文献速递药物不良反应与药物警戒

基于图神经网络整合体外hERG实验与药物警戒数据预测QT延长风险

Structure-Based Prediction of QT Prolongation Risk Using Graph Neural Networks: An Integrative Approach Combining In Vitro hERG Assays and Pharmacovigilance Data.
PubMed 文献 · Clin Pharmacol Ther · 2026-02-06

本研究开发了整合体外hERG抑制数据、FAERS药物警戒信号和分子结构的可解释图神经网络框架,用于预测药物致QT延长风险。最终数据集包含4,808个小分子,GATv2模型交叉验证ROC-AUC为0.838,外部验证ROC-AUC为0.859,原子度数和氢原子数为主要预测特征。

要点

  • GATv2模型交叉验证ROC-AUC 0.838,外部验证ROC-AUC 0.859
  • 原子度数和氢原子数为主要预测特征,与已知构效关系一致
  • 该框架符合ICH S7B/E14和CiPA指南,可作为结构决策支持工具

核心结论

  • 整合体外hERG数据、FAERS信号和分子结构的GNN框架可预测药物QT延长风险。
  • GATv2模型表现最佳,外部验证ROC-AUC 0.859,敏感度0.80,特异度0.82。

研究设计与样本

  • 研究整合PubChem AID 588834体外hERG抑制数据、FAERS药物警戒信号和分子结构信息。
  • 最终数据集包含4,808个小分子,具有二元QT风险标签。
  • 比较GINE、GCN、GraphSAGE和GATv2四种GNN架构,采用分层五折交叉验证。

主要发现

  • GATv2交叉验证ROC-AUC 0.838,PR-AUC 0.830,F1-score 0.756。
  • 全数据集重训练后ROC-AUC 0.918,PR-AUC 0.908,F1-score 0.847。
  • 外部验证集AID 1671200(n=2,405)ROC-AUC 0.859,敏感度0.80,特异度0.82。
  • 原子度数和氢原子数为主要预测特征,与已知构效关系一致。

临床怎么用

  • 该框架可作为基于结构的决策支持工具,辅助早期药物开发中QT风险预测。
  • 预测结果与ICH S7B/E14和CiPA指南对齐,支持临床前安全性评估。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Drug-induced QT-interval prolongation, a non-specific biomarker of increased risk for Torsades de Pointes (TdP), is a major safety concern in drug development. While in vitro hERG inhibition assays are required for early-phase screening, pharmacovigilance data from sources like the FDA Adverse Event Reporting System (FAERS) provide complementary insights. Integrating these heterogeneous data with molecular structure offers a promising, yet underutilized approach to predict proarrhythmic risk. We developed an interpretable graph neural network (GNN) framework integrating in vitro hERG inhibition data (PubChem AID 588834), FAERS-derived pharmacovigilance signals, and molecular structure information. Canonical SMILES were converted into molecular graphs using RDKit, and atom- and bond-level features were encoded. Four GNN architectures (GINE, GCN, GraphSAGE, and GATv2) were compared via stratified five-fold cross-validation. The best-performing model, GATv2, was further interpreted using Integrated Gradients to identify structural features contributing to QT liability. The final data set comprised 4,808 small molecules with binary QT-risk labels. GATv2 achieved a cross-validated ROC-AUC of 0.838, PR-AUC of 0.830, and F1-score of 0.756. Retraining on the full data set yielded ROC-AUC 0.918, PR-AUC 0.908, and F1-score 0.847. External validation on an independent hERG assay (AID 1671200, n = 2,405) confirmed strong performance (ROC-AUC 0.859, sensitivity 0.80, specificity 0.82). Atomic degree and hydrogen count were dominant predictors, consistent with known SARs. This GNN-based framework integrates structural and pharmacological data to predict QT risk, providing a transparent, structure-based decision-support tool aligned with ICH S7B/E14 and CiPA guidelines.

来源:Clin Pharmacol Ther,查看原文。版权归原作者所有。

引用

  1. Enokiya T, Kunitomo R, Yamaguchi T, et al. Structure-Based Prediction of QT Prolongation Risk Using Graph Neural Networks: An Integrative Approach Combining In Vitro hERG Assays and Pharmacovigilance Data. Clin Pharmacol Ther. 2026. PMID: 41652797. doi:10.1002/cpt.70220

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。