Applications of Artificial Intelligence in Research on Traditional Chinese Medicine Metabolomics

doi:10.19803/j.1672-8629.20250880

Abstract

Abstract: Objective To explore the applications of artificial intelligence (AI) in research on traditional Chinese medicine (TCM) metabolomics in order to upgrade the intelligent analysis of complex systems of TCM. Methods Following the metabolomics research workflow, this review outlined AI applications in such spheres as data processing, metabolite identification, interpretation of mechanisms, and quality control of TCM. Specific examples were cited to demonstrate the strengths and weaknesses of AI. Results AI enables high-throughput, automated preprocessing of metabolomic data so that quality control and feature screening are improved. Integrated with databases and molecular networking, AI can shed light on mapping relationships from vast data on mass spectrometry for intelligent metabolite predictions. By automatically identifying complex patterns in high-dimensional data and assessing feature contributions, AI facilitates differential metabolite selection via feature selection, deep relationship mining, and interpretability analysis. Network analysis, machine learning, and knowledge graphs can combine to offer insights into the mechanisms of TCM. Furthermore, AI can assist in identification of geographical origins and quality control by analyzing secondary metabolites. While AI enhances data processing efficiency, accuracy of predictions, and multi-dimensional integration, such challenges persist as the lack of data standardization, limited model interpretability, and insufficient domain-specific adaptation. Conclusion AI can empower TCM metabolomics research and contribute to the informatization and intellectualization of the analysis of complex mechanisms of TCM.

Key words: Traditional Chinese Medicine(TCM), Metabolomics, Biomarker, Artificial Intelligence(AI), Machine Learning, Mechanism of Action

CLC Number:

R962
R282

LI Yaolei, CHENG Xianlong, LIN Yongqiang, LIU Jing, WEI Feng. Applications of Artificial Intelligence in Research on Traditional Chinese Medicine Metabolomics[J]. Chinese Journal of Pharmacovigilance, 2026, 23(5): 481-486.

