Specializes in capital markets transactions and I'm pleased to present our 11:30 A.M. presenter. In the Lotus East Room we have Panna Sharma from Lantern Pharma. Good morning everybody. Thank you. I know I'm the only thing between you and lunch probably, so I'll try to make this the best 20 minutes of your morning. I'm going to tell you about what we're doing at Lantern, but first of all, thank you for attending. I'm glad I've got this time because this is fairly unique. I really want you guys to ask questions. That's to me the most important thing. If you're at a table, make sure your table asks at least one question. One question per table. Okay, great. I like that already. Delegating, clearly a leader. We're a public company on NASDAQ, ticker is LTRN. I may make statements that we may or may not update in the future. I urge you guys to take a look at our forward-looking statements. They're on our website, they're also filed in the SEC. What do we do? You hear a lot about AI. Who has heard about AI in this room? Unbelievable, right? What we do is AI for good. We take AI, which is a lot of data and understanding of biology, and we try to look at doing it faster and faster and cheaper and less expensively. Since I joined the company back at end of 2018, early 2019, we've now developed 12 drug programs in a couple of years. Three of them are now in the clinic, meaning we're not just theorizing AI. We actually took that AI, created very, very targeted clinical medicine, and put it into trials. Those trials are actually impacting humans. I'll talk about that. Today the exciting opportunity that we have is not just our patents and our reduction in cost and our clinical stage lead drug candidates, but it's because of the AI. We have not just one opportunity at the company, not two, five, five very unique opportunities. Three of them in drugs that we can license or sell that I'll talk about in great detail today. One in the core AI platform itself, which is actually going to be accelerating its launch into market as an open access platform for all cancer drug developers. I'll talk a little bit about that. The last one is a whole new company. We're entering a new era of precision neuro-oncology, which I'll talk about. A few years ago we developed a whole new drug using our AI proprietary platform looking at different types of brain cancer. Our drug now has fast track designation in glioblastoma (GBM). We've dosed patients with glioblastoma (GBM) and now we're going into a phase I-B, not only in adult, but also in pediatric. This isn't just AI theory, this is AI for good that actually has generated not one, but five different opportunities for investors to monetize downstream. Let's talk about our business model. Our business model has multiple routes to success. We can actually reposition a drug, meaning if there's a molecule that we like in the world somewhere, we buy it and license it and we figure out what makes it work or not work, how will it work with other drugs, and we put that back into a trial. We've done that with LP-300. It's in a phase II trial and in a trial that there is no other drug in this trial. It's for people who do not smoke, but they get lung cancer. It's about 17% of people in the United States. I think almost every family knows someone who gets lung cancer who doesn't have a history of tobacco use. In East Asia, it's about 35% - 40%. It's a growing issue. We're the only trial that's active today in phase II that actually is going after this multibillion dollar indication, all found because of AI and modeling. We can develop totally new drugs, drugs that never existed. We have two first-in-human drugs. These are synthetically lethal molecules, highly potent, and they're both in trials today. We have a pretty important call coming up on November 5th. We'll talk about the results of our 63-patient phase I trial in advanced solid tumors. We also put out a press release yesterday about our LP-284 drug, which has had a complete metabolic response in non-Hodgkin’s lymphoma. Third, which I'm also very excited about, is our platform now has grown. The first time we built the platform, it took really like a year for me to even get happy, maybe a year and a half. The second time we upgraded, it took less than a year. The third time it took less than six months. Now we did it again and it's taking less than four months. Most importantly, each time we update it, it becomes easier to use, more friendly. We're going to be launching it now for all cancer drug developers as an open access platform. We're going to take a page out of the Deep SEQ or OpenAI playbook and let everyone use it. Why limit it to ourselves? We're going to monetize it through a freemium model. We'll talk more about that too. Our core business is that we have a diverse and unique AI-driven pipeline. Again, drug in phase II for never smokers will have data before the end of the year. As an interim readout, we have three trials now that are launching, one paid