Artificial intelligence algorithms drive the deciphering of traditional Chinese medicine by analyzing the chemicalome, targetome, and bioactivome

Abstract

Artificial intelligence (AI) is reshaping the research paradigm of traditional Chinese medicine (TCM) in a profound way. This review offers a systematic account of how AI algorithms propel the modernization of TCM through the integrated analysis of three core concepts: the chemicalome, referring to the collection of in vitro and in vivo chemical constituents derived from TCM; the targetome, defined as the set of biological macromolecules that engage in interactions with TCM components; and the bioactivome, signifying the range of integrated biological activities and phenotypic outcomes induced by TCM interventions. First, it illustrates how AI enables comprehensive characterization of complex in vitro and in vivo chemicalomes by revolutionizing mass spectrometry analysis and metabolite identification techniques. Next, it examines how AI works in conjunction with experimental technologies to systematically predict the targetome and validate these predictions. Furthermore, the review clarifies how AI deciphers the bioactivome arising from TCM interventions and uncovers mechanisms through the integration of multi-omics datasets. Finally, it explores methodologies for establishing comprehensive interconnections among the chemicalome, targetome, and bioactivome. This analytical framework demonstrates that AI functions not just as a tool to enhance research efficiency, but also as a foundational methodology capable of systematically decoding TCM and linking traditional wisdom with modern science.

Acknowledgments

We gratefully acknowledge financial support from the Strategic Priority Research Program of the Chinese Academy of Sciences (XDB0830200 and XDB1260301), the National Natural Science Foundation of China (T2225002 and 82274064), and the Lingang Laboratory (LGL-8888-02).

Ethical statements

Not applicable.

Author contributions

The authors confirm contributions to the review as follows: conception and design: Xin G, Song H; draft manuscript preparation: Song H, Liang Z, Zhang X, Yang F; analysis and interpretation: Zheng M, Xin G. All authors reviewed and approved the final version of the manuscript.

Data availability

Data sharing is not applicable to this review as no datasets were generated or analyzed.

Conflict of interest

The authors declare that they have no conflict of interest.

References

[1] Vamathevan J, Clark D, Czodrowski P, Dunham I, Ferran E, et al. 2019. Applications of machine learning in drug discovery and development. Nature Reviews Drug Discovery 18: 463-477

[2] Yang H, Sun L, Wang Z, Li W, Liu G, et al. 2018. ADMETopt: a web server for ADMET optimization in drug design via scaffold hopping. Journal of Chemical Information and Modeling 58: 2051-2056

[3] Torng W, Altman RB. 2019. Graph convolutional neural networks for predicting drug-target interactions. Journal of Chemical Information and Modeling 59: 4131-4149

[4] Olivecrona M, Blaschke T, Engkvist O, Chen H. 2017. Molecular de novo design through deep reinforcement learning. Journal of Cheminformatics 9: 48

[5] Cui H, Wang C, Maan H, Pang K, Luo F, et al. 2024. scGPT: toward building a foundation model for single-cell multi-omics using generative AI. Nature Methods 21: 1470-1480

[6] Atanasov AG, Waltenberger B, Pferschy-Wenzig EM, Linder T, Wawrosch C, et al. 2015. Discovery and resupply of pharmacologically active plant-derived natural products: A review. Biotechnology Advances 33: 1582-1614

[7] Li S, Xiao W. 2025. General expert consensus on the application of network pharmacology in the research and development of new traditional Chinese medicine drugs. Chinese Journal of Natural Medicines 23: 129-142

[8] Chen YH, Bi JH, Xie M, Zhang H, Shi ZQ, et al. 2021. Classification-based strategies to simplify complex traditional Chinese medicine (TCM) researches through liquid chromatography-mass spectrometry in the last decade (2011-2020): Theory, technical route and difficulty. Journal of Chromatography A 1651: 462307

