Accelerating pharma: How digital labs and AI are transforming drug development

Speaker A: Foreign.

Speaker B: This is talking Digital Industries, the podcast for technologies and trends that drive sustainable digital enterprises. I'm your host, Alex Chavez. When we're sick, we want medicine that works quickly and effectively. But most people, and I include myself here, give little thought to the long and complex journey that it takes to create that medicine. And uh, it's a costly process that stretches across years. Today we'll explore how the digital enterprise from Siemens is helping pharma and life sciences teams to not only speed up that process, but also to get costs down and to make manufacturing more sustainable, ultimately to get treatments into patients hands as quickly and as safely as possible. I'm joined by three experts who know pharma and life sciences inside and out and let me introduce them. I have with me here Siobhan Fleming, she is the solution owner for Digital Lab at Siemens. I'm glad you could join us.

Speaker C: Glad to be here, Alex.

Speaker B: Andy Whitehawk, he is a digital enterprise and pharma expert also from Siemens.

Speaker D: Nice to be here.

Speaker B: And Sean Ruane, principal data scientist at the Medicines Manufacturing Innovation center, or MMIC M, which is part of the center for Process Innovation, also known as cpi. I'm so happy you're here, Sean.

Speaker A: Thanks for having me on, Alex.

Speaker B: Very nice. So before we jump into the technology, I'd love to hear from each of you what sparked your passion for pharma and life sciences and what keeps you motivated today. Sean, would you like to go first?

Speaker A: So I actually started working at Unilever where I was looking at how soaps behave in various different circumstances. But then at the same time my granddad was going through cancer, so decided to take the skills that I was learning in all the area, which was very exciting, very interesting, um, and try and use them to try and better people's health, essentially to try and see if it could make a difference there. And that led me to work at cpi where we're doing lots of very exciting things, working with lots of different innovations and processes. And that's kind of what keeps me motivated. The potential of all these different things that we're working on, how they could make things cheaper, faster and easier for patients.

Speaker C: Siobhan I initially came to the pharma industry through roles in robotics and software. But it quickly became clear to me that science and technology directly impact lives and the pharmaceutical industry keeps the patient in focus at all times. More recently I lost a close family member to cancer. And that has made it really relevant, really personal for me and has brought clarity to the importance of our work. So now I understand Better the need for speed and in availability of new treatments and the difference that different modalities like tablets or liquids can have for individual patients.

Speaker B: Thank you, Andy.

Speaker D: Yeah, um, I have been working in the pharmaceutical industry for about 20 years now, but actually came through it from a business background, working for a software company and sort of almost fell into the pharmaceutical industry, but I fell in and I've stayed. I love the people that are here, um, because we're all united by this goal and I mean our customers, meaning the pharmaceutical companies are driving to make patients lives better for cures and so on and so forth. And when you're working with a customer, and of course we're trying to build a plant, the idea is to build the plant or to work on a process. But there is at the end a goal we have in seamless this expression technology to transform the everyday for everyone. Nothing transforms your life more than a medicine. Yeah, you need medicines to transform or to continue your life and there's nothing more meaningful, if you like, than what we do in the pharma and life sciences industry and the goals we bring to help everybody to do that.

Speaker B: So for all three of you, really personal reasons, while I was getting ready for this podcast, I came across a statistic that I found very surprising, that it takes around 10 years to get a medicine on the market. But I know that all three of you are working to get those timelines down. Sean, why don't you tell us a little bit more about what CPI is doing? You touched on it briefly in your introduction, but there's more.

Speaker A: CPI with the Centre for Process Innovation, we look at how we make things throughout various different industries, but especially in pharma, which is the area that I'm in, we look how we can make them faster, we can make them cheaper, and how we can basically help the UK economy and help various different small companies to try and get into the market. So here at the mmic, the Medicines Manufacturing Innovation Centre in Glasgow is where we host our grand challenges. And these are big collaborative programs where we bring together multiple large companies like GSK, AstraZeneca and we try and solve problems that can only be solved by collaborating in a kind of pre competitive space before you start bringing things to market. So we've got three grand challenges running at the moment. We've got Grand Challenge 1, which is a continuous pharmaceutical tablet manufacturing line. We've got Grand Challenge 2, which is a next generation clinical trial packaging line that can produce clinical trials for patients as quickly as possible. Grand Challenge three, where we're looking at improving the sustainability of oligonucleotides. So oligonucleotides are really promising drug. They're being used for things like blindness, being used for things like muscular dystrophy and um, there's hundreds of them currently in clinical trials. But the way that we currently manufacture them is very, very unsustainable. It produces lots and lots of nasty solvents like acetonitrile, which are toxic and potentially explosive. So we're trying to minimize the amount of solvents that we're producing in the environment. Especially as more and more of these drugs are going to be coming out and being produced at very large scales.

