SMART researchers develop novel UV and machine learning-aided method to detect microbial contamination in cell cultures
Singapore-MIT Alliance for Research and Technology (SMART)Peer-Reviewed Publication
Cell therapy, a treatment that involves transferring living cells into a patient to help restore function or fight disease, shows great potential for treating diseases such as cancers, inflammatory diseases, and chronic degenerative disorders. However, a critical and long-standing challenge faced in the manufacturing of cell therapy products (CTPs) is ensuring that cells are contamination-free before patient use, with serious implications for patients who often need rapid access to potentially life-saving therapies.
Researchers from the Critical Analytics for Manufacturing Personalized-Medicine (CAMP), interdisciplinary research group (IRG) of Singapore-MIT Alliance for Research and Technology (SMART), MIT’s research enterprise in Singapore, in collaboration with Massachusetts Institute of Technology (MIT), A*STAR Skin Research Labs (A*SRL), and National University of Singapore (NUS), have developed a novel method that can quickly and automatically detect microbial contamination in CTPs early on during the manufacturing process to implement timely corrective actions.
This method analyses light absorption patterns using machine learning and ultraviolet light to provide an intuitive, rapid "yes/no" contamination assessment. It offers significant advantages over traditional sterility tests, including a faster contamination detection period, a simpler workflow with no additional preparation required, reduced manpower requirements, and lower costs.
Future research aims to broaden the application across a wider range of microbial contaminants and test the model's robustness across more cell types. Beyond cell therapy manufacturing, this method can also be applied to the food & beverage industry as part of microbial quality control testing to ensure food products meet safety standards.
- Journal
- Scientific Reports