[9] Patti GJ, Yanes O, Siuzdak G. 2012. Innovation: Metabolomics: the apogee of the omics trilogy. Nature Reviews Molecular Cell Biology 13: 263-269

[10] Wang Y, Zhao J, Xu Y, Tao C, Tong J, et al. 2023. Uncovering SOD3 and GPX4 as new targets of Benzo[α]pyrene-induced hepatotoxicity through Metabolomics and Chemical Proteomics. Redox Biology 67: 102930

[11] Gong P, Cui N, Wu L, Liang Y, Hao K, et al. 2012. Chemicalome and metabolome matching approach to elucidating biological metabolic networks of complex mixtures. Analytical Chemistry 84: 2995-3002

[12] Zheng X, Cai X, Hao H. 2022. Emerging targetome and signalome landscape of gut microbial metabolites. Cell Metabolism 34: 35-58

[13] Zhao MY, Chen YH, Wang WY, Sun WP, Xiao HH, et al. 2022. A strategy to comprehensively analyze the bioactivity of complex herbal prescriptions via peak-by-peak cutting and knock-out chromatography: Qiliqiangxin capsule as an example. Journal of Separation Science 45: 2446-2457

[14] Liu FT, Chen YH, Wang WY, Zhang JN, Sun RB, et al. 2025. A comprehensive analysis of volatile and nonvolatile components in berberis fortunei and its inhibition against HT29 colorectal cancer cells through GC-IMS, LC-QTOF-MS, and docking-based network analysis. Phytochemical Analysis 36: 2349-2361

[15] Yang F, Liang Z, Zhao H, Zheng J, Liu L, et al. 2025. Mass spectral database-based methodologies for the annotation and discovery of natural products. Chinese Journal of Natural Medicines 23: 410-420

[16] Wang M, Carver JJ, Phelan VV, Sanchez LM, Garg N, et al. 2016. Sharing and community curation of mass spectrometry data with Global Natural Products Social Molecular Networking. Nature Biotechnology 34: 828-837

[17] Yan Z, Ning J, Luo Z, Li D, Wang H, et al. 2025. Systematic analysis of the chemical components of gentiana urnula harry sm using SIRIUS and liquid chromatography high-resolution mass spectrometry. Rapid Communications in Mass Spectrometry 39: e10005

[18] Wei JN, Belanger D, Adams RP, Sculley D. 2019. Rapid prediction of electron-ionization mass spectrometry using neural networks. ACS Central Science 5: 700-708

[19] Stravs MA, Dührkop K, Böcker S, Zamboni N. 2022. MSNovelist: de novo structure generation from mass spectra. Nature Methods 19: 865-870

[20] Jiang M, Sha Y, Zou Y, Xu X, Ding M, et al. 2025. Integration of deep neural network modeling and LC-MS-based pseudo-targeted metabolomics to discriminate easily confused ginseng species. Journal of Pharmaceutical Analysis 15: 101116

[21] Wang H, Zhang L, Li X, Sun M, Jiang M, et al. 2024. Machine learning prediction for constructing a universal multidimensional information library of Panax saponins (ginsenosides). Food Chemistry 439: 138106

[22] Mi N, Cheng T, Li H, Yang P, Mu X, et al. 2019. Metabolite profiling of traditional Chinese medicine formula Dan Zhi Tablet: An integrated strategy based on UPLC-QTOF/MS combined with multivariate statistical analysis. Journal of Pharmaceutical and Biomedical Analysis 164: 70-85

[23] Chen Z, Lin Z, Wan H, Li C, Jin W, et al. 2025. Rapid and accurate metabolite identification of traditional Chinese medicine based on UPLC-Q-TOF-MS coupled with UNIFI analysis platform and quantitative structure-retention relationship: Danshen-Honghua herbal pair as an example. Journal of Pharmaceutical and Biomedical Analysis 257: 116696

