Advertise on podcast: Smart Biotech Scientist | Master Bioprocess CMC Development, Biologics Manufacturing & Scale-up, Cell Culture Innovation

Hard-to-treat cancers like pancreatic ductal adenocarcinoma (PDAC) have long defied conventional therapies. Radiopharmaceuticals, combining targeted therapy with diagnostic power, are creating new opportunities in precision oncology. Host David Brühlmann speaks with Bryan Miller of Crown Bioscience, who explains how Crown's strategic partnerships, rigorous quality standards, and adaptive study design are shaping radiopharmaceutical development—delivering speed, safety, and real clinical impact. In this episode, you'll learn: The promise and practical implications of theranostics—agents used for both diagnosis and treatment (02:44)Definitions and distinctions between CDX (cell line-derived xenograft) and PDX (patient-derived xenograft) models, and why PDX models better recapitulate tumor heterogeneity (05:11)Strategies for building more predictive, clinically relevant research models (06:09)Balancing rapid innovation with rigorous quality standards—why robust QC systems enable speed without compromising safety (08:01)Key advice for scientists entering radiopharmaceutical development, including how to choose the right research partners (09:53)Why effective collaboration between biotech companies and CROs is akin to a well-chosen partnership (10:50)The future outlook for radiopharmaceuticals and their impact on hard-to-treat cancers (12:21)Strategic insight: Focusing on theranostic radiopharmaceuticals—agents that combine diagnostics and therapy—offers a high-impact strategy for hard-to-treat cancers like PDAC. By enabling simultaneous patient stratification and targeted treatment, theranostics can accelerate development, improve clinical outcomes, and create a competitive advantage in areas where traditional therapies are limited. Where do you see radiopharmaceuticals and advanced preclinical models making the biggest impact in oncology or beyond? Explore the full conversation to learn how Bryan Miller and Crown Bioscience are scaling innovation for the next generation of cancer therapies. Connect with Bryan Miller: LinkedIn: www.linkedin.com/in/bryan-miller-148344aa Crown Bioscience: www.crownbio.com Next step: Need fast CMC guidance? → Get rapid CMC decision support here Support the show

Imagine treating cancer with the precision of a guided missile—delivering radioactive payloads directly to tumor cells. Radiopharmaceuticals are reshaping cancer diagnostics and therapy by pairing tumor-targeting molecules with radioisotopes for diagnosis or therapy. But what does it really take to develop these therapies, and why is interest from scientists, biotech companies, and pharma accelerating? In this episode, we're joined by Bryan Miller, Director of Scientific and Technical Operations at Crown Bioscience UK. From a PhD in cardiac disease to leading preclinical oncology and radiopharmaceutical programs, Bryan brings hands-on insight into building advanced cancer models and translating innovative therapies from bench to clinic. Topics discussed include: Bryan Miller's path from cardiac disease research to leading preclinical cancer model development (03:03)Crown Bioscience's comprehensive cancer model platforms, from organoids to PDX and humanized in vivo models (04:05)How radiopharmaceuticals differ from traditional chemotherapies in terms of safety and speed, including the concept of theranostics (07:32)The reasons behind the surge of interest in radiopharmaceuticals within science and industry (09:04)The importance of selecting the right preclinical model for success—and how AI and data-driven approaches will shape future workflows (10:11)Critical pitfalls and unique technical challenges in radiopharmaceutical drug development (12:46)Crown Bioscience's collaborative approach with Medicines Discovery Catapult to navigate the complexities of radiopharmaceutical research (13:35)The diverse client needs, from small startups to global pharma companies, and how mature their development programs can be (14:20)Strategies for scaling preclinical and translational capabilities to meet growing demand in radiopharmaceutical studies (16:04)Strategic insight: Radiopharmaceutical success requires integrated design from the start—combining precise model selection, targeting strategy, isotope choice, linker chemistry, and rigorous QC. Programs that establish this comprehensive foundation early move faster and with higher translational confidence than those addressing these elements sequentially or treating any aspect as a downstream refinement. If you're curious about the real challenges of drug development, the rise of theranostics, and how data-driven approaches (including AI) are shaping preclinical workflows, this episode delivers actionable strategies and insider perspectives for scientists and biotech innovators alike. Connect with Bryan Miller: LinkedIn: www.linkedin.com/in/bryan-miller-148344aa Crown Bioscience: www.crownbio.com Next step: Need fast CMC guidance? → Get rapid CMC decision support here Support the show

