Smart Biotech Scientist | The CMC and Bioprocessing Podcast for Process Development and Manufacturing Leaders

How do you take a model that works in process development and get it accepted for use in GMP manufacturing? That question stalls most bioprocess modeling projects before they start. Ignasi Bofarull-Manzano, Senior Data Scientist and CMC Consultant at Körber Pharma, pushes back on the premise: the process you run today is already governed by a mathematical model, fitted once at small scale during process characterization and then left untouched for years, even as the process shifts.
Part 1 separated digital models from digital shadows and digital twins, and made the case for starting with the decision rather than the data. Part 2 goes into the plant: what regulators actually require, what the numbers looked like on a real biologics process, and where a team should start on Monday morning.
Topics covered:
Core differences—and surprising similarities—between modeling in development versus manufacturing (02:35)
Regulatory requirements: credibility assessments, model risk, and validation steps for digital twins (05:07)
Real-world example: How deploying an end-to-end process model led to 35% yield increase for Takeda, and considerations for ROI in manufacturing (08:34)
Advice for startup leaders on when to invest in modeling and how to scale efforts case-by-case (11:42)
Steps for scientists new to modeling: identifying bottlenecks, starting simple, and proving value offline before scaling up (12:26)
The importance of understanding basic statistics before relying on AI-generated models (15:22)
A stepwise summary for deploying digital modeling effectively in biotech (16:01)
Smart insight: The digital twin is the last step, not the first. Identify the bottleneck, build the simplest model that supports the decision, and concatenate it end to end so you can see how a parameter moves final drug substance quality rather than one unit operation's output. Prove the value offline. Only then connect interfaces, because that is where the cost and the validation burden live. Teams that lead with the twin arrive at the C-level with a proof of concept and no evidence. Teams that lead with the offline model arrive with a number.
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 Burkov
Episodes 05 - 06: Hybrid Modeling: The Key to Smarter Bioprocessing with Michael Sokolov
Episodes 17 - 18: How Extracting Gold From Your Data Accelerates Process Development with Ioscani Jiménez del Val
Episodes 263 - 264: Why AI and Automation Tools Won't Deliver Until Your Lab's Data Is Connected with David Hardy
Connect with Ignasi Bofarull-Manzano:
LinkedIn: www.linkedin.com/in/ignasi-bofarull
Körber Pharma website: www.koerber-pharma.com
Support the show

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 Burkov
Episodes 05 - 06: Hybrid Modeling: The Key to Smarter Bioprocessing with Michael Sokolov
Episodes 17 - 18: How Extracting Gold From Your Data Accelerates Process Development with Ioscani Jiménez del Val
Episodes 263 - 264: Why AI and Automation Tools Won't Deliver Until Your Lab's Data Is Connected with David Hardy
Connect with Ignasi Bofarull-Manzano:
LinkedIn: www.linkedin.com/in/ignasi-bofarull
Körber Pharma website: www.koerber-pharma.com
Support the show

How do you turn a lab-born regenerative medical device into a solution that surgeons actually want to use and investors want to back? The path from academic innovation to clinical adoption is full of practical hurdles and strategic pivots, where compelling science alone isn’t enough.
David Brühlmann welcomes back Eva-Maria Balet, whose journey spans tissue engineering research at EPFL to leading Regenosca through first-in-human trials, fundraising, and an executive MBA completed while running the company. This conversation covers the practical realities behind that journey, from quality control to clinical setbacks to investor pitches.
Topics discussed:
Defining TissueSpan’s regulatory path and quality control as a medical device (02:49)
The significance of first-in-human studies and what early clinical experience reveals (04:11)
Selecting an initial clinical indication and opportunities for technology expansion (05:50)
Realistic assessment of where soft tissue repair technologies apply—and where they do not (07:18)
The stepwise progression from in vitro to animal models in product development (08:18)
Navigating setbacks, including the impact of Covid-19 on clinical trials, and the value of adaptability (10:36)
Bridging science and business in biotech fundraising and communication (12:15)
Key takeaways from pursuing an executive MBA alongside building a biotech company (13:42)
The importance of collaboration, mindset, and meaningful networks in driving biotech innovation (15:19)
Smart insight: The transition from scientist to founder brought its own learning curve. Eva-Maria pursued an executive MBA while running Regenosca, and points to financial and business vocabulary as the skill she'd have built earlier if she could. For a technical founder or CMC lead, the lesson isn't to become a business generalist, it's that the moment you're translating a manufacturing process or clinical dataset into an investor pitch, fluency in the language of accounting, market strategy, and cost structure becomes as load-bearing as the science itself.
This week's episode with Eva-Maria Balet steps out of bioprocessing into MedTech, following a collagen scaffold from EPFL lab bench to first-in-human implant. These back-catalog picks cover similar ground: what it takes to win investor buy-in beyond the science, the discipline of turning a lab process into GMP manufacturing, why regulatory classification shapes a product's whole trajectory, and what it really takes to commercialize a lab discovery.
Episodes 259 - 260: Why Strong Science Isn't Enough to Get Funded: What Investors Actually Look For with Michael Rome
Episodes 257 - 258: Why Regulatory Affairs Belongs in Drug Design: 30 Years of CMC Lessons from Discovery to GMP Manufacturing with Milan Tomic
Episodes 105 - 106: From Proteins to Cell Therapy: Why ATMPs Aren't Just Complex Biologics with Oliver Kraemer
Episodes 183 - 184: From Lab to Market: Secrets to Commercializing Cutting-Edge Biotech Innovations with Chervee Ho
Connect with Eva-Maria Balet:
LinkedIn: www.linkedin.com/in/eva-maria-balet-72561737
Regenosca website: www.regenosca.com
Support the show

