中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 上海药物研究所
  3. 中国科学院上海药物研究所
Machine learning and chemometric methods for high-throughput authentication of 53 Root and Rhizome Chinese Herbal using ATR-FTIR fingerprints

文献类型：期刊论文

作者Liu, Xiaoyu3,4; Liu, Xiaokang3; Wang, Jiawei3; Zang, Daidi3; Yang, Yang2; Chen, Qinhua2; Guo, De-an1,2,3,4
刊名JOURNAL OF CHROMATOGRAPHY B-ANALYTICAL TECHNOLOGIES IN THE BIOMEDICAL AND LIFE SCIENCES
出版日期2025-06-15
卷号1260页码:10
关键词Root and rhizome Chinese Herbal ATR-FTIR T-SNE Chemometric Fingerprint Machine learning
ISSN号1570-0232
DOI10.1016/j.jchromb.2025.124630
通讯作者Guo, De-an(daguo@simm.ac.cn)
英文摘要To address the identification challenges caused by morphological similarities in Root and Rhizome Chinese Herbal (RRCH), this study developed a discrimination system integrating Attenuated Total Reflectance Fourier Transform Infrared Spectroscopy (ATR-FTIR) with multimodal machine learning. 53 kinds of RRCH collected from China were analyzed using ATR-FTIR to acquire spectral fingerprints. An innovative analytical framework was established, combining chemometric Partial Least Squares Discriminant Analysis (PLS-DA) with optimized machine learning models: t-distributed Stochastic Neighbor Embedding (t-SNE), optimized decision trees, optimized discriminant analysis, naive Bayes, optimized SVM, optimized KNN, SVM kernels, and optimized ensemble learning. Multivariate analysis revealed distinct spatial distribution patterns of chemical characteristics among the 53 RRCH species. t-SNE projections demonstrated significant cluster separation in two-dimensional feature space, confirming strong correlations between spectral fingerprints and phytochemical compositions. The SVM model outperformed others, achieving 100 % classification accuracy on both training and validation sets, with a markedly shorter identification time compared to PLS-DA. This ATR-FTIR-machine learning hybrid system enables high-throughput authentication of RRCH and establishes a scalable technical framework for herbal quality standardization. The methodology provides critical insights into chemical marker discovery through vibrational spectrum-feature relationship mapping, advancing intelligent discrimination of botanically similar medicinal materials.
WOS关键词SPECTROSCOPY ; QUALITY ; L. ; SAFFRON
资助项目Sanming Project of Medicine in Shenzhen[SZZYSM202106004] ; Qi-Huang Chief Scientist Program of National Administration of Traditional Chinese Medicine (2020)
WOS研究方向Biochemistry & Molecular Biology ; Chemistry
语种英语
WOS记录号WOS:001487564900001
出版者ELSEVIER
源URL[http://119.78.100.183/handle/2S10ELR8/317914]  
专题中国科学院上海药物研究所
通讯作者Guo, De-an
作者单位1.Chinese Acad Sci, Shanghai Inst Mat Med, Natl Engn Res Ctr TCM Standardizat Technol, Shanghai Res Ctr Modernizat Tradit Chinese Med, Shanghai 201203, Peoples R China
2.Shenzhen Baoan Authent TCM Therapy Hosp, Shenzhen 518101, Peoples R China
3.Chinese Acad Sci, Zhongshan Inst Drug Discovery, Shanghai Inst Mat Med, Zhongshan 582400, Peoples R China
4.Nanjing Univ Chinese Med, Sch Chinese Mat Med, Nanjing 210023, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Xiaoyu,Liu, Xiaokang,Wang, Jiawei,et al. Machine learning and chemometric methods for high-throughput authentication of 53 Root and Rhizome Chinese Herbal using ATR-FTIR fingerprints[J]. JOURNAL OF CHROMATOGRAPHY B-ANALYTICAL TECHNOLOGIES IN THE BIOMEDICAL AND LIFE SCIENCES,2025,1260:10.
APA Liu, Xiaoyu.,Liu, Xiaokang.,Wang, Jiawei.,Zang, Daidi.,Yang, Yang.,...&Guo, De-an.(2025).Machine learning and chemometric methods for high-throughput authentication of 53 Root and Rhizome Chinese Herbal using ATR-FTIR fingerprints.JOURNAL OF CHROMATOGRAPHY B-ANALYTICAL TECHNOLOGIES IN THE BIOMEDICAL AND LIFE SCIENCES,1260,10.
MLA Liu, Xiaoyu,et al."Machine learning and chemometric methods for high-throughput authentication of 53 Root and Rhizome Chinese Herbal using ATR-FTIR fingerprints".JOURNAL OF CHROMATOGRAPHY B-ANALYTICAL TECHNOLOGIES IN THE BIOMEDICAL AND LIFE SCIENCES 1260(2025):10.

入库方式： OAI收割

来源：上海药物研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。