Thank you everybody for being here today. I'm delighted to introduce Shawn O'Connor, who's the CEO of Simulations Plus. Thank you for joining us, Shawn. I'll turn it over to Shawn to give a brief overview of Simulations Plus and the platform, and then we can go through some questions as well as any questions that we have from the audience. Over to you, Shawn. Very good. Thank you, Mark. Thanks for having us here for the conference. Simulations Plus, we'll be celebrating our 30th anniversary existence as a company this coming year. So, not a new, new player into the marketplace, and biosimulation is not a new, new, new functionality in support of drug development, either. Beginning in the 1990s, the use of a combination of technology and science, mathematics, statistics, along with chemistry, physics, and biology led us to the development of in silico models, models of biology, models of disease state, model of drug characteristics, all in support of providing efficiency, accelerated timelines, to the drug development process. Our platform of solutions span the gamut of application in discovery, early-stage discovery, the lead optimization process, running through into the clinic, preclinical translational impact with biosimulation, into the lab, out of the lab, and through animal testing, first- in- human, and into phase two and phase three clinical studies, as well as post-approval applications of modeling and simulation that supports bioequivalence waivers, the elimination of additional clinical trial support for formulation changes in the manufacturing of drugs. Biosimulation has been in place for many years now, gaining acceptance both from a scientific perspective, from a drug sponsor perspective, and importantly, along the way, regulatory support in support of using in silico approaches. In that regard, probably not the first mention of FDA support in animal testing areas is a recent example of the expanding use cases for biosimulation that has supported the growth and adoption, and yet a continuing long roadmap of further application of biosimulation into the future. Our business is primarily a software licensing business. We provide tools, modeling capability, and models, pre-developed models, for our clients and their internal resources to deploy and use. We also have a scientific consulting service component to our business to support our clients who need additional capacity and/or have not reached that stage of building an internal department, and outsource for these biosimulation support along the way. Basic overview of the company. Open to questions. That's great. Well, thank you for that background, Shawn. And I look, I mean, obviously, you do a lot of different things, as you talked about, kind of over the value chain, you know, for drug development. Now, help me think about, you know, where in the drug development process you're delivering your services. You know, is that in the sort of discovery phase? Is it in the preclinical phase? Is it in the clinical phase? You know, maybe those applications kind of vary, but, you know, I think as people think about AI and drug discovery increasingly today, they sort of think about, you know, the early-stage design of a drug. You know, I'd be curious as you sort of think about, you know, where you guys deliver values, sort of how that looks. Yeah, we touch the full continuum of drug development, obviously some focus areas. When you look at the success ratios of out of discovery into the clinic and through the various stages, there's ripe opportunity to improve the batting averages along the full continuum. Our earliest stage applications is through a product called ADMET Predictor, ADMET absorption, distribution, metabolism, toxicity. It's a tool that deployed AI, machine learning, back in the 1990s, to provide predictive characteristics of a molecular structure, based simply on its drawing, if you will. That utility is applicable in the lead optimization process, along with other inputs, other tools, contributing to the identification of drug candidates to take into the clinic. That said, that represents maybe 15% of our support to our clients. The majority of our biosimulation tools are deployed once the drug candidate moves into the clinic. Several areas of high emphasis. Our PBPK modeling tool, GastroPlus, that approach in terms of modeling and simulation is significantly utilized in translational medicine. So taking that candidate into the lab through animal testing and into first-in-human testing, PBPK approaches allow for a tremendous amount of predictive predictability and design input into animal testing and early efficacy toxicity assessments for first-in-human trials. That approach, that PBPK approach, though, is as well utilized in there further into the clinic, and as I referred to before, it also is used in you know post-approval changes, bioequivalence waivers as well. PKPD is the third area, significant area of modeling and simulation biosimulation support, and that is a technique and a platform that is really focused on profiling drugs, drug characteristics, and its application is in dosing regimens and patient population stratification. In a world in which, maybe the big blockbuster applies to every patient, drug