收藏切换
Integrative analysis of differential metabolites between Paeoniae Radix Alba and Paeoniae Radix Rubra with non-targeted metabolomics and interpretable machine learning
收藏切换
Qi CHEN1, 2, Guo-qi FAN1, 2, Yi-rui GUO1, Li-hua ZUO2, 3, Han-bing LI4, Dan-ping DENG5, Cheng-hui ZHU5, Zhi SUN2, 3, *, Gai-zhi LIU1, *
Acta Pharmaceutica Sinica | 2026, 61(3) : 871 - 880
Less
收藏切换
Acta Pharmaceutica Sinica | 2026, 61(3): 871-880
• Original Articles •
Integrative analysis of differential metabolites between Paeoniae Radix Alba and Paeoniae Radix Rubra with non-targeted metabolomics and interpretable machine learning
Full
Qi CHEN1, 2, Guo-qi FAN1, 2, Yi-rui GUO1, Li-hua ZUO2, 3, Han-bing LI4, Dan-ping DENG5, Cheng-hui ZHU5, Zhi SUN2, 3, *, Gai-zhi LIU1, *
Affiliations
  • 1College of Pharmacy, Henan University of Traditional Chinese Medicine, Zhengzhou 450046, China
  • 2Department of Pharmacy, the First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, China
  • 3Henan Engineering Research Center of Clinical Mass Spectrometry for Precision Medicine, Zhengzhou 450052, China
  • 4School of Medicine, Henan University of Traditional Chinese Medicine, Zhengzhou 450046, China
  • 5Chenzhou Municipal Hospital of Traditional Chinese Medicine, Chenzhou 423000, China
Published: 2026-03-12 doi: 10.16438/j.0513-4870.2025-1131
Outline
收藏切换

Ultra-high performance liquid chromatography coupled with quadrupole-Orbitrap high-resolution mass spectrometry (UHPLC-Q-Orbitrap-HRMS) was applied for the non-targeted metabolomic characterization of Paeoniae Radix Alba and Paeoniae Radix Rubra decoction pieces. Differential metabolites were identified through multivariate statistical analysis. Interpretable machine learning methods, including random forest (RF), adaptive boosting (AdaBoost), and extreme gradient boosting (XGBoost), were further employed to build classification models, and the Shapley additive explanations (SHAP) algorithm was used to evaluate the contributions of characteristic metabolites. A total of 44 metabolites were identified, including 9 flavonoids, 8 phenolic acids, and other types of metabolites, among which 12 showed significant differences between the two kinds of decoction pieces. In the test set, the RF model exhibited superior performance. SHAP analysis indicated that gluconic acid, quercetin, kaempferol, L-aspartic acid, taxifolin, and oxypaeoniflorin significantly contributed to model discrimination, with L-aspartic acid showing elevated levels in Paeoniae Radix Alba, while the other metabolites were relatively higher in Paeoniae Radix Rubra. The metabonomics-machine learning strategy established in this study provides potential chemical evidence for elucidating the efficacy differences between Paeoniae Radix Alba and Paeoniae Radix Rubra and offers new insights into the identification, origin traceability, and characteristic marker discovery of other easily confused traditional Chinese medicines.

Paeoniae Radix Alba  /  Paeoniae Radix Rubra  /  non-targeted metabolomics  /  differential metabolite  /  machine learning  /  SHAP analysis
陈琪, 范国旗, 郭伊瑞, 左莉华, 李寒冰, 邓丹萍, 朱承慧, 孙志, 刘改枝. 基于非靶向代谢组学与可解释机器学习的白芍与赤芍饮片差异代谢物研究. 药学学报, 2026 , 61 (3) : 871 -880 . DOI: 10.16438/j.0513-4870.2025-1131
Qi CHEN, Guo-qi FAN, Yi-rui GUO, Li-hua ZUO, Han-bing LI, Dan-ping DENG, Cheng-hui ZHU, Zhi SUN, Gai-zhi LIU. Integrative analysis of differential metabolites between Paeoniae Radix Alba and Paeoniae Radix Rubra with non-targeted metabolomics and interpretable machine learning[J]. Acta Pharmaceutica Sinica, 2026 , 61 (3) : 871 -880 . DOI: 10.16438/j.0513-4870.2025-1131
Year 2026 volume 61 Issue 3
233
103
Cite this Article
BibTeX
Article Info
doi: 10.16438/j.0513-4870.2025-1131
  • Receive Date:2025-09-22
  • Online Date:2026-09-21
  • Published:2026-03-12
Article Data
Affiliations
History
  • Received:2025-09-22
  • Revised:2025-12-09
Affiliations
    1College of Pharmacy, Henan University of Traditional Chinese Medicine, Zhengzhou 450046, China
    2Department of Pharmacy, the First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, China
    3Henan Engineering Research Center of Clinical Mass Spectrometry for Precision Medicine, Zhengzhou 450052, China
    4School of Medicine, Henan University of Traditional Chinese Medicine, Zhengzhou 450046, China
    5Chenzhou Municipal Hospital of Traditional Chinese Medicine, Chenzhou 423000, China
References
Share
https://castjournals.cast.org.cn/joweb/yxxb/EN/10.16438/j.0513-4870.2025-1131
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT