Predicting the grades of Astragali radix using mass spectrometry-based metabolomics and machine learning
Astragali radix (AR, the dried root of Astragalus) is a popular herbal remedy in both China and the United States. The commercially available AR is commonly classified into premium graded (PG) and ungraded (UG) ones only according to the appearance. To uncover novel sensitive and specific markers fo...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-10-01
|
| Series: | Journal of Pharmaceutical Analysis |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2095177920310376 |
| _version_ | 1831588483806789632 |
|---|---|
| author | Xinyue Yu Jingxue Nai Huimin Guo Xuping Yang Xiaoying Deng Xia Yuan Yunfei Hua Yuan Tian Fengguo Xu Zunjian Zhang Yin Huang |
| author_facet | Xinyue Yu Jingxue Nai Huimin Guo Xuping Yang Xiaoying Deng Xia Yuan Yunfei Hua Yuan Tian Fengguo Xu Zunjian Zhang Yin Huang |
| author_sort | Xinyue Yu |
| collection | DOAJ |
| description | Astragali radix (AR, the dried root of Astragalus) is a popular herbal remedy in both China and the United States. The commercially available AR is commonly classified into premium graded (PG) and ungraded (UG) ones only according to the appearance. To uncover novel sensitive and specific markers for AR grading, we took the integrated mass spectrometry-based untargeted and targeted metabolomics approaches to characterize chemical features of PG and UG samples in a discovery set (n=16 batches). A series of five differential compounds were screened out by univariate statistical analysis, including arginine, calycosin, ononin, formononetin, and astragaloside Ⅳ, most of which were observed to be accumulated in PG samples except for astragaloside Ⅳ. Then, we performed machine learning on the quantification data of five compounds and constructed a logistic regression prediction model. Finally, the external validation in an independent validation set of AR (n=20 batches) verified that the five compounds, as well as the model, had strong capability to distinguish the two grades of AR, with the prediction accuracy > 90%. Our findings present a panel of meaningful candidate markers that would significantly catalyze the innovation in AR grading. |
| first_indexed | 2024-12-17T22:15:13Z |
| format | Article |
| id | doaj.art-8f69b33449844cf78fab602f5f51c081 |
| institution | Directory Open Access Journal |
| issn | 2095-1779 |
| language | English |
| last_indexed | 2024-12-17T22:15:13Z |
| publishDate | 2021-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Pharmaceutical Analysis |
| spelling | doaj.art-8f69b33449844cf78fab602f5f51c0812022-12-21T21:30:38ZengElsevierJournal of Pharmaceutical Analysis2095-17792021-10-01115611616Predicting the grades of Astragali radix using mass spectrometry-based metabolomics and machine learningXinyue Yu0Jingxue Nai1Huimin Guo2Xuping Yang3Xiaoying Deng4Xia Yuan5Yunfei Hua6Yuan Tian7Fengguo Xu8Zunjian Zhang9Yin Huang10Key Laboratory of Drug Quality Control and Pharmacovigilance, China Pharmaceutical University, Ministry of Education, Nanjing, 210009, China; Department of Pharmaceutical Analysis, School of Pharmacy, China Pharmaceutical University, Nanjing, 210009, ChinaKey Laboratory of Drug Quality Control and Pharmacovigilance, China Pharmaceutical University, Ministry of Education, Nanjing, 210009, ChinaCenter for Biological Technology, Anhui Agricultural University, Hefei, 230036, ChinaKey Laboratory of Drug Quality Control and Pharmacovigilance, China Pharmaceutical University, Ministry of Education, Nanjing, 210009, ChinaKey Laboratory of Drug Quality Control and Pharmacovigilance, China Pharmaceutical University, Ministry of Education, Nanjing, 210009, ChinaKey Laboratory of Drug Quality Control and Pharmacovigilance, China Pharmaceutical University, Ministry of Education, Nanjing, 210009, ChinaKey Laboratory of Drug Quality Control and Pharmacovigilance, China Pharmaceutical University, Ministry of Education, Nanjing, 210009, ChinaKey Laboratory of Drug Quality Control and Pharmacovigilance, China Pharmaceutical University, Ministry of Education, Nanjing, 210009, ChinaKey Laboratory of Drug Quality Control and Pharmacovigilance, China Pharmaceutical University, Ministry of Education, Nanjing, 210009, ChinaKey Laboratory of Drug Quality Control and Pharmacovigilance, China Pharmaceutical