opportunities are drawn further and farther between. Personalized medicine drives us into stratifying patients and identifying patients that the efficacy toxicity profile trade-offs are applicable to subsets of populations, and PKPD modeling is a key tool in that endeavor. All of that leads to the development of protocols for clinical trials, and our input into those clinical trials is significant on the front end, as well as simulating those clinical trials to assess if the likely outcome is adequate, or tweaks and changes to that protocol will improve the likely success of those clinical trials downstream. Great. Well, thank you. You know, I think it's interesting you talk about having used, you know, AI/ML in your products for, you know, decades now. You know, I think there's a perception that, you know, certainly number one topic at this conference appears to be kind of AI, and, you know, I think increasingly people are focused on, you know, the impact of AI on drug discovery, you know, over the last few years and the potential for, you know, novel accelerated drug development. I'm curious from your seat, obviously, you've been doing this for a long time. You know, how have you seen the drug development process change recently with the advent of sort of some of these, you know, newer tools? Are we at the cusp of a fundamentally new way of developing drugs, or is this kind of more of an augmentation of existing research? Yeah, Mark, it took us 10 minutes before we got to AI. I'm surprised that it took us that long to get there. You know, AI is, you know, a revolutionizing everything we do in life, and drug development is an area of high potential in terms of the application of AI as a tremendous tool in the kit here, to accelerate time frames, analysis of data, and certainly something that we have in our toolkit. We see tremendous advancement focus in terms of the use of AI in early-stage drug discovery, the search for new targets, biomarkers, and candidates based upon the gathering and accessing of you know wider populations of data to pinpoint and input into candidate opportunities to move into the clinic. You know, AI is a great tool. It's, you know, it flounders without the scientific input and components there. So the industry is making strides in that regard. Probably the first challenge encountered is, you know, data in. The quality of data in is equivalent to the analysis that comes out, and it's heightened the industry's focus in terms of how do I collect and manage and warehouse our data and position it for use in these areas. Ultimately, we've seen, you know, some increases in terms of candidate identification. And as those candidates move perhaps more quickly, but more abundance, into the clinic, biosimulation value then kicks in. Identification of targets that may be higher in predictable success are great. It funnels and leads to more opportunities for more drug programs that still have that gauntlet of drug development requirements to play out on a go-forward basis. So it's an exciting introduction into our field, both in the context of the you know candidate delivery that it brings, as well as how we can utilize that AI technology as well in our biosimulation approach. I'm curious, Shawn. I mean, obviously, you know, AlphaFold, you know, predicting kind of 200 million, you know, protein structures potentially. Obviously, that creates a lot of opportunity for you in terms of incremental demand that might come into the funnel. But as you sort of think about your business today, it sounds like you've been using AI/ML for a long time. You know, what do you see as kind of the core opportunities for AI within your business? What investments are you making, you know, to take advantage of some of these, you know, advancements? Yeah, where is AI provide value? It provides value in search and find data a bit more quickly. It can assist in terms of interrogating those data sets more quickly and with higher throughput. Importantly, you know, we think of AI and other industries and robots, the agentic AI capabilities that come into play in our world, I think are going to be the most relevant, you know, improving data management and data interrogation. But in the end, the productivity of our scientists, the building of models, the assessment of models that, based upon the data I have, what will be most impactful to a decision at hand is, you know, not an overnight process. There's an assessment of that data, the concept of what model works, the logistics of building that model, running that model, perfecting it, eliminating hallucinations of a biosimulation approach, and then updating it as more data arrives, bearing fruit to that model over the 10-12-year cycle time of a drug. That's a lot of work effort by that modeling scientist. An environment in which one of the gating items for biosimulation adoption has always been the scarce resource of the scientist that is well-positioned to do this type of work. Introducing agentic AI to automate many of the steps of this process, or at least accelerate their speed to completion and putting that scientist into a world of evaluation, and where he can deliver his scientific knowledge, not on the building of the model, but in terms of the