Novel method detects microbial contamination in cell cultures
In a significant leap forward for medical technology, researchers from the Critical Analytics for Manufacturing Personalized-Medicine (CAMP) interdisciplinary research group, part of the Singapore-MIT Alliance for Research and Technology (SMART), alongside collaborators from MIT, A*STAR Skin Research Labs, and the National University of Singapore, have unveiled a groundbreaking method for the rapid and automated detection of microbial contamination in cell cultures. This novel approach, which leverages ultraviolet light absorbance and advanced machine learning, promises to revolutionize the manufacturing of cell therapy products (CTPs), ensuring safer and quicker treatments for critically ill patients.
Cell therapies are a beacon of hope for a wide range of debilitating diseases, including cancers and chronic disorders. However, a critical bottleneck in their production has been the time-consuming and labor-intensive process of sterility testing. Traditional methods can take up to 14 days, while even rapid microbiological methods (RMMs) still require a week and complex, skill-dependent procedures like cell extraction and growth enrichment. Such delays can be life-threatening for patients in urgent need of treatment.
The innovative method developed by the SMART CAMP team addresses these challenges head-on. By measuring the UV light absorbance of cell culture fluids and employing sophisticated machine learning algorithms to identify contamination patterns, the system can provide a “yes/no” assessment in under half an hour. This non-invasive, label-free technique eliminates the need for cell staining or extraction, streamlining the workflow and significantly reducing both complexity and costs, as it requires no specialized equipment.
Shruthi Pandi Chelvam, a senior research engineer at SMART CAMP and the lead author of the research paper, emphasized the method’s strategic importance. “This rapid, label-free method is designed to be a preliminary step in the CTP manufacturing process as a form of continuous safety testing, which allows users to detect contamination early and implement timely corrective actions,” she stated. “This approach saves costs, optimizes resource allocation, and ultimately accelerates the overall manufacturing timeline.”
The power of artificial intelligence in this breakthrough was further highlighted by Rajeev Ram, the Clarence J. LeBel Professor in Electrical Engineering and Computer Science at MIT and a principal investigator at SMART CAMP. “By introducing automation and machine learning, we hope to streamline cell therapy manufacturing and reduce the risk of contamination,” Professor Ram explained. “Specifically, our method supports automated cell culture sampling at designated intervals to check for contamination, which reduces manual tasks and enables continuous monitoring for early detection.”
Published in the prestigious journal Scientific Reports, the paper, titled “Machine learning aided UV absorbance spectroscopy for microbial contamination in cell therapy products,” details how this AI-powered solution offers a significant advantage over current practices. Its simplicity and speed mean that quality control can become a continuous process, rather than a final, time-consuming hurdle.
Looking ahead, the researchers plan to broaden the method’s scope to detect a wider array of microbial contaminants relevant to good manufacturing practices and different cell types. Beyond its immediate application in cell therapy, this versatile AI-driven detection system holds promise for other industries, including food and beverage, where microbial quality control is paramount for public safety.
This development underscores the transformative potential of AI in critical sectors like healthcare and manufacturing, paving the way for more efficient, safer, and accessible medical treatments globally.
