Sign in Subscribe
Artificial intelligence

Researchers Develop AI Framework to Quantify Traditional Chinese Medicine Mechanisms

Strategic Insights

— 1 min read

Researchers from China Pharmaceutical University have developed a novel interpretable graph artificial intelligence (GraphAI) framework to study the complex compatibility mechanisms of traditional Chinese medicine (TCM). The study, published in the Journal of Pharmaceutical Analysis, features a multidimensional TCM knowledge graph that integrates various standardized modules, including TCM terminology, Chinese patent medicines, and pharmacognostic origins. The GraphAI framework utilizes neighbor-diffusion and graph neural networks to model Chinese herbal formulas and uncover compatibility roles and etiological types.

Key Takeaways:

  • The GraphAI framework integrates seven standardized modules, including TCM terminology, Chinese patent medicines, and pharmacognostic origins.
  • The framework utilizes neighbor-diffusion and graph neural networks to increase target coverage from 12.0% to 98.7% and model inter-CHP relationships.
  • The model quantitatively captured classical compatibility roles, such as 'monarch-minister-assistant-guide,' and uncovered TCM etiological types derived from diagnostic and efficacy patterns.
  • The research concluded that the herb pair Radix Astragali-Rhizoma Phragmitis may offer therapeutic value for managing long COVID-19.
  • The GraphAI framework provides a scalable and interpretable platform for TCM mechanism research and discovery of bioactive herbal constituents.

Statistics:

  • 6,080 Chinese herbal formulas (CHFs) were modeled as graphs with CHPs as nodes.
  • The model increased target coverage from 12.0% to 98.7% using neighbor-diffusion strategy.
  • Radix Astragali-Rhizoma Phragmitis was identified as a high-attention herb pair with three active compounds, i.e., methylinissolin-3-O-glucoside, corydalin, and pingbeinine.

Sources:

  • "Quantifying compatibility mechanisms in traditional Chinese medicine with interpretable graph neural networks." Journal of Pharmaceutical Analysis, 2025, 15(8):101342. (Journal of Pharmaceutical Analysis - http://www.journals.elsevier.com/journal-of-pharmaceutical-analysis/)
  • Zeng, J., et al. (2025) "Quantifying compatibility mechanisms in traditional Chinese medicine with interpretable graph neural networks." Journal of Pharmaceutical Analysis, 2025, 15(8):101342.
  • NewsRx. New COVID-19 Research Has Been Reported by Researchers at China Pharmaceutical University (Quantifying compatibility mechanisms in traditional Chinese medicine with interpretable graph neural networks). Medical Letter on the CDC & FDA. September 14, 2025; p 128.

Read more