Speaker D: Maybe I'll just jump in there because I think that the key around the MMIC collaboration is collaboration. The fact that they're working in this pre competitive space, they coined this term the triple helix of collaboration between academia, government and industry itself. And Siemens is a proud founding member of the MMIC to bring the industrial expertise and the technology to be able to help GSK, AstraZeneca and other pharma companies, big or small, with those grand challenges. So we've been involved in all of the challenges in some way providing different aspects of our uh, huge technology portfolio to solve some of those challenges like continuous, like clinical trial, like sustainability. So I think it's an important thing to mention this idea of pre competitive collaboration. And that's one of the great things about the pharma industry is that there is a willingness and an openness to do that because it helps the patient and it also helps the economy. That's what the CPI sells to do as well.

Speaker B: Siemens has a uh, solution that helps pharma and life sciences companies on this journey. It's called Enterprise recipe management. Why don't you tell us a little bit more about that Andy?

Speaker D: Yeah, with pleasure. So enterprise recipe management is a concept that we've been driving for five or six years really around bringing different components of our portfolio, uh, to be able to drive the recipe across the enterprise, hence the name. But where do we start from? We start from actually that automation part, from manufacturing. We need a recipe to be able to manufacture at scale. When I'm building the recipe, when m, I'm designing that recipe, when you think of a TV celebrity cook when they're designing a recipe, there's one doing it for, you know, for you, for your family. Another is doing it for large restaurants or whatever, scaling up. If you want to scale that up, then that's a whole different ball game and you have to make decisions and that will understanding the parameters, the quality, the process parameters, understanding those throughout is important. What that means is being able to connect the person who's configuring the manufacturing plant with the data and the insights and the decisions that were made when somebody was designing that recipe. So enterprise recipe management is really about pulling together all the data that's needed for the recipe. However, now we're looking and we're going even further. We've made some recent acquisitions, companies called Dotmatics and Altair, which is allowing us to go further into the drug discovery part. And this is going to be really key about bringing all that data together across the process, across the recipe, across manufacturing, to be able to be more efficient, have those insights and to drive efficiency, drive cost, drive quality. So, um, on and so forth.

Speaker B: And using these technologies that you've just described, what do you think? How can we compress this 10 years?

Speaker D: Yeah, but that's the killer question, right? Because it's always so many different aspects and nobody, including me, is going to stand up and say, well, because of Siemens technology, we get it down to seven years, but we are squeezing all these different parts that the clinical trials. So maybe with Siemens technology, maybe not. But if we can make clinical trials shorter and you can analyze the data more quickly, if we can reduce the number of experiments, there are all these different things. The aspiration of the industry is to reduce that by half, by three to five years. But there are certain aspects that have to be checked. And we want the medicines that we take, we want them to be safe and we want them to work. Yeah, that's the underlying thing. So that's crucial. That's why it takes 10 years, because of the processes that are put in place to safeguard us as patients. So these still have to be followed. Technology will help to squeeze that and make that faster. How much faster? It's difficult to say, but we can see areas in where our customers are reducing the number of experiments by 25 to 30%, where they're able to accelerate some of the knowledge transfer, for example, as well. So we see real, real tangible benefits there. So not just Siemens, but the industry will be shaving years off that process as we move forward.

Speaker B: Siobhan, maybe you can take us on a deep dive on one of the elements of the enterprise, recipe management.

Speaker C: So what supports us, Alex, in this end to end story is mature management of the data. So the pharmaceutical industry and the research and development space and lab space in particular, are, uh, swimming in data. The recipe is born in the lab. Scientists are Given a molecule, often from the drug discovery stage, and they need to work out how best is this molecule delivery to the patient and how best do we then manufacture the that product to bring it to the patient. Our solution, riffinex helps scientists by giving them a digital platform where they can design the experiments that are needed to do that work. So there is a library of drag and drop elements that they can reuse. Similar to if you were making a recipe from a book and you know that if you want to make a certain type of sauce, this is how you do it. So that can be reused in this new product. All of that data is then captured in one system in a reusable and accessible way. So when we talk about data, we talk about fair. The data needs to be findable, accessible, interoperable and reusable. So that is the core value that this solution is bringing. Removing paper from the lab, making sure that the data is in one system and is available to all of the people who will need it in the lab, and then also through the life cycle of that product.