for by the Danish government in advanced bladder cancer. There's no drug approved in third line bladder cancer, and that's what we're going after. We think this is a very potent drug. Bladder cancers, about 40% of them have what's called DNA damage repair deficiency, and we're targeting that mechanism specifically. We have two other trials, monotherapy and in combination for triple negative breast cancer, where we have fast track. Fast track is very important. It gives us extra commercial protection, but very importantly it allows us to get to an approval from a phase II trial. That is very important. This could be a multi billion dollar win for us. In all the preclinical models, which I'll get into a little bit, we saw complete tumor regression regardless of their sensitivity to olaparib. The third very unique trial is in people who become drug resistant but have a very specific mutation, STK11 KIAP1 mutation in non-small cell lung cancer. We are going after people who have that very specific mutation in combination with a checkpoint doublet that's currently the standard of care. As you can see, all of these trials are very, they're all precision oncology trials and they all are focused on exploiting a unique vulnerability in that cancer. Our drug that we had some announcements about yesterday, we have orphan designation in two lymphomas. One is mantle cell lymphoma, which is a terrible disease, it always comes back. We have a drug that has an orphan status and we've had some very good response in high grade B cell lymphoma. Each of these opportunities can be worth hundreds of millions of dollars. I'm not going to tell you when and how we're going to license it. I can't predict the future, but pharmas are interested in literally every single one of these. This one is very important. I'll get into the data that we already have, and then we're going to spin out Starlight Therapeutics. If you own Lantern, you'll own Starlight. Starlight is going to be focused entirely on only on brain cancers. This was developed through AI. The very first time our AI platform said this drug star 001 is going to work in brain cancer, guess what we did? We ignored it. We do what all good scientists do. We ignored it because we thought our team was like, well, we don't really believe the AI. Why is it going to work in brain cancer? We don't know if it's brain penetrant. There's no real mechanistic reason that we should believe it. GBM's really difficult in general. Maybe it's a weird data set that it stumbled upon. We looked at it again and again and brain cancer kept coming up in the hit list. We can't ignore it. We decided to test it. In fact, brain cancer was among the most sensitive. Not only adult, but also pediatric. We have multiple trials now designed in Starlight. Not just one. We're not just going after GBM, we're going after GBM, we're going after ATRT where we have a rare pediatric disease voucher. We're also going after DIPG and medulloblastoma with the Poetic Consortium. We've got multiple targets. We also will have an investigator led trial at MD Anderson in first line therapy with GBM. Starlight is a precedent. I'll talk a little bit about it because I'm very excited about it now because we're looking to private, public or private finance. The spin out. The last company that got sold that had a drug not even approved, but a PDUFA in brain cancer, H3K27 mutant brain cancer, was bought for $953 million. That company was trading at $0.60 - $0.70 and six months later was trading at $6 or $7. I took one of the board members who actually was with the company Oncoceutics that got sold to Chimerix and Chimerix was bought by Jazz. Lee Shallop, he's on our board now. He's one of the few guys in the world who's actually seen a drug in brain cancer go from an idea all the way through approval. Lee's on our Board. He's joined, he's really excited about this drug also. We can obviously get a lot of values out of someone like Lee. Yeah, anytime you want, please. I'm going to try. I have 20 minutes. I'm going to get into it. Yes, we also have collaborations that are AI. We don't just do everything, we do it with other companies. These are companies we own some equity in, actuate. We own some IP rights, we own the potential license. This drug and we're doing new drug development in a brand new class called antibody-drug conjugates. Our AI platform, which we're going to becoming more and more public or different sleeves of it, has now probably, actually this number is probably very old. It's probably 3,400 billion at this point. We try to do. These are the kinds of issues that we try to do. On top of the data, we have algorithms. The great thing about algorithms, when I first started with the company, I'd go over to my two algorithm guys, their names kind of rhymed. It was Yuvinesh and Umesh. I would go, Yuvinesh and Umesh, let's do these algorithms. We only had like three or four algorithms and they took all weekend to run, all week. They would always be