[24] Li Y, Liu X, Zhou J, Li F, Wang Y, et al. 2025. Artificial intelligence in traditional Chinese medicine: advances in multi-metabolite multi-target interaction modeling. Frontiers in Pharmacology 16: 1541509

[25] Feinberg EN, Joshi E, Pande VS, Cheng AC. 2020. Improvement in ADMET prediction with multitask deep featurization. Journal of Medicinal Chemistry 63: 8835-8848

[26] Zhang X, Liu T, Fan X, Ai N. 2017. In silico modeling on ADME properties of natural products: Classification models for blood-brain barrier permeability, its application to traditional Chinese medicine and in vitro experimental validation . Journal of Molecular Graphics and Modelling 75: 347-354

[27] Daina A, Michielin O, Zoete V. 2017. SwissADME: a free web tool to evaluate pharmacokinetics, drug-likeness and medicinal chemistry friendliness of small molecules. Scientific Reports 7: 42717

[28] Xiong G, Wu Z, Yi J, Fu L, Yang Z, et al. 2021. ADMETlab 2.0: an integrated online platform for accurate and comprehensive predictions of ADMET properties. Nucleic Acids Research 49: W5-W14

[29] Chen L, Xia B, Wang Y, Huang X, Gu Y, et al. 2024. CMSSP: a contrastive mass spectra-structure pretraining model for metabolite identification. Analytical Chemistry 96: 16871-16881

[30] Li L, Wang X, Ma R, Hou M. 2024. An integrating strategy for systematic profiling of Chinese patent drug's chemicalome and associated metabolome: Huanghou antidiarrhea dropping pills as a case study. Journal of Chromatography. B, Analytical Technologies in the Biomedical and Life Sciences 1234: 124029

[31] Zhu H, Chang W, Zhou C, Xu C, Su W, et al. 2021. Chemicalome and metabolome profiling of Chai-Gui Decoction using an integrated strategy based on UHPLC-Q-TOF-MS/MS analysis. Journal of Chromatography. B, Analytical Technologies in the Biomedical and Life Sciences 1185: 122979

[32] Wang HY, Qu C, Li MN, Li CR, Liu RZ, et al. 2022. Time-series-dependent global data filtering strategy for mining and profiling of xenobiotic metabolites in a dynamic complex matrix: application to biotransformation of flavonoids in the extract of Ginkgo biloba by gut microbiota . Journal of Agricultural and Food Chemistry 70: 14386-14394

[33] Song HP, Chen J, Hong JY, Hao H, Qi LW, et al. 2015. A strategy for screening of high-quality enzyme inhibitors from herbal medicines based on ultrafiltration LC-MS and in silico molecular docking. Chemical Communications 51: 1494-1497

[34] Hao H, Kirchhoff F. 2025. Navigating drug discovery with targetome. Targetome 1: e001

[35] Nguyen T, Le H, Quinn TP, Nguyen T, Le TD, et al. 2021. GraphDTA: predicting drug-target binding affinity with graph neural networks. Bioinformatics 37: 1140-1147

[36] Öztürk H, Özgür A, Ozkirimli E. 2018. DeepDTA: deep drug-target binding affinity prediction. Bioinformatics 34: i821-i829

[37] Bai P, Miljković F, John B, Lu H. 2023. Interpretable bilinear attention network with domain adaptation improves drug-target prediction. Nature Machine Intelligence 5: 126-136

[38] Wu H, Liu J, Jiang T, Zou Q, Qi S, et al. 2024. AttentionMGT-DTA: A multi-modal drug-target affinity prediction using graph transformer and attention mechanism. Neural Networks 169: 623-636

[39] Chen L, Tan X, Wang D, Zhong F, Liu X, et al. 2020. TransformerCPI: improving compound-protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments. Bioinformatics 36: 4406-4414

[40] Zhao Y, Xing Y, Zhang Y, Wang Y, Wan M, et al. 2025. Evidential deep learning-based drug-target interaction prediction. Nature Communications 16: 6915

