Hello, this is Paul Kuntz with RedChip Companies. I want to thank everyone for joining us for what promises to be an exciting session with Lantern Pharma. Today's session is centered around a live real-time demonstration of withZeta.ai, Lantern Pharma's next generation AI platform designed to transform how oncology drugs are discovered, particularly in rare cancers. Rather than just talking about the technology, you'll actually see it in action, executing research workflows, synthesizing complex scientific data, and generating insights in real time. This is a rare opportunity to observe how AI is being applied at the front lines of drug development. Lantern Pharma, which trades on the Nasdaq under the ticker LTRN, is positioning this platform not only as a scientific engine, but as a scalable subscription-based business with meaningful commercial potential.
Joining us today is Panna Sharma, Chief Executive Officer, President, and Director of Lantern Pharma, who will guide us through the demonstration and discuss the broader implications of the technology. We'll begin with the presentation to demo momentarily, followed by a Q&A session. All participants lines will remain muted, but you can submit questions at any time using the Q&A button at the bottom of your Zoom window. Before we begin, please allow me to read the safe harbor statement. This call may contain forward-looking statements within the meaning of the Private Securities Litigation Reform Act of 1995. All statements pertaining to future financial and or operating results, along with other statements about the future expectations, beliefs, goals, plans, or prospects expressed by management, constitute forward-looking statements. Any statements that are not historical facts should also be considered forward-looking. Of course, forward-looking statements involve risks and uncertainties.
With that, Panna, please go ahead.
Paul, thank you very much, and thank you for attending this morning. I'm gonna give a little bit of background. Hopefully, everyone can see my screen okay that I'm sharing. We launched withZeta internally as a tool to actually help us better understand which indications to pursue and which drug combinations made sense in cancers. It started really as a genesis when I was presenting at a rare disease conference, and I was talking about how Lantern was using data to better understand indications and how we were bringing indications and pinpointing them with our drugs with precision, and that we ended up with six orphan drug designations and four rare pediatric disease designations and two fast track. There was someone in the audience who asked, really, you know, how were we able to do this so quickly?
That got me thinking, well, what if we could do it not just for ourselves? What if we could do it for every drug developer? What if we could use the promise of the cloud computing and these new emerging AI architectures that can understand natural language and can generate real-time queries and that could go and digest complex publications? What if we could bring all that technology, integrate it in a way which is trained exclusively in the domain of understanding disease and developing medicine? We embarked on a journey at Lantern to say, well, what's one of the most complex areas? We said rare cancers. They're by nature complex. There's not enough data. It's very scattered.
We said, let's go on this mission to try to create a multi-agentic, multi-tool architecture that obviously serves our needs first as drug developers, but then can serve the needs of the tens of thousands of biotechs, cancer centers, drug developers, scientists, students, and even patients trying to better understand rare cancers and coming up with more cost-effective and more timely insights. We started this mission. The market, though, for rare cancers is quite significant. withZeta has over 438 highly curated cancers. It has complex information, bioinformatic, the current state of the disease, the biomarkers of interest, disease progression, trials that have succeeded, trials that have failed, drugs that have succeeded and failed. It's probably the most comprehensive collection of curated.
On top of that, there's still about 5 million patients globally that are affected by rare cancers. Although they're rare, in totality, though, it's about 30% of all deaths every year in cancer are rare cancers. We thought, what if we could do all the literature search real-time? What if we can look at all the pathway analysis to predict anything from blood-brain barrier penetrability of a drug to the chemoinformatic nature of a drug, to its topology, to ADMET predictions? On top of that, what if we can create new compounds? What if we can optimize compounds? What if we can create new molecular structures and analyze their features?
On top of that, what if we can actually, as we're doing the research, create a living knowledge graph that is able to package the information and share it across our internal institution or across our colleagues? As we got that, we saw that the agentic multi-tool architecture wasn't just repackaging information. It was actually creating complex connections and generating new scientific knowledge. It was advancing our understanding in ways that really accelerated the path from what could take hours, days, weeks, literally into minutes. We'll see this live today. We'll actually go and solve for a real cancer today. What we did on top of that, we said, well, not everyone wants the depth of information. We got feedback from early users that we should have like a super deep mode called investigator mode.
