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
Integration of deep neural network modeling and LC-MS-based pseudo-targeted metabolomics to discriminate easily confused ginseng species

文献类型：期刊论文

作者Jiang, Meiting3,4; Sha, Yuyang2; Zou, Yadan3,4; Xu, Xiaoyan3,4; Ding, Mengxiang3,4; Lian, Xu2; Wang, Hongda3,4; Wang, Qilong3,4; Li, Kefeng2; Guo, De-an1,3,4
刊名JOURNAL OF PHARMACEUTICAL ANALYSIS
出版日期2025
卷号15期号:1页码:12
关键词Liquid chromatography-mass spectrometry Pseudo-targeted metabolomics Deep neural network Species differentiation Ginseng
ISSN号2095-1779
DOI10.1016/j.jpha.2024.101116
通讯作者Li, Kefeng(kefengl@mpu.edu.mo) ; Guo, De-an(daguo@simm.ac.cn) ; Yang, Wenzhi(wzyang0504@tjutcm.edu.cn)
英文摘要Metabolomics covers a wide range of applications in life sciences, biomedicine, and phytology. Data acquisition (to achieve high coverage and efficiency) and analysis (to pursue good classification) are two key segments involved in metabolomics workflows. Various chemometric approaches utilizing either pattern recognition or machine learning have been employed to separate different groups. However, insufficient feature extraction, inappropriate feature selection, overfitting, or underfitting lead to an insufficient capacity to discriminate plants that are often easily confused. Using two ginseng varieties, namely Panax japonicus (PJ) and Panax japonicus var. major (PJvm), containing the similar ginsenosides, we integrated pseudo-targeted metabolomics and deep neural network (DNN) modeling to achieve accurate species differentiation. A pseudo-targeted metabolomics approach was optimized through data acquisition mode, ion pairs generation, comparison between multiple reaction monitoring (MRM) and scheduled MRM (sMRM), and chromatographic elution gradient. In total, 1980 ion pairs were monitored within 23 min, allowing for the most comprehensive ginseng metabolome analysis. The established DNN model demonstrated excellent classification performance (in terms of accuracy, precision, recall, F1 score, area under the curve, and receiver operating characteristic (ROC)) using the entire metabolome data and feature-selection dataset, exhibiting superior advantages over random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost), and multilayer perceptron (MLP). Moreover, DNNs were advantageous for automated feature learning, nonlinear modeling, adaptability, and generalization. This study confirmed practicality of the established strategy for efficient metabolomics data analysis and reliable classification performance even when using small-volume samples. This established approach holds promise for plant metabolomics and is not limited to ginseng. (c) 2024 The Author(s). Published by Elsevier B.V. on behalf of Xi'an Jiaotong University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
资助项目National Key R&D Program of China[2022YFC3501805] ; National Natural Science Foundation of China[82374030] ; Science and Tech-nology Program of Tianjin in China[23ZYJDSS00 030] ; Tianjin Outstanding Youth Fund, China[23JCJQJC00 030] ; China Postdoctoral Science Foundation-Tianjin Joint Support Program[2023T030TJ]
WOS研究方向Pharmacology & Pharmacy
语种英语
WOS记录号WOS:001409865400001
出版者ELSEVIER
源URL[http://119.78.100.183/handle/2S10ELR8/315953]  
专题中国科学院上海药物研究所
通讯作者Li, Kefeng; Guo, De-an; Yang, Wenzhi
作者单位1.Chinese Acad Sci, Shanghai Res Ctr Modernizat Tradit Chinese Med, Shanghai Inst Mat Med, Shanghai 201203, Peoples R China
2.Macao Polytech Univ, Fac Appl Sci, Ctr Artificial Intelligence Driven Drug Discovery, Macau 999078, Peoples R China
3.Haihe Lab Modern Chinese Med, Tianjin 301617, Peoples R China
4.Tianjin Univ Tradit Chinese Med, State Key Lab Chinese Med Modernizat, Tianjin 301617, Peoples R China
推荐引用方式
GB/T 7714		 Jiang, Meiting,Sha, Yuyang,Zou, Yadan,et al. Integration of deep neural network modeling and LC-MS-based pseudo-targeted metabolomics to discriminate easily confused ginseng species[J]. JOURNAL OF PHARMACEUTICAL ANALYSIS,2025,15(1):12.
APA Jiang, Meiting.,Sha, Yuyang.,Zou, Yadan.,Xu, Xiaoyan.,Ding, Mengxiang.,...&Yang, Wenzhi.(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(1),12.
MLA Jiang, Meiting,et al."Integration of deep neural network modeling and LC-MS-based pseudo-targeted metabolomics to discriminate easily confused ginseng species".JOURNAL OF PHARMACEUTICAL ANALYSIS 15.1(2025):12.

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。