基于元路径引导的迁移学习结合临床验证用于识别中药-药物相互作用
Metapath-guided transfer learning with clinical validation for identifying herb-drug interactions.
摘要(中文译文)
药物联用可改变代谢并引起具有临床意义的药代动力学相互作用。草药-药物相互作用（HDIs）尤其难以识别，因为经过验证的案例稀少且草药产品化学组成复杂。我们旨在开发Meta-HDI，一种元路径引导的迁移学习框架，利用大型药物-药物相互作用图来改进HDI预测及其可解释性，并在临床药代动力学层面前瞻性验证其预测。本研究将计算深度学习框架的开发与一项涉及18名参与者的前瞻性临床交叉试验及体外人类肝微粒体实验相结合。Meta-HDI结合了GCN编码器和最短路径LSTM与分层注意力机制，以生成可解释的机制链。我们在三个体内HDI类别和临床病例中，将模型与基线方法进行了基准比较。在交叉研究中评估了多奈哌齐与草药方剂加味逍遥散和大建中汤之间的预测相互作用，随后使用微粒体实验进行机制验证。Meta-HDI将微平均AUROC提高至0.95（从≤0.60），并正确分类了全部八个临床病例。消融研究强调了蛋白质-蛋白质和药物-蛋白质边的关键作用。在临床试验中，联合给药增加了多奈哌齐的暴露量（C增加1.6倍；AUC增加1.5倍），且无严重不良事件。注意力权重和微粒体实验确定falcarinol和glabranin为CYP2D6抑制剂（IC分别为45 µM和4.5 µM）。Meta-HDI缓解了HDI数据稀缺问题，同时提供了机制性、临床可解释的预测。我们的框架展示了其在草药-药物联合给药决策支持方面的潜力，但仍需要在多种药物和草药产品中进行更广泛的验证。
Abstract
Drug co-administration can alter metabolism and cause clinically important pharmacokinetic interactions. Herb-drug interactions (HDIs) are particularly hard to identify because validated cases are scarce and herbal products are chemically complex. We aimed to develop Meta-HDI, a metapath-guided transfer-learning framework that utilizes large drug-drug interaction graphs to improve HDI prediction and interpretability, and to prospectively confirm its predictions at the clinical pharmacokinetics level. This study integrates the development of a computational deep learning framework with a prospective clinical crossover trial involving 18 participants and in vitro human liver microsome assays. Meta-HDI combines a GCN encoder and shortest-path LSTM with hierarchical attention mechanisms to generate interpretable mechanistic chains. We benchmarked the model against baselines across three in vivo HDI classes and clinical cases. The predicted interaction between donepezil and the herbal formulas Gami-soyosan and Ojeok-san was evaluated in the crossover study, followed by mechanistic validation using microsome assays. Meta-HDI improved the micro-averaged AUROC to 0.95 (from ≤0.60) and correctly classified all eight clinical cases. Ablation studies highlighted the essential role of protein-protein and drug-protein edges. In the clinical trial, co-administration increased donepezil exposure (1.6-fold C; 1.5-fold AUC) without serious adverse events. Attention weights and microsome assays identified falcarinol and glabranin as CYP2D6 inhibitors (IC 45 µM and 4.5 µM). Meta-HDI mitigates HDI data scarcity while providing mechanistic, clinically interpretable predictions. Our framework demonstrated its potential for decision support in herb-drug co-administration, though broader validation across diverse drugs and herbal products is needed.
如何引用
AMA
Won-Yung Lee, Kyoung Hoon Mo, Surin Kim, Do Hoon Keum, Byung Hak Jin, Sangjin Kim, et al. Metapath-guided transfer learning with clinical validation for identifying herb-drug interactions.. Phytomedicine : international journal of phytotherapy and phytopharmacology. 2026; doi:10.1016/j.phymed.2026.158421.
APA
Won-Yung Lee, Kyoung Hoon Mo, Surin Kim, Do Hoon Keum, Byung Hak Jin, Sangjin Kim, et al (2026). Metapath-guided transfer learning with clinical validation for identifying herb-drug interactions.. Phytomedicine : international journal of phytotherapy and phytopharmacology. https://doi.org/10.1016/j.phymed.2026.158421
GB/T 7714
Won-Yung Lee, Kyoung Hoon Mo, Surin Kim, Do Hoon Keum, Byung Hak Jin, Sangjin Kim, et al. Metapath-guided transfer learning with clinical validation for identifying herb-drug interactions.[J]. Phytomedicine : international journal of phytotherapy and phytopharmacology, 2026 doi:10.1016/j.phymed.2026.158421.
在 PubMed增强版 阅读全文
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出