so nervous about running these algorithms. Now we can spin up and run about a million algorithms automatically every single day in an afternoon. I don't need two guys. The machine does it itself and the machine creates new algorithms and the machine learns from the algorithm. We have tons of algorithms that are self-learning. We actually applied for two patents on self-learning algorithms called Ensemble, where it's a meta trainer algorithm that learns from the algorithms that work and don't work and automatically tweaks them constantly using a DevOps environment. It's very exciting. We're not just doing AI, we're going to open that up, but we're focused on developing. We're routinely ranked as one of the top end-to-end AI drug discovery companies. Out of all the drug companies that are trying to use AI, we're also entirely focused only on cancer, which is great. We've got two platforms that are launching. The first one is Predict BBB. It not only predicts whether a drug will cross the blood-brain barrier better and faster than anything else, but also it has tons of other molecular features. This is a Trojan horse into actually designing drugs from the chemistry side based on molecular feature optimization. The second tool that we'll be announcing in the next couple weeks is Zeta. Because we've been very good at rare cancers, one of the most challenging things in developing drugs for rare cancers is finding experts, finding data, assembling information, understanding why that rare cancer doesn't work to other known drugs, and understanding all the challenges. We happen to be good at it, we happen to have a certain way of thinking about it, which is why we have 11 FDA designations. We said, what if we could do this for all rare cancers. We've compiled what we believe is the world's best co-scientists for developing rare cancers. Imagine you had a team of all this at your disposal every single day of the world's smartest rare cancer scientists. First of all, you couldn't even get a meeting with them. I'm being honest. There's a guy I know at Cornell and we were going to talk about a rare blood cancer. It took two, two and a half, three weeks. This is a colleague of his to talk about some really delicate issues. Zeta is alive 24 hours a day. Not only just the biologist, but the chemist, the epidemiologist, the clinical trialist, the person who's learned from 12,000 different rare cancer trials and has ingested over 30,000 different papers, all at your disposal. Zeta is launching. It's going to be very exciting. We're going to dominate the rare cancer space. We're going to do this as a licensing, but as a freemium model. It'll be called with Zeta. Let's talk about our drugs and their mechanisms. I know that was a question. Yes. This table is dominating with questions. John. My question is using the AI platforms. With the emergence now of quantum computers, IBM, Google coming out. Yep. Okay. Does that. Partnership or. I think for Quantum, Quantum will definitely speed it up, but the problem is the need to rewrite some of the software. There are some tools that are being used to bridge existing software into Quantum. The things that it would be best for would be to do gene analysis, but that's already pretty fast. Quantum is kind of overkill for that. Maybe for drug design, looking at thousands of different features and analogs and epitopes of a drug all at once, that could be very powerful. If I had extra cash, it would be a good thing to worry about, but the current tools work really well. Very good question. Sorry, go ahead. The other question is, why wouldn't you partner with some of the fairly large drug companies? That's our model. That's our model. That's our model. Are you doing any of that right now? We're beginning to talk to them. The challenge with a lot of the pharma community, as you probably know, is arrogance. We talked to them and they said, all right, show us what you're doing. You're only in phase I. You're only in phase II. The biggest challenge in AI is people. It's not AI, it's not machines, it's not data. All that is available. Mind you, the biggest challenge with the adoption and the domination of medicine with AI is people. People just get in the way. The challenge is, unfortunately, the older the person, the more in the way. Every rare cancer drug scientist is old. They're not 30 somethings, very few. Most of them are older, they've been around and they are difficult to change their minds and they don't know how to use computing. If you go tell them here's what we're doing, they're like, oh yeah, whatever, go ahead, go publish it. Come back to us in two years and let's do a symposium. That's just not the future of medicine. I have a different question. This table is dominating with questions. Come on, Michael, you got to get your table going over there. Okay, I'm coming from an investor point of view. If I hear your presentation, you sound like a $45 billion company. When I look at your market cap, you are a $45 