, or you can click on "Raise the Hand" and speak directly, and we'll try to unmute your line. Thank you. We've got the first question. I'll repeat the question before I answer it. Thank you, John, for your question. The question is from John, "How is the pace and quality of enrollment in Asia compared to the U.S.?" It is about 2-4x faster. They got ramped up, faster. Some sites are slower than others, but in terms of output, just in this past few months, we saw an equal amount of output from Asia as we saw in the U.S. Of course, their timeline from onboarding to first patient was phenomenally faster, and it's just accelerating. I think it'll be 3-4x faster ultimately this year because of Asia. Great question. Next question is from John also. In the ADC REALM, and with help from RADR, what are the opportunities for ADCs that substitute the toxic payload with another immunotherapy? With another, with an immuno, it depends on what kind of immunotherapy, whether it's a modulating agent or a binding. I think doing an antibody conjugate is potentially challenging. If you do it with a small molecule that's an immunomodulating agent, like an IL agent or others, I think, yes, that it's possible. You're going to start seeing many of those. You're going to see the, one of the things that we're actually looking at, it's a great question, John, is actually things that have multiple payloads, so more than one payload. That's actually very exciting. It's a space that, probably, you know, it's not on our plate right now, but I do think that design of multi-payload, multi-payload and bispecifics with multi-payloads is definitely going to be in the future. You may have payloads that are both immunomodulating and also toxic. I think you're going to see a lot of innovation. Now, the challenge is, of course, always then testing those, because right now, one of the most expensive points in testing ADCs is testing them in the non-human primates. How you test the non-human primates for some of these more complex architectures that are being imagined will be something that we got to sort out. Yeah, theoretically, that's definitely doable. It requires a level of precision biology and data collection that is just beginning to happen. That's a perfect area for AI. It's a wonderful question. I'm going to turn it over to Chad. Yeah. Hi, Panna. Thank you. Just wondering for the harmonic update in the later this year, that we expect to get, if you could just set the stage for, you know, where you guys think you're going to be, how much data you think you're going to have, what, what would you look, what would you look for in, in that update? Sir, your question was on harmonic data, correct? Correct. Yeah. We've enrolled a nice chunk of patients in Asia and also in the U.S. in the last few months. We are continuing to see the same kind of trend in terms of the clinical benefit. I think we hope to have a nice chunk of patients that will have multiple scans in terms of, you know, RECIST criteria. I think sometime in mid to late Q2, we'll have the next readout, but the key one will come at 30 events. If we have 30 events, that will probably be closer to the end of the year, and that'll be an important time because then we'll be able to decide, do we take this into a larger, larger trial? It will also give confidence that we'll have data, enough data to partner out the asset. We'll probably do something more near-term to kind of showcase that the trends that we saw in the early cohort are continuing in the existing cohort, which has included a lot of patients from Japan and Taiwan. Okay. If I may, just a follow-up in a different direction on your ADC programs, what should we be looking for next? Obviously, there'll be two things. You know, we've talked about that. We made a conscious effort on this call not to focus on it because we wanted to focus more on the clinical assets and some of the other AI features. We have got some exciting preclinical data that we are validating. We put out some data last year in terms of HER2- low and HER2- medium, but definitely HER2- low expressing cancers where we saw tremendous potency, several fold higher than existing FDA-approved agents, with our cryptophycin-linked ADC that we have designed. We also have another one that is in the Illudin and Acylfulvene family that we are working on, some very exciting new payloads that are super, super potent, you know, 100-500 times more potent than LP-184. We have some targets in mind. We will have more preclinical data as the year progresses. We also will announce a couple of partnerships with groups that are using our ADC AI platform as an analytical tool. Those are the two things to expect. Thank you. We've got a great question from Clay Heighten. Clay asked a question about providing results in LP-184 in Q4, and then it was pushed. When will you provide results? That's a great question on the 184 data, Clay. The 184 data originally was expected in Q4, because we expected to see MTD around dose level 9 or 10. What's mostly changed is that the enrollment has gone to higher dose levels, and that's basically added to the time. The calculations for PK and availability of the drug seem to end up more like rats than dogs. Our thought was, you know, we'll probably end up somewhere in between, but we're definitely much more like rats in terms of the amount of drug that humans can take. That's actually a good thing because we're seeing higher therapeutic, sorry, higher likelihood of having therapeutic doses at these higher cohorts, these double-digit cohorts. We're now in cohort 11- 12, and so each cohort takes about a month. That's exactly why we see that. Nothing other than