A collaboration between IBM and Cornell University seeks to improve ways to keep the global milk supply safe.

Raw milk is the main ingredient used in pasteurized milk for drinking, infant formula, cheese, yogurt and other grocery items. Normally researchers test samples for specific pathogens, like bacteria or viruses, to keep the milk supply safe.

The IBM-Cornell collaboration will combine next generation sequencing with bioinformatics, which allows for testing milk samples for multiple pathogens simultaneously, said Kristen Beck, Ph.D., research staff member for IBM Research – Almaden.

“By sequencing the microbiome, you are able to identify all pathogens in the sample and potentially new microbes that may not have been observed previously,” she said. “You are also able to gain insights about the food host, i.e. is the product what it claims to be. From this technique, you get an indicator for pathogens, food fraud, anomaly detection and more.”

IBM Research, as part of the Consortium for Sequencing the Food Supply Chain that it launched with Mars, Inc. in 2015, is using the community of microbes known as the microbiome to characterize the food samples. By sequencing and analyzing the DNA and RNA (genetic code) of food microbiomes, Cornell and IBM Research will create new tools that monitor raw milk to detect anomalies that represent food safety hazards and possible fraud.

The research project will collect genetic data from the microbiome of raw milk samples in a “real-world” scenario at the Cornell University dairy plant and farm in Ithaca.

“As nature’s most perfect food, milk is an excellent model for studying the genetics of food,” said Martin Wiedmann, Ph.D., Gellert Family Professor in Food Safety for Cornell University. “As a leader in genomics research, the (Cornell) Department of Food Science expects this research collaboration with IBM will lead to exciting opportunities to apply findings to multiple food products in locations worldwide.”

The IBM-Cornell collaboration will look to provide systems that not only minimize the chance that a food hazard will reach the consumer but also prevent food fraud.

“Food fraud in the sense of milk from animals other than cows is less common for economic reasons,” Dr. Beck said. “Cow’s milk is cheaper than goat or sheep milk, for example, but food fraud as it relates to subpar dairy from undesired farms is an issue. Sequencing the milk microbiome can help with source tracking to proactively identify food fraud before it becomes a quality assurance or food safety issue.”