million company. There's the arbitrage. Somewhere in between is probably which is. That you are a kid in the candy store. You know, you're doing all of these things using a small market cap. Why would you do that? Rather than focus on a few and execute them well, rather than feeling good that you are into all of these things, is it because you don't know what is going to succeed or is. I don't think anyone in drug development knows what's going to succeed. You are good at that. Instead of having these multiple things done and having investors wonder which is going to do that, why would you not say these are the two things we believe based on our algorithms and AI we believe has the highest probability of success, and we'll pursue that. That's where we believe the drugs that we're pursuing, LP-184 and LP-300, that's where most of our capital has the highest probability of success. The AI is a fraction of the cost of what we're doing. If we don't do the AI now, someone else will do it. It's a foot race. If we can get do this rare cancer AI agent in two years, someone else will have done it. We're an AI company that makes drugs. Is your valuation AI based, is that because of valuation or is it because of the market potential? We are an AI company that makes drugs. I don't know how to, you know, if you want to put us into a box, that's wonderful. I would say that the future of medicine is going to change. It's already changing. If you can bring a great example, a company here in New York called Schrodinger spent tens and tens of millions of dollars creating a synthetically lethal drug that killed two patients in a non-Hodgkin’s lymphoma trial. We developed a non-Hodgkin’s lymphoma drug, LP-284, for $3.5 million from scratch in less than three years and actually got complete remission in our first lymphoma patient, complete metabolic remission. I think if that is the future, if I were a VC, I'd be like, okay, I want you to bring a drug into a clinical trial for under $10 million. That's the new benchmark. If you can't do it, I'm not going to fund you. I think the world of medicine is changing and I want to avoid being put into boxes because boxes are what make challenges. We have 11 FDA designations. All these were powered with the data and AI that we then took in the clinic. I'm going to now talk a little bit about the drugs and the trials and the data. The first one is LP-300. We believe that market potential is over $4 billion globally. This really focuses, like I said, on people that get lung cancer, non-small cell lung cancer, but are not smokers. This presentation is available on our website as well. You can go there and grab it. We give this drug, we co-administer it with carbopemitrexate. Obviously, it's a big, big disease category, but people who get lung cancer, they're never smokers, typically have mutations in the kinase domain. Our drug is a pan-kinase modulator, meaning it works on all these overexpressed kinase receptors, but it doesn't really work on these canonical mutations that occur in smokers. When we saw that, we said that there must be something with this drug that's working in the kinase domain. We also saw what we, and this was historically well documented for this drug, is that once it enters the cell, it modulates the redox cycle, the signaling pathway, so it restores the cell's ability to actually be sensitive to chemotherapy or any other drug. That's what it was initially designed for, actually was restoring sensitivity by reducing glutathione and thioredoxin. The drug works with a 1, 2, punch 1. It binds to very specific kinase receptors on the surface of the cell, but it doesn't bind permanently or covalently. It's kind of like an ice pick into a keyhole. It jams in there, and through cysteine interaction, it denatures the receptor so it no longer recognizes the proteins that drive the tumor's growth. After it screws up the cell, it goes inside the cell and it resets the redox cycle. The chemo double can then kill the cell. We've seen this in trials now. We've seen people who are no longer responding to chemotherapy and failed become resensitized to chemotherapy and actually get a pretty good response. This is a 90 patient trial. We'll have some interim readout later this year. We're enrolling in Taiwan, Japan, and the United States. I think we just finished enrollment in Japan, and again we're enrolling in East Asia because it occurs there at about two to two and a half times higher rate in East Asia because of EGFR mutations. We had a good clinical benefit rate. Six out of the seven initial patients in the first cohort responded. They were a very, very heterogeneous mix of male and female. Prior lines of therapy were pretty significant, and they're all over the U.S., and we had a good set of very high responders and a good set of stable partial responders. Based on that, we expand. In fact, one of the responders, we put out a press release after this data that they actually went from a partial 57% response