Rapid Identification of Trace Pharmacodynamic Substances in Traditional Chinese Medicine via SERS and Deep Learning
Biosensors · 2026
DOI: 10.3390/bios16030139 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biosensors, 2026. Verfasst von Huixuan Yang und 9 weiteren Autor:innen. Beteiligte Einrichtung: Hebei International Research Center for Medical-Engineering, Chengde Medical University, Chengde 067000, China. Hauptthemen laut MEDLINE: Deep Learning, Medicine, Chinese Traditional, Spectrum Analysis, Raman, Drugs, Chinese Herbal. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hebei Natural Science Foundation, Open Research Project of the Key Laboratory of Traditional Chinese Medicine Research and Development in Hebei Province, Hebei Province College Students' Innovation and Entrepreneurship Training Program.
Abstract (Originalsprache)
In the modernization of traditional Chinese medicine (TCM), trace detection of pharmacodynamic substances faces a critical challenge: insufficient sensitivity, which significantly hinders accurate quality assessment and standardization. Conventional techniques often fail to measure trace components in complex sample matrices. Therefore, the development of a rapid, effective, sensitive, and reliable analytical method, along with a corresponding quality evaluation system, is of great importance. This study used moth wing (MW) scales as a template to fabricate an Ag/MW SERS substrate via magnetron sputtering. The optimal Ag30/MW SERS substrate (30 min sputtering) achieved an enhancement factor of 6.47 × 106 and good reproducibility (minimum RSD: 7.03%). Principal component analysis (PCA) was integrated with four deep learning algorithms (MLP, Transformer, ResNet, DNN) to detect three typical TCM pharmacodynamic substances in pure standard solutions: atractylon, cimifugin, and timosaponin A-III. The models enabled rapid identification, with the MLP model reaching 95.00% accuracy. This research provides a novel, highly accurate, and efficient detection method with potential for TCM pharmacodynamic substances, demonstrating feasibility for bioactive compound identification in model systems, and shows promising potential for future application in TCM composition analysis and quality control.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Hebei International Research Center for Medical-Engineering, Chengde Medical University, Chengde 067000, China.
- Hebei Key Laboratory of Study and Exploitation of Chinese Medicine, Chengde Medical University, Chengde 067000, China.
- School of Nursing, Chengde Medical University, Chengde 067000, China.
- State Key Laboratory of Metastable Materials Science and Technology, Key Laboratory for Microstructural Material Physics of Hebei Province, School of Science, Yanshan University, Qinhuangdao 066004, China.
Förderung
- Hebei Natural Science Foundation
- Open Research Project of the Key Laboratory of Traditional Chinese Medicine Research and Development in Hebei Province
- Hebei Province College Students' Innovation and Entrepreneurship Training Program
- Hebei Province College Students’ Innovation and Entrepreneurship Training Program
Zitieren
APA
Yang, H., Chen, M., Wang, J., Tong, X., Li, H., Chen, H., Yu, Z., Zhao, C., Wang, M., & Shi, G. (2026). Rapid Identification of Trace Pharmacodynamic Substances in Traditional Chinese Medicine via SERS and Deep Learning. Biosensors. https://doi.org/10.3390/bios16030139
Vancouver
Yang H, Chen M, Wang J, Tong X, Li H, Chen H, et al. Rapid Identification of Trace Pharmacodynamic Substances in Traditional Chinese Medicine via SERS and Deep Learning. Biosensors. 2026. doi:10.3390/bios16030139
BibTeX
@article{Yang2026,
author = {Yang, Huixuan and Chen, Mingyuan and Wang, Jiayi and Tong, Xufei and Li, Huiru and Chen, Hao and Yu, Zengshan and Zhao, Chunying and Wang, Mingli and Shi, Guochao},
title = {Rapid Identification of Trace Pharmacodynamic Substances in Traditional Chinese Medicine via SERS and Deep Learning},
journal = {Biosensors},
year = {2026},
doi = {10.3390/bios16030139}
}
EUVIMED