evaluation of the model and improvement of that model, is an area ripe for improvement in terms of expanding the productivity of modeling scientist community, which allows for a more rapid deployment and adoption across all of the biosimulation use cases that exist out there. If AI is contributing more candidates into the mix, that wave of incremental work effort can be responded to with more efficient model building and biosimulation. Yeah, lots of opportunities as you point out. And I think, you know, one of the sections of AI is that it's going to make things easier, software easier to develop, the deployment of solutions, you know, all those type of things. I think as you think about, you know, the entry of large sophisticated technology players, people developing their own models, you know, I'd be curious. You obviously got a very long history of doing this, validated models, you know, large data assets. Like, what do you think of as the competitive advantage to kind of building and training AI models in the biosimulation space that, you know, Simulations Plus has? Yeah, you know, we've been in this business for 30 years now, and, you know, the advent of AI tools and whatnot certainly provide capabilities that are there, but I can't overemphasize the contribution, the knowledge on the science side. We saw a tremendous inflow of capital into AI life science startups, focused in the discovery space that, you know, encountered very quickly. This is not translating facial recognition capabilities into drug development, maybe in terms of MRI reading, imaging, type of things, but the knowledge of deep knowledge from a, you know, basic science perspective. Physics, chemistry, and biology, from a medicinal perspective in terms of disease states and disease knowledge. The combination of the great tool with that knowledge is, you know, two very important ingredients into the mix, and that's where we've been living for 30 years. A number of other sort of notes in the, you know, in the business here. Data is very important, and it's not just simply accessing data. There's a wealth of public data that's available, could be accessed by most anyone. There's proprietary data. We, through the years, have had many collaborations and partnerships with pharma biotech companies in which we've gotten access to proprietary data that have informed our models, our algorithms that drive those models. But access to the data is not the only factor. It's your knowledge in terms of curating that data, if you will, into meaningful data sets. You know, simply put, you know, you've got data from five different clinical trials with regard to a specific class of drug or target, whatever it might be. But the differential protocols in those trials requires how do they combine? How do you compare that data in a useful way that, you know, may be appropriate from a data management point of view, but not from a therapeutic knowledge point of view? Tremendous curation capability. You know, there's a couple other barriers there that are very significant. The investment in our biosimulation tools that has been made over the years by our clients doesn't get ripped out and replaced very quickly. That's a significant investment, both in terms of standard operating procedures, IT infrastructure, and leading ultimately to regulatory modes. The FDA open to the use of biosimulation, open to the use of AI, but at the same time, AI is sometimes a black box. Those black box answers are there with regard to well-established GastroPlus Monolix ADMET Predictor platforms offered by Simulations Plus, utilized by the FDA internally, very acceptable when a client, a drug sponsor, comes to the table at the FDA and presents analysis that is output from our platforms. Going to the FDA with a you know a coded-up solution that leads to some analysis puts the FDA in a hold on, let's look at the source code, let's give us some more time frame to make this analysis. There's a good regulatory moat there, as well that, you know, all in all, it requires us to continue to be adept and fast-moving, continue to update and improve both our algorithms, the contents of our models, as well as the functionality of our products that basically translate an ability to use an AI tool to embedding that AI tool into the workflow of a scientist where, I think our expertise comes into play significantly. And I guess on the topic of regulators. I mean, you know, I think biosimulation is, you know, to your point, it's been around for decades. I think a lot of people really stood up and took notice in April this year when the FDA came out and sort of announced a roadmap to, you know, reducing animal testing and preclinical safety studies and that the adoption of computational modeling as a tool would be part of achieving that. You know, I'd be curious to, you know, hear from you how you, you know, think about the opportunity that opens up for Simulations Plus and where are we in the adoption curve today versus where you see as an opportunity to go, you know, the next five, 10, 15 years, you know, if the FDA continues to lean into this as, you know, a potentially interesting innovation, you know, that can start to replace some of the legacy clinical trials? Yeah. Announced in