The cultivated meat industry has captured headlines and struggled with economics. Meanwhile, plant cell biomanufacturing is quietly solving the cost equation and approaching commercial launch. The question isn't whether cellular agriculture can work at scale. It's which applications will get there first, and what bioprocessing innovations will make it possible. In Part 2, we dive into the commercialization challenges that separate laboratory curiosity from market-ready products. Steven Lang tackles the hard questions: How do you replicate chocolate's complex flavor profile without traditional fermentation? What analytical infrastructure ensures product consistency and safety? And how do you build the right team and data foundation to navigate the journey from premium launch to commodity-scale production? Steven's background spanning Johnson & Johnson, Genentech, and Upside Foods gives him a unique perspective on what works and what doesn't when translating biopharma rigor to food applications. At California Cultured, he's applying those lessons to launch high-flavanol cocoa powder in 2026, with a clear roadmap to commodity cocoa and coffee thereafter. In this episode: The challenge of replicating chocolate’s taste and fermentation in the lab (02:39)How plant cell culture differs from conventional farming and its advantages for safety and scalability (03:03)Analytical methods and equipment needed for consistent, safe, and high-quality cultured cocoa products (05:05)The potential for cell-based food to minimize heavy metals and other contaminants in chocolate (06:09)Environmental implications: tackling climate change, deforestation, and the realistic timeline for widespread adoption of lab-grown foods (06:50)Emerging opportunities beyond cocoa and coffee—saffron, ginseng, echinacea, and even lab-grown wood (08:40)Key advice for scientists and entrepreneurs interested in entering the cellular agriculture field (10:12)Building successful teams and robust data foundations in biotech startups (11:43)Key takeaway: Cellular agriculture's future isn't a single technology replacing conventional food production. It's multiple parallel approaches creating resilience in global food systems. The opportunity is clear: the technical principles you've mastered in biopharma translate directly to food applications, but the faster commercialization timelines and novel business models require rethinking what "stage-appropriate development" means. The question for bioprocess leaders is whether you'll help build the solutions to bridge the food production gap, or watch from the sidelines as food security becomes the defining challenge of our generation. Here is the previous conversation with Steven Lang: Episodes 55-56: Cultivated Meat: A Promising Future or an Inevitable Bubble? with Steven LangConnect with Steven Lang: LinkedIn: www.linkedin.com/in/steven-lang-b003406 California Cultured Inc.: www.cacultured.com Next step: Need fast CMC guidance? → Get rapid CMC decision support here Support the show

What if the chocolate industry's reliance on equatorial farms—and the deforestation that comes with it—could be eliminated entirely? Plant cell bioreactors are doing that, producing real cacao without a single tree. But this isn't just about chocolate. It's about fundamentally rethinking how we manufacture food at scale, and the bioprocessing innovations emerging from this shift have implications far beyond the food industry. Steven Lang, Head of R&D at California Cultured, spent two decades mastering mammalian cell culture at biopharma giants like Johnson & Johnson and Genentech. Then he made a radical pivot: applying those same bioprocessing principles to cultivate plant cells for food production. His mission? Prove that cellular agriculture extends far beyond the cultivated meat narrative, and that plant cell manufacturing offers a faster, more economical path to market. At California Cultured, Steven's team is scaling cacao and coffee production using innovative low-cost plastic bioreactors instead of expensive stainless steel vessels. They've engineered plant cell media formulations that operate at a fraction of typical bioprocessing costs. And they're preparing to launch their first commercial product—high-flavanol cocoa powder—in 2026. What you'll discover in this episode: Why cellular agriculture ≠ cultivated meat (07:16) – Steven's frustration with the narrow definition that's holding the industry back, and why plant cell culture deserves equal attentionPlant vs. animal cell culture fundamentals (09:26) – Technical comparison: totipotent plant cells, callus formation, adaptation to suspension culture, and how cacao cell lines are developed from explantsAchieving 30-40% pack cell volume in 7-day batches (11:14) – Process parameters: ambient temperature growth, low pH environments, minimal downstream processing, and maintaining product consistency without genetic modificationThe economics that change everything (14:38) – How plant cell media costs and simple raw material requirements create commodity-scale economicsThe Tesla model for biotech (15:58) – Strategic rationale for launching with premium high-flavanol cocoa powder first, then using that revenue runway to optimize for commodity pricingLow-cost bioreactor innovation (18:23) – Why plastic vessels beat stainless steel, contamination management in low-pH cultures, and scale-out strategy over traditional scale-upDecentralized biomanufacturing (23:10) – Converting underutilized office space into production facilities, onshoring food ingredient production, and what this means for emerging markets and supply chain resilienceThe bigger picture beyond cacao (24:23) – Four approved drugs already produced via plant cell culture, the expanding landscape of ingredients (saffron, ginseng, echinacea), and why stage-appropriate models matter for cellular agriculture's futureThe strategic insight: While the cultivated meat industry struggles with cost structures and consumer acceptance, plant cell manufacturing is quietly proving the business model. The lesson for bioprocessing professionals? Sometimes the fastest path to commercialization isn't the most obvious one, and the innovations happening in food manufacturing today could reshape how we think about bioproduction economics across industries. Here is the previous conversation with Steven Lang: Episodes 55-56: Cultivated Meat: A Promising Future or an Inevitable Bubble? with Steven LangConnect One bad CDMO decision can cost you two years and your Series A. If you're navigating tech transfer, CDMO selection, or IND prep, let's talk before it gets expensive. Two slots open this month. Support the show