We should have a mode that's maybe quick, more conversational, more based on speed rather than comprehensive depth. We call that explorer mode. You can switch between these modes. Ultimately, even a reporter mode, which can take very complex, you know, pages and pages or volumes of information on your research and compress it into a report or a dialogue that you can share as a more formal documentation. On top of that, we thought as we got more deep into this, the needs of different scientists are different. You know, some want to get general information. There's a person who wants to actually design a trial, even in our own team, and they wanna go deep on trial design.
Maybe someone who wants to go deep on biomarker selection and design experiments to validate biomarkers and look at, you know, CRISPR data and look at, you know, other information from biomarker studies. There may be someone who's more focused on the therapy, on translating molecular insight into actual clinical activity. We created scientists that are tuned to how scientists really think, whether it be a medicinal chemist who's doing de novo drug design or a clinical trial strategist or a clinical oncologist or a biomarker person. We created these personas inside of withZeta, you can select persona, you can change. You may wanna design a drug, then you may wanna go right into better understanding its clinical implications. You may wanna switch into designing a trial. The great thing about all these is that they can actually all talk to one another.
They're not individual. They all can interact with one another. In future versions of Zeta, we'll actually have teams of these co-scientists. Again, we'll see that in action today. Multiple research modes, a network of agents and tools, and co-scientists. We have a lot of these different parameters now. What we're gonna see today, real time as we dig into it, is we're gonna query for rare cancers. We're gonna see the knowledge graph in action. We're gonna actually do some molecular analysis and then generate a new novel molecule here this morning. All over everyone's cup of coffee or morning tea. In the next 20, 30 minutes, we're gonna go deep on cancer and then actually get into designing a drug and looking at combinations.
I'll come back to this presentation and talk about what's next withZeta, for now, let's dive into the tool itself. I'm gonna switch over to my actual computer screen. This is from an earlier session I was doing, let's go ahead and start a new session. As I said, this is where you typically land when you go to withZeta. I have the screen a little bit larger than normal just to make sure everyone can see it. Again, it defaults to the general scientist, we can ask any question, just in natural language. You can even use your voice. Before we dive in, let me give you a couple of the features.
In the sidebar, you can start new chat, like most, you can go through various chats that you've had before, go through them and select something from a prior session. You can switch into different modes. If you wanna do light mode, in fact, we can do that today, or you can go to dark mode, or you can set it to your default. You can go into the toolkit. The toolkit's very important because this is the structure of how Zeta thinks. We put a knowledge base, proprietary knowledge base across rare cancers, as well as gave it information about the standards of care.
We guardrailed it with a cancer taxonomy, gave it all the information from hundreds of thousands of clinical trials and their outcomes, a drug database, a massive research document library that continues to grow. It's got over 1.2 million knowledge objects. On top of that, we have a very large molecular analysis engine, a large quantitative model as we mentioned earlier this week, a model to do blood-brain barrier permeability, also to design new molecules from scratch. All these agents, they talk to one another. We pass information from the natural language interface to the tools, the proprietary databases, also to external resources that are highly selective.
PubMed, rare disease ontologies like the NCI Thesaurus, certain cell line references, and of course, the FDA to look at approved indications, safety warnings, dosing information, et cetera. This is very comprehensive. This is exactly what any team in biotech would want at their disposal. The great thing about it is that it's available 24 hours a day. Just log in just like you would to Claude or GPT, but this case very, very deep in cancer drug development. Let's ask it a question. In fact, let's ask it through audio. What rare blood cancers are in high patient need in children? As it starts thinking through, you're going to see all the literature that it digests quickly. Of course, you've got credits here, so people who subscribe will have credits.
