AI shines a new light on microbial contamination detection

A groundbreaking method to detect microbial contamination in cell therapy products has been developed through a collaboration between MIT, SMART, A*STAR Skin Research Labs, and the National University of Singapore. This innovation addresses a critical bottleneck in cell therapy manufacturing by reducing contamination detection time from 14 days to under 30 minutes, potentially saving the lives of critically ill patients who cannot afford to wait for traditional sterility testing methods before receiving treatment.

The big picture: Researchers have developed an automated, machine learning-powered method that analyzes ultraviolet light absorbance patterns to quickly detect microbial contamination in cell therapy products.

• The technique provides a simple “yes/no” contamination assessment without requiring cell staining, extraction, or specialized equipment, making it significantly faster and less expensive than existing methods.
• This innovation serves as a preliminary safety testing step during manufacturing, allowing for early detection and timely corrective actions while optimizing resource allocation.

Why this matters: Cell therapy represents a promising frontier in treating cancers, inflammatory diseases, and degenerative disorders, but manufacturing has been hampered by lengthy contamination testing procedures.

• Traditional sterility testing methods require up to 14 days to detect contamination, creating dangerous delays for critically ill patients who need immediate treatment.
• Even advanced rapid microbiological methods (RMMs) still require up to seven days and depend on complex processes and skilled workers.

In plain English: The researchers developed a system that shines ultraviolet light through cell cultures and uses artificial intelligence to recognize patterns associated with contamination, similar to how humans might identify visual differences between clean and contaminated substances.

What they’re saying: Senior Research Engineer Shruthi Pandi Chelvam emphasized how the method enables early contamination detection and timely corrective actions.

• “This approach saves costs, optimizes resource allocation, and ultimately accelerates the overall manufacturing timeline,” said Chelvam, who is the first author of the paper.
• MIT Professor Rajeev Ram noted: “By introducing automation and machine learning, we hope to streamline cell therapy manufacturing and reduce the risk of contamination… This enables cell cultures to be monitored continuously and contamination to be detected at early stages.”

Looking ahead: Researchers plan to expand the technology’s capability to detect a wider range of microbial contaminants and test its effectiveness with more cell types beyond mesenchymal stem cells.

• The method also shows promise for applications outside medicine, particularly in food and beverage industry safety testing.
• The research was published in the journal Scientific Reports in a paper titled “Machine learning aided UV absorbance spectroscopy for microbial contamination in cell therapy products.”