April, doubled our revenues in the May and then quarter. No, not quite that fast. I'll start at the high level, you know. Biosimulation has grown over the years with a series of expanding use cases. There have been animal testing efforts or announcements of uses of biosimulation in the past, not specific to animal testing, but in other areas that generally take a window of time, a period of debate and analysis, scientific debate, leading to guidelines and, you know, the definition of that barrier. What boxes do you need to check in order to diminish or eliminate an animal test? That process is commencing post the announcement in April, and it will play out its course. And like these similar announcements in the past are wind in the sails in terms of adoption of biosimulation and growth of Simulations Plus that accrue over time and build, you know, support for our growing business. The animal testing one will be a little bit more, I think, controversial. There'll be debate on both sides. The sensitivity of the confidence in toxicity safety that comes through animal testing, how do you rely on in silico input to avoid that? I mean, the over and under that I get is that this is a three to five-year sort of time window before we start seeing INDs approved without animal testing. No doubt I would anticipate that, you know, as the guidelines get defined, those first pilot cases will not be, yeah, we'll waive animal testing. They'll be, yeah, let's do that. By the way, let's do a small sample-sized animal test, alongside it to confirm our belief here. These things will develop over time. On the, you know, topic of discussions with clients today, in terms of what do we think it means, and that will build over time as the guidelines become better defined to start ultimately driving, okay, we need more scientists to do this biosimulation, software revenue to Simulations Plus and/or consulting input from Simulations Plus as well. In today's world, we do a lot of work in that translational medicine phase. Our product, GastroPlus, has 12 different species models in it. It's used in order to predict how it's going to perform in an animal test, in the development of the protocol for that animal testing to take place, in the evaluation of how we can reduce population sizes in animal testing. The bar has been efficient animal testing. That bar now becomes how do we eliminate the animal testing. And that will focus on, okay, let's take that predictive capability, and skip the animal testing input that comes in that sequence, to reaching a bar, a confidence level that allows you to go direct to first in human. Functionality is after there. The tightness of those predictive analyses that will be scrutinized. Is there more and different data from organ-on-a-chip solutions that can provide more input to refine those algorithms and enhance the predictive capability here? All to be sorted out, and look forward to it because, as we've seen with other initiatives of this nature, they then drive, most importantly, a significant advancement in terms of cost and timeline to get through these steps. But those ROIs deliver revenue back to Simulations Plus. We look forward to participating in this evolution as it takes place. Be patient. It's not overnight, though. Yeah, well, look, I think it says one thing that's true of, you know, the industry. It's the shared objective of bringing more effective, safer drugs to market. Yes. With this, you know, to your point, I think, expecting to continue to see innovation and, you know, driving towards that goal. You know, I guess nothing's linear in, you know, in the way it sort of plays out. You know, patience obviously is an important virtue. You know, I think it's no surprise to anyone that the biopharma biotech demand environment has been challenging over the last few years. Mm-hmm. You know, how do you see the current demand environment? You know, any insights you can share into how your customers are seeing the world? Yeah. Yeah. It's, you know, I mean, the headlines are well known. You know, you know, starting really, you know, a couple years back in terms of patent expiration and IRA pricing negotiation and, you know, leading to certainly this year, the introduction of IRA and most favored nation pricing and FDA reductions, on and on and on, shocks to the system in terms of our client base. It's an industry that typically, when surprised, hunkers down and slows down. You know, it tends to digest those headlines and stabilize and move forward. But it has been a cost-constrained environment, a low-funding environment. You know, I think, you know, all those headlines will come and go. You know, if you look beyond and don't get distracted by those headlines, underlying is a challenging step down in ROI in drug development. The return on the massive investment that is made has continued to decline, screaming out for improvements, efficiency, timeline, accuracy, success rates along the way in terms of 5,000 molecules into the system to get one approval. Those batting averages need to improve. And you know, my confidence in biosimulation is high given the fact that you know, underlying all the comings and goings of headlines, that improvement in ROI, biosimulation is a key contributor