Add to citation manager EndNote|Ris|BibTeX

URL: https://zgywjj.magtechjournal.com/EN/10.19803/j.1672-8629.20250880

https://zgywjj.magtechjournal.com/EN/Y2026/V23/I5/481

References

[1] FAN J, LI YL, YANG S, et al.Two Polysaccharides from Polygonum multiflorum Thunb. Exert Anti-Aging by Regulating P53/P21 Pathway and Amino Acid Metabolism[J]. International Journal of Biological Macromolecules, 2025, 306(3):141573.
[2] YANG J, GUAN P, YU D, et al.MetCohort:Precise Feature Detection and Correspondence for Untargeted Metabolomics in Large-Scale Cohort Studies[J]. Anal Chem, 2025, 97(19):10155-10162.
[3] LI YL, FAN J, CHENG XL, et al.New Revolution for Quality Control of TCM in Industry 4.0:Focus on Artificial Intelligence and Bioinformatics[J]. Trends in Analytical Chemistry, 2024, 181(Part B):118023.
[4] LI D, CHEN R, XU X, et al.Integrated Metabolomics and Network Pharmacology to Reveal the Mechanisms of Shexiang Baoxin Pill Against Atherosclerosis[J]. Phytomedicine, 2024, 135:156138.
[5] XU Y, CAO L, CHEN Y, et al.Integrating Machine Learning in Metabo-lomics:a Path to Enhanced Diagnostics and Data Interpretation[J]. Small Methods, 2024, 8(12):e2400305.
[6] ZHAO C, ZHAO T, SHEN Q, et al.Practical Guidance for Training Machine Learning Models in Metabolomics and Mass Spectrometry Research[J]. Anal Chem, 2025, 97(42):23005-23013.
[7] DENG Y, YAO Y, WANG Y, et al.An End-to-End Deep Learning Method for Mass Spectrometry Data Analysis to Reveal Disease-Specific Metabolic Profiles[J]. Nat Commun, 2024, 15(1):7136.
[8] IDKOWIAK J, DEHAIRS J, SCHWARZEROVÁ J, et al.Best Practices and Tools in R and Python for Statistical Processing and Visualization of Lipidomics and Metabolomics Data[J]. Nat Commun, 2025, 16(1):8714.
[9] YANG Q, HONG J, LI Y, et al.A Novel Bioinformatics Approach to Identify the Consistently Well-Performing Normalization Strategy for Current Metabolomic Studies[J]. Brief Bioinform, 2020, 21(6):2142-2152.
[10] FU J, ZHANG Y, WANG Y, et al.Optimization of Metabolomic Data Processing Using NOREVA[J]. Nat Protoc, 2022, 17(1):129-151.
[11] LIANG YJ, YANG CT, CHEN CW, et al.SMART 2.0 Statistical Metabolomics Analysis:an R Tool 2.0[J]. Anal Chem, 2025, 97(46):25453-25468.
[12] JIN ZL, CHEN L, WANG Y, et al.Application of Machine Learning in LC-MS-Based Non-Targeted Analysis[J]. TrAC Trends in Analytical Chemistry, 2025, 189:118243.
[13] QIANG H, WANG F, LU W, et al.Language Model-Guided Anticipation and Discovery of Unknown Metabolites[J]. bioRxiv, 2024, 11(13):623458.
[14] DING Y, LUO X, GUO J, et al.Identification of Gut Microbial Bile Acid Metabolic Enzymes via an AI-Assisted Pipeline[J]. Cell, 2025, 188(21):6012-6027.
[15] CHEN L, XIA B, WANG Y, et al.CMSSP:a Contrastive Mass Spectra-Structure Pretraining Model for Metabolite Identification[J]. Anal Chem, 2024, 96(42):16871-16881.
[16] MENG F, ZHANG G, XIAO W, et al.MedMeta:an AI-Enabled and Genomics-Based Database for Functional Profiling of Secondary Metabolites in Medicinal Species[J/OL]. Engineering,(2025-09-17)[2026-04-20]. https://doi.org/10.1016/j.eng.2025.09.007.
[17] KE WH, WANG YY, ZENG YP, et al.DMetFinder:a Novel Mass Spectrometry Analysis Tool for Comprehensive Drug Metabolite Detection[J]. Talanta, 2026, 298(Part A):128918.
[18] CHEN Y, WANG B, ZHAO Y, et al.Metabolomic Machine Learning Predictor for Diagnosis and Prognosis of Gastric Cancer[J]. Nat Commun, 2024, 15(1):1657.
[19] YANG S, LI Z, LI W, et al.Unraveling the Variations and Relationships between Phytochemical Constituents and Anti-Inflammatory Potentials of Three Zanthoxylum Species through Metabolomics and Explainable Machine Learning[J]. Industrial Crops and Products, 2024, 212:118281.
[20] WINCHESTER LM, HARSHFIELD EL, SHI L, et al.Artificial Intelligence for Biomarker Discovery in Alzheimer’s Disease and Dementia[J]. Alzheimers Dement, 2023, 19(12):5860-5871.
[21] MA J, WEI P, XU X, et al.Machine Learning-Assisted Analysis of Serum Metabolomics and Network Pharmacology Reveals the Effective Compound from Herbal Formula against Alcoholic Liver Injury[J]. Chin Med, 2025, 20(1):48.
[22] LIU Y, ZHANG F, GE Y, et al.Application of LLMs/Transformer-Based Models for Metabolite Annotation in Metabolomics[J]. Health and Metabolism, 2025, 2(2):7.