What happens when we move beyond oversimplified cell cultures and truly embrace the complexity of human biology? In this episode of the Smart Biotech Scientist Podcast, we explore how advanced 3D cell models are reshaping preclinical research—recreating human tissue microenvironments to better understand tumors, immunotherapies, and gene and cell therapies. David’s guest is Catarina Brito, Principal Investigator at ITQB NOVA and Head of the Advanced Cell Models Laboratory at iBET and ITQB NOVA (Portugal). Her work bridges academia and industry through iBET, a unique partnering organization that integrates cell engineering, bioprocessing, and translational modeling. Catarina’s pioneering models help both pharma leaders and startups predict drug resistance and immunogenicity earlier and more reliably, accelerating the path to safer, more effective therapies—well before clinical trials begin. Topics discussed: Understanding the contribution of stromal and immune cells to therapy outcomes in tumor microenvironments (03:42)Studying immune responses to gene therapy vectors with advanced neural models (04:31)Combining multi-omics and spatial data with AI for predictive biology and patient-specific digital twins (05:16)Catarina’s advice: Start simple, let the biological question dictate model design, and avoid premature overengineering (06:53)Importance of reproducibility, process controls, and standardization in advanced models (08:10)How academic-industry collaborations drive model development, scalability, and real-world relevance (08:42)Common pitfalls: Overengineering, poor cell source selection, insufficient system validation (11:03)Next steps for precision medicine and translational research using advanced cell models (13:08)Want to know how leading scientists make advanced cell models actionable and collaborative for pharma breakthroughs? Tune in for practical strategies, real-world collaborations, and pitfalls to avoid as you scale your own translational research. Connect with Catarina Brito: LinkedIn: www.linkedin.com/in/catarina-brito-ibet Advanced Cell Models Lab – iBET: www.ibet.pt/laboratories/advanced-cell-models-lab Next step: Need fast CMC guidance? → Get rapid CMC decision support here Support the show

