IBM and Cornell big data protects milk supply chain
July 5, 2017
IBM and Cornell University are using next-generation sequencing, bioinformatics and big data analytics to help reduce the chances that the global milk supply is impacted by safety breaches.
With the onset of this dairy project, Cornell University has become the latest academic institution to join the Consortium for Sequencing the Food Supply Chain, a food safety initiative that includes IBM Research, Mars and Bio-Rad Laboratories.
"Through this partnership with Cornell University, we are extending the consortium work to a broader range of ingredients, leveraging artificial intelligence and machine learning, to gain new insights into how microorganisms interact within a particular environment," said Jeff Welser, vice president and director at IBM Research.
The opportunity for improving food safety is large; the US Department of Agriculture estimates that Americans consume more than 270kg of milk and milk-based products per person per year. Fresh food such as meat, dairy and produce represent a great risk for food safety incidents.
Specifically, raw milk is the main ingredient used in pasteurised milk for drinking, infant formula, cheese, yogurt and other common grocery items. Normally, raw milk samples are tested for a few specific groups of bacteria. However, the Consortium for Sequencing the Food Supply Chain is using the community of microbes or bacteria known as the microbiome to characterise the food samples at an unprecedented resolution.
By sequencing and analysing the DNA and RNA (genetic code) of food microbiomes, researchers plan to create tools that can help monitor raw milk to detect anomalies that represent food safety hazards and possible fraud.
Characterising what is normal for a food ingredient can better allow the observation of when something goes awry. Detecting unknown anomalies is a challenge in food safety and serious repercussions may arise due to contaminants that may never have been seen in the food supply chain before.
"As a global leader in food safety and dairy research, we are committed to using our multidisciplinary expertise to secure the world's food supply against harmful microbial contamination," said Kathryn Boor, the Ronald P Lynch Dean of the College of Agriculture & Life Sciences. "Bringing Cornell into a private-public partnership with IBM, a world leader in technology and innovation, has the potential to deliver transformative research in the area of food safety and health."
While many food producers already have rigorous processes in place to ensure food safety hazards are managed appropriately, this application of genomics will be designed to enable a deeper understanding and characterisation of microorganisms on a much larger scale than has previously been possible. Consortium researchers will conduct several studies comparing the baseline data of raw milk with known anomalies to help create proven models that can be used for additional studies. They will continue to provide innovative methods that could reduce the chance of a food hazard reaching the final consumer and provide a tool to assist against food fraud.
The consortium was officially launched in January 2015 by IBM Research and Mars. Bio-Rad Laboratories, a provider of life science research and clinical diagnostic products, joined the consortium in 2016. This collaborative food safety initiative aims to leverage advances in sequencing to further the understanding of what can help make food safe.
The consortium is conducting the largest-ever metagenomics study to categorise and understand microorganisms and the factors that influence their activity in various food matrices. This work could eventually be extended into the larger context of the food supply chain – from farm to fork – and, using artificial intelligence and machine learning, may lead to insights into how microorganisms interact within a particular environment.
The research project will collect genetic data from the microbiome of raw milk samples in a real-world scenario at Cornell's dairy processing plant and farm in New York. The facility is unusual in that it represents the full dairy supply chain from farm to processing to consumer. This initial data collection will form a raw milk baseline and be used to expand existing consortium bioinformatic analytical tools.
"As nature's most perfect food, milk is an excellent model for studying the genetics of food," said Martin Wiedmann, professor at Cornell's College of Agriculture & Life Sciences. “As a leader in genomics research, the Department of Food Science anticipates this research collaboration with IBM can lead to exciting opportunities to apply findings to multiple food products in locations worldwide.”
Kristen Beck, technical lead researcher at IBM Research, added: "We are thrilled to collaborate with Cornell to develop new ways to help keep our food supply safe before fraud or contamination hits by developing advanced algorithms, applying machine learning and mathematical modelling to sequence data. Safe food is the first step towards human health. We're extremely optimistic that with Cornell's involvement in the consortium we will make a difference in improving not only food safety, but our overall health as well."