Speaker B: And when I think of data automatically comes to mind. Artificial intelligence, perhaps you can say a few words about that.

Speaker C: So AI is something that is transforming the pharmaceutical industry. Andy already mentioned our acquisitions of Dotmatics and Altair, which are really strengthening Siemens position in AI across all industries. But for us, very specifically in the pharmaceutical industry, dotmatics will improve our capabilities in drug discovery, which is something that currently takes a lot of desk work and takes more brain power and cognitive power than humans are really capable of doing at the moment. With AI, we can take past medical journals, we can take past experiments that have been done on the drugs that we already have. We can take real world evidence, we can take clinical data and we can use that and apply AI to it to really dig down into that to discover new molecules, to discover repurposing opportunities for existing drugs that are already on the market and really get a better handle on what the possibilities are. And of course, genomics also to better understand the human body and how drugs operate on the body. The increased abilities in the drug discovery area then lead to this potential bottleneck in drug development and process development, which is where AI is coming into its own again. We're using solutions like Riff and X, which help us to manage and orchestrate the activities, but also solutions like Siemens Heaths, which helps us to evaluate the experiments that we have already run and now suggest to our scientists what is the next best place that you should be looking to best manufacture this drug or to best formulate this drug. So that, again, reduces by orders of magnitude the amount of experiments and the time that's needed to bring this drug to the next stage.

Speaker B: That seems to me like it must tie in really well to a project that you're working on, Sean, that also has the potential of becoming a future grand challenge.

Speaker A: Yes. So we're working on something at cbi. We call in the Lab of the Future program. Um, so everybody's currently going on this digital journey where they're trying to transform their labs into a more productive environment where scientists don't have to write things down all the time. But there's no current standard pathway to approach this. So people are struggling at it. So what we're trying to do is work with some really key organizations. People are making standards that work across the industry, not just for one person and not just in one lab, but across labs all the way across all the things that we're doing in the pharma industry. And we're trying to bring them together in a space to talk to vendors and talk to pharmaceutical companies and connect these standards together into a framework that people can called adopt in, you know, a lab where you're measuring how good your drug is, a lab where you're deciding how to make your drug better. And we're trying to build a single framework that you can do to approach all of your data, uh, bring it in with all the context of what people have been doing, why it's been measured, and then let you take that and make decisions quickly. And also bring in all the cool technologies that we're all hearing about, things like AI and have some standard way of approaching that together as a collaboration.

Speaker B: Siobhan, as the solution owner for Digital Lab, you must be really excited about this development.

Speaker C: I am, um, more excited than I've been in the many years that I've been working in the pharmaceutical industry. I think what we're seeing is the tipping point and the convergence of all of the technologies that are available to us being brought to bear on the pharmaceutical lab. So whether that is managing our data through solutions like riffy, using AI for drug discovery, drug development, and even for process development, um, simulation, smart laboratory infrastructure which makes the life of the scientists physically more pleasant by a better environment for them and for the product. Indeed. So I think what we're seeing is really the Siemens approach to technology to transform the everyday is now being brought into the lab of the future. And for me, that is very exciting, very cool.

Speaker B: Our time is coming to a close. But before we go I'd like to hear from each one of you what you see as the next big thing to transform pharma and life sciences. Andy, would you like to start?

Speaker D: So I think there's two AI, uh, we've talked about that already. Being able to harness AI in the right way and the power of that data. So not just AI, so building on that foundation, using AI effectively to get better insights, to be fast in production, to be able to program robots, whatever it might be. And I think there's still a lot to be done based on that data. And the other one, if I may just a second one, is the metaverse is being able to use that to be able to create this digital world of your plant, of your lab, being able to understand how that can operate much more effectively. The tools are out there now to be able to bring these different simulations together through the comprehensive digital twin that we have to be able to really get a deeper understanding of the process, the plant, the equipment and even the patient.

Speaker A: Sian what I'm most excited about is potentially how much more we could be automating tasks in labs, taking the mundane things off scientists so they can be using their brains to make important decisions on what needs to be done to make drugs.

Speaker B: And Siobhan, what has you excited, what

Speaker C: has me excited, Alex, is the potential of these technologies that we've been talking about, using AI and data to reduce the time that it takes to bring a, uh, drug to market. So at the beginning we talked about this 10 year cycle. If we see the potential of reducing that to five or six years, imagine the impact that has on our patients.

Speaker B: Great way to end because that would mean that we get those treatments into patients hands more quickly. Thank you Andy, Sean and Siobhan for your time. It's been great speaking to you and to our listeners. If you want more information, go to siemens.com pharma thank you for joining us today and stay tuned for our next episode.