EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

A deep learning and digital archaeology approach for mosquito repellent discovery

Jennifer N Wei iD, Carlos Ruiz iD, Marnix Vlot iD, Benjamin Sanchez-Lengeling iD, Brian K Lee iD, Luuk Berning iD, Martijn W Vos, Rob W M Henderson, Wesley W Qian, Jacob N Sanders, D Michael Ando, Kurt M Groetsch und 4 weitere

Chemical Senses · 2025

DOI: 10.1093/chemse/bjaf021 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Chemical Senses, 2025. Verfasst von Jennifer N Wei und 15 weiteren Autor:innen. Beteiligte Einrichtung: Google Research, Brain Team, Cambridge, MA, USA. Hauptthemen laut MEDLINE: Insect Repellents, Deep Learning, Drug Discovery, Archaeology. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIAID NIH HHS, NIH HHS, Bill and Melinda Gates Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Insect-borne diseases kill > 0.5 million people annually. Currently available repellents for personal or household protection are limited in their efficacy, applicability, and safety profile. Here, we describe a machine-learning-driven high-throughput method for the discovery of novel repellent molecules. To achieve this, we digitized a large, historic dataset containing ~19,000 mosquito repellency measurements. We then trained a graph neural network (GNN) to map molecular structure and repellency. We applied this model to select 317 candidate molecules to test in parallelizable behavioral assays, quantifying repellency in multiple insect vectors of the pathogens of disease and in follow-up trials with human volunteers. The GNN approach outperformed a chemoinformatic model and produced a hit rate that increased with training data size, suggesting that both model innovation and novel data collection were integral to predictive accuracy. We identified > 10 molecules with repellency similar to or greater than the most widely used repellents. We analyzed the neural responses from the mosquito antennal (olfactory) lobe to selected repellents and found strong responses to many of the tested compounds, including those predicted to be strong repellents. Results from the antennal lobe recordings also demonstrated a correlation between the evoked responses to strong repellents and our GNN representation. This approach enables computational screening of billions of possible molecules to identify empirically tractable numbers of candidate repellents, leading to accelerated progress towards solving a global health challenge.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Insect RepellentsDeep LearningDrug DiscoveryArchaeologyAnimalsHumansNeural Networks, ComputerMosquito VectorsCulicidae

Stichwörter der Autor:innen

DEETantennal lobechemical structuredeep learningmosquito repellentolfaction

Substanzen

Insect Repellents

Autor:innen und Institutionen

  • Google Research, Brain Team, Cambridge, MA, USA.
  • Department of Biology, University of Washington, Seattle, WA, USA.
  • TropIQ Health Sciences, Nijmegen, The Netherlands.
  • Osmo, New York, NY, USA.
  • Google Books Team, Mountain View, CA, USA.

ORCID-Profile: Jennifer N Wei, Carlos Ruiz, Marnix Vlot, Benjamin Sanchez-Lengeling, Brian K Lee, Luuk Berning, Richard C Gerkin, Alexander B Wiltschko, Jeffrey A Riffell, Koen J Dechering

Förderung

  • NIAID NIH HHS
  • NIH HHS
  • Bill and Melinda Gates Foundation
  • National Institutes of Health

Zitieren

APA

Wei, J. N., Ruiz, C., Vlot, M., Sanchez-Lengeling, B., Lee, B. K., Berning, L., Vos, M. W., Henderson, R. W. M., Qian, W. W., Sanders, J. N., Ando, D. M., Groetsch, K. M., Gerkin, R. C., Wiltschko, A. B., Riffell, J. A., & Dechering, K. J. (2025). A deep learning and digital archaeology approach for mosquito repellent discovery. Chemical Senses. https://doi.org/10.1093/chemse/bjaf021

Vancouver

Wei JN, Ruiz C, Vlot M, Sanchez-Lengeling B, Lee BK, Berning L, et al. A deep learning and digital archaeology approach for mosquito repellent discovery. Chemical Senses. 2025. doi:10.1093/chemse/bjaf021

BibTeX
@article{Wei2025,
  author = {Wei, Jennifer N and Ruiz, Carlos and Vlot, Marnix and Sanchez-Lengeling, Benjamin and Lee, Brian K and Berning, Luuk and Vos, Martijn W and Henderson, Rob W M and Qian, Wesley W and Sanders, Jacob N and Ando, D Michael and Groetsch, Kurt M and Gerkin, Richard C and Wiltschko, Alexander B and Riffell, Jeffrey A and Dechering, Koen J},
  title = {A deep learning and digital archaeology approach for mosquito repellent discovery},
  journal = {Chemical Senses},
  year = {2025},
  doi = {10.1093/chemse/bjaf021}
}
Kostenlos starten →