[41] Paton AE, Boiko DA, Perkins JC, Cemalovic NI, Reschützegger T, et al. 2025. Connecting chemical and protein sequence space to predict biocatalytic reactions. Nature 646: 108-116

[42] Shah PM, Zhu H, Lu Z, Wang K, Tang J, et al. 2025. DeepDTAGen: a multitask deep learning framework for drug-target affinity prediction and target-aware drugs generation. Nature Communications 16: 5021

[43] Cao D, Chen M, Zhang R, Wang Z, Huang M, et al. 2025. SurfDock is a surface-informed diffusion generative model for reliable and accurate protein-ligand complex prediction. Nature Methods 22: 310-322

[44] Namba S, Iwata M, Nureki SI, Yuyama Otani N, Yamanishi Y. 2025. Therapeutic target prediction for orphan diseases integrating genome-wide and transcriptome-wide association studies. Nature Communications 16: 3355

[45] Gonzalez G, Lin X, Herath I, Veselkov K, Bronstein M, et al. 2025. Combinatorial prediction of therapeutic perturbations using causally inspired neural networks. Nature Biomedical Engineering (Epub ahead of print)

[46] Zhang Y, Leung AK, Kang JJ, Sun Y, Wu G, et al. 2025. A multiscale functional map of somatic mutations in cancer integrating protein structure and network topology. Nature Communications 16: 975

[47] Li J, Dan W, Zhang C, Liu N, Wang Y, et al. 2024. Exploration of berberine against ulcerative colitis via TLR4/NF- κB/HIF-1 α pathway by bioinformatics and experimental validation . Drug Design, Development and Therapy 18: 2847-2868

[48] Kurzawa N, Leo IR, Stahl M, Kunold E, Becher I, et al. 2023. Deep thermal profiling for detection of functional proteoform groups. Nature Chemical Biology 19: 962-971

[49] Leo IR, Kunold E, Audrey A, Tampere M, Eirich J, et al. 2025. Functional proteoform group deconvolution reveals a broader spectrum of ibrutinib off-targets. Nature Communications 16: 1948

[50] Jafari R, Almqvist H, Axelsson H, Ignatushchenko M, Lundbäck T, et al. 2014. The cellular thermal shift assay for evaluating drug target interactions in cells. Nature Protocols 9: 2100-2122

[51] Malinovska L, Cappelletti V, Kohler D, Piazza I, Tsai TH, et al. 2023. Proteome-wide structural changes measured with limited proteolysis-mass spectrometry: an advanced protocol for high-throughput applications. Nature Protocols 18: 659-682

[52] Piazza I, Beaton N, Bruderer R, Knobloch T, Barbisan C, et al. 2020. A machine learning-based chemoproteomic approach to identify drug targets and binding sites in complex proteomes. Nature Communications 11: 4200

[53] Luo P, Liu D, Zhang Q, Yang F, Wong YK, et al. 2022. Celastrol induces ferroptosis in activated HSCs to ameliorate hepatic fibrosis via targeting peroxiredoxins and HO-1. Acta Pharmaceutica Sinica B 12: 2300-2314

[54] Biggs GS, Cawood EE, Vuorinen A, McCarthy WJ, Wilders H, et al. 2025. Robust proteome profiling of cysteine-reactive fragments using label-free chemoproteomics. Nature Communications 16: 73

[55] Peng W, Yang Y, Lu H, Shi H, Jiang L, et al. 2024. Network pharmacology combines machine learning, molecular simulation dynamics and experimental validation to explore the mechanism of acetylbinnankadsurin A in the treatment of liver fibrosis. Journal of Ethnopharmacology 323: 117682

[56] Edwards AM, Owen DR. 2025. Protein-ligand data at scale to support machine learning. Nature Reviews Chemistry 9: 634-645

