Integrating Artificial Intelligence with Traditional Wisdom: The Rise of Computational Ethnopharmacology for TCM Discovery and Interaction Prediction

Abstract

Traditional Chinese Medicine (TCM) faces a persistent “black box” problem arising from multi-component, multi-target, and nonlinear synergistic mechanisms that challenge reductionist biomedical paradigms. This review synthesizes major breakthroughs (2024–2025) and argues that computational ethnopharmacology represents a paradigm shift beyond classical network pharmacology. We propose a four-layer architecture—data, semantic, topological, and structural layers—integrating evidence-oriented databases (e.g., HERB 2.0), GraphRAG-enabled LLM mining of classical texts, hypergraph/heterogeneous GNN modeling of formula compatibility, and AlphaFold 3–driven structural inference coupled with inverse docking and molecular dynamics. Focusing on clinically actionable herb–drug interaction prediction, we further outline validation and reporting checklists to improve reproducibility and safety translation, and highlight dry–wet closed-loop directions for future research.