What if the failure rate in clinical trials isn't about picking the wrong drug candidates—but about testing them in the wrong models? When you move cells from a 2D culture plate into a bioreactor, you're not simply scaling volume. You're fundamentally changing the biological context. Cell density shifts. Mass transfer dynamics evolve. Mechanical cues emerge. The cells sense these changes and respond—often in ways that derail strategies built on oversimplified assumptions. Most preclinical research still relies on flat plastic surfaces and animal models that miss critical aspects of human biology. The result? Therapeutics fail late in development because the models couldn't predict how human tissues would actually respond. In this episode, David Brühlmann speaks with Catarina Brito, Principal Investigator at ITQB NOVA and Head of the Advanced Cell Models Laboratory at iBET and ITQB NOVA in Portugal. Catarina's career-defining insight came early: studying glycan-protein interactions in murine versus human cells revealed that species differences weren't just nuances—they were fundamental gaps that could mislead entire research programs. Catarina and her team have developed neural, liver, and tumor models that capture the multicellular complexity and microenvironmental cues that 2D cultures cannot replicate. Her work creates preclinical models sophisticated enough to predict human responses while remaining scalable for drug development workflows. Highlights of the episode: Limitations of traditional 2D cell cultures and animal models in capturing realistic tissue behavior and therapeutic responses (06:27)Catarina Brito's personal scientific journey: from discovering model limitations to pioneering 3D culture systems in neural and liver tissues (04:19)How advanced 3D models recreate cell-to-cell interactions, tissue-specific microenvironments, diffusion gradients, and multicellular complexity (10:35)Regulatory movements toward reducing animal models, and the challenge of validating advanced alternatives for systemic biology studies (09:10)Key differences in designing bioreactors for various cell types, with practical examples from liver and neural models (15:16)The impact of scalable, robust 3D models on accelerating drug development and improving selection of candidate therapies (17:22)Key Takeaway: Bioprocess development starts when you choose the model that validates your therapeutic approach. If that model can't capture the biology that matters, every downstream optimization is built on a flawed foundation. In Part 2, Catarina reveals how 3D tumor microenvironments expose drug resistance mechanisms invisible in 2D cultures, and her vision for AI-powered digital twins enabling personalized medicine. Subscribe & Review: If this conversation changed how you think about preclinical model selection, leave a review on Apple Podcasts. Your reviews help other biotech scientists discover these insights. For more CMC development insights, visit smartbiotechscientist.com. Connect with Catarina Brito: LinkedIn: www.linkedin.com/in/catarina-brito-ibet Advanced Cell Models Lab – iBET: www.ibet.pt/laboratories/advanced-cell-models-lab Next step: Need fast CMC guidance? → Get rapid CMC decision support here Support the show

The biotech industry stands on the verge of a radical transformation thanks to artificial intelligence (AI) and machine learning (ML). But even the most sophisticated algorithms are only as smart as the data feeding them. David Brühlmann sits down with Troy Lionberger, Chief Business Officer at A-Alpha Bio, whose team has quietly shattered the data ceiling by measuring and curating more than 1.8 billion protein interactions. Troy Lionberger brings an insider’s perspective from the frontlines of machine learning-powered drug discovery. From partnering with leading biotechs to redesigning classic antibodies for previously “impossible” targets, Troy’s work pushes the edges of what’s tractable in biologic therapeutics. What you'll hear in this episode: Limitations of public data sources like the Protein Data Bank and their impact on current protein engineering approaches (03:11)Why combining energetic (ΔG) and structural data matters for building predictive protein engineering models (05:43)A-Alpha Bio’s approach to generating 1.8 billion protein interaction measurements for machine learning—what this enables today and what’s possible next (06:30)Examples of how A-Alpha Bio’s platform solves challenging therapeutic problems, such as optimizing molecules for 800+ HIV variants and engineering dual-specific antibodies (07:36)The ongoing debate: What capabilities should biotech companies keep in-house, and what works best outsourced to service providers? (09:59)The potential of synthetic epitopes as vital tools for training models beyond the Protein Data Bank—introducing the Synthetic Epitope Atlas (12:09)Key takeaways for scientists: the importance of diligence amidst rapidly evolving AI claims, and advice for accelerating R&D with the right data (14:57)Wondering how to move protein therapeutics from “interesting” to “impactful” without waiting for years of crystal structures? Listen in to learn how you can harness next-gen machine learning tools and custom datasets for your development projects. Connect with Troy Lionberger: LinkedIn: www.linkedin.com/in/troylionberger A-Alpha Bio website: www.aalphabio.com Next step: Need fast CMC guidance? → Get rapid CMC decision support here Support the show

