Exploring Insecticidal Molecules with Random Forest: Toward High Insecticidal Activity and Low Bee Toxicity.

Insecticidal molecules with high activity are crucial for global pesticide reduction and food security. However, their usage is limited by their concomitant high toxicity to bees. Balancing insecticidal activity and bee toxicity remains a critical challenge in the exploitation of new insecticidal molecules. In this study, we propose a novel strategy for exploiting molecules that are both highly effective against pests and minimally harmful to bees. A series of molecules were synthesized and tested to train a machine learning (ML) model for predicting insecticidal activity against pests. Meanwhile, another ML model was trained by using publicly available data to predict bee toxicity. The models demonstrated good performance, with mean AUC values of 0.88 ± 0.05 for insecticidal activity and 0.91 ± 0.01 for bee toxicity. By integrating these two models, we successfully predicted and experimentally validated a molecule that exhibited a high insecticidal activity and low bee toxicity. This dual-ML-model approach offers a promising pathway for the development of insecticidal molecules that are both effective and environmentally safe, thereby contributing to sustainable agricultures.