Quality assessment of traditional Chinese medicine based on data fusion combined with machine learning: A review

Chinmedomics: a potent tool for the evaluation of traditional Chinese medicine efficacy and identification of its active components

As an important part of medical science, Traditional Chinese Medicine (TCM) attracts much public attention due to its multi-target and multi-pathway characteristics in treating diseases. However, the limitations of traditional research methods pose a dilemma for the evaluation of clinical efficacy, the discovery of active ingredients and the elucidation of the mechanism of action. Therefore, innovative approaches that are in line with the characteristics of TCM theory and clinical practice are urgently needed. Chinmendomics, a newly emerging strategy for evaluating the efficacy of TCM, is proposed. This strategy combines systems biology, serum pharmacochemistry of TCM and bioinformatics to evaluate the efficacy of TCM with a holistic view by accurately identifying syndrome biomarkers and monitoring their complex metabolic processes intervened by TCM, and finding the agents associated with the metabolic course of pharmacodynamic biomarkers by constructing a bioinformatics-based correlation network model to further reveal the interaction between agents and pharmacodynamic targets. In this article, we review the recent progress of Chinmedomics to promote its application in the modernisation and internationalisation of TCM.

Identification of Active Components for Sports Supplements: Machine Learning-Driven Classification and Cell-Based Validation

The identification of active components is critical for the development of sports supplements. However, high-throughput screening of active components remains a challenge. This study sought to construct prediction models to screen active components from herbal medicines via machine learning and validate the screening by using cell-based assays. The six constructed models had an accuracy of >0.88. Twelve randomly selected active components from the screening were tested for their active potency on C2C12 cells, and 11 components induced a significant increase in myotube diameters and protein synthesis. The effect and mechanism of luteolin among the 11 active components as potential sports supplements were then investigated by using immunofluorescence staining and high-content imaging analysis. It showed that luteolin increased the skeletal muscle performance via the activation of PGC-1α and MAPK signaling pathways. Thus, high-throughput prediction models can be effectively used to screen active components as sports supplements.

Application of Data Fusion in Traditional Chinese Medicine: A Review

Traditional Chinese medicine is characterized by numerous chemical constituents, complex components, and unpredictable interactions among constituents. Therefore, a single analytical technique is usually unable to obtain comprehensive chemical information. Data fusion is an information processing technology that can improve the accuracy of test results by fusing data from multiple devices, which has a broad application prospect by utilizing chemometrics methods, adopting low-level, mid-level, and high-level data fusion techniques, and establishing final classification or prediction models. This paper summarizes the current status of the application of data fusion strategies based on spectroscopy, mass spectrometry, chromatography, and sensor technologies in traditional Chinese medicine (TCM) in light of the latest research progress of data fusion technology at home and abroad. It also gives an outlook on the development of data fusion technology in TCM analysis to provide references for the research and development of TCM.

Spectrum-Effect Relationship in Chinese Herbal Medicine: Current Status and Future Perspectives

The quality of Chinese herbal medicine (CHM) directly impacts clinical efficacy and safety. Fingerprint technology is an internationally recognized method for evaluating the quality of CHM. However, the existing quality evaluation models based on fingerprint technology have blocked the ability to assess the internal quality of CHM and cannot comprehensively reflect the correlation between pharmacodynamic information and active constituents. Through mathematical methods, a connection between the "Spectrum" (fingerprint) and the "Effect" (pharmacodynamic data) was established to conduct a spectrum-effect relationship (SER) of CHM to unravel the active component information associated with the pharmacodynamic activity. Consequently, SER can efficiently address the limitations of the segmentation of chemical components and pharmacodynamic effect in CHM and further improve the quality evaluation of CHM. This review focuses on the recent research progress of SER in the field of CHM, including the establishment of fingerprint, the selection of data analysis methods, and their recent applications in the field of CHM. Various advanced fingerprint techniques are introduced, followed by the data analysis methods used in recent years are summarized. Finally, the applications of SER based on different research subjects are described in detail. In addition, the advantages of combining SER with other data are discussed through practical applications, and the research on SER is summarized and prospected. This review proves the validity and development potential of the SER and provides a reference for the development and application of quality evaluation methods for CHM.

Identification of Turtle-Shell Growth Year Using Hyperspectral Imaging Combined with an Enhanced Spatial-Spectral Attention 3DCNN and a Transformer

Turtle shell (Chinemys reecesii) is a prized traditional Chinese dietary therapy, and the growth year of turtle shell has a significant impact on its quality attributes. In this study, a hyperspectral imaging (HSI) technique combined with a proposed deep learning (DL) network algorithm was investigated for the objective determination of the growth year of turtle shells. The acquisition of hyperspectral images was carried out in the near-infrared range (948.72-2512.97 nm) from samples spanning five different growth years. To fully exploit the spatial and spectral information while reducing redundancy in hyperspectral data simultaneously, three modules were developed. First, the spectral-spatial attention (SSA) module was developed to better protect the spectral correlation among spectral bands and capture fine-grained spatial information of hyperspectral images. Second, the 3D convolutional neural network (CNN), more suitable for the extracted 3D feature map, was employed to facilitate the joint spatial-spectral feature representation. Thirdly, to overcome the constraints of convolution kernels as well as better capture long-range correlation between spectral bands, the transformer encoder (TE) module was further designed. These modules were harmoniously orchestrated, driven by the need to effectively leverage both spatial and spectral information within hyperspectral data. They collectively enhance the model's capacity to extract joint spatial and spectral features to discern growth years accurately. Experimental studies demonstrated that the proposed model (named SSA-3DTE) achieved superior classification accuracy, with 98.94% on average for five-category classification, outperforming traditional machine learning methods using only spectral information and representative deep learning methods. Also, ablation experiments confirmed the effectiveness of each module to improve performance. The encouraging results of this study revealed the potentiality of HSI combined with the DL algorithm as an efficient and non-destructive method for the quality control of turtle shells.