A Survey of Pharmacokinetics of Traditional Chinese Medicine Based on Multimodal Artificial Intelligence Data Fusion

doi:10.11871/jfdc.issn.2096-742X.2025.02.015

Abstract

Abstract:

[Objective] Traditional Chinese medicine is complex because of its multi-component and multi-target mechanisms of action. With its exceptional data processing capabilities, artificial intelligence has demonstrated significant potential in the discovery of targets and efficacy research concerning traditional Chinese medicine ingredients, thereby attracting considerable attention from both academia and industry. However, conventional artificial intelligence methods encounter challenges in integrating multi-dimensional data during the training process, which can lead to the omission of modalities and subsequently impact the accuracy and effectiveness of drug identification. [Methods] This article explores the application of artificial intelligence technologies, particularly deep learning, in the pharmacokinetics of traditional Chinese medicine. It also examines practical methods for multi-modal data fusion and elaborates on the application of these methods in drug-target interactions, drug-drug interactions, and protein-protein interactions. [Results] This article provides multi-angle knowledge services for pharmacokinetic research such as target prediction of traditional Chinese medicine, drug interaction, and quantitative analysis. [Conclusions] The application of multi-modal data fusion methods is expected to improve the efficiency and accuracy of traditional Chinese medicine research, promote the modernization of traditional Chinese medicine, and promote its widespread application around the world.

Key words: multimodal data fusion, artificial intelligence, traditional Chinese medicine, pharmacokinetics

GUO Huijie,ZHOU Yongjie,XU Jianzhen. A Survey of Pharmacokinetics of Traditional Chinese Medicine Based on Multimodal Artificial Intelligence Data Fusion[J]. Frontiers of Data and Computing, 2025, 7(2): 149-160, https://cstr.cn/32002.14.jfdc.CN10-1649/TP.2025.02.015.

