277: Your Bioprocess Data Already Holds 35% More Yield: From End-to-End Models to Digital Twins with Ignasi Bofarull-Manzano - Part 1

Most bioprocess teams believe a digital twin demands vast datasets and sophisticated models. Ignasi Bofarull-Manzano argues both assumptions are wrong, and that the data already sitting in your Excel files, historians and ELNs is probably enough to start.Ignasi Bofarull-Manzano, Senior Data Scientist and CMC Consultant at Körber Pharma, breaks down what a digital twin actually is, where modeling pays back fastest across the product lifecycle, and how to tell a real business case from an expensive proof of concept.In this episode:Misconceptions about data requirements for digital twins—why quality and context of data matter more than sheer quantity (02:40)Ignasi’s journey from curiosity in biology to a career in data science, modeling, and digital twins (04:31)Clear distinctions between digital models, digital shadows, and digital twins, explained with real-world analogies (06:42)How to approach digital development when faced with legacy data silos and scattered analytics (09:56)The importance of starting with a focused business need instead of chasing trends or buzzwords (12:28)Insights into where modeling truly delivers value in the product lifecycle—development versus manufacturing (13:11)Strategies for small companies to leverage digitalization and data from the ground up (15:56)An accessible overview of physics-informed AI, physical AI, and hybrid modeling—and their application in bioprocessing (18:15)The comparative advantages of physics-informed AI versus hybrid models in different bioprocessing contexts (24:45)Smart insight: Do not start with the model. Start with the bottleneck. Identify the business need first, then the decision the model must support, then the minimum data required for that context of use. Build the model offline, concatenate it end to end across unit operations rather than optimizing one in isolation, and prove the value before connecting a single interface. Teams that skip this sequence end up building models because models sound impressive, and those projects get expensive before they get useful.Before a digital twin can earn its keep, you need connected data, the right model, and a clear decision for it to support. These four episodes cover that ground — data silos, hybrid and mechanistic modeling, and twins built to survive regulatory scrutiny.Episodes 215 - 216: From Data Silos to Autonomous Biomanufacturing: Digital Twins and AI-Driven Scale-Up with Ilya BurkovEpisodes 05 - 06: Hybrid Modeling: The Key to Smarter Bioprocessing with Michael SokolovEpisodes 17 - 18: How Extracting Gold From Your Data Accelerates Process Development with Ioscani Jiménez del ValEpisodes 263 - 264: Why AI and Automation Tools Won't Deliver Until Your Lab's Data Is Connected with David HardyConnect with Ignasi Bofarull-Manzano:LinkedIn: www.linkedin.com/in/ignasi-bofarullKörber Pharma website: www.koerber-pharma.comSupport the show