Antibody therapeutics have transformed modern medicine, but for many scientists, developing new candidates still feels like searching for a needle in a haystack—a slow, expensive, and unpredictable process. Structural biology and high-throughput data generation are now collapsing that haystack, offering unprecedented visibility into the molecular handshake that drives life: protein-protein interactions. In this episode, David Brühlmann sits down with Troy Lionberger, Chief Business Officer at A-Alpha Bio, for an in-depth discussion on protein-protein interactions and how advances in data generation and machine learning are transforming antibody discovery and drug development. Troy Lionberger shares his journey into biotechnology, challenges long-held beliefs about antibody development, and explains how Alphabio's high-throughput affinity measurements are shortening timelines and improving outcomes for therapeutic development. In this episode, you’ll learn about: The historical and current challenges in characterizing these interactions at scale (06:22)How new technologies—especially high-throughput platforms—are changing the needle-in-the-haystack approach (08:40)A comparison of traditional in vivo and in vitro antibody discovery methods, along with their strengths and limitations (09:06)The evolving role of AI and machine learning in antibody discovery and lead optimization (12:11)Real-world examples of how A-Alpha Bio’s approach is compressing years of work into months without sacrificing quality (13:58)The science behind A-Alpha Bio’s AlphaSeq technology and how it leverages yeast display and genomics for large-scale affinity measurements (20:43)The practical affinity range the technology can measure, covering most therapeutic applications (23:25)Whether you’re a scientist navigating CMC or a biotech professional curious about next-generation workflows, this episode offers practical insights into both traditional and emerging methodologies in the field. Connect with Troy Lionberger: LinkedIn: www.linkedin.com/in/troylionberger A-Alpha Bio website: www.aalphabio.com Next step: Need fast CMC guidance? → Get rapid CMC decision support here One bad CDMO decision can cost you two years and your Series A. If you're navigating tech transfer, CDMO selection, or IND prep, let's talk before it gets expensive. Two slots open this month. Support the show

For generations, silkworm pupae were discarded as waste from silk production. Now, KAICO is proving these organisms can function as highly efficient protein factories—producing complex vaccine antigens at yields and costs that challenge conventional bioreactor-based manufacturing. With a PCV2 oral vaccine already registered in Vietnam and a human norovirus vaccine preparing for Phase I clinical trials, the silkworm platform is moving from proof-of-concept to commercial reality. In Part 2, Masafumi Osawa, Business Development Lead at KAICO, walks us through the company's product pipeline, the regulatory landscape for this unprecedented platform, and why silkworm-based manufacturing could reshape global vaccine accessibility. From farm-scale validation to regulatory dialogue with Japan's PMDA, this episode bridges platform science with product development. Stops along our Silk Road to biomanufacturing KAICO’s approach to expressing complex proteins, including oral and injectable vaccines for animals and clinical-stage human health products (00:40)Immune-enhancing feed additive for pigs against PCV2 (registered in Vietnam), companion animal products, and human norovirus vaccine entering Phase 1 trials (02:50)Advantages of silkworm-produced antigens for both injectable and oral vaccines, and comparison to plant-based systems (04:57)How silkworm production enables rapid scale-out and high-yield protein expression for global accessibility (05:34)Speed of vaccine development with the silkworm platform—example with SARS-CoV-2 recombinant protein produced in three months (08:08)Key regulatory differences between animal and human vaccine development, including country-specific classification and global harmonization efforts (09:14)Sustainability and distributed manufacturing potential of silkworm-based systems (11:10)Milestones toward the first human biologic produced in silkworms, with phase 1 trials starting soon (12:27)Protein yield per silkworm pupae—scalability advantages compared to conventional bioreactor approaches (14:04)Masafumi Osawa’s thoughts on the future of silkworm-based biologics: from democratized therapies to personalized medicines (15:15)Want to know if silkworms can solve your tough protein expression problems? Tune in now to learn how KAICO’s biotech is set to redefine what’s possible for vaccine development, and how their distributed, cost-effective approach could open doors across sectors. Connect with Masafumi Osawa,: LinkedIn: www.linkedin.com/in/masa-osawa KAICO Ltd.: www.kaicoltd.jp/en Next step: Need fast CMC guidance? → Get rapid CMC decision support here Support the show

