Mos-Gen: A Generative Molecular Framework for Mosquito Insecticide Design
2026-06-01 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed a new AI tool called Mos-Gen to design chemicals that can kill mosquitoes, which spread deadly diseases. Their method combines two advanced models to create new mosquito-killing compounds with a specific chemical feature. They made and tested fourteen candidate chemicals, and most of the predicted effective ones worked well in real tests, while the predicted ineffective ones did not. This shows their tool can accurately find promising mosquito insecticides. Their work aims to help find safer and better mosquito control options.
mosquito-borne diseaseschemical insecticidesmolecular generative modelsvariational autoencoder (VAE)Uni-Moldisulfide-containing compoundsallicin derivativesexperimental validationmosquitocidal activityartificial intelligence in drug design
Authors
Lina Wang, Yaning Cui
Abstract
Mosquito-borne infectious diseases cause more than 700000 deaths worldwide each year. The long-term use of conventional chemical insecticides has induced serious resistance problems, creating an urgent need to develop novel, highly effective, and ecologically sustainable alternatives. While existing artificial intelligence approaches in this domain have focused primarily on activity prediction and classification, they leave a critical gap in the de~novo generation of novel molecular scaffolds. In this study, we propose Mos-Gen, a motif-aware generative collaborative framework that couples the pretrained molecular representation model Uni-Mol with a variational autoencoder (VAE), specifically tailored for the design of disulfide-containing allicin derivatives as mosquito insecticides. Among the generated candidates, fourteen compounds -- comprising nine predicted positives and five predicted negatives -- were selected for chemical synthesis and experimental validation. The hit rate among the predicted positives reached 78%, whereas none of the predicted negatives exhibited mosquitocidal activity. These experimental results fully validated the high-precision screening capability of the Mos-Gen framework.