Video
PAIR seminar : AI and biomanufacture of ATMPs
Prof. Cui began his presentation by outlining the current progress of ATMPs, including tissue engineering, stem cell and cell therapies, and gene therapies. Biomanufacturing of ATMPs presents a range of complexities and challenges due to the intricate nature of these therapies. The manufacturing processes often require highly specialised facilities and equipment to ensure product safety, consistency and efficacy. Maintaining stringent quality control is particularly challenging, as ATMPs are predominantly patient-specific or involve living cells that are sensitive to environmental conditions. Regulatory requirements are rigorous and continually evolving, necessitating robust documentation and validation procedures. Additionally, scaling up production from laboratory to clinical and commercial levels can be difficult, as processes that work on a small scale may not translate seamlessly to mass production. These factors, combined with the need for skilled personnel and high production costs, make ATMP biomanufacturing a complex and demanding endeavour.
Prof. Cui therefore suggested that AI has significant potential to reduce the costs of biomanufacturing ATMPs by optimising various stages of the production process. AI-driven analytics can streamline process development by rapidly analysing large datasets to identify optimal conditions for cell growth, gene editing or tissue engineering, thereby reducing the need for costly trial-and-error experimentation. Machine learning algorithms can predict and prevent manufacturing deviations, improving batch consistency and minimising waste. AI can also enhance supply chain management by forecasting demand and optimising inventory, thus reducing storage and material costs. Furthermore, automation powered by AI can reduce labour costs and increase throughput by enabling real-time monitoring and control of complex bioprocesses. Collectively, these advancements can make ATMP production more efficient, scalable and affordable, ultimately increasing patient access to these cutting-edge therapies.
Event date: 18/11/2025
Speaker: Prof. CUI Zhanfeng
Hosted by: PolyU Academy for Interdisciplinary Research
Prof. Cui therefore suggested that AI has significant potential to reduce the costs of biomanufacturing ATMPs by optimising various stages of the production process. AI-driven analytics can streamline process development by rapidly analysing large datasets to identify optimal conditions for cell growth, gene editing or tissue engineering, thereby reducing the need for costly trial-and-error experimentation. Machine learning algorithms can predict and prevent manufacturing deviations, improving batch consistency and minimising waste. AI can also enhance supply chain management by forecasting demand and optimising inventory, thus reducing storage and material costs. Furthermore, automation powered by AI can reduce labour costs and increase throughput by enabling real-time monitoring and control of complex bioprocesses. Collectively, these advancements can make ATMP production more efficient, scalable and affordable, ultimately increasing patient access to these cutting-edge therapies.
Event date: 18/11/2025
Speaker: Prof. CUI Zhanfeng
Hosted by: PolyU Academy for Interdisciplinary Research
- 1:24:29
