Explore the challenges and opportunities in using AI and machine learning in cell therapy development
AI and machine learning can optimize cell production processes, reducing costs and increasing efficiency. However, there are challenges including accountability, cognitive biases, and the need for human oversight. Despite these challenges, with the proper precautions AI has the potential to revolutionize cell therapy manufacturing.
In this webinar, you'll learn how to effectively apply AI and machine learning to cell therapy process development. We'll explore key techniques, such as designing experiments for optimal results, and examine a case study focused on optimizing perfusion in allogeneic T cell manufacturing.
Discover how to construct comprehensive datasets for AI training, including the importance of sourcing data from multiple donors and runs. We'll present findings from a high-efficiency perfusion process that enables cell expansion beyond standard benchmarks, showcasing how machine learning can support scaling in a 1L production bioreactor while maintaining a favorable phenotype profile.
Additionally, we'll discuss future opportunities for AI and machine learning in advancing cell therapy processes, as well as potential limitations of these technologies in CGT development.
You'll learn:
- How to build robust datasets for AI development and training
- Results from a machine learning case study that achieved high T-cell density at reduced media costs
- Future directions for AI and machine learning in cell therapy, along with insights on where these technologies may be less suitable
About the Presenters
Alex Sargent, PhD
Director of Process Development, Charles River
Casey Nevins
Editor, BioInsights