For over 4,000 years, silkworms have connected civilizations through ancient trade routes. Now, KAICO Ltd., a Japanese biotech spin-off from Kyushu University, is transforming these creatures into living bioreactors capable of producing complex recombinant proteins and vaccine antigens—without the bioreactors, expensive media, or massive water consumption of conventional platforms. Masafumi Osawa, Business Development Lead at KAICO, brings an unconventional path to biotech. Trained in cultural anthropology with fieldwork experience in Indonesia, he witnessed firsthand the healthcare disparities that drive his current mission. After years in pharmaceutical business development at Towa Pharmaceutical, he joined KAICO to help scale a technology he believes could reshape global vaccine accessibility. His cross-cultural expertise now proves invaluable as KAICO expands internationally, with active partnerships in Vietnam and Thailand and growing interest from other regions. Episode highlights: Masafumi’s transition from anthropology to biotech, and how cross-cultural expertise benefits global health collaborations. (04:15)The founding story of KAICO, spun out from Kyushu University and focused on recombinant proteins and vaccine antigen production (08:45)Step-by-step overview of the silkworm baculovirus expression system, including pupae handling and bioprocessing basics. (10:28)Practical differences between silkworms, E. coli, mammalian, and insect cell culture platforms—exploring advantages and drawbacks. (13:10)Strategies KAICO uses to control silkworm variability, including SPF grade sourcing, diet, environment, and documentation for pharmaceutical acceptance. (15:08)Production scalability: a single pupa can match 100–1000 ml of insect cell culture, with major implications for cost and environmental footprint. (16:42)Downstream harvesting and purification—how KAICO extracts and processes proteins from silkworm pupae, keeping methods largely familiar to traditional systems. (19:31)Regulatory and GMP challenges of using live organisms, and KAICO’s approach to satisfying authorities and ensuring product consistency. (21:43)Whether you’re curious about alternative biomanufacturing methods or want a transparent look at silkworm-based protein expression from research to the clinic, this episode delivers practical insights and thoughtful discussion. Connect with Masafumi Osawa: LinkedIn: www.linkedin.com/in/masa-osawa KAICO Ltd.: www.kaicoltd.jp/en Next step: Need fast CMC guidance? → Get rapid CMC decision support here One bad CDMO decision can cost you two years and your Series A. If you're navigating tech transfer, CDMO selection, or IND prep, let's talk before it gets expensive. Two slots open this month. Support the show

Biomanufacturing has always dealt with the challenge of turning vast, complex datasets and intricate production steps into life-changing therapies. But when batch records multiply and process deviations loom, how do biotech teams make sense of it all? In this episode, we move beyond theory to the nuts and bolts of how AI - when thoughtfully deployed - can turn bioprocessing chaos into actionable intelligence, paving the way for the factory of the future. Our guest, Ilya Burkov, Global Head of Healthcare and Life Sciences Growth at Nebius AI, doesn’t just talk about data wrangling and algorithms—he’s spent years building tools and strategies to help scientists organize, contextualize, and leverage real-world datasets. Having worked across tech innovation and pharmaceuticals, Ilya Burkov bridges cutting-edge computation with the practical realities of CMC development and manufacturing, making him a trusted voice on how bioprocessing is rapidly changing. Highlights from the episode: Advice for biotech scientists on learning from innovations in other industries (00:02:21)Tackling the complexities of organizing huge and often unstructured datasets in bioprocessing (03:08)Techniques and tools to structure, label, and prepare data for AI—including Nebius’s in-house tool, Tracto AI (06:24)Strategies for startups and small teams—how to begin implementing AI and what areas of bioprocessing to focus on first (10:12)The vision for the “factory of the future”: AI-driven, interconnected, and self-learning manufacturing environments (08:11)Navigating the decision between on-premise and cloud computing for scalable, cost-effective AI workloads (12:32)The importance of partnership between scientists and AI, emphasizing collaboration and data-driven decisions (00:15:47)Wondering how to kick off your own AI-enabled bioprocessing project, or what to insource versus outsource as you scale? This episode gives you a grounded starting point—minus the buzzwords and empty promises. Connect with Ilya Burkov: LinkedIn: www.linkedin.com/in/ilyaburkov Contact email: [email protected] Nebius: www.nebius.com If this topic grabbed you, you'll love these related episodes focusing on advanced modeling, continuous manufacturing, and Digital Twins Episodes 213 - 214: From Developability to Formulation: How In Silico Methods Predict Stability Issues Before the Lab with Giuseppe LicariEpisodes 85 - 86: Bioprocess 4.0: Integrated Continuous Biomanufacturing with Massimo MorbidelliEpisodes 05 - 06: Hybrid Modeling: The Key to Smarter Bioprocessing with Michael SokolovEpisode 153 - 154: The Future of Bioprocessing: Industry 4.0, Digital Twins, and Continuous Manufacturing Strategies with Tiago MatosEpisodes 173 - 174: Mastering Hybrid Model Digital Twins: From Lab Scale to Commercial Bioprocessing with Krist GernaeyNext step: Need fast CMC guidance? → Get rapid CMC decision support here Support the show

