Evaxion A/S (EVAX) Earnings Call Transcript & Summary

Good afternoon, everyone in here and also good afternoon to everyone out there. I guess for some of you, it's good morning. Some of you is very early morning and some of you it's even evening, I can just say I'm super pleased with the very broad attendance that we're having for our event today. So welcome to the Evaxion R&D Day. I have been looking very much forward to this. Today, we will be taking the opportunity of going into details with our AI-Immunology platform. I'm Christian Kanstrup, I'm the CEO of Evaxion and I also just want to introduce my co-host for the day, our Co-Founder and Chief AI Officer, Andreas Mattsson who will be helping me taking us through the day.

Yes. And I'm truly excited, I mean, I've worked for this moment for 15 years since I started in 2008 with Niels Moller, and here we are. So I really hope today will give us a lot of good interactions with you guys, Q&As. And also, I really hope that you get inspired of our AI-powered research.

And I can only say Andreas said earlier on today. I've been looking forward to this for 15 years. Finally, I get to talk about all the things we can do. So..

Yes.

Now is the time.

Definitely.

And how are we going to do it? What we have been doing is we have been putting together. No, we believe it is a super exciting agenda for the day. It's structured in 4 sessions. First, an introductory session, covering a little bit about Evaxion and the platform, but also very importantly, about a key building block of our AI-Immunology platform, which goes across all the different parts of the platform. So super important introduction here as well. Then we will be zooming in on the infectious disease side of the business. After that, we will be talking about the personalized cancer vaccines. And then the final session 4 is going to be about some truly novel precision cancer concepts, which we are looking very much forward to be discussing with you. And this is not only going to be a one-way presentation. This is, hopefully, as you say, going to be a super interactive session. So we will have Q&A sessions. And the way that's structured is the first one is at the very end of session 1. But after that, in each of the following sessions, after each individual presentation, we will be having a Q&A session. And the way it works, it's simple for you guys in here, you just raise your hand and ask a question. All of you guys out there, please just post a question in the chat, and we will pick them up here. So a lot of interaction, hopefully, is a good way of getting to ask the questions you have on your mind. And we are looking forward to answering those. So that's how we're going to do it, right? And then just one thing before we get going, this is a slide. We will be talking about the future. And you all know when we talk about the future it's uncertain. So let's keep that in mind when we go through the presentations of today. And the reason for you're not leaving, right? And you want to share a little bit about what you're hoping beyond what you already said that we're going to get out of the day before we dig into the introductory session.

Yes, exactly. So I really hope that you get the perspective of -- this is hard work and then also that we started so a long time ago that we now have ahead of the game. And we really -- and now we're really benefiting from it. And this is really crystallizing in something beautiful. And of course, it's getting saving life and improving life with AI-Powered immunotherapies, that's what we're doing of AI-Powered vaccines also.

That's a good expectation for the day. So let us do that. Then let me just start out. I mean, most of you know Evaxion. So I'm not going to spend a whole lot of time talking about Evaxion, but I'm just going to spend a little bit of time setting the scene, right? So who are we? Who is Evaxion? We are a pioneering -- important is not biotech [fake bio]. It might sound like semantics, but it is an important difference. Then we have a validated in leading AI platform, AI-Immunology, which is what you will be hearing about today. And this is for past and effective vaccine target discovery, design and development. And with AI-Immunology, we can develop groundbreaking, both personalized and precision vaccine for cancer and infectious diseases. And one interesting thing about Evaxion, which is also important when we discuss today is when Andreas and Niels 15 years ago founded Evaxion, it was actually as an AI company. As an AI company with the objective of decoding the human immune system. I think it's also fair to say, at that point in time, people were looking at you guys smiling a little bit thinking that's fun. You can't do that. That's never going to work. Of course, fast forward to today, everybody is claiming they can do AI-based target discovery. We have the difference. We have been doing this for 15 years constantly developing and refining our model and our capabilities. So I guess it's fair to say it was worse. People were smiling and laughing a little bit about you, but now we are in a good position. So a pioneering [fake bio]. Also important is why we are here. We are here for saving lives and improving lives with AI-Immunology. And to say that is what gets me out of it every morning thinking today, I will together with all my colleagues, be working on saving and improving lives. And if anybody doubts that there's a need for us, look at the numbers here, 10 million deaths a year due to cancer. That is a huge number that we need to improve. Also 8 million deaths a year due to infectious diseases, huge number. We need to improve that. So we are here for saving and improving lives with AI-Immunology. And how do we do it? What's our strategy? We have what we call a 3-pronged business model based upon AI-Immunology, focusing on realizing value via multi-partner approach. So the way you should think about it is the core of Evaxion that's AI-Immunology. That is what we will be talking about the rest of the day today. An AI-Immunology, that is about the target discovery, design and development, vaccines within cancer and infectious diseases. What's also important when we look at AI immunologies, we can design a new target in just 24 hours. If you think about how long it takes to discover a new type with traditional methods, doing it in 24 hours, it's a significant and very strong value proposition towards partners. So discovery, design development new vaccines within cancer infectious diseases in just 24 hours. What's also important and that's another strong value proposition towards partners is with delivery modality agnostic, meaning whether a partner prefer peptide-based delivery, DNA, mRNA, it doesn't matter. It doesn't matter because the target that we design and discover with our AI-Immunology platform, that is delivering modality agnostic. And finally, and what you also hear about today and which is super important and something we haven't really talked about a lot is we have a modular architecture, our AI-Immunology platform is built up of building blocks, which can be combined in many different ways to give inside outcome. So it's not like we're doing a lot of different things. We're actually having some very unique building blocks, which we put together in distinct ways to generate a certain outcome. What does that mean? That means, of course, we have a high degree of scalability. It also means that we have a flexible model, which is important to both partners. So the core AI-Immunology, more of our strategy, how do we generate value that we do by the 3 promises we call it, its targets, its pipeline and its responders. Targets. That's a multi-partner approach to either single or multiple target, vaccine target, discovery, design and development agreements, teaming up with Pharma, developing novel vaccines. An example here, that is the collaboration we just announced a couple of weeks ago with MSD where we have partnered up to develop a novel vaccine against a bacterial infectious disease where no vaccine is available today. That's what we are doing here, teaming up with pharma, addressing significant unmet need. Second element, that's pipeline. It's progressing high-value compounds into either clinical or preclinical development. We of course, our most advanced asset is EVX-01, which is Phase II metastatic melanoma, we just released the initial Phase II data towards the end of last year, supporting the very strong Phase I data that we have seen. Another example here is the partnership we have with Afrigen Biologics, where we partnered around one of our pipeline assets, EVX-02, having Afrigen Biologics pursuing an mRNA-based version of that compound. Finally, it's about responders. This is taking our data, our predictive capabilities deploying that in a slightly different way than what we are doing with the rest of the business, but it's still about saving and improving lives. Here, we had a proof of principle for our checkpoint inhibitor, prediction model, which we leased towards the end of last year. Checkpoint inhibitor market is reaching USD 53 billion in 2024. Think about that, $53 billion for a single class and checkpoint inhibitor while [Indiscernible] therapy or golden standard for immunotherapy is still only a fraction of patients who respond to them. If we are capable of taking our predictive capabilities, our data insights and predicting who are the patients who are not going to respond to a checkpoint inhibitor. So you can get that patient on to a well, more effective therapy quickly. You have the patient, you help society, save a lot of cost. You will also hear more about that later. To look at our strategy, 3-pronged business model is about targets, pipeline responders, AI-Immunology at its core. Pretty simple, lots of opportunities hard to execute upon, but we are well on our way, as you will also see data. And another thing that's important and which leans into Andreas and those being last 15 years ago, this is a fact that we have been building a multidisciplinary capability set around the platform. On top of that, we have also been building state-of-the-art facilities. And why is this important? This is important because many of the AI companies today claim that they can do target discovery. They have a couple of retrospective data sets they are working on. We have been building a multidisciplinary capability set, allowing us to do constant learning loops, generate our own data, generate proprietary data, quickly test our hypothesis and continue to developing and feed our model. And if you look at it, I mean, it starts with the disease biology, then it spans target discovery, design and the whole preclinical clinical CMC. It's a strong capability base we have been building around the AI-Immunology platform. What's also important is just out here, we have our state-of-the-art lab. We have our state-of-the-art animal facility, which again allows the bioinformatics team here, come up with a hypothesis. We go straight into the lab and test it in the animals. And that gives us the unique advantage compared to the other companies who started doing AI a few years ago. And the fact that we have been working on this for a long time also means that we have something which not many others have, which is a clinical validation of our platform. What you see here is data from our EVX-01 Phase I trial. There are 2 cohorts. The blue one is locations where our model predicts the new antigens we're using here, targeting here a high-quality neoantigens. The red ones are patients where the model says, these are not so good, third quality neoantigens. And of course, any given patient will have a different number of targeted neoantigens of varying quality. When the model says these are high-quality targets, we also see that the active means to a statistically significant longer progression-free survival, meaning that when the model says, these are good targets, this is going to work, it also works. So clinical validation of our platform, which is quite unique and also a testament to the capabilities we have been building around the platform. And all of this, you can say that sums up to this, that we have a differentiated platform. The validation of the AI-Immunology platform in multidisciplinary capabilities, that do put us in a different and clearly differentiated platform or position when you compare it to other companies. And it is something, which is enhancing the value of our platform is something this is a super strong value proposition towards partners. And it's also something, which has materialized in a very strong pipeline. It's clear that our pipeline to demonstrate performance and scalability of our AI-Immunology platform. I'm not going to go into detail with the pipeline because there will be plenty of opportunity to touch upon that in the subsequent presentations, but we will be getting in to detail, but it is really a testament to the scalability of our AI-Immunology segment. And then I'm just going to wrap up with looking back a little bit because -- however, we actually fair in terms of progressing on our strategy. This goes about 6 months back. I think it's fair to say we have seen a very strong execution on our strategy. If we look at the slide here, in September, we announced a collaboration with a leading pharma around discovering and developing a novel vaccine candidate. That's the one where we announced a couple of weeks back, it's MSD then we have successfully completed the first couple of phases of that and are now pressing into the next phase, super exciting to be teaming up with a world leader in vaccines in developing a novel vaccine candidate against a bacterial infectious disease with a high unmet need. We also, has touched upon pronouncing collaboration with Afrigen Biologics. We have been publishing encouraging initial Phase II data on EVX-01. And also important, we deliver the proof of principle for our responder model, AI, responder model for checkpoint inhibitors. And then what you also hear much more about data is we've been working around the precision vaccine concept, super exciting concept because it can, one, help us address patients with cancer, where traditional immunotherapy doesn't work. We can also help us broadening the opportunity space for cancer vaccines. You'll hear much more about that during today. And then the final thing is we've been raising funds a couple of times. First towards the end of last year and then early this year, in both of these rounds, we had MSD participating, investing, which also means that MSD now is our biggest shareholder with around 15% of the shares, so having a corporate partner working on a novel vaccine, but also same company as a sizable shareholder. It's of course also something that means a lot to us and is a testament to what we do. Finally, before getting to Andreas is looking ahead, plenty of exciting milestones. The last 6 months have been exciting. The next year is going to be exciting. We will have milestones both on single compounds on collaborations, on platform, et cetera. I will not go into detail with this now because focus is on today, and all the discussions that we will be having. But just say that rest assured, there will be a number of exciting milestones coming over the time ahead. But now is time to look at AI-Immunology. And who would be better at giving an overview of what it actually is, then I would say the father of the AI-Immunology.