[57] Mayr F, Möller G, Garscha U, Fischer J, Rodríguez Castaño P, et al. 2020. Finding new molecular targets of familiar natural products using in silico target prediction. International Journal of Molecular Sciences 21: 7102

[58] Zhong F, Wu X, Yang R, Li X, Wang D, et al. 2022. Drug target inference by mining transcriptional data using a novel graph convolutional network framework. Protein and Cell 13: 281-301

[59] Wang B, Pan B, Zhang T, Liu Q, Li S. 2025. Transfer learning and permutation-invariance improving predicting genome-wide, cell-specific and directional interventions effects of complex systems. Advanced Science 12: e09456

[60] Zhao WS, Chen KF, Liu M, Jia XL, Huang YQ, et al. 2023. Investigation of targets and anticancer mechanisms of covalently acting natural products by functional proteomics. Acta Pharmacologica Sinica 44: 1701-1711

[61] Nie HJ, Fu YJ, Long S, Wang JY, Zhao WS, et al. 2025. Chemoproteomics reveals proteome-wide covalent and non-covalent targets of withaferin A. Acta Pharmacologica Sinica 46: 1782-1793

[62] Wang C, Shi J, Rao Q, Shen B, Su C, et al. 2025. Obtain substance of anti-glioblastoma from Erigeron breviscapus through fragment-based target research (FBTR): An efficient strategy for pharmacology investigation and optimization of natural products. Journal of Pharmaceutical Analysis 15: 101366

[63] Zhou W, Gao Y. 2025. Phenotype-target coupled drug screening: a high-efficiency framework for innovative drug discovery from CHMs. Engineering 57: 10-13

[64] Wang Y, Sui Y, Yao J, Jiang H, Tian Q, et al. 2024. Herb-CMap: a multimodal fusion framework for deciphering the mechanisms of action in traditional Chinese medicine using Suhuang antitussive capsule as a case study. Briefings in Bioinformatics 25: bbae362

[65] Zhang L, Zheng Y, Shao M, Chen A, Liu M, et al. 2025. AlphaFold-based AI docking reveals AMPK/SIRT1-TFEB pathway modulation by traditional Chinese medicine in metabolic-associated fatty liver disease. Pharmacological Research 212: 107617

[66] Guo F, Tang X, Zhang W, Wei J, Tang S, et al. 2020. Exploration of the mechanism of traditional Chinese medicine by AI approach using unsupervised machine learning for cellular functional similarity of compounds in heterogeneous networks, XiaoErFuPi granules as an example. Pharmacological Research 160: 105077

[67] Liu K, Hong B, He ST, Du S, Ke J, et al. 2025. The potential mechanisms and material basis of Fuzheng Jiedu decoction broad-spectrum inhibiting coronaviruses. Virologica Sinica 40: 125-136

[68] Yan D, Zheng Q, Chang K, Hua R, Liu Y, et al. 2025. Artificial intelligence in traditional Chinese medicine: from systems biological mechanism discovery, real-world clinical evidence inference to personalized clinical decision support. Chinese Journal of Natural Medicines 23: 1310-1328

[69] Zhang JN, Pei ZD, Wang WY, Zhao MY, Pei WH, et al. 2024. Integration of high-resolution LC-Q-TOF mass spectrometry and multidimensional chemical-biological analysis to detect nanomolar-level acetylcholinesterase inhibitors from different Parts of Zanthoxylum nitidum . Journal of Agricultural and Food Chemistry 72: 17328-17342

[70] Wang S, Fu JL, Hao HF, Jiao YN, Li PP, et al. 2021. Metabolic reprogramming by traditional Chinese medicine and its role in effective cancer therapy. Pharmacological Research 170: 105728

[71] Zhang R, Zhu X, Bai H, Ning K. 2019. Network pharmacology databases for traditional Chinese medicine: review and assessment. Frontiers in Pharmacology 10: 123

