Novel UV and Machine Learning-Aided Method Detects Microbial Contamination in Cell Cultures

Cell therapy holds great potential in treating diseases such as cancers, inflammatory conditions, and chronic degenerative disorders by manipulating or replacing cells to restore function or combat disease. A significant challenge in manufacturing cell therapy products (CTPs) is ensuring that the cells are free from contamination before being administered to patients. Current sterility testing methods, which rely on microbiological techniques, are time-consuming and can take up to 14 days to detect contamination. This delay poses a risk to critically ill patients who urgently need treatment. Although advanced techniques like rapid microbiological methods (RMMs) can reduce testing time to seven days, they still require complex procedures, such as cell extraction and the use of growth enrichment mediums, and rely heavily on skilled personnel for sample handling, measurement, and analysis. This highlights the need for more efficient methods that provide faster results, meet patient timelines, and involve simple workflows without compromising the quality of the CTPs.

Researchers from the Critical Analytics for Manufacturing Personalized-Medicine (CAMP, Singapore), an interdisciplinary research group of Singapore-MIT Alliance for Research and Technology (SMART), along with collaborators have developed an innovative solution to quickly and automatically detect microbial contamination in CTPs during the manufacturing process. By measuring the ultraviolet (UV) light absorbance of cell culture fluids and employing machine learning to identify light absorption patterns indicative of microbial contamination, this novel testing method aims to reduce sterility testing time, enabling quicker availability of CTP doses for patients. This is especially critical in cases where timely administration of treatments could be life-saving for terminally ill patients.

In a study published in Scientific Reports, the SMART CAMP team explained how they integrated UV absorbance spectroscopy with machine learning to create a method for label-free, non-invasive, and real-time detection of cell contamination in the early stages of CTP production. This new approach has several advantages over traditional sterility tests and RMMs. It eliminates the need for cell staining to identify labeled organisms, thus making the process label-free. Additionally, it bypasses the invasive procedure of cell extraction and provides results in less than 30 minutes. The method offers a quick "yes/no" assessment of contamination, enabling automation of cell culture sampling with a streamlined workflow that requires no extra incubation, growth enrichment mediums, or extensive manpower. Furthermore, the system does not need specialized equipment, making it a cost-effective solution.

“Traditionally, cell therapy manufacturing is labor intensive and subject to operator variability,” said Prof Rajeev Ram, Principal Investigator at SMART CAMP, MIT Professor, and corresponding author of the paper. “By introducing automation and machine learning, we hope to streamline cell therapy manufacturing and reduce the risk of contamination. Specifically, our method supports automated cell culture sampling at designated intervals to check for contamination, which reduces manual tasks such as sample extraction, measurement, and analysis. This enables cell cultures to be monitored continuously and contamination to be detected at early stages.”

Related Links:
CAMP