Thanks, Christian. So AI-Immunology is a platform. It's a true differentiator. And like I said in the beginning, we have worked with this for many years, 15 years actually. So now we really harvest on it. We are ahead of the game. And now I will tell you about not to go into too much detail about it right now, but just tell what is it and what can it do? So AI-Immunology platform consists of 5 different models, AI models, where it has been trained in cancer and infectious diseases. Two of the models, they are within the infectious diseases. That's EDEN and RAVEN. And the other 3 models that's within the cancer that's PIONEER, obsERV and AI-Deep. So in the next all the presentations, we will go deeper and deeper in all the models and explain them. But also -- in the next slide, I will tell you about actually the slide that Christian talked about, that we can actually link we have a clear link between prediction and patient outcome. And to me, that is first time, I have not seen any other companies showing that or publications and so forth. So this is truly unique that we have been able to validate our platform in humans. So -- and as Christian said, this is truly unique that you -- that we are able to have a prediction that are linked to the outcome of the vaccine that we gave in patients. So here, but the take-home here also that this actually tells us that is very important that the things you put in the vaccine is the right thing. So and what we can do, we can use our prediction score to tell us, "is this the right thing?" so this is truly unique for us. And just to put things into perspective, before I go too much into the details with the platform, I think you deserve to know the journey how this starts and so forth. So it started with my mother actually being a researcher within vaccines, [indiscernible] vaccines. And that, of course, inspired me. So at that time in 2008 where the global readiness for AI was really low, I had a vision that I would put the immune system into a computer and then make better vaccines. And like Christian said, people there, of course, left, but they thought it was cool. And I just continued. So me and Niels, for 6 years, we struggled and got a lot of nondilutive funding in to prove that the EDEN system that I have made actually work. So it works by faster and cheaper, identifying the right components that should be in infectious disease vaccine. So that worked out, and we succeeded. But then we also went into cancer in 2016. We -- it was actually because of the checkpoint inhibitor invention that you could actually use immune system to fight the cancer. So that discovery led us to having an ambition of actually making personalized cancer vaccines. So we collected a team of a -- a dream team from [Indiscernible] where I come from, with super cool and very, very good [Indiscernible]. We built PIONEER. And after that -- we then collected a team of experts within a preclinical AI validation. So at that time, so now we actually have a super team so we could go into the clinic. And we went into the clinic in 2019 with our first personalized cancer vaccine and where we use the PIONEER model to make the vaccine. And that's called EVX-01. That was done at [Halo Hospital]. And the next year, we moved fast. So next year, we opened a new study in Australia with our vaccine called EVX-02. We were very blessed because in [indiscernible] one of the top scientist in the world within cancer, she was the PI of this study [Indiscernible]. And also in Australia, Professor [Georgina Long] was also a star in melanoma cancer. She also led the study. So good guys on board, you can have success. So we IPO-ed in 2021. And then it was really a crazy time because at that time we also had COVID hitting us. So we were actually pushed in the direction of making -- enhancing our AI-Immunology platform to predict virus vaccines. Before that we have had the focus on bacterial vaccines. So that meant that we created a new model. We built a new model called RAVEN. The 2 next years, we created AI-Deep and obsERV. So AI-Deep is predicting checkpoint inhibitor response and obsERV is predicting a new type of cancer antigens that we will present later. And then, of course, the global readiness throughout the years through [Indiscernible] and we are very [Indiscernible] that we have partner between us like never before and also have big pharma on board, so we can make vaccines together and have the big guys carrying them out to the patients. So why do we need AI-Immunology. Well, like Christian said, millions are dying from cancer each year. Also infectious disease is almost the same by 8 million almost. So with AI-Immunology, we are able to discover and assess the protectiveness of the antigens. And we're also able to design them within hours, faster, cheaper, and we are speeding up the vaccine discovery process. So that is our solution to this problem. And let me take one step back because, I mean, sometimes we forget what it is a vaccine and what is the antigens of a vaccine. So a vaccine teaches the body to fight an infectious agent and disease. It is a drug that is introduced to the body, then it can trigger immuno response where you can prevent the disease or you can control it. So you could guide the immune system to take the right decisions. A vaccine antigen that's a part that you put into the vaccine. So that is a part of the infectious agent where you can train the immune system to learn to attack the bacteria or virus in the right spot. And with AI-Immunology, we are able to identify these components, these antigens very fast and very cheap, and we're also identifying the ones that are highly protective. Now I'm going to talk about how -- what is actually the basics of creating a good vaccine, not only the antigens, but also -- what do you need to understand. So you need to understand the disease. You need to understand the immune response, and you need to understand how to design the vaccine. And all this come together you have to put in to connect the dots here in order to make an effective vaccine. And the AI-Immunology is actually built upon these areas. So we have -- we decode the disease, we decode the immune response and we make a vaccine based on our -- this is actually just code. This is AI coding. So these can be divided in building blocks. So with AI-Immunology, we have this example with the small building blocks where we utilize them across the models. So we build up like Lego, build it up. And now I'm going to show you how we actually built one of our -- that comes later. Sorry about that. So to be -- to go a little bit more in the details, so what we do with our building blocks is actually by -- this is the coding? What do you mean by that? We're actually finding the weak spots of the disease with this code. Of course, so we had 13 building blocks here that we can combine when we built the models. Then the immune response to coding, that's where we go in, and we understand the immune system and then we rank these weak spots, which ones to attack. We consider B-cell, T cell and anti presenting cells that part of the immune system where we need to rank these components, these antigens, weak spots. Yes, we have 6 out there, right? Then we have the vaccine design. We consider safety. We consider to optimize the sequence, we also have models to design antigens to remodel it. And there, we have these 7 building blocks. So now it's going to be fine because now we're going to build a model. So the way that we have built obsERV. First, we made the first layer. That was a decode the disease. We picked out the important needed building, blocks needed in the model, then we have a second layer where we decode the immune system, decode immune response. And there, when we want to identify this kind of cancer target, we need these models -- these building blocks. And as same goes here, we just build it up. Here, we consider safety and the quality of the antigens. And also we observed here is personalized. So we need a personalized building block to put that into the model. And we have obsERV 1.0. So as you can see here, these are the ready to -- and these are the models we have now and all the building blocks in the models. And we have demonstrated that by using the AI models, we have built up a scalable pipeline products, vaccines against infectious diseases and cancer. But we can build new models. We can -- so what is next? Well, our building block architecture enables us to scale to other therapeutic areas. And right now, we are in cancer -- we are in bacterial diseases, and we are in bio diseases. But it doesn't stop here. I mean, what about autoimmune diseases, what about imbalances in the [Indiscernible] what about allergies and what about parasites. So in summary, -- so with Evaxion, we are the first mover of using AI for vaccine target discovery, design and development, and we have a clear differentiated position. We have trained our AI modality platform in cancer and infectious diseases, and we have clinically validated it. And our AI-Immunology platform consist of building blocks that we can utilize across models and build new ones. And then, like I said, AI-Immunology building blocks modeling system, you can call it, or architecture. It enables us to scale to other therapeutic areas beyond cancer and efficiencies. But just to [Indiscernible] into the next presentation, one of our building blocks is actually represented across all the models. It's essential building block and that is -- have its own presentation today. And that Michael will talk about that. That's called EvaxMHC here. And Michael has a PhD in bioinformatics from DTU and are the lead architecture in RAVEN and in EvaxMHC. Over to you Michael.

Yes, thank you. So I will talk about EvaxMHC. So it's -- it's really one of our core building blocks and it's used across all of our model. The reason that it's used across all of our models is that is really used across the immune system. So it's -- it models a very important interaction between the MHC molecule and peptides. So what I've shown here is the schematic of cell and T cell interacting together. So this happens all over the body in the immune system between normal cells, between immune cells and between T cells, a central player in the immune system. So what is happening here is that the cell is displaying something via this peptide to a T cell receptor. And this T cell receptor functions kind of like an antibody. So it has similar properties to an antibody. And it recognizes this peptide and it can recognize a good peptide, something that belongs to the body, and it can recognize the bad peptides, so something that belongs to a disease, pathogen or cancer. So that is really what is being communicated. So the cell could say, "I am diseased with a virus and show this peptide to the immune system. " And the immune system will react and maybe kill the cell or it could be an immune cell that says I found this peptide, it is dangerous, we need to do something about -- so that's really why this is so core in the immune system. So the MHC molecule, as shown here, it's a large protein. It sits on the outside of the cell. And it has this binding group on the top of the protein where you have this little peptide located. So -- and what is really crucial here is that this MHC molecule is incredibly diverse. So there are -- if we all have the same clone, if we all had identical immune system, you could just have a virus randomly evolve and then say, "Oh, look, I'm no longer being displayed on the MHC molecule, then you will just destroy it all. So that's obviously not very good. So then we have developed this diverse repertoire of MHC molecules that is different from person to person. Yes, so that is, of course, nice from an immune point of view, but it's a little bit annoying from a modeling point of view because that means that we have to model all 26,000 Class 1 alleles, which are the Class I is the one that is sort of communicating in danger from normal cells to the immune system and 11,000 Class II alleles, which is the one that's sort of the between the immune system communication. So we really need to have a handle on all of these. So how we are looking at this problem. We are taking a peptide, which is a string of amino acids. And then we are decoding those down to a letter. There are 20 amino acids, so we used 20 letters for this. The similar, the MHC molecule, it's a protein. So it's also composed of amino acids, so we can also decompose that to a string of amino acids. And usually, you will compress that a little bit to say that what are the essential amino acids in the binding groups. And then what is the challenge here is that there is an incredible amount of different peptides that you can have, and there are quite a lot of MHC molecules. So we need to figure out is a given peptide, a binder to a given HLA molecule. And the reason that we need to know this is that if we have a cancer patient, they have a certain HLA type, we need to know what neoantigens are being presented by this patient or we're designing a T-cell vaccine, and we need to know which types of T-cells antigens are present in this population. So we need to know exactly what peptides we have to design on what vaccine with. And to show here is that modeling this actually has some real-world importance. So -- Andreas mentioned obsERV, I will mention it again, that -- and Christian will talk about it for later. But -- we have actually tried this with our previous version and then our new version. And this is designing cancer antigens. So what you see here in the middle is a growth curve for cancer. So what you want is the least amount of cancer possible. So that is the yellow line at the bottom, and that's our new building block here, compared to our older building block, which gives less cancer, but it doesn't quite carry it. So for certain applications, this really does matter that would keep developing these tools. And so the way that we do this is that we -- first and foremost, we need the data. So there is luckily a lot of data on this out there in the literature and publicly available, and then we take as much as we can. And then we also generate some of our own and what we try to do this as cleverly as possible. So it matters the most. And then we look for our -- what are our blind spots in this area. So as I mentioned before, there is sort of a family of these genes are many different and they group together. So which ones are kind of similar. So the ones that are similar, if we already have data for these, we don't need to generate more data. And that is what you see on the right. So we have some on the far left of the plot, which are the ones that we have data for. And these we don't need more data. And then we have some that go to the right. They are far away where maybe -- we don't have data. And then we also look at another component, which is how often is represented in the population. So that means that it's more likely that somebody will have this deal. So then we generate where our biggest blind spots are, and we try to do this continuously. And then finally, for this iteration, we've also upgraded the architecture, the modeling approach quite a lot. So we have used a brand-new architecture, a deep learning. And we have also made a new training approach called the Generative Adversarial Network that I'll get back to. So this is how we normally do it. Like I said, we have our MHC molecule on the left, encoded as a string of letter. We have our peptide encoded as a string of letters that is 9 amino acid long because that is the amount of amino acids usually fit into this group. And then we feed it into a neural network, which then learn -- does this MHC match this peptide. And this works really well. But what we solved was that we actually didn't get through all of our data before the model finished training. So we actually had a functional model, but we didn't use all of our data. So that puts us in a nice position because we can actually upgrade the neural network to something much deeper and much more complicated because now we are going from a medium data situation to an actual big data situation. So that means that we can make the next generation. And what we do is that we looked at language modeling. So we do that quite a lot when we do process because they are quite similar problems when you put them into the computer language, it's composed of words or letters, strong together that makes a sentence, that makes sense. And proteins are strong together by amino acids that are together and then the sort of mega protein. So very different fields, but they're machine learning methods, they are quite similar. And as you all know from ChatGPT and all the things, there has really been some incredible success in this area. So that is also why we are taking a lot of inspiration. The main source of all of this success comes from -- on the left, this transformer architecture. So there is a way of setting up a neural network to learn these language-specific learnings. And what it started with was the machine translation. So you have some input, which could be a sentence in Spanish or English. The new encode that using a transformer, so the encoder transformer, and that is then transformed into some -- a lot of magic numbers, so a large matrix of just numbers, which is then fed into the decoder, which decodes into a new language. So that could be a Spanish or English or whatever you want. So then you learn the structure of the language. And then on the right is just for showing how ChatGPT work, then you just predict the next work. So you'll write a sentence, what is the likely next word. And that is actually all that's happening in that moment. That's quite interesting that it works so well. But all of them are based on the transformer, so we chose to use the encoder or decoder because it fits our problem quite well, we can encode the MHC sequence. That is sort of the language that we are speaking. So what fits in this group and what doesn't. And then we use this encoded MHC sequence, together with the peptide and then that is decoded into a prediction, this is a binder, is this a nonbinder -- and this should work really well. But initially, it really didn't. It just never ever gave a right answer. It just gave complete nonsense. So that means that we had to take it to the next level to actually train this model to make sense. And the way that we did this is through something called Generative Adversarial Network, as I mentioned before. So this means that we basically take the network and then we duplicate it. So now we have 2 networks. So one networks, it makes fake peptides. So it basically deep fakes a peptide. And then we have another network that it learns whether or not this the input is a defect peptide or real peptide that we have from our data center and that means that these model can learn together that it's a more stable way of training them. So initially, you just randomly initialize your model. So that means that the output will be complete [Indiscernible]. So that means it's really easy to recognize. Is it a fake peptide, is it a real peptide? That's very easy. So you learn slowly. But then as you learn to recognize the difference, you alter the generator, the ones that makes the fake peptides will also learn to make better fake peptide. So therefore, you train together these models. But that also means that once you are finished with this pre-training step, you have a model that really knows what are the intrinsics of peptides. So how -- so there has sort of a deep understanding of what is a peptide. So that means that we take it to the actual training and train what is a binder and what is a nonbinder -- it has a really -- it has a much more stable and improved way of doing it. Yes, so we are training together. Class I and Class II. Normally, you train these separately, and then we fine-tune models using only Class I data and only Class II data in here. So what we get is these curves and they show gradual progression. So you want good recall that is how often you find you're positive and you want good precision. That is how often is what you say is positive, actually positive. So you want to go to the right and want to go up. So that is what -- so the perfect predictor would be square in this platform. So as you can see, we have our beginning -- our starting point framework, and then we add this transformer and then we get better, and we get better for both. And then we have this Generative Adversarial Network and then we get better for Class 1, and we get a lot better for Class II. So you can really see that the area between the curves is quite large. And that is really significant because it's a much more complicated challenge to predict these Class II bindings. Yes. And we can also prepare. So like I told you before, there are thousands of different alleles. So each dot here is representing one allele -- so as you can see, there is quite a difference between the performance of the different alleles, so that depends how much data and so on. But we have really pushed a lot of the alleles up -- and we are really the ones that are at the very far bottom, we have also taken those quite a lot of. So compared to ourselves and also compared to what we have -- what you can find in the literature and what you can -- is freely available on the instrument. Yes. So like I said before, I'll reiterate, this actually has real-world implications. We can -- in our obsERV model, we can see that antigens that we design using our new model. It has a much -- is more responsive in the immune system, react to it's much higher. If we look at the neoantigen immunity, we have a higher precision. So we have more hits when we use our newest model. So that's really why this is used across all of our different models. And finally, the peptide MHC, it's really key. I would like to, of course, reiterate this, and it's really crucial for modern vaccines to get this right. So for some vaccines, T-cell vaccines, the cancer vaccines, you need to get this right. There is no other options, for B-cell vaccines it really helps. And our newest iteration, version 4 of this building block, it's quite a significant improvement in this field, and that actually improves real world vaccine performance. Thank you.

