Binding Affinity Prediction and Pesticide Screening against <i>Phytophthora sojae</i> Using a Heterogeneous Interaction Graph Attention Network–Based Model

Phytophthora root and stem rot in soybeans results in substantial economic losses worldwide. In this study, a machine learning model based on a heterogeneous interaction graph attention network model was constructed. The PDBbind data set, comprising 13,285 complexes with experimental <i>pK</i>_a or <i>p</i>K_i values, was utilized to train and evaluate the model, which was subsequently employed to screen candidate compounds against chitin synthase of <i>Phytophthora sojae</i> (<i>Ps</i>Chs1) in the Traditional Chinese Medicine Systems Pharmacology database, comprising 14,249 compounds. High-scoring candidate compounds were docked with <i>Ps</i>Chs1 protein using Discovery Studio, and their interaction energies were evaluated. Molecular dynamic simulations spanning 50 ns were performed using GROMACS to explore the stability of the complexes, trajectory analysis was conducted with root-mean-square deviations, and the hydrogen bonds, radius of gyration, MMPBSA binding free energy, and binding modes were analyzed. MOL011832 and MOL011833 were identified as potential pesticides, both of which were present in the herb <i>Schizonepeta</i> through database retrieval. The inhibitory effects of an ethanol extract of <i>Schizonepeta</i> against <i>P. sojae</i> were subsequently explored and confirmed in biological experiments. Overall, this study proves the feasibility and high efficiency of pesticide discovery using graph neural network-based models.