Recent research from North Carolina State University, published in Parasites & Vectors and Royal Society Open Science, suggests that localized mosquito-control practices may create conditions that favor the evolution of insecticide resistance in mosquito populations.

Aedes albopictus, commonly known as the tiger mosquito, is an invasive species that has become widespread across much of the eastern United States. It breeds in a variety of artificial and natural containers that collect standing water, such as gutters and buckets.

In North Carolina, control of this mosquito is often managed at the household level, either through private mosquito-control services or by individuals applying pyrethroid insecticides. These chemicals are widely used because they are effective against adult mosquitoes and considered among the safer insecticides for use around people, pets, and homes, but they are typically applied without coordination among neighboring properties.

Modeling Mosquito Mutations

In one study, a team led by Jennifer Baltzegar tracked the emergence and spread of a resistance mutation known as F1534S in tiger mosquitoes in Wake County between 2016 and 2024. They looked at the F1534S mutation, which researchers have associated with knockdown resistance.

The mutation was absent from the Wake County samples collected in 2016 and 2017. In 2023, the researchers detected the resistance-associated mutation in 84% of the sampled residential areas, and they found it in 39% of the mosquitoes they sampled. The researchers’ models indicated that the resistance allele was under strong selection pressure, meaning mosquitoes carrying it had a significant evolutionary advantage in the local environment.

“Homeowners with money will pay to spray for mosquitoes, which selects for localized resistance,” said Martha Burford Reiskind, associate professor of biological sciences at NC State and corresponding author on both papers. “Over time, as more and more resistance builds up in the population, it will become harder to control populations. The insecticides will no longer be as effective.”

Wealth as a Selection Pressure

A second study, led by Cole Butler, looked at how resistance is distributed across neighborhoods with different property values. The team sampled mosquito populations across 31 residential blocks throughout Raleigh, covering a range of property values. They found that neighborhoods with higher total property values, which the researchers used as an indicator of likely spending on pest control, showed higher frequencies of resistance. While the study did not track individual spraying habits, the pattern suggests that greater private investment in mosquito control may be contributing to the spread of resistance.

That pattern breaks from how insecticide resistance usually spreads globally. “We see the rapid rise of pesticide resistance in places like South America and Asia where there is continuous spraying in some countries,” Burford Reiskind said. “But resistance driven by private mosquito control is novel in the contiguous U.S., to our knowledge.”

How the Mutation Actually Works

The F1534S mutation occurs in the mosquito’s gene for the voltage-gated sodium channel, which is the same site where pyrethroid insecticides act. This genetic alteration decreases the mosquito’s sensitivity to pyrethroids and thus enables some individuals to survive exposure to insecticides. The resistance allele is only partially recessive, so not all mosquitoes display the full effect. As a result, the mutation can spread through a population before resistance is noticeable.

“This mutation is often the first to show up when there’s insecticide resistance,” Burford Reiskind said.

Where the Research Goes Next

Beyond being a nuisance, tiger mosquitoes can transmit diseases such as dengue, Zika, chikungunya, and dog heartworm. While the current studies did not assess disease transmission directly, Michael Reiskind, a professor at NC State and co-author of both papers, notes that future research will expand to include a broader range of neighborhoods. “We want to make a better effort to get a diversity of neighborhoods, age, and wealth to extend our findings and see whether they work at different housing densities and wealth levels,” Reiskind said.

The researchers recommend using integrated pest management techniques since these methods decrease the need for chemical insecticides. They stressed that eliminating standing water where larvae develop is a key preventive measure. Effective pest control means addressing the entire life cycle and not depending just on chemical insecticides.

Putting these integrated approaches into practice may be challenging since many suburban homeowners already rely on seasonal mosquito-spraying services. The rapid development of resistance in Wake County suggests that managing this trend will likely require cooperation among homeowners, pest control companies, and public health agencies. Achieving that cooperation may require these groups to rethink how they manage private mosquito control.