[23] MA X, SHEDLOCK CJ, MEDINA T, et al.AI-Driven Framework to Map the Brain Metabolome in Three Dimensions[J]. Nat Metab, 2025, 7(4):842-853.
[24] MUTZ J, INIESTA R, LEWIS CM.Metabolomic age (MileAge) Predicts Health and Life Span:a Comparison of Multiple Machine Learning Algorithms[J]. Sci Adv, 2024, 10(51):3743.
[25] SCHUHKNECHT L, ORTMAYR K, JÄNES J, et al. A Human Metabolic Map of Pharmacological Perturbations Reveals Drug Modes of Action[J]. Nat Biotechnol, 2025, 43(12):1996-2008.
[26] WU IW, LIAO YC, TSAI TH, et al.Machine-Learning Assisted Discovery Unveils Novel Interplay between Gut Microbiota and Host Metabolic Disturbance in Diabetic Kidney Disease[J]. Gut Microbes, 2025, 17(1):2473506.
[27] LI Y, FAN J, JIN H, et al.New Vision for TCM Quality Control:Elemental Fingerprints and Key Ingredient Combination Strategy for Identification and Evaluation of TCMs[J]. Eur J Med Chem, 2025, 281:117006.
[28] LI YL, JIN HY, WEI F, et al. A Method for Tracing the Origin of Chinese Herbal Medicines by Fusing Elemental Fingerprints and Secondary Metabolite Profiles (一种融合元素指纹和次级代谢物轮廓的中药产地溯源方法):China, 202411801839.5[P].2025-03-18.
[29] LI YL, JIN HY, WEI F, et al. An Identification Method for the Geoherbalism of Chinese Herbal Medicines Based on Artificial Intelligence Integrating Multi-Omics Technology (基于人工智能融合多组学技术的中药道地性识别方法):China, 202411801541.4[P].2025-03-18.
[30] LI YL, WU H, FAN J, et al.Innovative Perspective on the Geographical Origin and Quality of Peucedanum praeruptorum Dunn through the Integration of Inorganic and Organic Substance Profiles[J/OL]. Journal of Pharmaceutical Analysis,(2025-07-11)[2026-4-20]. https://doi.org/10.1016/j.jpha.2025.101405.
[31] LI YL, JIN HY, WEI F, et al. A Method and System for Identifying the Geo-Authentic Production Area of Peucedani Radix Based on Machine Learning (一种基于机器学习的前胡药材道地产区识别方法及系统):China, 202410836824.6[P].2024-09-17.
[32] LI YL, JIN HY, WEI F, et al. A Method and System for Identifying the Planting Pattern of Peucedani Radix Based on Machine Learning (一种基于机器学习的前胡药材种植模式识别方法及系统):China, 202410836836.9[P].2024-09-17.
[33] LI YL, JIN HY, WEI F, et al.Introduction and Quality Factors of Peucedanum praeruptorum Dunn[J]. Chinese Journal of Pharma-covigilance(中国药物警戒), 2024, 21(11):1315-1320.
[34] WU JQ, DENG SQ, YU XY, et al.Identify Production Area, Growth Mode, Species, and Grade of Astragali Radix Using Metabolomics“Big Data”and Machine Learning[J]. Phytomedicine, 2024, 123:155201.
[35] WANG BY, PAN BY, ZHANG TY, et al.Transfer Learning and Permutation-Invariance Improving Predicting Genome-Wide, Cell-Specific and Directional Interventions Effects of Complex Systems[J]. Adv Sci, 2025, 12(46):e09456.
[36] BAO H, ZHANG X, WANG X, et al.MS2MP:a Deep Learning Framework for Metabolic Pathway Prediction from MS/MS-Based Untargeted Metabolomics[J]. Anal Chem, 2025, 97(27):14200-14209.
[37] WANG X, CHEN Y, LI Z, et al.Enhanced Structure-Guided Molecular Networking Annotation Method for Untargeted Metabolomics Data from Orbitrap Astral Mass Spectrometer[J]. Anal Chem, 2025, 97(22):11506-11514.
[38] ZHAO J, ZHOU Y, BAO H, et al.MODA:a Graph Convolutional Network-Based Multi-Omics Integration Framework for Unraveling Hub Molecules and Disease Mechanisms[J]. Brief Bioinform, 2025, 26(5):532.
[39] YAN CQ, FAN RQ, NING YP, et al.Applications and Prospect of Deep Learning Model in Early Warning of Toxicity of Traditional Chinese Medicine[J]. Chinese Journal of Pharmacology and Toxicology(中国药理学与毒理学杂志), 2022, 36(3):231-240.
[40] YU P, YAN X, HONG J, et al.Geographical Origins of Angelica Sinensis Using Functional Compounds and Multielement with Machine Learning-Based Fusion Approaches[J]. Food Chem, 2025, 471:142747.
[41] WANG SQ, SHEN L, SONG LY, et al.Application and Discussion of Deep Learning Techniques in Quality Control of Traditional Chinese Medicines[J]. Chinese Traditional and Herbal Drugs(中草药), 2025, 56(16):6048-6057.
[42] YAN DY, ZHENG QG, CHANG K, et al.Artificial Intelligence in Traditional Chinese Medicine:from Systems Biological Mechanism Discovery, Real-World Clinical Evidence Inference to Personalized Clinical Decision Support[J]. Chinese Journal of Natural Medicines, 2025, 23(11):1310-1328.