Thank you, Mike. And I think this is quite unique, right? And that also speaks to this, you say, the unique architecture we have of our platform where we have these building blocks that we are using across the platform. So that means when you come up with something absolutely brilliant, which increases predictive power, we just plug it into where it fits in all the different models, and we have a major benefit here. So I think that's quite unique that we have this building block approach here. So with that, we have time for Q&A and those who are online, please just type in questions in the chat. And those who are in this room, please just raise your hand and place your questions.

Could you try to explain the level of, let's say, precision that is needed for enhancing the efficacy of a vaccine?

Yes. So that's a very good question. So it also depends what you have available. So if we're looking at something like a pathogen, then you have thousands of peptides, you have a lot to chose from. So then -- it doesn't matter too much how much you are precision. So there you need maybe 75% precision or something. So -- but if you have something like a cancer or [Indiscernible], there you only have protein. So you really need to get those right. So going from what we normally see 80% to 90% or 95%, it makes a hell a lot of difference because one more hit that makes a difference of whether it's an efficacious vaccine or not. So we need to change those -- those improvements in that area.

I don't see any questions here. Do you see any?

I don't see any either.

That was because it was perfect and clear. No we know it's a little bit technical start, but it's also so central for the whole platform that is worth spending time on and because that is really what is helping us improving and -- saving and improving lives that you have building block which can increase the predicting capabilities beyond what you can do with any other tool out there. So it's super important. Richard, any comments on Moderna's vaccine? And how does your technology compared to theirs-- maybe we will cover that in the PIONEER section -- or do you want to...

I don't know which one, but I can look it out.

Okay. We'll take that in the PIONEER session.

Could you try to explain what kind of data set would you need to enhance your models efficacy competition? Would that be external real world data or animal models or data?

Yes. So how would you normally generate this model if you look at a cell and you see what it presents. So then you can get a lot of data out of, but you don't get the disease state of the cell. So more data that models what happens when the cell is like in danger. That is the type of data that really improves these models.

Well, I think one important point is also -- when I joined, I was kind of -- why don't we talk about how many data we have, right? And then I kept being told by the team was as fine, but it's more the quality of the data and the different data sets, right? So I think it's getting that right competition. That's, of course, also the fact that we can generate a lot of data ourselves here, gives something quite unique. So it's not about how many terabyte, but some extent, but it's also the composition of data.

So is it more the description of the cell and the knowledge about how cells actually function that can enhance the vaccine design at precision?

Sorry, you're talking specifically or vaccine design in general.

In general.

Yes. So then it's -- it is sort of picking it apart, right? So there are some blind spots where, yes, we don't know really how -- what happens when you have these disease states or other parts of the interaction. So those are really incredibly difficult to model. So it's also a question of where did you use your resources because there is one spot where you could have an incredible improvement, if you could predict this, but also you would need billions of data points [Indiscernible] that don't exist. So that is just not really feasible. So you need to really spend your resources where they actually matter and where your model can [Indiscernible].

I have a question for both speakers. So just wondering about the Phase I data. It's interesting to know an equal 6 means, in 6 patients per drug or 6 molecules.

6 patients.

And then you gave a high predictive antigen with a high score and the antigen the lowest core and no placebo.

So that was the best -- yes, because that was the best vaccine that we can create. So we couldn't find any more optimal new antigens based on the [Indiscernible] we had -- so -- and that will -- and after that, so that actually was difference on the [prediction]. And this should also come back to the question also from [Indiscernible] and so forth that is really important, the quality of the new antigens that you use. And I know -- I think that that's my memory -- I think it's 20 new antigens used in the vaccine, [Indiscernible]. Yes, it's a lot, right? But here, we have another proof -- you only have 10 in general, but we show that it's extremely important that we have the right new antigens and that we can show with our prediction scores because we could let the outcome of the clinical trial with that prediction call.

And then we have Lee, good question. How do MHC predictions translate into CD4 and CD8 reactivity?

Yes, that is also a big area of research where we are going because -- of course, you the very first slide, there is a third component, the T-cell receptors that also need to react to these peptides. And modeling this is incredibly complex. There are billions of TCRs. And so you need to say that the peptide in C binding is a prerequisite, but it doesn't mean that you have reactivity. So we are doing the best we can to model this, and we can improve a little bit, but it's still sort of an open area. So you need this binding, but that doesn't guarantee reactivity.

And then we have another question around the announcement from yesterday that Novo Nordisk Foundation and EIFO and NVIDIA is going together and creating, let's say, 1 of the 5 biggest supercomputers in the world and what that means for us. I think I wish we had time this event for -- this event here, but even though many of us know foundation quite well, that's not what we did. But of course, obviously, very good news because it is going to be something which is going to be supporting the life science world in Denmark and AI. But I think what it practically means, probably too soon to say. But definitely an important step forward in advancing and creating an even more supportive life science environment in Denmark when it comes to AI. And then Michael, what is your gut instinct about the progression of EvaxMHC, where are we at 4.0, what are the quantum leaps that we can expect? I mean if we can get any better.

There's always been for improvement and especially this Class II. So for instance, the whole field has been kind of neglecting. So we're using the 1 called DR. So -- but there's also DP and DQ and they have been a little bit neglected. But I think with the performance we're seeing, we can now actually take those into account and the reason why they are -- there's 2 of them coupled together. So it makes it exponentially more complicated. But we can slowly start to see the performance where we can actually use these. And of course, we're going to keep trading. We're going to keep using new models, and I can also see there's some questions about diffusion models. We're definitely also going to look into those to see if that can improve our performance. So the whole field of deep AI is evolving extremely rapidly. And that means, of course, that we can just take into all these architectures and techniques and then just try them out and see what works. So once we have something that works then we, of course, dive deep and then make it really work well for our contents. It's really exciting.

Then we have final 1 here, have you tested the propensity of using your AI [indiscernible] also peptide [indiscernible] responses to cognitive peptides that are naturally recognized something we...

Not yet, no. But that is definitely also very exciting.

Excellent. I think quite clear that a super important building block, which is crucial for the whole platform and quite unique predictive capabilities. But -- and thanks for the questions here because in the interest of all of you getting a break as well, we'll end the questions here, and then we start in little less than 15 minutes. So thank you to you, Michael, for taking approvals. [Break]

Okay. Take a seat. I come back [ from the spring ] and I don't think I need to introduce the next speaker because you're already seeing him [indiscernible] will you take it from here?

Yes. I would love to. Thanks for break, and nice to see you again. So I will present we are in the next session here will have EDEN and RAVEN -- so EDEN this best class model, [indiscernible] components that create antibodies in the bar. So why do we need EDEN? Well, the global debt of the macro -- antimicrobial-resistant intentions is [indiscernible]. So just to give you some numbers here, today, 10 million plus of cancer each year. When you look at the antimicrobial resistant bacterias, is 1.3. So it's a subpart of what we explained in the last session. There was 8 million in total infectious diseases, this part is 1.3 today. But it's predicted that in 30 years, we will have the same amount of [indiscernible] against -- in antimicrobial resistant bacteria infections, as we have [indiscernible] today. So there's a huge need of doing something. We can't -- this happen. So we need AI for accelerating the vaccine development against these bacterial infections, and vaccines have a prudent track record of combating the infections. With traditional vaccine development techniques like reverse technology, you can find the right antigens but you have to be [ docking ]. It's very expensive, and it takes a long time. And I will go into details of that in some slides where you can see some examples. We use EDEN to rapidly identify the antigens -- but we also find the ones that are highly protective and they're very broadly protected. I also shown that data. So we have a solution to this problem and so as I showed you in the last presentation, we have built EDEN with these components. So as you can see, some of the building blocks are T cell antigens. Some of the building blocks are EvaxMHC, as Michael talked about and then we -- you can see that we actually are targeting both virus and bacteria. So how does it work? So EDEN identified with the novel protection antigens by future recognition. So what that is actually like facial recognition. You use the features of a protein, you train on these features, and then you learn how to find new highly protective proteins. So EDEN had been trained on highly protected proteins, very unique highly protection proteins to find new, very unique highly protection proteins that are [ novel ]. One feature could be the surface of the antigen that are likely to be where an antibody can bind. That could be a feature. That's actually one of the features of EDEN, but there are many features in EDEN. So how does EDEN work? It works by taking the proteins -- all the proteins, all the immuno acids sequences of bacterias proteome. Proteome is actually just all the proteins in a bacteria that is called the proteome. So that -- all of these protein sequences are feeded into EDEN and here you see this is just an example. There's 2,607 team proteins feeded in. Then it calculates for about 24 hours and then the output is a list for each protein, what is a predictive score on this protein should be protective or not. So as you can see here, the score is from 0 to 1. So in the top the best protein here that EDEN have found is ranked as #1. And that has almost 1 as an EDEN score. So what we do here is in action -- we then process the proteomes of a given bacteria, we want to make a vaccine against then we get the rank list. When we look in the top and then we take these potential highly protected proteins. We express those so we [indiscernible] physically and then we tested in the lab for protection. So we have AI score and then we have a reality check if this is [indiscernible] projection. And that I will show you later, actually, it's pretty remarkable and first time ever it's done in the world actually, as shown in the world, to my knowledge that you can actually rank protectiveness being realized with the actual AI scale. And that's what you see here. So the EDEN AI scale [indiscernible] with protection and we can use it to identify not only rapid and with low-cost antigens that are in -- but we can actually see -- okay, we're actually getting proteins that are highly protective. So this is this is the top rank of each of these 4 bacterias that we have tested. So not the bad ones, but the ones that we found to be highly ranked. And here you see a significant coalition on all the different bacteria. So its gonorrhea, [indiscernible] and Staphylococcus aureus, so the 2 in the middle, maybe people don't know. But at least we know Staphylococcus and gonorrhea. So this is truly unique. We actually have an AI score and then we have reality. And we see a coalition. So this is finding -- before it was finding the best antigens, this is -- we can outperform reverse vaccinology, doing things faster and better. We can nail down and filter down instead of testing tons of proteins like in reverse vaccinology, we only test few proteins. And this is a study done by Novartis, is a reverse vaccinology study. So what they're doing is that they test hundreds of proteins. It took them many, many years to make this and they ended up having a pool of proteins, those ones here and tested them in animal models. Before that, we did a lot of analysis and so forth. But then they found these proteins and tested them out. And the red ones are the one that are highly protective. Then in [indiscernible] did the same. This is Staphylococcus A bacteria. They did the same. They also found some of the same protein as Novartis also took years of work and they found additional one, as you can see, 1 red protective protein [indiscernible] approaching. So what if we just run EDEN? Well, in the top rank of EDEN all the proteins that have been protected, we found in the top 4 rank, we found all the proteins they used years of work to identify. We found that just by running our EDEN model [indiscernible] and what we also found was we found in '23, completely novel potential protective proteins, never been tested before. So just to recap. So we took the proteomes of the -- the proteome of the bacteria of Staphylococcus A. And we ran it through in EDEN, it took us 48 hours only instead of years and then we pinpointed the ones that were protected. So 8 proteins was found in [indiscernible], but we still have the additional blue ones that we could test out and see [indiscernible]. Okay. So how do we use this? We have used EDEN to solve the problem -- to solve the gonorrhea problem because -- at least, we believe that it will be a vaccine that works, of course, in humans, but at least we have found the right entities. But first, I will show you here the numbers because gonorrhea is skyrocketing, is becoming antimicrobial resistant and people die of it. So gonorrhea is caused by bacterial cause -- it is gonorrhea bacterium. And it's -- the problem with gonorrhea is that it actually is not often that you have symptoms. So these numbers are only the numbers that are with symptoms, right? So we have a lot of the populations that have actually gonorrhea and it's a huge problem. So that's also why CDC have treated that gonorrhea as a burden threat and that we have to do something about it because people, as you can see, are dying from sepsis. And babies are born blind. You've got in facility, and you've got the damage to the nervous system and so forth. It's doing a lot of problems, and that is rising now. So what we did, we used EDEN, and say, okay, we want to make a gonorrhea vaccine. We processed the gonorrhea [indiscernible] through EDEN, we then took the top 30 of the highly protective predictive proteins, but only the predictive project, these are just predictions. And then we express those and then we tested it out at the UMass Chan Medical School with our very good collaborator [indiscernible]. And we tested out each protein in the top 30. And then we saw that you have that reality actually correlated with the prediction score. So it was a huge happiness when we saw this because we -- now we knew that these 2 proteins that we have in our vaccine, EDEN 1 and EDEN 2, the 2 antigens, they are highly, highly protected. And we then have made a vaccine where we put the 2 antigens together is called infusion protein and then we have one drug. So we have surprised of the production. So -- but also, as you can see, that EVX-02 has a higher or more robust protection than the other 2. So EVX-B2, is comprised of EDEN 1 and EDEN 2. So 2 proteins, 2 antigens together. And another thing was, okay, now we have this candidate now we have this vaccine. Now we want to test the broadness of it. I mean because what EDEN does was that is analyzed the broadness of the vaccine also. So we actually have a vaccine candidate with these 2 antigens in the vaccine candidate that are able to cure. And this is the biggest -- to my knowledge, biggest clinical strain bactericidal killing study ever done. So you see that actually the vaccine can kill the bacteria -- all the bacterias, the 50 bacteria. Normally, when we see this bactericidal killing assays, you only see maybe half of the killing. So the question is on -- so the question is how effectful is this compared to other candidates out there? We have to benchmark it. So what we did was that we knew that GSK and LimmaTech Biologics and Griffith University together are working on our gonorrhea vaccine. And they are out and publishing a lot and going on conferences and they always talk about this protein. This protein NHBA, a protein is also an antigen. So it's a vaccine candidate. That is known to be highly protected against meningitis B, is also a Neisseria bacteria. That is a component of the [indiscernible] vaccine. So it's -- so in meningitis, this protein is -- has high success in the [indiscernible] vaccine. And GSKs, they are also working on this protein. So we, of course, wanted to benchmark our EDEN antigen 1 and 2 towards this highly protected protein. And what we can see here is that our EDEN 1 protein is more protective than this superantigen. And our EDEN 2 is less protective asset. So we believe we have a really truly unique and very powerful EVX-B2 gonorrhea vaccine. This EVX-B2 vaccine has -- that is the one that we have made our partnership with Afrigen Biologics. That are now testing it out in mRNA. But, okay, why is this so protective? I mean because actually, we -- when we look at the at the prediction, we saw that these proteins in the top rank. We saw that these proteins are actually cell division proteins. And [indiscernible] said, okay, okay, why does EDEN tells us that this is a protected protein, it shouldn't be. It should not be on the surface because of cell division. But we said, okay, let's try because the AI system is telling us this is a protective one. And then we test it out. And that is the most protected protein that we have ever seen. So why is it so protected? It's actually because it's not inside the cell all the time. It actually goes out of the bacteria and the service and that is why -- but -- that is why we can attack it. And when it goes out is when it's dividing. So the bacteria is dividing and is vulnerable. In that -- so this is a bacteria that are dividing to, and then we hit it there and then we kill it. So it's a bit like Star Wars. If you know the interest part, we go for it and then the weak spot, sorry. If you know the weak spot, you go for it, right? So this is actually an AI made picture that we made because then we couldn't because as we can present it. So the [indiscernible]. So -- but this goes up the potential of -- this is a new class of antigens, and we see this type of protein also in other bacterias where there is no vaccine available, where there's a huge medical need, so we have -- now we have the real options of going forward with this and big partnerships. And Yes, this is just that EDEN is behind several of our infectious disease product candidates, as you can see. So we really utilize the effectiveness of it. And in summary, EDEN [indiscernible] protection in identifying the most protected antigens and potentially enabling lower risk because you have a highly protected protein in the clinic. Then EDEN outperforms the vaccinology for faster and cheaper vaccine cover, and we have a solution to gonorrhea with our EVX-B2 vaccine. Then we have our unprecedented bacterial killing with our vaccine -- our B2 vaccine. And we have benchmarked it against the leading antigen and it outperforms it. And then also EDEN have helped us to find a completely new type of antigens that we can use broadly.

[indiscernible] think of Chris, you don't need to think. Do you have a question already. Let's get those 2 questions.

So first, do you have any feature for the count for full structure of the protein solubility, how easy it is to actually express it and purify it and productibility of the protein? That's the first question. Second question, what is in percent protection? Is that based on cell-based assays or [indiscernible].

Yes, a really good question. So the first one, so this has been tested by UMass University [indiscernible] in highly advanced sexually transmitted model. So it's a really unique model. Only one lab can do it in the world actually...

So it is a percent protection?

Yes, that's a percent protection when you have reality of the antigens, how protected they are. So that's the sexually transmission model. So you actually -- what you're doing, you're actually giving them antibiotics so you remove the [ microphone ] and then you go in and then you push them with hormones. So they got [indiscernible]. And then you can actually infect it with the gonorrhea bacteria, and that's what we show. So that's what show, it's actually clearance model, where I see the -- how fast it gets cleared so that's a protection.

Then we have a question here. How do you make your prediction based on the proteom with EDEN? What are the predictions based on? And what do you match them with.

So we take -- in gonorrhea, we took all the protomes that we could find. And we feeded it with EDEN and then we calculated something called a cross protective score, so we get the broadness of the vaccine. So it's about also having this conservation.

And then when you mean [ objective ], what kind of experimental models were considered to predict the protectiveness against -- of the protein against the bacteria.

Yes. So gonorrhea, that was the sexual transmission model. But the other 3 bacterias that was survival. So it's actually just such small where you vaccinated and then you see it survived or not. So it's a more top bound model.

And then a little bit long same line, how did you train the model, and this is in the reverse vaccinology, assume you did use the data from Novartis into cell publications or you did not use the publications, so it was just based on the already trained EDEN model, right?

Yes. So some of the proteins that EDEN have been trained on why -- coincidence was that a couple of these proteins that were found were also trained in EDEN. But when we then did the prediction, we left it out. So we have -- so you should imagine EDEN as a system where you have proteins that you train on, you have a lot of proteins to train on. But when we then want to predict another bacteria and if you have used like Staph aureus proteins, and you had use that to train and you want to predict on [indiscernible] protein, you don't check that brain in EDEN. You don't use that component [indiscernible]. So EDEN has a lot of brains where they -- so it's not biased to what is predicting because else is just predicting what was trained on. So it's important to leave out the proteins that you want to predict on or the whole bacteria type. And that's how we do it.

And then looking at the competitive landscape, are there similar AI companies developing AI predictive antigens? And can they also do it within 24 hours.

I've not seen other companies presenting this. I have -- I know that the Oxford University having some academic prediction tools, but they have not talked about how fast they can do it and so forth. So not to my knowledge.

And then I see there are quite a few questions. We'll take a few more, and then we'll ensure that those we didn't get to answer now. We will follow up with answers on those. And I don't know any questions in here before we take a few more here.

You didn't answer my first question.

First one, yes, that was, sorry about that. Let's [indiscernible].

[indiscernible] producibility. So okay, there's [indiscernible] sequence this year output, right? [indiscernible] sequence, how do you know that you can produce...

Yes, exactly -- question. So when we get the output, you have a protein as a full length protein, but sometimes this protein cannot be produced as you're saying, because it can be sit in the membrane and it can have some elements that are not reproducible. So what we do that we use additional bioinformatic analysis tools and then we go in and that was also in our building block vaccine layer we go in and then we remove these elements that can be produced and then we put it together, we [indiscernible] it together. And then we have a structural prediction building block that go in and ensure that is still the right folding and the right one. And [indiscernible] fold is really amazing. Thanks for asking.

And then with regards B2 do the 2 antigens target the same or complementary biologic pathway. And do you see synergistic potential of combining the 2?

That's a really good question. So the ones that were the most protected you could say, better than the GSK protein. That is a true [indiscernible] protein. The other one is also [indiscernible] protein. But that is called [indiscernible]. And that had some has a dual function. So it's also responsible for invasion. So it's actually used as -- the bacteria uses protein to come into the cell -- the human cells. So they have shared the functions, but they also difference. So synergistic effect, yes, I strongly believe that, that will be the case.

And then 1 other question, which is how come EVX-B1 and B2 don't have a corporate partner. And of course, for EVX-B2, we do have a partner, Afrigen Biologics for lower and middle income countries, but we don't for -- outside that, and we don't [indiscernible] B1. And why don't we have that? We haven't been that active in partnering, and that's, of course, a key focus for us now to advance our assets via our new multipartner approach. So we are out there talking to different partners. And -- once again, thank you for all the questions, and I'm sorry that we can't get to answer the moment, but we need to get on to something just as exciting as what we have been and will you introduce the next... Yes. So as you can see, this is RAVEN. And RAVEN is going to be presented by Michael again. So the key architect here -- from RAVEN. So thanks, Mike.

Yes. So I'll talk about RAVEN. So RAVEN is our model for making T-cell antigens something that we think of in quite underappreciated in infectious disease vaccines. So really, our key goal here is to distill down the monogenic component in the whole pathogen into something that is easily produced and very immunogenic. So for instance, the [ Big Spaghetti ] here is the spike from SARS-CoV-2 virus, the common vaccine component, that is in all the different vaccines that are around. And -- it works really well. And the reason that it works really well is that it has really a lot of T cell antigens. So that is what is highlighted here is just 1 T-cell antigen for 1 person. So like I said before, we all have different HLA. So we're all going to respond to this quite differently. But there's not always a lot of antigens in 1 of these important sub units. And there's also the whole concept of you also need T cells for different parts of vaccines. So we want to include the whole pathogen. So here, we show the old genome the SARS-CoV-2, the pervades a spike. It's a small component of the whole virus. So what we also would like to do is to take out the crucial components. We call them hotspots that we can then show the T cells and have a really efficacious vaccine to boost even more. And so what we call a hotspot is really just a collection of T cell antigens. So they're going to be again different from person to person, we really need to make sure that we have a good collection and we have the right connection. So that is what this quarter. So as I've also told you that you really need T cells to get the B cells going, which is the antibody producing cells. So if we provide the right T cells, we can really boost the antigen response. And so that we have also shown here, and this is a quite nice small study where we have 2 different primes. We have the classical spike protein. And then we have 2 T-cell vaccines. So there are only some of these small components that we take out, and we made 2 of them just to show that it works twice. And then we boost with the spike man. So the interesting here is on the left and the right is that the antibody tied us they go up to a similar level to the normal vaccine, and they catch it up using only a single shot of the spike protein. And you might ask, why then do something that is already as good as the other vaccine. But the really key feature here of these T cell vaccine is that they are really, really easy to make. So we can make them in DNA. We can make them in RNA. We aren't going to make them in DNA. We make them for our [ personalized ] trials. That means that we make them really fast and we make them like we need them, okay, we'll make them in a couple of weeks. So there are incredibly easy to make and they work across different modalities. So that is why there are a lot of potential in having these T-cell vaccines. And one of the potential here is in a corona like situation, where it takes a while to get the spike virus in production, and it takes a while to actually confirm that it works. But we know that the T cell part is going to work, so we start making that and then we start production on the SARS-CoV. So once we have the vaccine, the T-cell vaccine, we already have primed the immune system for this vaccine. And that means that the response this time is going to be drastically faster. And then we have also seen that we know from cancer and viruses that we need to kill a T cell. So it's a separate part of the immune system and they surveyal cells that are infected or cancerous and then they kill them. So we also -- what if we only target these? What if we don't have in piece of component. And first and foremost, we try to find these hotspots. And then here, we targeted a mouse because that's what we're going to tested on, and we saw that we got quite a good hit rate on what we predicted. We got almost all of them response against almost all of them, which is really nice. But also crucially on the right, we actually see that these mice that are vaccinated with this, they can survive a lethal challenge. So they do get sick. It's not as a great vaccine as a B cell vaccine, but they are protective. And this is a vaccine that we can make in big weeks. So as soon as any virus comes, as soon as we know the DNA, this is really, really fast to do, then we can start producing a vaccine. And so far, we have done this many, many, many times, it has worked every time. So you can always produce a vaccine. As really sort of the key to these vaccines is that they are so fast. Yes. So we have a model and then we have different ways to utilize it. So we have the stand-alone T cell vaccine that I just talked about. It is protective. It is not -- it is not the best vaccine, but it is very fast, and it works very well. Then we have the prime combo with a B-cell vaccine, which you can sort of prepare. And then so the response time is a little slower, but it's still quite fast. And then finally, we're also developing into the model, but we can now regraft these T cell epitopes that we find into the B cell. So we have like a wild structure vaccine, a more classical vaccine that takes us longer, but it's really high in protectiveness. So the way that this works is that you have a picture of our genomes. So sometimes it's just one virus that comes up. Sometimes it's a whole family of viruses. So you bunch those together, and you run them from a vaccine, so you'll find out what type of epitopes are there. Then you decide on the target calculation, this will upon a database, so we know all the many thousands of HLA types. And then you look how are they distributed in this population. And then you have extremely large matrix of millions of potential antigens. And then you -- and then the key thing here is really selecting the right hotspots that are complementary to each other which is not going to respond to the same antigens on somebody else. So you need maybe some for me, for somebody else. And then if somebody else is also responding to mine. So you sort of have this extreme combinatorial space that you need to distill the virus down into the right hotspots. So that is the key change. So we are good for this in the hindsight of 2020. So we have looked at what people have discovered in SARS-CoV-2 so that is the peaks going up. And then we have looked at what predictions did we make on day 1 of the pandemic. And we think they line up quite nicely. It took at least 8 months to find the [ purple ] peaks. It took us a day to find the [ Blue peaks ] that is going down. So it really is a fast response platform. That's how we initially designed it to be. And then we have now that we -- on the other side, we have started looking into this structural modeling, how can we take these T cell epitope vaccines to the next level? And then you choose your B-cell antigen and we're just seeing how great EDEN are choosing in B-cell antigen. So that's a good starting point. or you maybe sometimes you just have one. So in terms of SARS-CoV-2, you really only have a spike that is going to be good protection. So that's what you have to work with. So that is also what we designed this from is from viruses when you should just have it's very limited selection, but we are also seeing indications that it's working quite well in the [indiscernible] space. Yes. And then we simply insert these T cell epitopes from either across the genome or across the whole can genome of all the different viruses into one antigen. And how we're doing this is through a structural modeling tool. This is also something that we developed a while ago and are still actively developing. So it's -- it's an auto encoder Terrative model that looks at small structure components, and then encode them into this. It's called the laden space. So it's -- again, it's just a big matrix of numbers, but it captures some very crucial things that you cannot see when you look at the structure on a computer or using your human brain. It's something that only the machines can see. And that means that we have a bigger space to grab these peptide centers. So we can really make some extremely efficient vaccines using this technology. Yes. So this is used in some of our newer products. And it's -- yes, so we're really exploring how we can use these, so it's only a few components that you need to add to really improve the efficacy of the vaccine. Yes. So we are finding these hotspots and we are really utilizing our capabilities in personalized space to make fast vaccines, and we can also see that we can choose to target specifically T cell epitopes that really boost B-cell vaccine candidates made a really great antibody repass. Thank you.

Yes. Michael, thank you so much. And I think it's also clear not just having EDEN or RAVEN, but the combination of the 2 offers quite unique opportunities for combining and really making a difference infectious diseases. So it's really an important asset. And then here does RAVEN take phase variation of antigen into consideration variation.

Yes. I don't -- unfortunately, I don't know how to face variation, but maybe we can talk later.

Can RAVEN predict antigens drift into account for viral antigens. So yes and no.

SSo we're really looking at the families of viruses. So we can see what has been. We can identify places where you have a high variability, so then we can target the conserved sites. So of course, when you put an enormous evolutionary pressure on the pathogen is probably going to evolve in a way that you might not be able to predict, at least we can hedge our bets as much as possible using like any technology that we have.

Any questions in the room. Good, thank you, Michael for both presentations. What we're going to do next is that we are going to transition into other part of the business, talking about the personalized cancer vaccines. But before we do so, we are going to take a break and be back here in about 15 minutes. So enjoy the break, and thank you again, Mike. [Break]

So thank you so much for coming back, and thank you so much for actually participating. So we have really a lot of big audience yesterday. So investors family, friends and the partners and so forth. So thanks a lot. And also, on the web. We have a lot of participants. So thanks for that also. It's actually our record and so that's nice. The next speaker -- now we're going into personalized cancer vaccines. And the next speaker is Thomas Trolle is a PHD in Bioinformatics. One of the dream team founders, you can say. So Thomas, it's a key architect of Pioneer, and Thomas is going to present this now. So thanks a lot, Thomas.

A very nice introduction to the team. Yes. So I'll be telling you guys a bit about our PIONEER model, which is our model for designing personalized cancer vaccines based on neoantigens. So in the past 10 to 20 years, there's really been a revolution within the treatment of cancers, and that has been based on these cancer immunotherapies using checkpoint inhibitors. These checkpoint inhibitor treatments allow physicians to treat certain cancers that were previously basically quite beatable with, for example, chemotherapy. And a good example of this is melanoma, where there's been a huge advance in the quality of care we can give to patients. However, when we sort of dig into the clinical trials that tested these checkpoint inhibitor treatments. We actually see that it was only around 20% to 30% of the patients in the trials that actually got a benefit from the treatment. So meaning that the tumor shrank during the treatment. So this highlights the need for improved treatments within this area. So neoantigen-based cancer vaccines are sort of the next logical step in the evolution of these cancer immunotherapies. And they are this because they arise from cancer-specific DNA mutations and this means that neoantigens are found specifically within the tumors of patients and absent from their other cells, from their other tissues. The fact that they are found specifically in their tumors allows neoantigen cancer vaccine to elicit strong and highly specific immune responses directly towards the tumor and hopefully avoiding a lot of side effects that we see from current cancer immunotherapies. And we also believe that the fact that we are triggering these highly specific immune responses allow us to synergize well with the current cancer immunotherapies, which is a big advantage when you're looking to validate these in the clinic. There is, however, a challenge in developing these neoantigen cancer vaccines, and that is the fact that each and every patient has a distinct set of neoantigens within their cancer cells. So here, I'm showing you a graph from a study where the authors analyzed the genomes of more than 300 tumors from melanoma cancer patients. And what you can appreciate is that the number of mutations and thereby potential neoantigens varied a lot from patients to patient with some patients having less than 100 mutations and some patients having several thousands. So we can already see here that, I mean, the set of neoantigens in each patient must dip. They also dug deeper and looked to sort of see where there are some mutations that maybe were found in several patients, and there were a few, but there were very few in far between. And there was not a single mutation that was found in each of the melanoma of patients. And bearing in mind that this is only melanoma. And if you move to lung cancer and colon cancer, the mutational landscape could also look very different between different cancers. So this is a bit of a challenge, you could say, in developing the universal neoantigen vaccine. And it's clear that sort of a traditional vaccine development approach where you have one vaccine that is relevant for all patients. That's not -- probably not going to be the most feasible way to continue in this space. So what we think the next step is to tailor the treatment more specifically to each patient. We're already seeing these precision medicine approaches being used today to treat cancer patients, where the doctors are able to measure various biomarkers on the tumors of patients and thereby direct patients to one or more different treatments. So with the PIONEER model, we are taking this to the very extreme, you can say, and we are basically designing for each patient a specific cancer vaccine that will fit his tumor specifically, his [ RNA ] tumor specifically and their immune system, of course, specifically, as Michael, very nicely introduced, there also can be differences in how our immune systems react to vaccines. So Andreas showed you a bit earlier about how we built PIONEER using these AI immunology building blocks and I'd like to just dig a bit deeper and show you how we actually came to deciding that these were the building blocks that were needed for the PIONEER model. So we designed PIONEER to model mechanisms that go on inside cancer cells that would lead to the generation of effective neoantigens for a cancer vaccine. So the first step is, of course, to identify the mutation within the DNA of the cancer that is sort of the whole basis for this working. Next, we look to see which of these mutations are within a gene and expressed in the tumor, which of these mutations that actually generate a neoantigen, which of the neoantigens are then presented on MHC. Again, as Michael went through earlier. This is a critical step in order for neoantigen to be effective and to be able to interact with the immune system. And here, we, of course, use EvaxMHC building block that Michael very nicely went through in the previous session. Next, we have some methods for predicting which of the presented neoantigens are likely to build on T cell response and finally, for up until now, the first 5 steps, we've sort of been looking at a single cell, but now we sum out looking at the tumor as a whole. And it's a known fact that tumors can be highly diverse in what -- which mutations they had in genomes. This is due to the way they evolve. Inside the body of the patients. And here, we also have a building block that allows us to look at the clonality of the neoantigens and select those that are present in all tumors basically. And finally, doing all this, we get our ranks list of neoantigens and then we use our vaccine design building blocks to design the personalized vaccine for each patient. So right now, a PIONEER is, of course, just one part of a much larger process that goes into creating these personalized cancer vaccines for patients. So here, for example, when a patient is enrolled in one of our trials. The first thing that happens is that we take a tumor sample and a normal sample from the patient. These samples are then DNA and RNA sequenced and this sequencing data is then the input that we use in PIONEER to design our personalized neoantigen vaccine. The design is then sent forth, and we then have a personalized vaccine manufacturing pipeline that produces in the actual vaccine. And then it is then given back to the patient, and in our trials, all our patients received personalized cancer vaccine in combination with checkpoint inhibitor. So the current state of the art [ better control ] for these patients. So the PIONEER model is the model that we have used to generate several of our oncology product candidates namely EVX-01, EVX-02 and EVX-03 and in the following slides, I will show you a bit of data from EVX-01 which is our product candidate that is furthest along in clinical development. So it is currently in Phase II, yes, being tested in the Phase II clinical trial. But I will show you some data from the Phase I clinical trial, which as Andreas said, was performed here in Halo hospital. So the EVX-01 is a peptide-based first neoantigen vaccine and it is mixed with an adjuvant, so a molecule that stimulates the immune system called CAF09b. In this trial, we only enrolled metastatic melanoma patients. And the primary endpoint since it was a Phase I trial was to see that it was safe for the patients to receive the treatment, but also to see that it was feasible for us to create the last vaccine for each patient. Patients received 6 shots. And as I said earlier, they got it in combination with checkpoint inhibitor therapy. So we had some really nice clinical data from this Phase I trial. First of all, we met the primary endpoint, which was the safety and tolerability. So I don't think any patients had any severe reactions to the neoantigens, which we were very happy to see. But we also looked into the immune responses that were generated in the patients. And we're very happy to see that we were able to measure neoantigen-specific immune responses in all of the 12 patients. When we look at the clinical data, we saw that 8 out of the 12 patients responded to the treatment and 2 actually had a complete response. So they were basically tumor free at one point in this time. So we're digging a bit deeper into this data, it was great, but we would also like to see if we could distinguish between the patients that did well and those that didn't. And here, we thought that maybe at the score that PIONEER signs each neoantigen that goes into the vaccine would be predictive of how the neoantigen would perform. So the first thing we did was we saw if the PIONEER score correlated with the likelihood of each neoantigen being immunogenic, so triggering an immune response in the patients. And we saw a pretty nice correlation with the neoantigen scoring higher being more likely to generate any good response. Furthermore, we then looked into how the neoantigens cost of the vaccine study each patient received how that correlated with their response. And once again, we saw that the patients that received the vaccines, which had to say, higher-quality neoantigens, so higher PIONEER scores. They were also much more likely to get a benefit from the treatment than those that received the low scoring antigens, this is all well and good, but we also decided we were going to look this at this at a more unbiased way. And here, I guess you will recognize this plot from a couple of other presentations. But what we then did was we decided to divide our 12 patients into 2 groups. So unbias, those with high the highest scoring neoantigens and those with the lowest and then see how did each of them fair. And as we can see, you can appreciate the blue curve that Six patients that have the highest scoring neoantigens, they had significantly longer progression-free survival. We did the same with the tumor mutational burden, which is sort of the traditional biomarker you use within cancer immunotherapy. And at least in our trial, we saw no difference between those with high mutational burden, those with a low indicating that PIONEER is really -- it does contain some extra information or as maybe specifically relevant for the neoantigen cancer vaccines. So this data set was really what you say, is the clinical validation of the PIONEER model as well as our AI immunology platform. Now we've been talking a lot about the EvaxMHC building block and how central it is to our models. So we really wanted to hit that phone. So to do this, we designed an experiment where we have our PIONEER model. And Instead of using the EvaxMHC building block, we switched that out with 2 other similar prediction tools for predicting the MHC presentation. So one, which is our old gold standard prediction tool, which is based on the EvaxMHC architecture, so very similar performance to that. And another highly cited prediction tool called [ mixMHC ] What we saw when we did that was that the precision with which we were able to predict these immunogenic neurotopes, it dropped. So we were so clearly seeing that EvaxMHC and the newest version of EvaxMHC is critical in order for us to get the optimal performance out of the PIONEER model. Good. So in summary, PIONEER model is our model for designing personalized cancer vaccines based on neoantigen -- it's been tested in 2 Phase I clinical trials and is being tested in an ongoing Phase II trial. We showed that the PIONEER scores are predictive of how likely a given neoantigens to be immunogenic and can also -- are also predictive of how likely a patient is to achieve clinical response to the treatment. And finally, we showed that EvaxMHC is a very core key building block in the model.

Thank you Thomas, to say I keep being impressed each time I see those data from the Phase I trial, even though I've seen it a quite a few times. That's exciting. And you had a follow-up question from before regarding the Moderna Merck personal vaccine A few thoughts on that without taking too much time.

Yes, you can always, of course, talk about that for a long time. But I could say in action, we, of course, we're excited to see that other companies are succeeding in the field of personalized neoantigen vaccine as they are paving the way for us to also continue. And it shows that the approach has merit. Were there any specific questions about that? As far as I'm aware, they haven't shown anything about how their predictions of neoantigens correlate with response, or with the immune system.

No, it was more a comparison of the technology, which is difficult to say too much about.

Yes. I can say that we don't know a lot about how Moderna chooses their neoantigens that is a tightly kept secret. But I guess we all here know that Moderna is, of course, an RNA company first. and maybe not AI or an immunology company at their core, without speaking too much more then, of course.

Good. Then a question here. Our PIONEER quality scores on a 0 to 1 scale, it looks like the top quality go among patients in the Phase I study was only around 0.3%. Can you help me understand it -- and Lee, I'm glad you asked that question because I have been asking the exact same a few times.

Yes, Yes, they are from a 0 to 1 scale. But of course, we build in the fact that there is a lot of uncertainty around the predictions. So in practice, I think the highest growing we've ever seen, it's around 0.6%. But in theory, once we get perfect predictions across the board, they will be from 0 to 5.

And then the question on current status of EVX-01 when Phase II results will be available and the answer to that is, I mean, we are in Phase II, and we are expecting the 1-year data readout in Q3 this year?

Yes.

And then another 1 on the Phase I study of EVX-03, when will that be started. As we have communicated, then we are not going to start the EVX-03 ourselves, but we are looking to do that in partnerships. And then this question here. How will you benefit from a personalized antigen vaccine how will earn customers' cost, how will you cope with this potential business model, pretty broad question, but also super important because, of course, it is a different business model than Yes, when you just produce an antibody in large scale and here you have different supply chain, but also a personalized vaccine, which means specifically for the patient and hence a completely different efficacy or potential at least.

Yes, can you comment on that? Well, first of all, because we are tailoring the treatment specifically to 1 patient, we, of course, believe there's potential for a greater effect than a one-size-fits-all approach, right? You can compare it to having a suit tailored for you. It's just going to fit better than one that you buy down in the store off the rack. With regards to cost, that is, of course, going to be a challenge. But I think we've had some good dialogues with the regulatory authorities and our partners within our personalized vaccine manufacturing pipeline. And they are definitely things that -- I mean, the risk profile between making a drug for one person and making a batch for $100,000 and is very different. So there are definitely things that can be done cheaper and faster in the personalized setting compared to a one-size-fits-all setting, yes.

But I think it's also fair to say that, I mean, now we are not looking to bring a personalized vaccine to the market ourselves. And when you get in a pharma partner used to handling large-scale supply chains and there are definitely opportunities for optimizing those processes and costs. And I think the work that we have been doing in getting the supply chain up and running for our clinical trials. That's quite impressive. And we have actually managed to get it to work very well. So when you talk about at values more patients, also potential for bringing costs down, right?

And are CAR-T treatments, which are in a personalized that are approved. So it is possible.

Then a good question here as well. Would you prefer further development in the metastatic setting with large tumor burden or probably the easier way in the adjuvant or new adjuvant setting, we should have the cadence here this...

Yes, it always goes first. I can definitely answer that. It's a good question. I was at a conference last year where we discussed exactly this. So my personal opinion is that I think the metastatic setting is great because if you can show with fewer patients that your treatment is going to have an effect. In the adjuvant setting, you actually have very few events so that patients that relapse that you actually need to treat a very large amount of a number of patients and that's fine if you're a big pharma. But I think for us, as a smaller biotech sort of going in the metastatic, the more challenging setting, that is definitely the way I would go.

And I know, Birgitte would have answered the same, I guess, so we don't know it.

We actually had a discussion a few weeks ago about the trends in the field, and I think you were Yes, faced it very nicely. The big companies, they do have more muscles. They do have more resources, and there is a tendency, they go for the adjuvant setting where the events are yes, there are fewer wins.

But in theory at least yes.

Yes.

Are there any questions in here? Otherwise, we'll...

I don't know how good it is, but I'll try. It wasn't really clear whether you're an antitussive mutation or do look at multiple mutations.

Great question. Yes. So each neoantigen generally has 1 mutation, but we can, of course, include multiple neoantigens from multiple mutations within the vaccine. So in our Phase II trial, for example, we aim to include 10 neoantigens in each vaccine from 10 distinct mutations, yes.

And then there's a question here around speed whether our platform is fast in identifying neoantigens compared to competitors and also turnaround time. You can say, of course, from having the biopsy, which we have in the vaccine administrative pneumatosis.

So yes, I can say that in our trials, we aim to -- from when we get the sequencing data to when we have the design, we aim to do that in less than 48 hours every time and we've basically been able to do that for all patients in our trial. But yes, I would say speed of design is a very small thing because the production time is actually what takes up a lot of time. And there, I know we have been in our Phase I trial as fast as 6 weeks from tumor biopsy to the patient actually receiving the treatment, which I think is quite fast. But yes.

Then the final question immunogenetic, I referred by you refers to humoral response? Would that also work, for example, DNA-based antigenic targets that might not have strong IGG response.

I have to read that Yes. So actually not. We are talking about the cellular response actually here, not a humoral response. So we -- it is a T cell-focused vaccine aiming to elicit a T cell response and not an antibody response.

Cool I think if no further questions here, then let's say thanks. Well, there's 1 final 1 here. The databases of neoantigens for defined tumor types where your AI can detect public use of neoantigens.

Are definitely databases of neoantigens out there. I will not comment on how complete I think they are. They're probably very bad from doing so. In theory, we could find and that is found in this database, but we don't use them. Everything is done based on the data we get for the individual patients. Thank you.

And I can only say we are looking very much forward to Q3 when we have the 1-year readout of EVX-01 Phase II that is going to be truly exciting. I think the interim data we showed at the end of last year, super encouraging. And I mean, this is also about the clinical validation of the PIONEER platform, but more important. So making a difference from locations with metastatic melanoma where as you say, I mean, even though checkpoint inhibitors are go therapy, then still very few patients actually do respond. So with that, Andreas, would you introduce the next speaker.

Yes. -- the next speaker is presenting obsERV. And it's Christian Garde. So has been here for ages. And -- so Christian has a PhD in Bioinformatics as well and are the key architect on obsERV and also on AI-Deep.

Thank you, Andreas. And I'm very happy to I'm very happy to have the opportunity to present this work -- it's a really a prime example of how we can utilize the AI immunology platform to really facilitate model development to meet medical needs. So just to we buy back a little bit to the previous talk, where Thomas presented nicely how we have our Pioneer model to design personalized neoantigen vaccines. And he also presented that PIONEER is able to quantify the quality of the neoantigens and he showed you this figure to the right where you can see that the patients in our clinical trial, EVX-01, those patients that have a high neoantigen quality, they actually have a longer progression-free survival compared to those patients that have a low neoantigen quality predicted by PIONEER. But that is, of course, also begs the question. So what about the patients who have very few neoantigens of high quality? What can we do about these patients? Can we provide them with a personalized treatment that will be more efficacious than those that the neoantigens can provide. So you really need another antigen source to supplement the neoantigens in order to optimize the personalized treatment here. And in that regard, I would like to introduce you to the endogenous retroviruses. The rest of this talk, I will refer to these as ERVs and the reason I'm introducing to this would be that they are really promising targets as cancer antigens. What are these? there are ancient viruses which infected our ancestors thousands of years ago. They have been lying in our DNA, and they have been passed down through generations. They're very abundant in the genome. And normally, they are not expressed in healthy tissue. But due to dis-regulation that happens in cancers, we suddenly have an expression of these ERVs, ERV antigens. So you really have the characteristic of a tumor-specific antigen year. There are a couple of examples in the literature that had described that ERVs can elicit specific T cell responses in mice, and they can also protect the mice from a tumor challenge. Furthermore, cancer in the measured -- in cancer patients, the T cell responses specific to ERVs have been measured. And finally, also in the laboratory the T cells are specific to the ERV antigens can actually kill tumor cell lines. So all these characteristics are really holds promise for the ERV. So we then wanted to dive in and make some analysis in order to substantiate whether the ERVs would be a useful source of antigens in the personalized setting. The first thing we did was to do a very large-scale analysis across a lot of different cancer types on thousands of cancer patients. We analyzed their genomic profile. And we counted up the number of neoantigens in the patient's tumors and also the number of ERVs being expressed in patients' tumors. Interestingly, if you look here at the figure, then you can see that for each cancer type represented each by a dot, you can see the median number of neoantigens versus the median number of ERV antigens in the tumors for the patients. And what you can see is that they are not correlated. Furthermore, they are not correlated within each cancer type note. And that's actually a good thing because -- then if you have a patient who have very few neoantigens, then there could be the possibility to find ERV sequence, which would be useful for designing a personalized treating. Yes. The next thing we did in order to substantiate further whether ERVs as an antigen source would be efficacious. We look into some cohorts of malignant melanoma patients treated with checkpoint inhibitor therapy. What we did was to analyze genomic profiles from genomic data from the baseline biopsies. And we then countered the number of neoantigens in the patient's tumors and the number of ERVs being expressed in the patient's tumors. Then we split the patients into 2 groups: a group of patients with a lot of neoantigens to get labeled as high TMB grew patients with few neoantigens are labeled as low TMB. If you focus on the plot in the center, -- then we further split the patients into groups based on the number of ERVs neoantigens being expressed in the patient's tumor. You can appreciate that these 2 curves fall on top of each other. So for these patients that have a lot of neoantigens, it doesn't matter whether you have a lot of ERVs antigens being expressed by a few. However, on the contrary, if you focus on the plot to the right, then you can see the group of patients with few neoantigens. And if you then again split these patients into 2 groups based on the number of ERV antigens then you can basically see that those patients that have a lot of ERV antigens being expressed in the tumor, so survival longer on the after checkpoint inhibitor therapy compared to those with very few ERVs being expressed. So this supports that ERVs could be a complementary source of antigens that could help the T cells to fight the cancer when there's very few quality neoantigens present in the tumor. For the next line of evidence we try to investigate was, well, can we actually find these on the surface of tumor cells, so here, we conducted some extra experiments in order to see which kind of MHC ligands do we have displayed on tumor cells. So we did that on 2 mouse tumors, one called the CD26, one called B16-F1. And what we found was that ERVs are actually presented on MHCs and we also found that our peptide MHC prediction tool, EvaxMHC is able to predict these. So that's a really good sign that we can actually find these based on genomic data. So now we had a lot of lines of evidence supporting that we could use this in a personalized setting. So we started developing our model obsERV utilizing our AI immunology platform. And we combined the different elements as such. But if we didn't look a little bit further down the root, then I have created a little schematic for you here to really show the flow from patient to the design of a vaccine using obsERV. So the first step is to collect tumor biopsy from the patient and that is to characterize the patient's HLA type and also identify those ERVs that are specifically expressed in the tumor. Then MHC ligands are predicted, and we rank the antigens, peptides within the of ERV agents based on the potency of the MHC -- predicted MHC hotspots. You can then choose the top ranking peptides. And you can formulate that as a vaccine, for instance, as peptides or in a nucleotide format, which can then be delivered back into the patient. And the nice thing about this is that it fits into an established clinical workflow. And it really aims towards in eliciting both the CD8 and CD4 T cell responses in order to achieve a sustained immune response, but also a sustained effect. So now having developed our observed model, we wanted to test this out in an animal setting. So we designed a personalized ERV based therapy for a mouse, and then we tried to vaccinate a group of mice with this designed therapy. And then we also vaccinated another group of mice with an empty plasmid. So that serves as a negative control. And then we saw how does the -- then we challenge the mice with the CD26 tumor cell line and so how well does the mice fair. So if you look at the plot to the right, then you can see how the tumor develops over time. It's time course we have the number of days after tumor inoculation along the first access and then you have the tumor volume on the y-axis. You can see that the negative control increases its volume exponentially as expected, whereas the obsERV designed vaccine actually completely prevents development of the tumor. Next thing we wanted to showcase was, well, EvaxMHC is a core component in obsERV. So what if we try to swap this out with a different tool, a gold standard tool. So we try to do that in order to really pinpoint the power of EvaxMHC, so we did that and also vaccinated mice, and this is shown as the red curve. And you can appreciate that this vaccine does not completely prevent the establishment of the tumor. We then also look into the T cell responses. And you can see here on the most right figure that specific T cell responses towards the EvaxMHC look actually is 3x stronger as compared to that of the gold standard tool. So it really underscores the importance of having a good MHC prediction tool. Finally, we are also more than 70 days later, try to measure if these T cell responses were really durable responses. So we measured again and we saw that the T cell responses were sustained. We also tried to do a secondary challenge on the EvaxMHC T cell group to see if they could still prevent establishment of the tumor and was still completely prevented. So a very strong and sustained fit. Yes. So now having established proof of concept in preclinic, we feel that we are ready to really test this out in a clinical setting. So that would basically be in a collaboration with a partner as the EVX-03 personalized trial. And this will be a trial where neoantigens and ERVs will be tested together and it will be delivered using our in-house developed delivery technology, which is powered with a ABC targeting unit. So in this trial, you can imagine that you have some patients with -- which have a lot of neoantigens. You can see that on the left figure, all the way on the top. For these patients, they would have a lot of high quality neoantigens and a lot of the new -- there would be a lot of neoantigens within the vaccine design. If you go further down, then you have patients with fewer and fewer high-quality neoantigens. And here, patients would then given treatments comprising more and more ERV derived petites. So it's really a way to ensure that most optimal personalized treatment is given to the patient. And this is how it fits into the pipeline. So as I said, it would be the next personalized trial. This will be tested into antigen.. So in summary, First, they are complementary antigen source to the neoantigens, and we have developed the obsERV model and for the design of ERVs based personalized cancer vaccines. And finally, also, we are ready with the paperwork. We have been in communication with the medical agencies in order to see if this is viable, and we feel ready with the paperwork work to really submit to initiate a clinical trial as soon as the suitable collaboration is established with the partner. Yes.

Thank you so much, Christian. I mean, completely novel target, which can be combined in different ways. That is super exciting. And also good to see here the EvaxMHC and see how much that actually matters for the product capabilities as well. So super interesting. Any questions here? Or any questions online. We have one here. Are you concerned about dilution effect when combining neoantigens and herbs in the same vaccine.

Well, I believe that this is something that we actually did test and we saw that the effect on the preventing tumor establishment was preserved. But I don't think that is a high concern.

How personal are ERVs sequential share or not across patients and/or do you see differences in an ERV expression cross patient. I can say so much, we are getting back to that later, but do you want to say a few things without revealing too much of what's going to happen after the break.

Yes. So -- in contrast to neoantigens, the sequence is concerned. And also to a much larger degree is the expression of the ERVs also preserved between cancer patients. So it's definitely a much more viable target for a precision-based approach as compared to the neoantigens.

We will probably hear more about that after the break. Any other questions? -- or we go for the last break of the day, then we are going to take a break and say, oh, how important is the DNA technology in EVX-03.

Yes. So we had an R&D Day last year showcasing how important it is to happen with ABC targeting neonatal in the delivery technology. But yes, that could also be moved to an RNA-based technology. So the DNA specifically, I would not comment on the importance of DNA specifically, but at least the ABC targeting unit we have seen is a key differentiator in how effective the vaccine is.

And then we have one did vaccine group have any adjuvant. I'm not perfectly sure what it refers to. But...

No, it did not have any adjuvant, but we did start out with an electroporation in order to schedule [indiscernible]

Thank you, and let's have a break. [Break]

So thank you so much for returning and we [indiscernible], so that's amazing, really love it. Now we are jumping into a new session, precision cancer concepts. And there, Christian Garde is presenting our AI-DeeP model.

Thanks, Andreas, for the introduction. Yes, so now we're shifting gears a little bit, and we're talking about prediction of response to actually an established drug. And so just to start out, checkpoint inhibitors are exploited by cancers in order to evade the immune system. And checkpoint inhibitors, they are antibody-based therapy that actually impairs this invasive mechanism in order to reinvigorate the immune system so that the immune system can kill cancer. This has really improved treatment of serval solid cancers and an increasing number of approvals for new cancer types that are coming every year. So it is becoming quite widely used and also as first-line therapy. Now since this has really improved the therapy of several cancer patients, it is also reflected in the market. And Christian already alluded to that the market for checkpoint inhibitors are already now fairly large. But it has actually been projected to reach all the way up to USD 150 billion by 2030 worldwide. So this is a big market. However, despite this being a clear improvement in patient care, then as Thomas also talked about in the PIONEER session, a large fraction of patients actually still do not benefit from the checkpoint inhibitor therapy. That, of course, is an issue. So there's really a demand for increasing -- or further development to increase the efficacy of the immunotherapies, but there's also a demand to identify those patients that do not respond to therapy. And that's also namely because as good as this therapy actually is, it also can cause quite severe side effects in certain patients. Yes, to the physicians' frustration, however, there are no established biomarkers, which are able to predict which patients actually do respond to the checkpoint inhibitor therapy. So that really underlines the issue here. So now I just want you to remember back to the previous sessions where Thomas nicely described how PIONEER is able to quantify in the quality of the new antigens and how that correlated to the progression-free survival of the patients in our in-house combination therapy trial. Furthermore, we also have the ObsERV drive biomarker, which we saw in the last session actually is predictive of the overall survival of melanoma patients receiving checkpoint inhibitor therapy. So we already have established that biomarkers derived from our 2 models for personalized cancer vaccine development and actually can be repurposed to biomarkers predictive of patient response. So we thought that we are in a pretty good situation here and have sort of a responsibility to develop a new model to help the physicians identify those patients that do not respond to checkpoint inhibitor therapy. So basically, the flow would be that you have a cohort of patients, some would be responding, some would not be responding and you have to identify those that respond. That will be based on a tumor biopsy, which the doctor would collect from the patients and then a genomic profile of the tumor biopsies, which would then be analyzed by an AI model to discriminate between the responders and nonresponders. So basically, this has to be done through the lens in our view of genomic biomarkers. And this has several benefits to the patients. If you can identify a patient that you know will not respond, then the patient can be redirected to an alternative therapy that could have potentially a higher chance of providing patients with a benefit. Furthermore, the patient would also avoid the risk of severe side effects. And of course, there's also an issue that is talked about now the impact on the health care budgets. So you could alleviate that by avoiding to treat patients that do not benefit from the treatment. Yes, the genomic biomarkers involve driver mutations, the environment of the tumor, the immune invasiveness of the tumor, also different sources of antigen burdens and of course, biomarkers derived from our PIONEER and ObsERV model. So put in the phrasing of the AI immunology platform, we basically take certain elements from the AI immunology platform in order to design our predictive model called AI-DeeP. On developing model, we then collected a lot of genomic data from 937 cancer patients who have -- who received checkpoint inhibitor therapy. The data was comprised genomic profiles of biopsies collected prior to the treatment. And we then used this data in order to identify the most predictive set of biomarkers, which was then advanced onto the final model development to really see if we can predict patients that have clinical -- do not respond to the checkpoint inhibitor therapy. Yes. So what we then saw was that we -- that if you look at the traditional biomarkers here is played in the figure with the red curve, then you can see that they actually fail to achieve a very, very high precision, which would be warranted in order to avoid depriving a patient or potentially curing therapy. On the contrary, you can see that the AI-DeeP model is actually able to achieve the high precision that is wanted and it does so for 28% of the patients that do not respond to therapy. So -- all in all, AI-DeeP could actually aid the physician in taking treatment decisions. So furthermore, we wanted to investigate. So now we have a range of really predictive biomarkers, but which of them is the most predicted biomarker. So we did that by conducting what is called a feature patient study within the field of machine learning. And that is basically a study where you estimate the importance of each of the biomarkers on the predictive phones. What we then discovered was that our in-house developed biomarkers derived from the PIONEER model and the ObsERV model actually ranked among the most informative biomarker whereas the more established biomarkers, the tumor mutational burden and the PD-L1 expression actually ranked as being much less informative. So in summary, we just want to list here that AI-DeeP leverages our PIONEER and ObsERV model in order to predict where the patients will respond to checkpoint inhibitor therapy, and it can do so quite accurately or subset of the -- on the subset of the nonresponding patients. And we are currently exploring opportunities for our commercial offering and also further clinical validation as a companion diagnostic.

Thank you, Christian. Super good presentation, but try to think about it, right? You are diagnosed with cancer. It would be nice to know upfront whether the therapy is going to work or not. So you don't have to spend 3 months on a therapy without side effects, which then turns out not to work. That's one thing. Another thing is $150 billion by 2030. This is a huge market. We can just support a little bit more efficient use of checkpoint inhibitors. It will mean a lot for societies and health care burden. So I think this is one of the area where even though it's slightly different than some of the other things but when we have the obligation to do because it is repurposing things. It's taking some building blocks, putting it together in a different way. And then it is about the data and predictive capabilities we have. So it might seem different but is in essence in the call what we do with AI immunology and this is going to make a huge difference for society we are in going to be successful in developing a companion diagnostic or whatever it's going to be when we get to the commercial offering. So questions.

Have you tried to use data on mycobacteria to, let's say, to enhance the predictability of your AI-DeeP model?

No, we have not tried that yet.

Would that be one route to...

That could be a way to expand the set of biomarker [indiscernible], that's true and that could also be a different scope of set of biomarkers for instance, derived from scans or others that could also complement the genomic biomarkers.

Then we have a question here. Some PD-1 inhibitors are approved in patients with certain PD Tier 1 levels. Are you saying that your tool could be more exact as a response predictor?

Yes.

That's exactly what -- so exciting here that this is going to be more precise, and we have shown it is more precisely what's available today. Any more questions out there in the online group. Otherwise, we'll say thank you, Christian. And then it's almost a little bit sad that we're coming up to the final presentation but is also going to be super exciting. So do you want to introduce next speaker?