This gives you a sense of the context window, meaning, you know, what is the percent of the maximum context window that is being used. What our team has done is made it dynamic, so it allows the conversations to continue fairly indefinitely. You never really run out of a context window. As you can see now, it's digested over 34 sources from PubMed publications, clinical trials, and it's going through trying to now make a systematic investigation. One of the things that we wanted to do is very important in science is transparency. As Zeta works on this, it actually shows you which tools it's using and then very importantly, how it's integrating the information. You can always go back in here and actually look at how did it arrive at the conclusion.
It's not a black box, and that's one of the more important things when you're doing kind of detailed knowledge and scientific work, is to really have the transparency in how did we arrive at the conclusions that we arrived at. Do we want to tweak them? Do we want to change the investigation? Just like any team, these tools are not gonna always be 100% right, but they're gonna be vastly more right and have all the information than wrong. They're gonna speed up the whole process of actually developing a drug, doing investigations, coming up with cutting-edge information and synthesizing. As you can see now, it's beginning to stream the information. It's gave us the blood cancers, pediatric blood cancers by high need, infant leukemia with certain rearrangements.
As you can see, these genes are highlighted in green, just the way a drug developer would want it. We trained it to think like a drug developer or a Lantern scientist, where certain genes are highlighted, papers are inversely highlighted, like in this gray and white, and then diseases are in red. This is very important because when you scan through literature information, you want these things to jump out, genes, proteins, tissues, diseases, and it highlights that real time. This is very important, and we'll come back to it because it's also part of the knowledge graph that gets created that you can share. This is what guides the knowledge graph creation as well. As you can see, it's got a number of rare blood cancers that it highlights.
It gives us what are the common threads for these high, you know, young age, poor survival, and also gives us an idea of like some new emerging trends. We can ask it, very importantly, we can switch over to a medicinal chemist mode. Let's do that. Can you discuss the challenges with Menin Inhibitors and rank some of the preclinical drug candidates in phase II and III trials? That's typically, if you're researching the space, you would take hours to go figure that out. It's not very likely you're gonna have something ready to go that has a deep dive on Menin Inhibitors in blood cancers for pediatric indications, and then rank order which ones are interesting. That's what this is gonna do in real-time.
Again, it's gonna access a number of tools and then also recurse through them and rank the preclinical. Clearly, it's gonna go through and start looking at some of these and then also rank them. It's great. Again, these are not questions that are pre-canned, you know. This is now really thinking about the challenges with Menin Inhibitors, differentiation syndrome, primary safety concern, brings up safety from other studies on these Menin Inhibitors. You can see both these drugs have 15%-25% incidence and severity in some of these blood cancers. 10%-20% across all Menin Inhibitors. Tells you what happens to patients, what the management requirements are, various options for dosing, and then eventually, of course, acquired resistance as the cancer changes. Limited response. Then it's gonna rank them.
Tier 1, obviously, is the one that's already approved, so that's gonna have the highest rank. It gives us the strengths of that and the weaknesses. Then it gives us the phase II registrational trial is the number two rank. This is KO-539. Regulatory submission anticipated. Great. It tells us what the results were from the phase I and the phase II. Again, gives us some of the strengths and some of the weaknesses, including some of the poor KMT2A activity, which is kind of interesting, and very limited pediatric data. Then goes and continues with other Menin Inhibitors as well. Tier two drugs. Then some of the early stage drugs. Again, exactly what we wanted. It gives us a ranking summary which we can cut and paste, so we can take this table.
Again, it tries to keep everything very brief and concise because that's the way, you know, scientists want to think. We want really the data. It puts it into a nice table. It tells us some of the insights. Very importantly, it updates the knowledge graph. You can see now that it has a knowledge graph that it updates, and you can play with the knowledge graph and look at the relationships. The drugs are in orange, disease in red, the genes in green. You can see how this gene relates to this KMT2A rearrangement acute leukemia. Obviously, you can go dig into that specific gene, that disease, and that drug. The wonderful thing about this is you can actually then also export this knowledge graph either as an HTML file which is interactive actually, or as a machine-readable JSON.