Across biotech labs, researchers swim in oceans of process data: sensor streams, run records, engineering logs, and still, crucial decisions get stuck in spreadsheets or scribbled into fading notebooks. The challenge isn’t having enough information, it's knowing which actions actually move the needle in cell culture productivity, process stability, and faster timelines. This episode, David Brühlmann brings on Ilya Burkov, Global Head of Healthcare and Life Sciences Growth at Nebius AI. With a career spanning NHS medicine, regenerative research, and cloud infrastructure, Ilya Burkov has lived the leap from microscope to server room. He’s seen firsthand how digital twins, autonomous experimentation, and cloud-first strategies are shifting the way biologics are developed and scaled. Topics discussed: Shifting from experimental-based to computational bioprocess development, and the evolving role of human expertise vs. AI (02:48)Ilya Burkov's journey from medicine and orthopedics to AI and cloud infrastructure (04:15)Solving data silos and making real-time decisions with digital twins and automated analytics (06:36)The impact of AI-driven lab automation and robotics on drug discovery timelines (08:51)Using AI to accelerate cell line selection, cloning, and protein sequence optimization (10:12)Why wet lab experimentation is still essential, and how predictive modelling can reduce failure rates (11:15)Reducing costs and accelerating development by leveraging AI in process screening and optimization (12:32)Strategies for smaller companies to effectively store and manage bioprocess data, including practical advice on cloud adoption and security (14:30)Application of AI and digital twins in scale-up processes, and connecting diverse data types like CFD simulations and process data (17:18)The ongoing need for human expertise in interpreting and qualifying data, even as machine learning advances (19:09)Wondering how to stop your own data from gathering dust? This episode unpacks practical strategies for storing and leveraging your experimental records - whether you’re in a major pharma or a small startup with limited tech resources. Connect with Ilya Burkov: LinkedIn: www.linkedin.com/in/ilyaburkov Contact email: [email protected] Nebius: www.nebius.com If this topic grabbed you, you'll love these related episodes focusing on advanced modeling, continuous manufacturing, and Digital Twins Episodes 213 - 214: From Developability to Formulation: How In Silico Methods Predict Stability Issues Before the Lab with Giuseppe LicariEpisodes 85 - 86: Bioprocess 4.0: Integrated Continuous Biomanufacturing with Massimo MorbidelliEpisodes 05 - 06: Hybrid Modeling: The Key to Smarter Bioprocessing with Michael SokolovEpisode 153 - 154: The Future of Bioprocessing: Industry 4.0, Digital Twins, and Continuous Manufacturing Strategies with Tiago MatosEpisodes 173 - 174: Mastering Hybrid Model Digital Twins: From Lab Scale to Commercial Bioprocessing with Krist GernaeyNext step: Need fast CMC guidance? → Get rapid CMC decision support here Support the show

Computational methods can predict stability issues before the lab. But how do you actually implement these approaches in your formulation workflow? From excipient selection to long-term stability prediction, in silico tools are transforming how biotech teams develop robust formulations while reducing costly trial-and-error cycles. In Part 2, Giuseppe Licari, Principal Scientist in Computational Structural Biology at Merck KGaA, returns to share practical implementation strategies for integrating computational methods into biologics formulation development. Giuseppe reveals how molecular dynamics simulations guide excipient selection, where current methods hit their limits, and how emerging AI capabilities are expanding what's possible in formulation prediction. Whether you're at a well-resourced pharma company or a lean startup, Giuseppe offers actionable guidance for leveraging computational tools to predict protein behavior, optimize formulations, and accelerate your development timeline. Topics covered: Predicting protein aggregation and excipient interactions before manufacturing (00:45)Using molecular dynamics to understand protein behavior over time and in different environments (03:03)The interplay between computational predictions and experimental stability studies (04:49)The limitations of current in silico methods for predicting long-term stability (05:08)Emerging use of AI and machine learning to predict protein properties and improve developability (06:36)Future possibilities: Generative AI for protein design and formulation prediction (08:06)Advice for small companies: leveraging software-as-a-service and external partners to access computational tools (09:55)The impact of increasing computational power on the field's evolution (11:12)Most important takeaway: being open and curious about new computational techniques in biotech formulation (12:08)Discover how to bridge computational predictions with experimental validation, navigate the current limitations of in silico stability forecasting, and position your organization to benefit from AI-driven formulation development, regardless of your resource constraints. Connect with Giuseppe Licari to continue the conversation and explore how computational approaches can solve your formulation challenges before you ever step into the lab. Connect with Giuseppe Licari: LinkedIn: www.linkedin.com/in/giuseppe-licari Next step: Need fast CMC guidance? → Get rapid CMC decision support here Support the show