the dose levels have gone higher, and we haven't seen any significant, serious adverse events, and we're now just beginning to see therapeutic levels of efficacy. That's added to the time. Hopefully that answers your question. Next question is on the dose in cohorts 11 and 12. I believe the dose is 0.61, right? mg? I believe it's 0.61. Clay, I will have to, I'll get back to that. Let me write that down. I'm going to have to look that up on my little board, but I believe it's 0.61 mg per kg, but let's find that out right now. I'm going to, while we look that up, I'm going to take another question, from anonymous attendee. When will we likely see STAR for pediatric? Wonderful question. We're working very closely with the POETIC Consortium. We're very close to getting a protocol that everyone can agree to for pediatric brain cancers. Dr. Marc Chamberlain and Sandra are leading up that efforts to interact with the POETIC Consortium. I think we will probably see that mid to late this year. We do have a protocol that seems to have enough people around the table, and we will be able to then exploit the rare pediatric disease designations and hopefully march towards getting our drug to patients. Part of that also is to have a clear signal in adult gliomas. We think those two factors will be easily checkmarked, and we will then launch into pediatric, of course, all subject to the right approvals. Next question is from Luca. Luca, thank you very much for your question. I will answer it. Says, what is missing to sign deals with other firms to discover new drugs? Yeah, great question. Luca, I, you know, we constantly look for deals. I think if there are deals out there, I think we would love to do it. There's, you know, I think partly is it does take a lot of financial, but really actual people resources. If you want to do this for others, they're going to pay you on an hourly or as a target amount. As a small company, bear in mind, you know, our scientists and data engineers are somewhat limited. And so we have focused on our own pipeline. But yeah, we'd like, we'd love to focus more on other people's pipeline as long as they're willing to pay us for it. I don't think our shareholders want us to do a lot of work unless we get either equity in the drug or get reimbursed significantly. I think, you know, we're happy to have discussions. So yeah, thank you. Great question. I mean, I think if there are, there are definitely conversations we have, they usually tend to break down, really around, you know, are they willing to give us enough equity in the molecule or enough upside to make it worth our while for us to stop working on our programs? One of the things that we're doing now is using agentic AI architecture to take some of these more simple initial analytic modules and put them out to the public. That is something that we plan on doing with three or four of these modules, the blood-brain barrier module, the ADC module, or aspects of the ADC module, some of the modules around differential gene expression and transcriptomic analysis, and a very exciting project codenamed Zeta that we'll be talking more about in the next 45-60 days. Thank you. Now, great question from Michael Montagas. Yeah, we've, Michael asked the question, have we reached out to Amazon? Yeah, we've had a lot of discussions with Amazon. Unfortunately, probably not at the right levels, but we've done a lot of education of Amazon about how big pharma needs are very different from drug developer kind of needs. And they're, you know, they're very good at kind of thinking about data storage and making data available, but the problems that we solve tend to be more computation rather than, compute intensive rather than necessarily just data intensive and data storage intensive. Yeah, I think groups like Amazon, like NVIDIA, are beginning to understand the potential this has. Again, you know, we're looking for people who would love to help us have those conversations with Big T ech. Part of our goal in making the agentic AI architectures publicly available is to drive those conversations. Thank you for that question. Please raise your hand if you have a question. We can put you live like we did with Chad, or please enter into the chat window. I think we have a question on the dose levels. That was just for responding to Clay. Yeah. Do you want to go back? Yeah. Clay, I think you'd ask a question about the dose levels for 184 and the current dose level 12 is 0.61 mg per kg. That's where we are now. Hopefully that answers your question. You can raise your hand, right? And we're at what percentage dose level, we're increasing from dose level? Is it 25%? I think that's what it is. Yeah, I think we're at a 25% level. I think it was 150 and 33 or 25. I think we're at 25% increase. Okay. I would love to answer any other questions as they come in. Again, we think we're well positioned for the year. We've got multiple readouts. We believe we're getting very close to some of the final cohorts for both 184, and approaching 284 later this year. We'll have data at least once, maybe twice for 300. We think, you know, once as we get the next big chunk of data from the current subjects that have been enrolled. We'll also have, in that update, updates from the initial lead-in cohort. We'll have some exciting data to report on those initial patients where we saw the 86% clinical benefit rate as well. That'll be coming, more near-term and then the larger report on 300 probably later in the year as we get 30 events. Thank you, everyone. I look forward to talking with many of you in upcoming meetings or one-on-ones. Thank you for your time today. Thank you to the Lantern team as well.