This is great because this allows an enterprise to save all the information across all your scientists as they're doing this work. Let's go back and ask withZeta to dive deeper into a new menin inhibitor. Can you help me design a novel menin inhibitor that has better potential to be combined with other drugs and reduces side effects? The great thing about this is also if it cannot do something, it's not going to do it. Unlike a lot of chat agents which try to make up stuff in order, you know, basically be sympathetic, it's actually going to tell you whether this challenge is really doable or not. In this case, since it's a pretty significant challenge, it's going to probably use 16 tools or maybe even more, and it's gonna think.
Imagine your team is thinking about Menin Inhibitors, you have a lot of detailed knowledge about the biology of menin inhibition. You wanna really target that mechanism. You can now do a deep dive and say, you know, is it possible to look at some of the existing scaffolds and structures and come up with something that is novel, but then also is going to be combined? We know that combinations oftentimes have more durable and deeper responses rather than a single monotherapy agent. First thing, you know, you would do as a team is you'd take a look at the scaffolds, you'd look at side effect issues, you'd look at what pathways maybe you wanna trigger or not trigger, and of course, look at all of the existing strengths and weaknesses in the existing drugs.
That's exactly what it's doing. It's conducting a systematic investigation of the current landscape, identifying the limitations, looking at some of the current limitations like efflux, PGP efflux problem, drug-drug interactions, potential issues with combination therapies. This is great. It identifies the flaws and the challenges, now it's gonna now start looking at designing an optimized analog using another one of its agents and tools. This is exactly the way a scientist would think. Imagine this is all being done in real time. As we do it, we can now see that this now has accessed over 128 different sources. 43 trials down to the openFDA, 74 different papers, five other outside publications, and it's doing all this real time.
Just in the moment that we've had, you know, started the webinar, now it's identifying the key problems, identifying the structural challenges, and actually is now iterating on actually creating a drug, which is quite interesting. Create the first drug. Obviously, this is the SMILES string, the weight, some of the key characteristics, topological polar surface area, logP values, rotatable bonds, but it doesn't pass all the drug likeness filters. Okay. It says it's gonna retry. It says the ethylene glycol modification backfired. It added a hydroxyl group that increased TPSA H-bond donors. It's gonna now iterate yet again.
This is really important because it tells you also if it fails in creating something new or if it at least thinks it failed, because now you have that history of, okay, this was attempted, but it seems to not get through the in silico filters. We've trained its generative chemistry modules and its molecular analysis filters to think about creating molecules that have more drug likeness and constantly trying to correct itself. It's gonna do one final iteration. Again, it passed certain filters. It continued to have two issues and wants to have optimal flexibility and wants to have lower H-bond donors, which, you know, it could be a trade-off. You could actually tell it, "Hey, Zeta, I'm fine with decreased CNS penetration," so go ahead and show me the drug.
Again, we like CNS penetration or, you know, getting through the blood-brain barrier. We think it's key. It's a great characteristic to have if you can do it. Again, we can always tell Zeta, "Hey, we wanna take that, claw that back and not worry about H-bond donors as much and show me the, you know, show me the iteration." It's gonna actually come up with a new SMILES string. Real time. That's one of the great features of this. Again, as it does it also updates the knowledge graph as well. We can start this conversation. Here we go. The final phenol hydroxyl change. It's designed a next-generation inhibitor. Here's the molecular structure, the SMILES string. It compares it to the original and how from what the optimization is.
Decreased molecular weight, fixed and passed many of these rules, increased bioavailability, has excellent H-bond donors and acceptors, then tells you how to design it, which is great. Current design, final metabolic optimization, predicted therapeutic advantage over some of the existing drugs, elimination of dangerous drug-drug interaction. Again, this is just one instance of Zeta. Imagine how you have multiple instances of Zeta, multiple Zetas that are trying to work on this problem in an afternoon. This is something to go after these Menin Inhibitors and design a new drug, then actually look at combination potential. This is something that would take literally months and probably hundreds of thousands of dollars for biotech. Here we're doing it real-time. I mean, literally in the 20 or so minutes.