What if you could predict formulation failures before ever touching a pipette? Computational approaches are revolutionizing biologics development, replacing trial-and-error experimentation with predictive intelligence that catches stability issues early and accelerates your path from candidate selection to clinic. In this episode, David Brühlmann welcomes Giuseppe Licari, Principal Scientist in Computational Structural Biology at Merck KGaA. A chemist by training, Giuseppe transitioned from wet lab experimentation to the predictive power of in silico modeling. Today, he operates at the intersection of computational biology and CMC development, using digital tools to screen candidates for developability, predict formulation challenges, and de-risk development programs before committing resources to the lab. Discover how computational methods are transforming the way biotech companies approach developability assessment and formulation strategy: Why maximizing shelf life isn’t always necessary in early development phases (02:56)The critical role of communication between computational and bench scientists (06:46)Core properties to assess for developability, including hydrophobicity, aggregation, charge, and immunogenicity (11:06)How accurate are in silico predictions, and where do they add the most value? (13:23)The limitations and strengths of machine learning and physics-based models in predicting protein behavior (15:19)The differences between developability, formulation development, and formulatability, and the value of early cross-functional collaboration (17:17)When to use platform formulations and when tailored approaches are needed for complex molecules (19:25)The advantages of using computational methods at any stage, especially for de-risking strategies (20:13)Listen in for practical strategies for integrating in silico predictions into your developability and CMC workflows, catching stability issues before the lab, and making smarter development decisions that save time, material, and money. Connect with Giuseppe Licari: LinkedIn: www.linkedin.com/in/giuseppe-licari Next step: Need fast CMC guidance? → Get rapid CMC decision support here One bad CDMO decision can cost you two years and your Series A. If you're navigating tech transfer, CDMO selection, or IND prep, let's talk before it gets expensive. Two slots open this month. Support the show

What happens when cell therapy innovation meets real patient urgency? In this conversation, the barriers between scientist and patient all but vanish, bringing clarity—and a new sense of mission—to some of the biggest problems facing advanced therapy manufacturing and delivery. Meet Jesús Zurdo, a biotech leader whose three decades of experience in innovation took on a whole new perspective when he became a leukemia patient himself. Seamlessly straddling the worlds of industry and patient care, Jesús Zurdo brings a refreshingly honest, systems-level view to cell therapies, manufacturing bottlenecks, and the realities of getting therapies from the lab to bedside. Topics discussed: Experiences and lessons from stem cell registries and point-of-care manufacturing models (03:15)Challenges and potential of autologous and allogeneic cell therapies, including scalability and accessibility (06:08)The promise and limitations of in vivo cell therapy, delivery risks and patient safety (07:06)Reflections on current trends in manufacturing automation, delivery platforms, and the risk of overengineering (09:49)Barriers to wider adoption of advanced cell therapies, including hospital infrastructure and economic constraints (13:31)The case for earlier lines of treatment with new modalities and value in learning from actual patient experiences (14:30)The importance of integrating voices of patients, clinicians, and developers when solving complex problems (17:31)Why urgency and remembering our future roles as patients should guide therapy development (18:51)Ready for bioprocessing to serve patients, yours included? For more insights and hands-on support, please subscribe so you never miss the next perspective-shifting episode. Connect with Jesús Zurdo: LinkedIn: https://www.linkedin.com/in/jesuszurdo Email: [email protected] Next step: Need fast CMC guidance? New on-demand CMC advisory → Learn more here Support the show