[72] Vandereyken K, Sifrim A, Thienpont B, Voet T. 2023. Methods and applications for single-cell and spatial multi-omics. Nature Reviews Genetics 24: 494-515

[73] Liu J, Chen Y, Cao Z, Guan B, Peng J, et al. 2020. Babao Dan inhibits the migration and invasion of gastric cancer cells by suppressing epithelial-mesenchymal transition through the TGF- β/Smad pathway . Journal of International Medical Research 48: 1-13

[74] Wang S, Zhao Y, Hu X. 2023. Exploring the mechanism of Suanzaoren decoction in treatment of insomnia based on network pharmacology and molecular docking. Frontiers in Pharmacology 14: 1145532

[75] Song HP, Wu SQ, Hao H, Chen J, Lu J, et al. 2016. A chemical family-based strategy for uncovering hidden bioactive molecules and multicomponent interactions in herbal medicines. Scientific Reports 6: 23840

[76] Zhang J, Li C, Zhang L, Heng Y, Wang S, et al. 2022. Andrographolide, a diterpene lactone from the Traditional Chinese Medicine Andrographis paniculate, induces senescence in human lung adenocarcinoma via p53/p21 and Skp2/p27. Phytomedicine 98: 153933

[77] Yang L, Wang H, Zhu Z, Yang Y, Xiong Y, et al. 2025. Network pharmacology-driven sustainability: AI and multi-omics synergy for drug discovery in traditional Chinese medicine. Pharmaceuticals 18: 1074

[78] Ren Z, Ren Y, Li Z, Xu H. 2024. TCMM: A unified database for traditional Chinese medicine modernization and therapeutic innovations. Computational and Structural Biotechnology Journal 23: 1619-1630

[79] Li X, Ren J, Zhang W, Zhang Z, Yu J, et al. 2022. LTM-TCM: A comprehensive database for the linking of Traditional Chinese Medicine with modern medicine at molecular and phenotypic levels. Pharmacological Research 178: 106185

[80] Wei Q, Zhou Y, Hu Z, Shi Y, Ning Q, et al. 2024. Function-oriented mechanism discovery of coumarins from Psoralea corylifolia L. in the treatment of ovariectomy-induced osteoporosis based on multi-omics analysis . Journal of Ethnopharmacology 329: 118130

[81] Yin YH, Li CH, Huang HP, Zhang C, Zhang SB, et al. 2024. A novel enzyme-based functional correlation algorithm for multi-omics reveals the potential mechanisms of traditional Chinese medicines: taking Jian-Pi-Yi-Shen formula as an example. Journal of Pharmaceutical and Biomedical Analysis 241: 115973

[82] Argelaguet R, Arnol D, Bredikhin D, Deloro Y, Velten B, et al. 2020. MOFA+: a statistical framework for comprehensive integration of multi-modal single-cell data. Genome Biology 21: 111

[83] Patel-Murray NL, Adam M, Huynh N, Wassie BT, Milani P, et al. 2020. A multi-omics interpretable machine learning model reveals modes of action of small molecules. Scientific Reports 10: 954

[84] Zhou W, Yang K, Zeng J, Lai X, Wang X, et al. 2021. FordNet: Recommending traditional Chinese medicine formula via deep neural network integrating phenotype and molecule. Pharmacological Research 173: 105752

[85] Dong X, Zheng Y, Shu Z, Chang K, Xia J, et al. 2022. TCMPR: TCM prescription recommendation based on subnetwork term mapping and deep learning. BioMed Research International 2022: 4845726

[86] Niu Q, Li H, Tong L, Liu S, Zong W, et al. 2023. TCMFP: a novel herbal formula prediction method based on network target's score integrated with semi-supervised learning genetic algorithms. Briefings in Bioinformatics 24: bbad102

[87] Xue Z, Shang Y, Yang L, Li T, Yang B. 2025. A tailored database combining reference compound-derived metabolite, metabolism platform and chemical characteristic of Chinese herb followed by activity screening: application to magnoliae officinalis cortex. Journal of Pharmaceutical Analysis 15: 101066