University, Ministry of Education, Nanjing, 210009, China; Corresponding author.Key Laboratory of Drug Quality Control and Pharmacovigilance, China Pharmaceutical University, Ministry of Education, Nanjing, 210009, China; Department of Pharmaceutical Analysis, School of Pharmacy, China Pharmaceutical University, Nanjing, 210009, China; Corresponding author. Key Laboratory of Drug Quality Control and Pharmacovigilance, China Pharmaceutical University, Ministry of Education, Nanjing, 210009, China.Astragali radix (AR, the dried root of Astragalus) is a popular herbal remedy in both China and the United States. The commercially available AR is commonly classified into premium graded (PG) and ungraded (UG) ones only according to the appearance. To uncover novel sensitive and specific markers for AR grading, we took the integrated mass spectrometry-based untargeted and targeted metabolomics approaches to characterize chemical features of PG and UG samples in a discovery set (n=16 batches). A series of five differential compounds were screened out by univariate statistical analysis, including arginine, calycosin, ononin, formononetin, and astragaloside Ⅳ, most of which were observed to be accumulated in PG samples except for astragaloside Ⅳ. Then, we performed machine learning on the quantification data of five compounds and constructed a logistic regression prediction model. Finally, the external validation in an independent validation set of AR (n=20 batches) verified that the five compounds, as well as the model, had strong capability to distinguish the two grades of AR, with the prediction accuracy > 90%. Our findings present a panel of meaningful candidate markers that would significantly catalyze the innovation in AR grading.http://www.sciencedirect.com/science/article/pii/S2095177920310376Astragali radixMetabolomicsMachine learningQuality markersPrediction model |
| spellingShingle | Xinyue Yu Jingxue Nai Huimin Guo Xuping Yang Xiaoying Deng Xia Yuan Yunfei Hua Yuan Tian Fengguo Xu Zunjian Zhang Yin Huang Predicting the grades of Astragali radix using mass spectrometry-based metabolomics and machine learning Journal of Pharmaceutical Analysis Astragali radix Metabolomics Machine learning Quality markers Prediction model |
| title | Predicting the grades of Astragali radix using mass spectrometry-based metabolomics and machine learning |
| title_full | Predicting the grades of Astragali radix using mass spectrometry-based metabolomics and machine learning |
| title_fullStr | Predicting the grades of Astragali radix using mass spectrometry-based metabolomics and machine learning |
| title_full_unstemmed | Predicting the grades of Astragali radix using mass spectrometry-based metabolomics and machine learning |
| title_short | Predicting the grades of Astragali radix using mass spectrometry-based metabolomics and machine learning |
| title_sort | predicting the grades of astragali radix using mass spectrometry based metabolomics and machine learning |
| topic | Astragali radix Metabolomics Machine learning Quality markers Prediction model |
| url | http://www.sciencedirect.com/science/article/pii/S2095177920310376 |
| work_keys_str_mv | AT xinyueyu predictingthegradesofastragaliradixusingmassspectrometrybasedmetabolomicsandmachinelearning AT jingxuenai predictingthegradesofastragaliradixusingmassspectrometrybasedmetabolomicsandmachinelearning AT huiminguo predictingthegradesofastragaliradixusingmassspectrometrybasedmetabolomicsandmachinelearning AT xupingyang predictingthegradesofastragaliradixusingmassspectrometrybasedmetabolomicsandmachinelearning AT xiaoyingdeng predictingthegradesofastragaliradixusingmassspectrometrybasedmetabolomicsandmachinelearning AT xiayuan predictingthegradesofastragaliradixusingmassspectrometrybasedmetabolomicsandmachinelearning AT yunfeihua predictingthegradesofastragaliradixusingmassspectrometrybasedmetabolomicsandmachinelearning AT yuantian predictingthegradesofastragaliradixusingmassspectrometrybasedmetabolomicsandmachinelearning AT fengguoxu predictingthegradesofastragaliradixusingmassspectrometrybasedmetabolomicsandmachinelearning AT zunjianzhang predictingthegradesofastragaliradixusingmassspectrometrybasedmetabolomicsandmachinelearning AT yinhuang predictingthegradesofastragaliradixusingmassspectrometrybasedmetabolomicsandmachinelearning |