to an improving ROI of a drug development process. And so while you know, we wish the environment was stronger, we wish clients would you know, unfortunately, I can spend X to save Y and the return is great in terms of more biosimulation, but I'm constrained in terms of making X investments. That certainly a good, you know, the biotech without funding can't make those investments and large pharma is slow to make those investments today. You fight through that. We've executed pretty well during this timeframe. Expect to continue that execution and revenue growth into the future and, you know, times will get better. And I, you know, I think obviously the long-term environment, as you sort of point to, you know, remains very much intact. I mean, perhaps you can spend a little bit of time on some of the strategic business realignment that you announced and sort of how that kind of. Yeah. Gets you up for growth in the future. Yeah, just completed in the past quarter or so reorganization. Simulations Plus over the years has grown both organic and organically and through the acquisition of other key components to the biosimulation portfolio of capabilities that we have today. That growth experience, you know, led to a company that was kind of portfolio managed in terms of separate entities. Over the last few years, we've ticked off and completed this year a consolidation into a more functional organization, breaking down the individual groups, combining ourselves into one software development business, one service business down the line. While, you know, from a bean counter perspective, that creates all kinds of efficiencies internally. The real driver has been that while these biosimulation solutions, much like our clients' organization, have grown up in silos, PKPD modeling, that segment of the scientific community developed that approach. QSP modeling, a separate sort of group, addressing types of problems in the continuum of drug development. We see more and more today that these methodologies have increased their impact when used together and in a combined way, to address problems from a multidisciplinary approach, leading to better decisions. And so, you know, I think we're a little ahead of the curve with our clients, but our approach here now is, here's a suite of platform software solutions that your the impact in terms of your development program, will be enhanced by their combined use. Our scientific consulting group, as opposed to, I've got a problem, can you help me out? What can we do from our PKPD group to solve it? It comes into a multidisciplined group, and right from the start, it's the input across the domains in terms of how can we most efficiently shed some light on the challenge that you face. So our go-to-market strategy is evolving to maybe a little bit ahead of our clients, but where our clients are headed in terms of their more holistic look at biosimulation and its impact. You know, in addition to the efficiencies from an internal perspective, you know, the integration of those products, the development of overriding cloud technology, AI components that can be developed once and applicable across our platform as opposed to our own development of them product by product also provides some acceleration in terms of our roadmap in terms of improving our platforms and their capabilities for our clients. Thank you. You know, we talked a lot about AI. We talked about FDA innovation. You know, obviously, you know, we talked about some of the strategic realignment you're doing to take advantage of, of kind of growth. I mean, as you sort of think to the future, you know, what do you see as the biggest opportunities for Simulations Plus? And how do you, you know, how what does your roadmap look like in terms of new market solutions, innovations to take advantage of that? Yeah. You know, really driven, you know, by what we see in the science, in the regulatory directions. We come back to animal testing as an opportunity that, again, we've always got some lead time. This is an opportunity for us to get ahead of the curve and be positioned for the reality of those applications, three years down, down the line. Biosimulation has, you know, I've been in the space for 30 years. We've leaped over the sort of adoption, the acceptance, of biosimulation as a useful tool in this process. And yet every year we find new ways to apply it. Staying current in terms of whether it is small molecule versus biologics. Our early days where we cut our teeth in the cardiac arena, which was top of stack in terms of R&D development. Today, oncology, other therapeutic areas are top of the list, in terms of improving creation of more data that improves the biosimulation modeling effort and predictive accuracy in these areas. So, you know, we look to be guided by advancements in science where drug development is turning in terms of therapeutic areas or type of therapeutics, and regulatory guidance, to continue what is, you know, a long runway of biosimulation value that we can bring to the drug development process. Right. Well, thank you for your time, Shawn. Sure. We really appreciate it and lots of opportunity in front of the platform and look forward to following on. Thank you much, right. Thank you.