Scientists use the machine studying method to trace down pathogenic mosquitoes


IMAGE: A female Aedes aegypti mosquito is given a blood meal from a human host. Utah State University biologist Norah Saarman and colleagues from the University of California, Davis and Yale University … More

Photo credit: James Gathany, CDC

LOGAN, UTAH, USA – You may not like mosquitoes, but they like you, says Utah State University biologist Norah Saarman. And wherever you lead, they will follow.

Some mosquitoes not only bite and buzz annoyingly, but also carry harmful diseases. Aedes aegypti, the so-called yellow fever mosquito and the subject of a recent study by Saarman and colleagues, is the main vector for the transmission of viruses that cause dengue fever, chikungunya and zika, and yellow fever in humans.

“Aedes aegypti is an invasive species in North America that is widespread in the eastern United States,” says Saarman, assistant professor at USU’s Department of Biology and at the USU Ecology Center, whose research focuses on evolutionary ecology and population genomics. “We are investigating the genetic connectivity of this species as it adapts to new landscapes and expands its range.”

With Evlyn Pless from the University of California, Davis and Jeffrey Powell, Andalgisa Caccone and Giuseppe Amatulli from Yale University, Saarman published results of a machine learning approach to mapping landscape connectivity in the February 22, 2021 issue of the Proceedings of the National Academy Sciences (PNAS).

The team’s research was supported by the National Institutes of Health.

“We’re excited about this approach, which uses a random forest algorithm that allows us to overcome some of the limitations of classic spatial models,” says Saarman. “Our approach combines the advantages of a machine learning framework and an iterative optimization process that integrates genetic and environmental data.”

In his native Africa, Aedes aegypti was a forest dweller who lived in uninhabited or hardly inhabited landscapes. The mosquito has since specialized in human feeding and thrives in human-affected areas, preferring piles of rubbish, polluted highways, and well-watered gardens.

“Using our machine learning model and the satellite imagery provided by NASA, we can combine this spatial data with the genetic data we have already collected to get a detailed picture of the movement of these mosquitoes,” says Saarman. “For example, our data shows they are attractive to human transportation networks, indicating that activities like tree nurseries are inadvertently moving these insects to new areas.”

Officials and land managers once relied on pesticides, including DDT, to keep the pesky mosquitoes at bay.

“As we now know, these pesticides have caused environmental damage, including harm to humans,” she says. “At the same time, mosquitoes are becoming resistant to the pesticides that we have found to be environmentally friendly. This is a challenge that can only be solved with more information about where mosquitoes live and how they move.”

Saarman adds that in addition to adapting to different food sources and resisting pesticides, the resilient survivors also adapt to different temperatures, allowing them to expand into colder areas.

Current methods of controlling pathogenic mosquitoes focus on biotechnological solutions, including innovative genetic modifications.

“We hope that the tools we have developed can help managers identify effective ways to keep mosquito populations small enough to prevent disease transmission,” Saarman says. “While native species play an important role in the food chain, invasive species like Aedes aegypti pose a significant public health risk that requires our vigilant attention.”


Disclaimer: AAAS and EurekAlert! are not responsible for the correctness of the press releases published on EurekAlert! by contributing institutions or for the use of information via the EurekAlert system.

Leave A Reply

Your email address will not be published.