Austin Burgess is a writer and researcher with a background in sales, marketing, and data analytics. He holds an MBA, a Bachelor of Science in Business Administration, and a data analytics certification. His work focuses on breaking scientific developments, with an emphasis on emerging biology, cognitive neuroscience, and archaeological discoveries.

Have you ever wondered how researchers use artificial intelligence (AI) in environmental science? Certain AI computer models can learn from scientific data and operate without manual programming, in a process called machine learning. Machine learning models can identify patterns in environmental datasets and help scientists assess public health risks linked to environmental conditions.

One well-known public health risk is the rise in antibiotic-resistant bacteria. These bacteria carry genes called antibiotic resistance genes that protect them from antibiotic medicines. As the number of these genes increases, the medicines become less effective, and diseases spread faster.

Agricultural soils are the largest reservoirs of antibiotic resistance genes, because manure from livestock like cows and pigs often contains leftover antibiotics fed to them. When used as fertilizer, this manure transfers antibiotics into the agricultural soil, where bacteria develop antibiotic resistance genes.

To better understand how antibiotic-resistant bacteria will affect global health in the future, scientists want to develop faster ways to detect antibiotic resistance genes. However, current methods of detection are slow and fail to predict future trends. To address this problem, a group of scientists from Algeria used machine learning models to predict the prevalence of antibiotic resistance genes in soil microbes under future climate scenarios, and to identify the key environmental drivers and high-risk areas.

​The team compiled existing microbial data from 3 public databases: the National Center for Biotechnology Information’s Sequence Read Archive, the Metagenomic Rapid Annotations using Subsystems Technology database, and the Joint Genome Institute’s Integrated Microbial Genomes & Microbiomes database. Their final dataset contained about 2,000 agricultural soil samples from 67 countries across 6 continents. These samples represented a wide range of soil characteristics, climate conditions, and different types of antibiotic resistance genes. 

They integrated the microbial dataset with climate data, including global temperature and precipitation measurements from WorldClim, and land use data, including crop types, irrigation systems, and livestock density from the European Space Agency Climate Change Initiative Land Cover maps. The researchers also included data on future climate projections for 2050 and 2070 from the World Climate Research Programme based on low, medium, and high global greenhouse gas emission scenarios. 

After preparing the datasets, the team set up 6 machine learning models that differ in terms of their data size, model complexity, analytical speed, and customization. These models included Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting (XGBoost), Random Forest (RF), Support Vector Machine (SVM), Deep Neural Network (DNN), and Logistic Regression (LR). 

They ran each model using different combinations of variables from their datasets, including soil properties, microbial community metrics, climate variables, and land use characteristics. To validate the models, the team separated the full dataset into 10 random subsets. They trained the models on 9 of the subsets, then recorded the result of the 10th subset. Each model repeated this process 10 times in a different order so that each subset was evaluated once in the results, using a technique known as stratified 10-fold cross-validation. The researchers scored each model on 5 performance metrics, including precision, sensitivity, and predictive power. Based on these results, they determined that LightGBM was the most accurate model. 

They found that the LightGBM model identified soil temperature as the strongest environmental predictor of antibiotic resistance genes. At soil temperatures above 18°C (about 64°F), the number of antibiotic resistance genes increased dramatically. The model also identified soil acidity, organic carbon content, moisture, and annual precipitation as influential variables, accounting for 71% of the increase in antibiotic resistance genes under future climate scenarios. Likewise, the LightGBM model predicted that the number of high-risk areas would increase by 35% under the high-emissions scenario, with South Asia, Sub-Saharan Africa, and Mediterranean Europe as the most vulnerable regions.

Based on the LightGBM model output, the team concluded that soil conditions will change to favor antibiotic resistance genes under all future climate scenarios. They also suggested that LightGBM is a fast and effective model for environmental predictions that could be used to assess other climate change risks such as natural disasters. They recommended that future researchers explore how to apply machine learning methods to early warning systems and utilize machine learning results in environmental management decisions. 

The post Predicting microbial antibiotic resistance with AI appeared first on Sciworthy.