to a complete response. They've been on it for now over two years. We know that it's not only getting the mechanism right, but also the durability of response, wide range of kinase receptors. Whether it be OSI or Selpercatinib or dabrafenib. We know that what we've seen in historical trials we're hoping to replicate. This is that we see an increase in two year survival by more than double and almost doubling of overall survival. This is a historical phase III trial that we analyzed. We think this is the kind of data that would get us to not only to an approval, but potentially to an accelerated approval. We're working with two biggest KOLs in Asia, Dr. Goto at the National Cancer Center Hospital in Tokyo and Dr. Lee at the National Kung University in Taiwan. Our next drug, which is a blockbuster drug, is LP-184. Market potential, over $10 billion. We've dosed 60 + patients. The great thing about the trial is we validated the mechanism, which is it causes double-stranded breaks in cancers that overexpress PTGR1 or have DNA damage repair deficiency. 1 in 4 to 1 in 5 cancers has that. We're going after those in lung cancer, the STK11 KEAP1, in bladder cancer, in TNBC that are no longer responsive to PARP through BRCA, and eventually also in pancreatic cancer. This is a great drug. We think this drug has multiple cancers that it can target. Massive indication, the mechanism of action was predicted through our AI and then it was correlated to PTGR1. We took it to the lab and did CRISPR studies editing out gene PTGR1 at Fox Chase. In fact, when you took it out, the cells weren't killed. When PTGR1 is overexpressed, all the cells died. This gave us a lot of excitement because this drug is cancer cell site activated. That's really important because it's a super potent drug, meaning nanograms of this drug will kill a cell, but only if the cell overexpresses its PTGR1, which only cancer cells do. That's very exciting. Some pictures, and in pancreatic, as you can see, these are two very aggressive different types of pancreatic cancer that were taken out of humans at Fox Chase and then put into mice. You can see in both cases these very aggressive tumors were destroyed. We also did it in TNBC across dozens and dozens of mice. As you can see, these tumors grew. When we dosed them just with our drug, we got complete and total remission regardless of PARP sensitivity. We published on it, we have patents, we got fast track designation in TNBC and orphan in pancreatic again. We finished this trial with 63 patients. We achieved our objectives of getting a good maximum tolerant dose to go in the future. We also validated the mechanism and we also got some really cool responses in some very challenging cancers, including thymic cancer, colorectal cancer, STK11 positive lung cancer, et cetera. Fairly safe. We had very few adverse events. We got a good phase II and we observed clinical benefit. 48% in a phase I is pretty unusual. We got to dose level seven or eight. I believe, David, that was when you got enough drug in the system to actually get the effect. Above that dose level, 48% of the patients got a clinical benefit. Now this is going into phase II and that's what's going to drive a pharma to buy this drug. We've got some great data. I urge you guys to take a look at the presentation online. Similar to 184, this is 284. This drug didn't even exist when we went public. We started this brainstorming on a whiteboard, and then in less than three years, we actually had a GMP manufactured drug, two orphan indications, multiple patents, and then we dosed a patient who now got a complete remission. We're pretty excited about our drugs. We know we are a medicine company. That's what we're focused on. We're doing it faster and cheaper because we use AI. One of those things we launched because of AI was Starlight, which we'll talk about in the future, which is our company that's totally focused only on brain cancers. This was born out of AI and it's a very exciting category. I don't have any time left, so I'm going to stop. As of last quarter, we had about $15.9 million. Our burn rate's about $4 million- $4.5 million a quarter, and hopefully we will license or sell these drugs in the near future. No warrants, no toxic events. We haven't raised capital since January of 2021. Okay, what's happening at the FDA currently, and it's been on public knowledge the last few weeks, is that the FDA are now really paying attention to AI models. Oh, yeah, yeah. There's an initiative that was announced September 30 from the White House. I mean, they announce something every day, but actually, for us, it was important. It was the use of AI in pediatric cancers initiative. We have the potential for four PRVs. So not one, not two, four. For a small company, it's a lot. We have four rare pediatric designations in ATRT, rhabdomyosarcoma, another sarcoma, and DIPG. Yeah, we have four of them, potentially, which is pretty exciting. That's all the time, guys. Thank you very much.