It gives us exactly how to now test this drug and what it's doing, and also gives us a development path. Computational validation, which we would do here in withZeta. It tells us how to do chemical synthesis, in vitro validation. We can actually ask withZeta now as a, let's say, as a general research scientist, "Can you provide me a detailed budget to develop this molecule from research grade to full GMP, along with an aggressive schedule?" We've made a drug. We've investigated this need in menin inhibition in pediatric. We know there's a high need. We targeted some scaffolds and ideas that we thought we could play around with. We have the potential molecule that it created after three iterations, which is fairly quick. Now we're also gonna have a budget. Again, all this is within 30 minutes.
Imagine you're a biotech and you're doing the same thing. This is typically what takes months and months of work, including a budget. This is a realistic budget. We've trained it, and we've given it anything that we do at Lantern for all of our drugs, and we've dosed over 100 patients across three different trials and some very, very challenging cancers. We've gone from ideas on a whiteboard all the way through a manufactured drug product, all the way to dosing people in the clinic, to writing investigator brochures, to securing 12 FDA designations. All that work that our team has done, all that is instilled inside of Zeta. Zeta has learned from it and improves it and does it faster.
We've trained it from all the outside collaborations that we've done with our institutions, and we've trained it with all the outside literature. It's like you have inside of Zeta this unbelievable amount of expertise and resources and the ability to generate new knowledge. Very importantly, you can take what has taken typically weeks, months, and sometimes years and compress that to days. Now it's gonna actually generate, you know, working right now on a budget. It's gonna use 11 different tools. It's gonna create a detailed budget and we can actually put it into reporter mode and then take that budget and submit it to our board, submit it to CROs, actually look at the budget, disagree, agree with it.
Again, you know, these budgets for some of these molecules can take, literally can take weeks, having gone through this myself. It's oftentimes pulling teeth from CROs to get these kind of detailed budgets. Here we, again, can do this in a matter of minutes. With that, I know we're coming up against some time limitations, and I'm gonna go ahead and ask folks to maybe provide some questions. We have some questions already. I'm gonna, we have a question here. "Could this look at failed terminated clinical trials and explain why they may not have worked?" Yeah, that's a great question. Why don't we actually go to that specifically? Start that in a new chat. I'm gonna go ahead and ask it.
Can you review some of the most recent phase II failures in rare cancer clinical trials and provide insights as to their limitations and why they failed? As it works on that, I'm going to go ahead and ask another question. Great question. Do we use this internally? Yes, we've been using it internally. We actually have, you know, probably now 50 going on 100 external users. It's growing pretty rapidly. The knowledge graphs, people, you know, love the knowledge graphs actually, and love the ability to budget and optimize molecules, et cetera. Yes, we use it internally, and we'll talk about, we'll have some press about how we've been using it internally and some of the new molecules that we're doing, actually in some very, very interesting novel biology as well.
Going back. Now you can see it's getting information, and as you can see, it's also going through all these trials, and again, has a library of over 560,000 some trials at its disposal. Another question, I'm gonna answer while it works on this is: Can multiple researchers collaborate on the same question? We have a very exciting collaboration capability. Like I said, the knowledge graph, you can share the knowledge graph as an interactive file. We are gonna have an enterprise feature where you can have teams work on the same problems or sets of problems.
Yes, we'll have a lot of enterprise and team collaboration features that are built in, so people can all look at that. Also you can share it. You can download it as a PDF, which I'll also show you. Here we go. It's got detailed answers on the failure question. Wow, this is really more interesting than I thought. It's giving probably even more detail than I would've even thought about, which is great. And giving us future recommendations on embracing basket trials, and I see cell therapy issues, which I would've said also, but I was not thinking in the domain of cell therapy. I was mostly thinking in, obviously, in small molecule and antibodies and ADCs. Yeah, cell therapy failures are massive. That could be a whole separate chapter we can talk and go into Zeta.
