FT-GNN Tool for Bridging HRMS Features and Bioactivity: Uncovering Unidentified Estrogen Receptor Agonists in Sewage

Identifying primary estrogen receptor (ER) agonists in municipal sewage is essential for ensuring the health of aquatic environments. Given the complex and variable chemical composition of sewage, the predominant ER agonists remain unclear. High-resolution mass spectrometry (HRMS)-based models have been developed to predict compound bioactivity in complex matrices, but further optimization is needed to effectively bridge HRMS features with ER agonists. To address this challenge, an FT-GNN (fragmentation tree-based graph neural network) model was proposed. Given limited data and class imbalance, data augmentation was performed using model predictions within the applicability domain (AD) and oversampling technique (OTE). Model development results demonstrated that integrating the FT-GNN with data augmentation improved the balanced accuracy (bACC) value by 6%-31%. The developed model, with a high bACC to identify more true ER agonists, efficiently classified tens of thousands of unidentified HRMS features in sewage, reducing postprocessing workload in nontargeted screening. Analysis of ER agonist transformation during sewage treatment revealed the anaerobic stage as key to both their removal and formation. Estrogenic effect balance analysis suggests that α-E2 and 9,11-didehydroestriol may be two previously overlooked key ER agonists. Collectively, the development and application of the FT-GNN model are crucial advancements toward credible tracking and efficient control of estrogenic risks in water.