[88] Zhang D, Zhang J, Chen S, Zhang H, Yang Y, et al. 2024. An integrated approach for studying exposure, metabolism, and disposition of traditional Chinese medicine using PATBS and MDRB tools: a case study of semen Armeniacae amarum . Chinese Medicine 19: 158

[89] Zeng J, Jia X. 2025. Quantifying compatibility mechanisms in traditional Chinese medicine with interpretable graph neural networks. Journal of Pharmaceutical Analysis 15: 101342

[90] Qiao Y, Hu L, Zhang J, Hu P, Luo X. 2025. Identifying novel therapeutic targets of natural compounds in traditional Chinese medicine herbs with hypergraph representation learning. Briefings in Bioinformatics 26: bbaf399

[91] Wei W, Zeng Q, Wang Y, Guo X, Fan T, et al. 2023. Discovery and identification of EIF2AK2 as a direct key target of berberine for anti-inflammatory effects. Acta Pharmaceutica Sinica B 13: 2138-2151

[92] Khanal S, Kumar A, Kumar P, Thakur P, Chander AM, et al. 2025. Unraveling bioactive potential and production in Ganoderma lucidum through omics and machine learning modeling. Chinese Herbal Medicines 17: 414-427

[93] Liu KX, Li N, Yin YH, Zhong ZJ, Li P, et al. 2022. An in-house database-driven untargeted identification strategy for deep profiling of chemicalome in Chinese medicinal formula. Journal of Chromatography A 1666: 462862

[94] Tian Y, Wan N, Zhang H, Shao C, Ding M, et al. 2023. Chemoproteomic mapping of the glycolytic targetome in cancer cells. Nature Chemical Biology 19: 1480-1491

[95] Zhou M, Wu B. 2025. Chinese medicine in regulating immune balance for the treatment of autoimmune diseases. American Journal of Chinese Medicine 53: 1615-1640

[96] Liu M, Wang Y, Deng W, Xie J, He Y, et al. 2024. Combining network pharmacology, machine learning, molecular docking and molecular dynamic to explore the mechanism of Chufeng Qingpi decoction in treating schistosomiasis. Frontiers in Cellular and Infection Microbiology 14: 1453529

[97] Chen J, Wei X, Zhang Q, Wu Y, Xia G, et al. 2023. The traditional Chinese medicines treat chronic heart failure and their main bioactive constituents and mechanisms. Acta Pharmaceutica Sinica B 13: 1919-1955

[98] Shang L, Wang Y, Li J, Zhou F, Xiao K, et al. 2023. Mechanism of Sijunzi Decoction in the treatment of colorectal cancer based on network pharmacology and experimental validation. Journal of Ethnopharmacology 302: 115876

[99] Ma S, Liu J, Li W, Liu Y, Hui X, et al. 2023. Machine learning in TCM with natural products and molecules: current status and future perspectives. Chinese Medicine 18: 43

[100] Gangwal A, Ansari A, Ahmad I, Azad AK, Kumarasamy V, et al. 2024. Generative artificial intelligence in drug discovery: basic framework, recent advances, challenges, and opportunities. Frontiers in Pharmacology 15: 1331062

[101] Guo Q, Hernandez-Hernandez S, Ballester PJ. 2025. UMAP-based clustering split for rigorous evaluation of AI models for virtual screening on cancer cell lines. Journal of Cheminformatics 17: 94

[102] Vigil-Vásquez C, Schüller A. 2022. De novo prediction of drug targets and candidates by chemical similarity-guided network-based inference. International Journal of Molecular Sciences 23: 9666

[103] Qadri YA, Shaikh S, Ahmad K, Choi I, Kim SW, et al. 2025. Explainable artificial intelligence: a perspective on drug discovery. Pharmaceutics 17: 1119