This article is more than 5 years old. Information may no longer be current.
Software identifies sources of fecal water contamination
Click Here to Manage Email Alerts
The use of an inductive machine learning method appears to have promise in microbial source tracking of fecally contaminated water, according to recent data.
“Identifying the species to which the traces belong would help in resolving conflicts about who is responsible for the fecal pollution of a river: a farm, an abattoir, a sewage treatment plant or a human population nucleus, for example,” Anicet R. Blanch, PhD, microbiologist at the University of Barcelona, said in a press release.
In the study, Blanch and colleagues applied microbial source tracking (MST) to two real-life scenarios using a machine learning software called Ichnaea. The researchers created predictive models for the water samples, which had varying levels of human and animal (cattle, pig or chicken) fecal contamination (point source, moderate, or low).
Anicet R. Blanch
The water samples were collected from irrigation channels with suspected exposure to fecal contamination in the Ebre Delta in Catalonia, Spain. Methods of MST used to evaluate the contamination sources included host-specific Bacteroides phages, mitochondrial DNA genetic markers, Bifidobacterium adolescentis and B. dentium markers, and bifidobacterial host-specific qPCR.
The researchers said almost all of the MST approaches accurately identified the source of contamination at the point source and in water samples of moderate concentration. In samples where fecal contamination was more diluted (less than 3 log10 colony-forming units of Escherichia coli per 100 mL), some of the methods were ineffective because the concentration of fecal pollution was below the detection threshold. Other factors that may impact the reliability of certain methods include the quality of samples used to train the computer learning models, as well as the parameters evaluated and their pertinence to the location of the water source.
The researchers wrote that the Ichnaea software shows promise in optimizing MST studies.
“Up until now, each research group proposed the indicators which they believed to be the most important, but Ichnaea eliminates the subjectivity by selecting the most essential for a reliable prediction from among the different variable parameters,” Blanch said in the press release. – by Jen Byrne
Disclosure: Infectious Disease News was unable to obtain financial disclosures at the time of publication.
Click Here to Manage Email Alerts