用药物基因组知识增强图神经网络，提升药物相互作用预测准确率
Pharmacogenomic Knowledge Graph Augmentation for Graph Neural Network-Based Drug-Drug Interaction Prediction
- 将药理基因组数据作为特征向量拼接至分子嵌入，补充结构之外的代谢路径信息
- 在配对级划分下，类型分类F1-macro提升至0.532（基线0.241），尤其改善CYP2C9相关预测
- 适用于需结合代谢通路知识的药物研发场景，尤其对基因组注释覆盖充分的药物有效
基于图神经网络（GNN）的药物-药物相互作用（DDI）预测依赖于SMILES生成的分子结构图。已有研究发现，模型性能受限于训练标签的结构信息含量——存在信息天花板，仅靠架构优化无法突破。本文探究是否可通过来自PharmGKB数据库的药理基因组先验知识部分突破该天花板，提供独立于分子结构的代谢通路背景。提取了四种临床重要酶（CYP2D6、CYP3A4、CYP2C19、CYP2C9）的底物、抑制剂、诱导剂注释，构建12维特征向量并拼接至分子嵌入后进行交互预测。在配对级与药物级数据划分下评估泛化能力。结果显示，在配对级划分中，知识图谱（KG）增强显著提升DDI类型分类效果（F1-macro：0.532 vs. 0.241基线）；而二元交互检测与药物级泛化仍受信息天花板限制（AUC提升：0.224 vs. 0.250基线）。对严格留出化合物的机制验证表明，增强后对CYP2C9介导的相互作用预测概率从0.033–0.117升至0.560–0.586。在Tox21毒性预测任务中的扩展实验也证实，该效果依赖于药理基因组注释覆盖率。这些发现为后续研究提出的多模态框架提供了依据。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。