Quantifying compatibility mechanisms in traditional Chinese medicine with interpretable graph neural networks

作者：Jingqi Zeng, Xiao‐Bin Jia · 发表于：Journal of Pharmaceutical Analysis · 年份：2025 · DOI：10.1016/j.jpha.2025.101342 · 被引用次数：23 · 研究领域：Traditional Chinese Medicine Studies、Metabolomics and Mass Spectrometry Studies、Traditional Chinese Medicine Analysis

Traditional Chinese medicine (TCM) features complex compatibility mechanisms involving multi-component, multi-target, and multi-pathway interactions. This study presents an interpretable graph artificial intelligence (GraphAI) framework to quantify such mechanisms in Chinese herbal formulas (CHFs). A multidimensional TCM knowledge graph (TCM-MKG; https://zenodo.org/records/13763953 ) was constructed, integrating seven standardized modules: TCM terminology, Chinese patent medicine (CPM), Chinese herbal pieces (CHPs), pharmacognostic origins (POs), chemical compounds, biological targets, and diseases. A neighbor-diffusion strategy was used to address the sparsity of compound–target associations, increasing target coverage from 12.0% to 98.7%. Graph neural networks (GNNs) with attention mechanisms were applied to 6,080 CHFs, modeled as graphs with CHPs as nodes. To embed domain-specific semantics, virtual nodes medicinal properties—therapeutic nature, flavor, and meridian tropism—were introduced, enabling interpretable modeling of inter-CHP relationships. The model quantitatively captured classical compatibility roles such as “sovereign–minister–assistant–courier,” and uncovered TCM etiological types derived from diagnostic and efficacy patterns. Model validation using 215 CHFs used for coronavirus disease 2019 (COVID-19) management highlighted Radix Astragali – Rhizoma Phragmitis as a high-attention herb pair. Mass spectrometry and target prediction identified three active comp...