Yes, definitely. So Jens Kringelum, PhD in Bioinformatics, VP of AI and innovation, the first employee in innovation. So -- and Jens is going to present some very, very exciting avenues we can check with a [indiscernible].

Yes. Thank you, Andreas and thank you for the introduction. So first and foremost, I'm very proud and honored that I'm allowed to be the last one. Thank you. But I also know that I am the one standing between drinks and snack, but I hope you still have some energy left for this because I think this is actually truly exciting. So we try to keep a little bit of mystery in the title of this talk. So I was a little bit sad when the very good questions to ObsERV came, took away a bit of the thunder, but I can tell you already now that, yes, you can make [indiscernible] and precision vaccine from these [indiscernible] targets, and this is a little bit what I've been showing today how we do that in action. But first of foremost, let's just remind ourselves on why this is actually important. So this figure here, this is probably the most famous figure in cancer visuals. It was first published in 2013 by a large consortium of global researchers. And what it shows is that it shows how many mutations are there in different types of cancers. And what we see to the right, that is the type of cancers that has a lot of patients. And then we also see that to the left, there are a number of cancer types that have mutations. And as Thomas was explaining, these notations are the source of modern personalized cancer vaccines. These are the input that we need for PIONEER to find very good new antigen sources. And as Thomas also showed, this is important for efficacy. So even though we have a great system, there might be some cancer types that is just very difficult to treat because they have a few targets for these model cancer vaccines. So locally, Christian, you came back alone and showed us that there are these [indiscernible] in the human genome. So these are the ones that has been inherent from our ancestors and we all have them and they constitute a huge part of the genome. And normally, they are all silent. But as Christian also showed, these for some reasons, starts to be used in cancer cells. They're not used in our filter cells, but they're used in cancer cells. And these are actually extremely good targets. So after realizing this, we started to look into. So what does the research actually tells us about this? Is there any proof that this works in patients and this there are. And if you're looking into the AML patency, we see here that people have actually done a lot of great research on this. And what we see here on the left is a research group that in 2020 published some data showing that just with from unvaccinated patients, they could see that the immune system is patient actually picks up somewhere. So they find that the immune system already without being priced by a vaccine is already picking up on these [indiscernible] targets. What we see in the middle of this is basically the same story, but from a different reasons group that they can actually take out blood from patients and stimulate that with the specific targets, and we see an immune response. This is quite remarkable. It tells us that we might be on to something that can be used in a vaccine. And what we see here to the right is that these are actually displayed on the surface of the cancer cells. Just as we saw in our experiments in the mouse cancer cells that Christian was talking about, we also see that when we look into humans. So these are important data for us to make decisions going forward with these kind of targets. So the next thing is it's all about data. So one thing we have done recently is to [indiscernible] of more than 15,000 patients and then run them through our PIONEER model and also run through our ObsERV model. And when doing that -- and this is just for selected cancer type. When doing that, we see that just that Christian was explaining to us that for some cancer types, we see a lot of it, but that's not correlated with a number of mutations. And here, I have just highlighted a specific class and type of cancers, and that is broad cancers. And we see that for some of these broad cancers, they just have a lot of these [indiscernible]. And of course, this could be very interesting cancer types for us to explore further. So -- now we are going into why is this so exciting? One thing we also realized was that some of these targets are shared among patients. That is very rare when we talk new antigens and we talk mutations. But when we talk about this, this is actually a common phenomenon. And another realization is that these are just viruses. They look a bit different from what we are used to. But back in the day when they infected one of our ancestors. Legos turbines that was then integrated into our genome. And we have already built an AI knowledge model that are very effective in designing driver sections, our win model So why don't we take building blocks from the [ brain model ] and build that into our offset model. That was exactly what we did. So we took the building blocks that is needed to build shared and precision vaccines from the [ brain model ] and build that into our offset model. And thereby, we created what we call the observed 2.0 AI-Immunology model. And by doing this, we will then able not only to do personalized earth and new antigen vaccines, but we were also able to make shared vaccines, where you make 1 or a couple of vaccine for the entire populations of cancer patients within a given type of cancers. And we took the new observed 2.0 and just employed it to a number of promising cancer types to see is this actually possible. And this is the results. And basically, the answer is yes, it's possible, but I would also tell you what this figure means. It is maybe a little bit complicated. So what we have here on the X axis. That is number of epitopes, a number of targets that the given vaccine, which targets each individual patients. And what we have on the Y axis is the likelihood of the vaccine accent inducing an immune response in a given patient in that population, in -- that having this type of cancer, that will then be able to target this target in the cancer cell. So what we see is that if we are just requiring the vaccine to have 1 target, if that is enough, that is normally not enough. Then what we see, for instance, in ALL cancers and AML cancers is that we -- we are at very high likelihood, just with 1 vaccine would be able to induce a numerous response in that patient that will target at least 1 target. And then we have 2 targets, 3 targets, 4 targets, 5 targets, 6 target, 7 targets. And if you look at 8 targets, you see that the likelihood is still very close to 1, meaning that's very close to 100%. And if you then go say, if you want 25 targets, then it goes a bit down. But what you also see is that for instance for lung cancer, it's very difficult to make a shared vaccine. So here, the concept is much more difficult, which means that in that case, you probably need personalized vaccines or a prescription vaccines. So another thing we started to look into these different cap syndications. And one specifically indication looked into was AML. This is a broad cancer that unfortunately hits children, but also adults. And when we start looking into the data that we have, we have one data set on children and we had another data set for adults and we wanted to see so do they have the same targets, or do they have different targets. And when we start looking into that, the first thing we did was to look to have the same number of IRF expressed. And what we see is actually that the children, if you are a child below 20 years old is being diagnosed at AML, you have a much lower number of IRF expressed than if you are an adult, above 20 years old. So these could be 2 different diseases actually. Also, what we investigated was that further this expression of IRF correlated with disease states, so how severe the other disease are, and that was not the case. It's simply only correlated with age. So there are some interesting aspects in that we wanted to explore even further. So we look into what IRF was actually expressed in adults and in children. And what we support that, that it was basically the same IRF, but adults just expressed more. So they have a call that is expressed. And then if you are an adult, and diagnosed with AML, which simply just have more IRF expressed. So we took our Observed 2.0 model and said, okay, but could we use this information to make even better vaccines. And then what we did was that, why don't we do 1 vaccines for adults based on the IRF expression in adults and another one for children. And what we see that if you do that for the adult population, it doesn't make a lot different because they are already having all the IRF expressed that we were targeting with a fully shared vaccines. But if you look into children and just look in the case where we won 25 targets, here there are a huge difference depending on where to make share vaccines for all AML patients or a physician vaccine based on which IRF actually expressed in these different patient populations. And this is, of course, something that we are going to explore even further in other indications. The split doesn't have to be in children and adults, to be based on co-expression of IRF based on HLA types. So what kind of different immune system do we have. So right now, we are exploring how we can use this platform even further to make new pipeline products. So my job currently is to explore how can we make this as fast as possible into the preclinical stage and of course, also later on into humans. And with that, I hope that I am convinced you that, again, IRF is a promising target, especially for these cancer types that are difficult to treat with our current modern vaccines. Also, we have developed this Observed 2.0 model that have building blocks from RAVEN, which allows us to do these shared or physician vaccines. And of course, this are trade new avenues. I think we had a question before on the manufacturing cost on the personalized medicine cost, we have a shared approach. The approach to market is different from the personalized approach. So with that, I hope that I just fueled your -- sparked your interest a little bit in this and just maybe open up the window into what is coming next in the field of cancer vaccines. With that thank you.

I think, Jens, a good thing is we know how fast we need to do it because we have promised that we will have a preclinical proof of concept for our precision based [indiscernible] in the second half. And this is exactly why I'm looking so much forward to each of that because it's a truly exciting concept combining a some of the great thing of personalized vaccine with some of the simplicity of the shelf solutions. So that is very exciting. We have a question here around can orphan diseases not necessary in cancer be a target for infection considering the fewer patient [ distribute ] clinical trial and fewer clinical successes can trigger approval for treatment use. Of course, some of these cancers are qualifiers orphan diseases. But it all depends on, yes our model and how it fits into. I don't know if you have a few thoughts on.

Yes. I mean I think that's definitely right, I mean orphan diseases help us a lot of great possibilities and also our models on building blocks can be applied in all those disease models as [indiscernible] were talking about. And in this case, there are also other non-cancer diseases, where doctor [indiscernible] plays a role.

That's true. It's also fair to say we still have ample opportunities within cancer and infectious diseases. I know we're talking about additional therapeutic areas, and that's also exciting, but we still have ample opportunity in where we are. But we also owe it to look beyond where we are now given the capabilities we have and the platform we have. Then 2 questions here. Can you please clarify observed 2.0 enables designing precision or shared vaccines? That's one. Have you looked into [indiscernible] expression patterns among AML patients with various genetic mutations such as TP53 and IDH.

Yes. I can tell a bit -- the last question. No, we have not booked that into that yet, but that's on our agenda. The second one, so it basically do both. So how we envision going from one fits all to fully personalized, that's sort of a sliding window. So you can say that for some specific indicating some specific diseases, there you need a fully personalized approach because that's just the nature of the disease. In other scenario, you can, for instance, like in [ ALO ] or other blood cancers, you can have one-fits-all approach. And then you can add everything in between there. So basically, what our system can do is that if you tell that you have data for an interesting indication and you want to make vaccine for that. And it basically tells you can you make a share one-fits-all, do you need to go to a physician approach by making it 2, 3, 4, 5, or do we need to go to a fully personalized approach. So that -- it can give you that number, basically, how many different designs, different vaccines do you need to make to cover this population and this disease and hopefully have an effect in patients.

Then we have another one. Does a vaccine use mutations in non-coding regions to predict new epitopes?

That's maybe more for you, Thomas [indiscernible].

Yes. No, we don't.

We are in [indiscernible] but also, I mean, we can say that at least for the personalized approach, we do depend on mRNA sequencing data. So we do know whether it's there in the cancer cell.

No questions in here. Then I think it's -- thank you, Jens, for interesting and definitely for [indiscernible]. Then I guess you know what they say, all good things come to an end. That's also the case here. But I have to say I told that you understand why Andreas has been looking forward to this for 15 years. It is a highly unique platform. And it's a platform which has been perfected by a very strong team. It's a platform which offers immense potential for addressing unmet needs, which is in the end, why we are here. And it's also a platform which has a lot of future perspective. So it's really been a pleasure having the opportunity of going through some of the details here. Without repeating things, of course, I do think this is clearly a new era in discovery, design and development of vaccines in the comparison up against reverse rationality, 2 companies spending. We don't know how many years, but many years on coming up with those 8 possible targets even doing it in a very quick way. That's super exciting. And then I mean just take the precision concept here as well, so many examples of what is the new area, new things. It's all about the enablement with AI. I'm not going to talk about that. There's too much talk about that. And we prefer rather just doing it and talking about it and then having the outcome matter. And I think again, this is about addressing the unmet needs. And it's also the first time we have given the insights into this modular architecture of the platform because I often had this question, why doing so many different things? Does it make sense? But we are actually not doing many different things. We're just putting things together in a way where we can do a lot of difference or make a lot of difference in the end that's what matters. And then, of course, the fact that we have our platform validated by partnerships already. We have a strong focus on generating partnerships because in the end, bringing these offerings to patients that do require partners. We are not going to be a commercial scale in an organization for the foreseeable future, if ever. But we are going to partner, and that's what we have strong focus on. And now, of course, always working with the partners to engage in dialogue, and we have exciting assets and moving forward to bringing that forward. Sure, Andreas, do you want to comment for a few conclusion remarks. Was this worth waiting 15 years...

Yes, exactly. So I'm truly grateful of this. And also, I mean, I feel like that we are very close of just like a rocket on the air. So I think really, this is really interesting. And let's see in 1 year where we are, but I hope you'll come back and hear more.

One important thing tomorrow, you all participants also you they are online, you will get a mail from us with a very brief question there. We would very much liking feedback as to what didn't work. So we can do even better next time. We like to continuously do better, and that's where we need your feedback. And then I just want to say, first of all, thank you to all the presenters. And not least the Corps team who have been doing a lot of work in getting us ready here. And then thank you to all of you for showing up here. It's great to have guests in the house and those online, I wish we could invite you for the drinks in the kitchen area, but we'll do that next time. And thank you so much to everyone for joining. This has been a true pleasure having a lot of good questions, and we'll follow up on those. We didn't get to answer yet. So with that, thank you so much for joining for a very active interaction and good time.