rAAV Manufacturing: The Challenges of Soft Sensing during Upstream Processing

Area of Science:

• Biotechnology
• Process Engineering
• Data Science

Background:

• Recombinant adeno-associated virus (rAAV) is crucial for gene therapies, but its large-scale manufacturing faces challenges with low yield and high costs.
• Current limitations in upstream processing hinder the widespread application of rAAV-based treatments.
• Real-time monitoring of critical process parameters (CPP) is essential for optimizing rAAV production.

Purpose of the Study:

• To review the challenges and potential solutions for developing soft sensors in rAAV production.
• To explore the application of soft sensing and predictive modeling for real-time monitoring of rAAV upstream processes.
• To address the need for fast and low-cost monitoring approaches in biopharmaceutical manufacturing.

Main Methods:

• Discussion of challenges from a data scientist's perspective.
• Analysis of predictor variable sets lacking viral titer data.
• Consideration of multi-step forecasting and multiple process phases.
• Examination of soft-sensor development strategies, including mechanistic models.

Main Results:

• Identified four key challenges in applying soft sensors to rAAV production.
• Critically discussed potential solutions to overcome these development hurdles.
• Highlighted the importance of integrating data science with bioprocess engineering for improved rAAV manufacturing.

Conclusions:

• Soft sensors offer a promising strategy for optimizing rAAV upstream processing.
• Addressing specific data science challenges is key to successful soft sensor implementation.
• Advancements in soft sensing can significantly reduce costs and improve yields in rAAV manufacturing, facilitating broader therapeutic use.