Scientists have developed an AI tool that is capable of pinpointing someone’s recent location using a sample of microorganisms they may have collected on their travels. The breakthrough, published in the journal, Genome Biology and Evolution, allows the scientists to identify whether someone recently visited the beach, deboarded at a nearby train station or took a walk through the park. The researchers found that microorganisms act like microscopic fingerprints and just like human populations, the microbial communities display geographical traces, which prompted the development of the AI tool.
Unlike traditional navigation system that uses GPS, researchers at Lund University in Sweden developed a Microbiome Geographic Population Structure (mGPS) that uses ground-breaking AI technology to localise the environments one may have visited by identifying the microbiome associated with that area. The word microbiome is used to describe all the microorganisms (bacteria, fungi, algae) in a particular environment.
“In contrast to human DNA, the human microbiome changes constantly when we come into contact with different environments,” Eran Elhaik, a researcher at Lund University and the study’s co-author told The Atlas.
“By tracing where your microorganisms have been recently, we can understand the spread of disease, identify potential sources of infection and localise the emergence of microbial resistance. This tracing also provides forensic keys that can be used in criminal investigations.”
How was the AI trained?
The researchers fed a huge quantity of microbiome data from different environments to its AI model. Microbe genomes collected from subways and urban environments in 53 cities, 237 soil samples from 18 countries, and 131 marine samples from nine bodies of water were used for the training.
“We analyzed extensive datasets of microbiome samples from urban environments, soil and marine ecosystems and trained an AI model to identify the unique proportions of these fingerprints and link them to geographical coordinates,” Elhaik said. “The results turned out to be a very powerful tool that can pinpoint the source site of a microbiome sample with impressive precision.”
Also read | Anthropic’s New AI Tool Analyses Your Screen And Acts On Your Behalf
How did the AI perform?
As per the study, the mGPS was successful in pinpointing the city source for 92 per cent of city samples. To further challenge the system’s accuracy, it was trained on data from the three most extensively sampled cities: New York, Hong Kong, and London. In Hong Kong, the mGPS was able to distinguish between two subway stations. just 564 ft apart while in New York City, it differentiated a kiosk from a handrail, less than a meter away.
However, in London, the accuracy took a hit as only half the samples were correctly assigned to their geographical cluster. The unkempt condition of London underground stations was described as the reason for low efficiency.
The innovation opens up new possibilities within medicine, epidemiology and forensics but adding microbiome data as it is collected will only further improve the tool, the researchers added.