Imagine a wound too large for the body to close on its own. That's the problem Eva-Maria Balet set out to solve, not with living cells, but with a structural bridge that lets the body's own healing mechanisms do the rest.
In this episode, David Brühlmann welcomes Eva-Maria Balet, Co-Founder & CEO of Regenosca. Trained at EPFL, Eva-Maria brought her fascination with cellular "factories" from academia straight into entrepreneurship. Rather than chasing elegant science for its own sake, she built her company around a single principle: start with a real clinical need and build backward, collaborating with clinicians from day one so every experiment serves a patient.
Highlights & Topics:
Why starting with clinical needs—not just scientific excitement—creates meaningful real-world impact in life sciences (02:38)
How Eva-Maria’s fascination with biotechnology guided her from cell factories to developing scaffolds for tissue repair (03:51)
The unmet challenges in current soft tissue repair treatments and where new solutions are needed (05:51)
What makes Regenosca’s fully-engineered collagen implant, TissueSpan, different from existing meshes and biological materials (07:09)
The biological mechanisms behind tissue regeneration using a temporary collagen scaffold (08:28)
Translating lab-scale research into a robust, scalable, and regulatory-compliant production process (10:34)
The practical realities and hurdles of navigating the medical device vs. biologic regulatory pathways (11:59)
Advice on building regulatory expertise into your founding team or leveraging consultants effectively (13:31)
The importance of interdisciplinary teams and trust when forming biotech startups (14:36)
Smart insight: Eva-Maria put it plainly: what works in the lab has to work reliably every single time you produce it for a patient. That shift, from proving a concept to controlling a process, from raw materials through in-process controls to final product testing, is the same discipline any CMC scientist recognizes: science alone doesn't get a product to patients. Reproducibility does.
This week's episode with Eva-Maria Balet steps out of bioprocessing into MedTech, following a collagen scaffold from EPFL lab bench to first-in-human implant. These back-catalog picks cover similar ground: what it takes to win investor buy-in beyond the science, the discipline of turning a lab process into GMP manufacturing, why regulatory classification shapes a product's whole trajectory, and what it really takes to commercialize a lab discovery.
Episodes 259 - 260: Why Strong Science Isn't Enough to Get Funded: What Investors Actually Look For with Michael Rome
Episodes 257 - 258: Why Regulatory Affairs Belongs in Drug Design: 30 Years of CMC Lessons from Discovery to GMP Manufacturing with Milan Tomic
Episodes 105 - 106: From Proteins to Cell Therapy: Why ATMPs Aren't Just Complex Biologics with Oliver Kraemer
Episodes 183 - 184: From Lab to Market: Secrets to Commercializing Cutting-Edge Biotech Innovations with Chervee Ho
Connect with Eva-Maria Balet:
LinkedIn: www.linkedin.com/in/eva-maria-balet-72561737
Regenosca website: www.regenosca.com
Support the show

Building a cell therapy company is hard. Building a genetically engineered iPSC therapy for the brain, on a preclinical budget, is one of the hardest translational problems in biotech. Every experiment has to move the program closer to an IND, or it's motion without progress.
That's the operating constraint Bilal Fares faces as CEO and co-founder of AzureCell, the University of Geneva spin-off engineering neuroprotective iPSC neurons for Parkinson's disease. In Part 2, he walks through how his team decides what to build, where AI and synthetic biology genuinely accelerate a CMC roadmap, and the four founder lessons he wishes he'd internalized earlier, including his conviction that scientists who use AI will replace those who don't.
Topics discussed include:
Strategies for prioritizing experiments and narrowing focus with limited resources (03:33)
How business opportunity validation programs helped define a product roadmap (04:08)
Integrating AI and synthetic biology into research programs—and where these tools do, and don’t, accelerate development (05:07)
Building a cell therapy platform for personalized approaches in neurological diseases beyond Parkinson’s (06:38)
Lessons learned in biotech leadership and why tackling big problems matters (08:08)
Key advice for aspiring biotech entrepreneurs: kill your own solutions quickly, and learn from others (09:27)
The importance of having a strong team and how a powerful mission attracts top talent (12:21)
AzureCell’s near-term plans and future goals, including upcoming fundraising and R&D milestones (13:30)
Smart insight: What separates successful biotech ventures from the rest? According to Bilal Fares, it is not just technical skill but mindset. First, choose a problem large enough to be worth the struggle. Second, try to “kill your solution as fast as possible”—engage experts, enter competitions, and seek brutal feedback early so you can pivot, improve, or abandon as needed. And finally, plan with the end (approval, patients, impact) always in sight.
If you enjoyed this, check out these episodes on cell therapy, where engineered cells can survive and do more than replace what's lost: Michael Rome's investor lens rounds it out for founders facing the same funding realities.
Episodes 269 - 270: How to Turn Mesenchymal Stem Cells into Programmable Cancer Delivery Vehicles with Jun Yung Woo
Episodes 253 - 254: How to Source, Manufacture, and Scale the Earliest Stem Cells for Allogeneic Cell Therapy Without Ethical Barriers with Yuta Lee
Episodes 249 - 250: How T Cell Activation Redefines TIL and CAR-T Manufacturing (Boosting Success Rates to 95%) with Chantale Bernatchez
Episodes 259 - 260: Why Strong Science Isn't Enough to Get Funded: What Investors Actually Look For with Michael Rome
Connect with Bilal Fares:
LinkedIn: www.linkedin.com/in/b-fares
AzureCell website: www.azurecell.co
Email: info@azurecell.co
Support the show