Novel graph neural network reveals binding mechanisms and environmental risks of PAHs interaction with estrogen receptor B

文献类型： 外文期刊

第一作者： Ren, Ying

作者： Ren, Ying;Wu, Xuan;Xi, Ziming;Li, Ronghua;Tang, Kuok Ho Daniel;Zeng, Xianlai;Pan, Junting

作者机构：

关键词： Polycyclic aromatic hydrocarbons; Estrogen receptor beta; Machine learning; Molecular docking

期刊名称：ENVIRONMENTAL POLLUTION （ 影响因子：7.3； 五年影响因子：8.1 ）

ISSN： 0269-7491

年卷期： 2025 年 384 卷

页码：

收录情况： SCI

摘要： Polycyclic aromatic hydrocarbons (PAHs) are widespread environmental contaminants that threaten ecosystems and human health by binding to estrogen receptor beta (ER beta) and disrupting endocrine function. Accurately identifying and predicting the interactions between PAHs and ER beta remains a key challenge in environmental science. To address this, we propose a Multi-Scale Dual-Stream Graph Attention Network (MS-DSGAT) for predicting PAHs-ER beta binding affinity. MS-DSGAT outperforms traditional machine learning models, achieving the highest prediction accuracy (R2 = 0.95) while offering strong interpretability. MS-DSGAT assigns Positional Attention Weights (PAW) to atoms in each PAH molecule, highlighting the critical influence of functional groups such as hydroxyl (-OH), amino (-NH2), and sulfonic acid (-SO3H) on binding affinity. These insights provide valuable guidance for targeted molecular modifications. Virtual screening of 6357 external chemicals using MSDSGAT identified approximately 6.6 % of the chemicals as high-affinity binders and 66.4 % as moderate binders. Molecular docking results further validate the model's interpretations, confirming functional groups as key determinants of binding affinity. By leveraging molecular graph representation, MS-DSGAT effectively predicts PAHs-ER beta interactions and can be extended to study other ligand-receptor interactions to identify potential endocrine disruptors, toxicants, and related compounds.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序