Figures/Tables 2

References 76

[1]	YAMAGUCHI S, KANEKO M, NARUKAWA M. Approval success rates of drug candidates based on target, action, modality, application, and their combinations[J]. Clinical and Translational Science, 2021, 14(3): 1113-22.
[2]	SHI X, CHANG M, ZHAO M, et al. Traditional Chinese medicine compounds ameliorating glomerular diseases via autophagy: A mechanism review[J]. Biomed Pharmacother, 2022, 156: 113916.
[3]	LI Y, WANG Y, TAI W, et al. Challenges and Solutions of Pharmacokinetics for Efficacy and Safety of Traditional Chinese Medicine[J]. Current Drug Metabolism, 2015, 169: 765-76.
[4]	SHI P, LIN X, YAO H. A comprehensive review of recent studies on pharmacokinetics of traditional Chinese medicines (2014-2017) and perspectives[J]. Drug Metabolism Reviews, 2018, 50: 161-92.
[5]	MULLARD A. Parsing clinical success rates[J]. Nat Rev Drug Discov, 2016, 15(7): 447.
[6]	LI Y, DENG X, XIONG H, et al. Deciphering the toxicity-effect relationship and action patterns of traditional Chinese medicines from a smart data perspective: a comprehensive review[J]. Front Pharmacol, 2023, 14: 1278014.
[7]	WANG Y, SHI X, LI L, et al. The Impact of Artificial Intelligence on Traditional Chinese Medicine[J]. The American journal of Chinese medicine, 2021: 1-18.
[8]	HIRSCHBERG J, MANNING C D. Advances in natural language processing[J]. Science, 2015, 349: 261-266.
[9]	JANIESCH C, ZSCHECH P, HEINRICH K. Machine learning and deep learning[J]. Electronic Markets, 2021, 31: 685-695.
[10]	PANDEY M A. Computer Vision[J]. International Journal for Research in Applied Science and Engineering Technology, 2023.
[11]	GHARBIA M, CHANG-RICHARDS A Y, LU Y, et al. Robotic technologies for on-site building construction: A systematic review[J]. Journal of Building Engineering, 2020, 32: 101584.
[12]	DAINA A, MICHIELIN O, ZOETE V. SwissADME: a free web tool to evaluate pharmacokinetics, drug-likeness and medicinal chemistry friendliness of small molecules[J]. Scientific Reports, 2017, 7: 42717.
[13]	HADNI H, ELHALLAOUIA M. In silico design of EGFR(L858R/T790M/C797S) inhibitors via 3D-QSAR, molecular docking, ADMET properties and molecular dynamics simulations[J]. Heliyon, 2022, 8(11): e11537.
[14]	GAO J, LI P, CHEN Z, et al. A Survey on Deep Learning for Multimodal Data Fusion[J]. Neural Computation, 2020, 32: 829-64.
[15]	LIU M, GAO Y, YUAN Y, et al. Efficacy and safety of herbal medicine (Lianhuaqingwen) for treating COVID-19: A systematic review and meta-analysis[J]. Integrative medicine research., 2021, 10(1): 100644.
[16]	HEARST M A. Support vector machines[J]. IEEE Intelligent Systems & Their Applications, 1998, 13: 18-28.
[17]	KITSON N K, CONSTANTINOU A C, GUO Z G, et al. A survey of Bayesian Network structure learning[J]. Artificial Intelligence Review, 2021, 56: 8721-814.
[18]	DAYHOFF J E, DELEO J M. Artificial neural networks[J]. Cancer, 2001, 91.
[19]	BREIMAN L. Random forests[J]. Machine Learning, 2001, 45: 5-32.
[20]	GU J, WANG Z, KUEN J, et al. Recent advances in convolutional neural networks[J]. Pattern Recognit, 2015, 77: 354-77.
[21]	HUGHES J, REES S, KALINDJIAN S, et al. Principles of early drug discovery[J]. British Journal of Pharmacology, 2011, 162: 1239-1249
[22]	NABIZADEH F, MASROURI S, RAMEZANNEZHAD E, et al. Artificial intelligence in the diagnosis of multiple sclerosis: A systematic review[J]. Mult Scler Relat Disord, 2022, 59: 103673.
[23]	IWATA H. Application of in Silico Technologies for Drug Target Discovery and Pharmacokinetic Analysis[J]. Chemical & pharmaceutical bulletin (Tokyo), 2023, 71(6): 398-405.
[24]	SAMPENE A K, NYIRENDA F. Evaluating the effect of artificial intelligence on pharmaceutical product and drug discovery in China[J]. Future Journal of Pharmaceutical Sciences, 2024, 10(1): 58.
[25]	ZHANG S, WANG W, PI X, et al. Advances in the Application of Traditional Chinese Medicine Using Artificial Intelligence: A Review[J]. The American journal of Chinese medicine, 2023, 51(5): 1067-1083.
[26]	ARORA P, BEHERA M, SARAF S A, et al. Leveraging Artificial Intelligence for Synergies in Drug Discovery: From Computers to Clinics[J]. Current pharmaceutical design, 2024, 30(28): 2187-2205.
[27]	MOINGEON P, KUENEMANN M, GUEDJ M. Artificial intelligence-enhanced drug design and development: Toward a computational precision medicine[J]. Drug Discov Today, 2022, 27(1): 215-222.
[28]	LU L, LU T, TIAN C, et al. AI: Bridging Ancient Wisdom and Modern Innovation in Traditional Chinese Medicine[J]. JMIR Med Inform, 2024, 12: e58491.
[29]	LI W, GE X, LIU S, et al. Opportunities and challenges of traditional Chinese medicine doctors in the era of artificial intelligence[J]. Frontiers in Medicine (Lausanne), 2023, 10: 1336175.
[30]	ZENG J, JIA X. Systems Theory-Driven Framework for AI Integration into the Holistic Material Basis Research of Traditional Chinese Medicine[J]. Engineering, 2024.
[31]	STAHLSCHMIDT S R, ULFENBORG B, SYNNERGREN J. Multimodal deep learning for biomedical data fusion: a review[J]. Briefings in Bioinformatics, 2022, 23.
[32]	CHEN H, ENGKVIST O, WANG Y, et al. The rise of deep learning in drug discovery[J]. Drug Discovery Today, 2018, 23(6): 1241-1250.
[33]	ZOU J, HUSS M, ABID A, et al. A primer on deep learning in genomics[J]. Nature Genetics, 2019, 51(1): 12-18.
[34]	TORRISI M, POLLASTRI G, LE Q. Deep learning methods in protein structure prediction[J]. Computational and Structural Biotechnology Journal, 2020, 18: 1301-1310.
[35]	NGUYEN T M, KIM N, KIM D H, et al. Deep Learning for Human Disease Detection, Subtype Classification, and Treatment Response Prediction Using Epigenomic Data[J]. Biomedicines, 2021, 9(11): 1733.
[36]	ZHANG S, BAMAKAN S M H, QU Q, et al. Learning for Personalized Medicine: A Comprehensive Review From a Deep Learning Perspective[J]. IEEE Reviews in Biomedical Engineering, 2019, 12: 194-208.
[37]	TWA M D. Deep Learning and Clinical Decision Support[J]. Optometry and Vision Science, 2018, 95(4).
[38]	SINGH K, PIYUSH P, KUMAR R, et al. Multimodal Data Extraction & Fusion for Health Monitoring System and Early Diagnosis[C]// proceedings of the 2024 International Conference on Computational Intelligence and Computing Applications (ICCICA), 2024.
[39]	LI Y, YANG M, ZHANG Z. A Survey of Multi-View Representation Learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2016, 31: 1863-1883.
[40]	GAO J, LI J, LI Y. Approximate event detection over multi-modal sensing data[J]. Journal of Combinatorial Optimization, 2015, 32: 1002-1016.
[41]	SHEN M R, HE Y, SHI S M. Development of chromatographic technologies for the quality control of Traditional Chinese Medicine in the Chinese Pharmacopoeia[J]. Journal of Pharmaceutical Analysis, 2021, 11(2): 155-162.
[42]	WEIWE C. Research Progress on Spectral Analysis for Traditional Chinese Medicine(TCM)[J]. Acta Laser Biology Sinica, 2015.
[43]	HAN C, LI J, HUI Q. Determination of Trace Elements in Jinqi, a Traditional Chinese Medicine[J]. Biological Trace Element Research, 2008, 122: 122-6.
[44]	LUAN X, ZHANG L J, LI X Q, et al. Compound-based Chinese medicine formula: From discovery to compatibility mechanism[J]. Journal of Ethnopharmacology, 2020: 112687.
[45]	WANG T, LIU J, LUO X, et al. Functional metabolomics innovates therapeutic discovery of traditional Chinese medicine derived functional compounds[J]. Pharmacology & Therapeutics 2021, 224: 107824.
[46]	ACAR E, PAPALEXAKIS E E, GURDENIZ G, et al. Structure-revealing data fusion[J]. BMC Bioinformatics, 2014, 15.
[47]	XU P, ZHU X, CLIFTON D A. Multimodal Learning With Transformers: A Survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45: 12113-12132.
[48]	LIANG P P, MORENCY L P. Tutorial on Multimodal Machine Learning: Principles, Challenges, and Open Questions[J]. Companion Publication of the 25th International Conference on Multimodal Interaction, 2023.
[49]	BALTRUŠAITIS T, AHUJA C, MORENCY L-P. Multimodal Machine Learning: A Survey and Taxonomy[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 41: 423-443.
[50]	ZHANG R, NIE F, LI X, et al. Feature selection with multi-view data: A survey[J]. Inf Fusion, 2019, 50: 158-167.
[51]	WEI Y, WU D, TERPENNY J. Decision-Level Data Fusion in Quality Control and Predictive Maintenance[J]. IEEE Transactions on Automation Science and Engineering, 2021, 18(1): 184-194.
[52]	WU Z, CAI L, MENG H M. Multi-level Fusion of Audio and Visual Features for Speaker Identification, F, 2005[C].
[53]	WEI Y W, WANG X, GUAN W, et al. Neural Multimodal Cooperative Learning Toward Micro-Video Understanding[J]. IEEE Transactions on Image Processing, 2020, 29: 1-14.
