arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2606.07698cs.LGcs.AI
收藏

基于图神经网络的药物相互作用预测的药理基因组学知识图谱增强

Pharmacogenomic Knowledge Graph Augmentation for Graph Neural Network-Based Drug-Drug Interaction Prediction

AI Solutions Berlin

Juergen Dietrich

AI总结:

本研究通过整合PharmGKB的药理基因组学先验知识(CYP酶注释)作为特征向量,增强图神经网络在药物相互作用预测中的性能,在配对数据划分下显著提升DDI类型分类,但未能突破信息天花板。

摘要:

应用于药物相互作用(DDI)预测的图神经网络(GNN)仅依赖由SMILES衍生的分子结构图。该系列先前的工作表明,模型性能受限于训练标签的结构信息含量——即信息天花板——仅靠架构改进无法克服。本研究探讨来自PharmGKB数据库的药理基因组学先验知识是否通过提供独立于分子结构且互补的代谢通路背景,部分关闭这一天花板。提取四种临床相关亚型(CYP2D6、CYP3A4、CYP2C19、CYP2C9)的细胞色素P450(CYP)酶底物、抑制剂和诱导剂注释,并将其作为12维特征向量在交互预测前与分子嵌入拼接。在配对水平和药物水平数据划分下进行实验,以量化对未见药物的泛化能力。结果表明,在配对水平划分条件下,知识图谱(KG)增强显著改善了DDI类型分类(F1宏平均:0.532对比基线0.241),而二元交互检测和药物水平泛化仍受信息天花板限制(AUC提升:0.224对比基线0.250)。对严格保留化合物的机制验证确认,增强优先改善CYP2C9介导的交互预测,概率从基线0.033-0.117提升至KG增强后的0.560-0.586。在Tox21基准上的单分子毒性预测扩展实验证实,该效果取决于药理基因组学注释覆盖度。这些发现为后续研究提出的多模态框架提供了动机。

英文摘要:

Graph neural networks (GNNs) applied to drug-drug interaction (DDI) prediction rely exclusively on molecular structure encoded as SMILES-derived graphs. Prior work in this series demonstrated that model performance is bounded by the structural information content of training labels -- an Information Ceiling -- that architectural refinements alone cannot overcome. The present study investigates whether pharmacogenomic prior knowledge from the PharmGKB database partially closes this ceiling by providing metabolic pathway context that is independent of, and complementary to, molecular structure. Cytochrome P450 (CYP) enzyme substrate, inhibitor, and inducer annotations for four clinically relevant isoforms (CYP2D6, CYP3A4, CYP2C19, CYP2C9) are extracted and incorporated as a 12-dimensional feature vector concatenated to the molecular embedding prior to interaction prediction. Experiments are conducted under both pair-level and drug-level data splits to quantify generalization to unseen drugs. Results indicate that knowledge graph (KG) augmentation substantially improves DDI type classification under pair-level split conditions (F1-macro: 0.532 vs. 0.241 baseline), while binary interaction detection and drug-level generalization remain bounded by the Information Ceiling (AUC inflation: 0.224 vs. 0.250 baseline). Mechanistic validation on strictly held-out compounds confirms that augmentation preferentially improves CYP2C9-mediated interaction prediction, with probabilities increasing from 0.033-0.117 (baseline) to 0.560-0.586 (KG-augmented). An extension to single-molecule toxicity prediction on the Tox21 benchmark confirms that the effect is contingent on pharmacogenomic annotation coverage. These findings motivate the multimodal framework proposed for the subsequent study in this series.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