Immunotherapy response, heterogeneity in sarcomas, manufacturing bottleneck in cell therapies, molecular subtyping, statistical design match reality. It's a great answer. Very good, detailed answer, and some good conclusions. Are not random events, but reflect systematic mismatches between trial assumptions and rare disease realities. This is definitely worth a whole article on this topic right here. This is category one trial design flaws. Category two, enrollment barriers. It's interesting. 40% of the failures are trial design flaws, which it gets into, including statistical power miscalculation. Category two, enrollment barriers, which are always tough. Very tough. Let me talk a little bit about some of the future. Yes, obviously, we can get into the trials.
This is a very good question about how does withZeta know when it has enough evidence to stop researching and provide an answer? Yeah, that's a great question. I mean, obviously, it exhausts its own knowledge tree. I think, you know, you can always improve it, so there's a bit of juggling in terms of, you know, is it gonna start filling the context window? Yes, there's definitely a lot of engineering behind the scenes in terms of the data and the context window, the number of matches, the number of tools being used. Again, it has various modes. It has an investigator mode, which will recurse more and use more tools in parallel, and then the explorer mode, which is about three recursive steps and uses fewer tools in parallel.
A lot of the knowing when to stop comes from the mode that you're going to be in. Again, you can always go back and say, "I want you to go deeper or less," or, "I want you to go into a specific tool." The other way that we designed Zeta in terms of enough is the scientist role. You know, does it have enough in terms of if you're doing a, you know, playing the role of a clinical oncologist or a biomarker? Do I have enough to get to conclusions about what a translational scientist needs to put out or a medicinal chemist, et cetera? A lot of it is driven partly by role and then partly here by the depth of the question.
Again, if you're a large pharma or a big biotech, you may also want to add your own external resources to it. You may have your own library. You may have your own compendium, your own pharmacy encyclopedias, your own datasets. In this version, you can actually add your own files. If you want to teach withZeta something that it does not know, you can add a file and say, "withZeta, please read this and tell me what you think," which is a great thing. You can also output from here. Again, it has the knowledge graph that you can share, but very importantly, it also has a PDF writer, so you can actually get the PDF document. Let me go ahead and stop sharing and go back to some of the enterprise features and discuss that.
We're gonna have more team workspaces to answer that question, where you automatically share knowledge graphs. We have collaborative annotation, better session history. We're gonna have social features where you can have credentialed researcher profiles linking their affiliations and their work. Multi-user investigation sessions, so that if, let's say, myself and John and Rick and Shelly all wanna work together, we'll be able to work together remotely. We'll have personalized feeds so that as you come back, it'll know, hey-Panna, you really were deep into these MEK inhibitors. Here's some other things that are relevant and recent or breakthrough. We'll also be able to white label this and allow API access and custom integrations. These are all the future, and we really think obviously drug development is a collaborative, you know, e-exercise, and Zeta's built for that.
withZeta really is to make scientists great. You know, every scientist wants to become better and better and stronger and faster and have more impact in the work that they're doing. These kinds of multi-agentic tools, these co-scientist tools, are really a wonderful example of how AI can be used for good. We continue to enhance it. We'll have deeper data modalities, we'll have more pathway mechanistic knowledge, greater biology models, and also mobile optimization and more tools to support IND preparation, filings, et cetera. This tool will become all-enhancing. Our vision is that for this to be almost like the Bloomberg for medicine, anyone involved in drug development or in the development of medicine and biomedical research, at least in cancer initially, and perhaps then in other categories, will have withZeta at their disposal.
I wanna thank all of you guys, I know I've gone a few minutes over, but thank you very much for walking through this. I think, you know, multi-agentic AI isn't just the next step, it's a really a fundamental reset of what is possible. withZeta is on the leading edge of representing how this can be a breakthrough in rare cancers, and eventually we think in medicine, and how we can bring human insight and expertise and autonomous scientific intelligence. This is how this will co-evolve together and bring us, we think, medicines faster, cheaper, and with greater precision.
With that, I'd like to conclude today's this morning's webinar and urge you guys to go to withZeta.ai, sign up, try it out, get your companies to subscribe, and let's push Zeta to become even a better and better and more powerful tool, especially in rare cancers where these drugs are definitely needed. All right. Thank you very much, and thank you all again for joining this morning.