[54]	LIU X, WANG L, WONG D F, et al. Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning[J]. ArXiv, 2020, abs/2012.14768.
[55]	KIELA D, GRAVE E, JOULIN A, et al. Efficient Large-Scale Multi-Modal Classification[C]// proceedings of the AAAI Conference on Artificial Intelligence, F, 2018.
[56]	WU C, ZHANG X C, YANG Z J, et al. Learning to SMILES: BAN-based strategies to improve latent representation learning from molecules[J]. Briefings in Bioinformatics, 2021.
[57]	SCHAUPERL M, DENNY R A. AI-Based Protein Structure Prediction in Drug Discovery: Impacts and Challenges[J]. Journal of Chemical Information and Modeling, 2022.
[58]	ZENG X, TU X, LIU Y, et al. Toward better drug discovery with knowledge graph[J]. Current Opinion in Structural Biology, 2021, 72: 114-126.
[59]	SAXENA S, SANGANI R, PRASAD S, et al. Large-Scale Knowledge Synthesis and Complex Information Retrieval from Biomedical Documents[J]. 2022 IEEE International Conference on Big Data (Big Data), 2022: 2364-2369.
[60]	EBRAHIMI S, ARIK S Ö, DONG Y, et al. LANISTR: Multimodal Learning from Structured and Unstructured Data[J]. ArXiv, 2023, abs/2305.16556.
[61]	PENG L, LIAO B, ZHU W, et al. Predicting Drug-Target Interactions With Multi-Information Fusion[J]. IEEE Journal of Biomedical and Health Informatics, 2017, 21: 561-572.
[62]	DENG Y, XU X, QIU Y, et al. A multimodal deep learning framework for predicting drug-drug interaction events[J]. Bioinformatics, 2020.
[63]	WANG B, XIE Z R, CHEN J, et al. Integrating Structural Information to Study the Dynamics of Protein-Protein Interactions in Cells[J]. Structure, 2018, 26 10: 1414-1424.
[64]	DAI Y, WANG G, DAI J, et al. A multimodal deep architecture for traditional Chinese medicine diagnosis[J]. Concurrency and Computation: Practice and Experience, 2020, 32.
[65]	GAW N, YOUSEFI S, GAHROOEI M R. Multimodal data fusion for systems improvement: A review[J]. IISE Transactions, 2021, 54: 1098-1116.
[66]	GALLO I, CALEFATI A, NAWAZ S. Multimodal Classification Fusion in Real-World Scenarios[C]. 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017, 5: 36-41.
[67]	BIAN J, LU H, DONG G, et al. Hierarchical multimodal self-attention-based graph neural network for DTI prediction[J]. Brief Bioinform, 2024, 25(4).
[68]	XIA X, ZHU C, ZHONG F, et al. MDTips: a multimodal-data-based drug-target interaction prediction system fusing knowledge, gene expression profile, and structural data[J]. Bioinformatics, 2023, 39(7).
[69]	YANG X, NIU Z, LIU Y, et al. Modality-DTA: Multimodality Fusion Strategy for Drug-Target Affinity Prediction[J]. IEEE/ACM Trans Comput Biol Bioinform, 2023, 20(2): 1200-10.
[70]	ZHONG K Y, WEN M L, MENG F F, et al. MMDTA: A Multimodal Deep Model for Drug-Target Affinity with a Hybrid Fusion Strategy[J]. Journal of chemical information and modeling, 2024, 64(7): 2878-2888.
[71]	DENG Z, XU J, FENG Y, et al. MAVGAE: a multimodal framework for predicting asymmetric drug-drug interactions based on variational graph autoencoder[J]. Comput Methods Biomech Biomed Engin, 2024: 1-13.
[72]	CHEN S, SEMENOV I, ZHANG F, et al. An effective framework for predicting drug-drug interactions based on molecular substructures and knowledge graph neural network[J]. Computers in Biology and Medicine, 2024, 169: 107900.
[73]	JIN Q, XIE J, HUANG D, et al. MSFF-MA-DDI: Multi-Source Feature Fusion with Multiple Attention blocks for predicting Drug-Drug Interaction events[J]. Computational Biology and Chemistry, 2024, 108: 108001.
[74]	DUTTA P, SAHA S. Amalgamation of protein sequence, structure and textual information for improving protein-protein interaction identification[C]// proceedings of the Annual Meeting of the Association for Computational Linguistics, F, 2020.
[75]	JHA K, SAHA S, KHUSHI M. Protein-Protein Interactions Prediction Based on Bi-directional Gated Recurrent Unit and Multimodal Representation[C]// proceedings of the International Conference on Neural Information Processing, F, 2020.
[76]	LEI H, WEN Y, YOU Z, et al. Protein-Protein Interactions Prediction via Multimodal Deep Polynomial Network and Regularized Extreme Learning Machine[J]. IEEE Journal of Biomedical and Health Informatics, 2019, 23: 1290-1303.