Artificial intelligence (AI) can help industry manage the terabytes of data generated during bioprocessing, according to a facility design expert. Automation is nothing new in biopharma. Industry has been automating aspects of production, handling, and transfer processes for decades with its aim being to ensure product consistency and minimize operator involvement.

More recently the focus has shifted to monitoring, in part due to growing regulatory support for quality by design (QbD) and process analytical technology (PAT). But while it may improve product quality and manufacturing efficiency, automated in-process monitoring generates huge amounts of data. Handling this information at the plant level is a major undertaking, according to Jörgen Harrysson, managing director of facility design consultancy at KeyPlants, who added that biopharma often struggles to “compile and manage the process data.” And volume is not the only challenge. According to research by the University of Cambridge, there are sometimes gaps in bioprocess data resulting from variations during production. This is a problem because it is harder to base analytical decision-making on incomplete information.

AI is a potential solution, according to a 2019 report by Deloitte. “AI technologies are poised to impact these [automated biomanufacturing] processes through real-time data processing and decision making that can make supply chains truly data-driven,” according to the report. “The ability to adjust processes and track medications in real-time will allow biopharma companies to manage their supply, quality, safety, security, and costs, resulting in more intelligent manufacturing and supply chain decision making.”

This view is shared by Harrysson who said, “We see big opportunities with automation and AI for biopharma companies. Engaging with an engineering company like KeyPlants with automation and AI expertise, as well as bioprocessing early on, can help companies to set a strategy and implement these new technologies.”

KeyPlants’ approach is to use modular design and bioprocessing systems that are interoperable and compatible to make the implementation of AI more straightforward. And according to Harrysson, all sectors of the biopharmaceutical industry are showing interest in the approach, even manufacturing in the monoclonal antibody (mAb) sector where processes are well established. “Although we have started to see more requests for cell and gene therapies, the demand for mAb facilities still seems to be larger. Other areas of demand include vaccines and biosimilar facilities. Modular facilities are suitable for any biomanufacturing plant and in particular for cell and gene therapies where speed and flexibility often are key drivers.”

Interest in modular manufacturing and AI is a global trend, noted Harrysson. “We currently see strong demand for biopharmaceutical facilities driven by lack of capacity due to R&D, successful new product launches, and an expanding global market. Big Pharma continues to spend the majority of their investment in Europe and [the] United States. We also see growth in Asia and [the] Middle East driven by the need for local manufacturing.”

Previous articleSelexis Cell Line Development Strategies
Next articleAdvancing Platelet-Based Therapeutics for Patients