Interpretable AI-driven multidimensional chemical fingerprints for geographical authentication of Euryales Semen

Abstract Euryales Semen (ES, Euryale ferox Salisb.) is a valuable aquatic food in Asia. Its quality and price depend on its geographical origins. To ensure the authenticity of ES, a tracing strategy using stable isotopes, elements, and starch composition with interpretable algorithms was successfull...

Full description

Saved in:
Bibliographic Details
Main Authors: Daixin Yu, Cheng Qu, Jing Nie, Pei Wen, Yuyang Zhao, Caiyan Dai, Hui Yan, Yuwei Yuan, Qinan Wu
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:npj Science of Food
Online Access:https://doi.org/10.1038/s41538-025-00510-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849235498610982912
author Daixin Yu
Cheng Qu
Jing Nie
Pei Wen
Yuyang Zhao
Caiyan Dai
Hui Yan
Yuwei Yuan
Qinan Wu
author_facet Daixin Yu
Cheng Qu
Jing Nie
Pei Wen
Yuyang Zhao
Caiyan Dai
Hui Yan
Yuwei Yuan
Qinan Wu
author_sort Daixin Yu
collection DOAJ
description Abstract Euryales Semen (ES, Euryale ferox Salisb.) is a valuable aquatic food in Asia. Its quality and price depend on its geographical origins. To ensure the authenticity of ES, a tracing strategy using stable isotopes, elements, and starch composition with interpretable algorithms was successfully developed. Results indicated that ES from different regions exhibited different chemical fingerprinting profiles. Tree-based intelligent algorithms were introduced for classification, and light gradient boosting machine (LightGBM) achieved the highest accuracy of 97.67%. The SHapley Additive exPlanation (SHAP) interpreted the LightGBM output for feature impact. Notably, the top 10 significant variables, encompassing Na, V, Ba, Sb, Cu, Ti, Mn, %N, amylose, and ratio of amylose to amylopectin (SHAP value >1.0), were selected as the key factors. Moreover, environmental factors were found to be significantly related to these key variables (p < 0.05). Overall, this study offers an effective strategy for the geographical origin traceability of ES or other aquatic crops.
format Article
id doaj-art-e99a3fbfad23477c881ca8a452da8193
institution Kabale University
issn 2396-8370
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series npj Science of Food
spelling doaj-art-e99a3fbfad23477c881ca8a452da81932025-08-20T04:02:45ZengNature Portfolionpj Science of Food2396-83702025-07-019111310.1038/s41538-025-00510-yInterpretable AI-driven multidimensional chemical fingerprints for geographical authentication of Euryales SemenDaixin Yu0Cheng Qu1Jing Nie2Pei Wen3Yuyang Zhao4Caiyan Dai5Hui Yan6Yuwei Yuan7Qinan Wu8Jiangsu Collaborative Innovation Center of Chinese Medicinal Resources Industrialization, Nanjing University of Chinese MedicineJiangsu Collaborative Innovation Center of Chinese Medicinal Resources Industrialization, Nanjing University of Chinese MedicineInstitute of Agro-product Safety and Nutrition, Zhejiang Academy of Agricultural Sciences; Key Laboratory of Information Traceability for Agricultural Products, Ministry of Agriculture and Rural Affairs of ChinaJiangsu Collaborative Innovation Center of Chinese Medicinal Resources Industrialization, Nanjing University of Chinese MedicineState Key Laboratory for Quality Ensurance and Sustainable Use of Dao-di Herbs, National Resource Center for Chinese Materia Medica, China Academy of Chinese Medical SciencesSchool of Artificial Intelligence and Information Technology, Jiangsu Province Engineering Research Center of TCM Intelligence Health Service, Nanjing University of Chinese MedicineJiangsu Collaborative Innovation Center of Chinese Medicinal Resources Industrialization, Nanjing University of Chinese MedicineInstitute of Agro-product Safety and Nutrition, Zhejiang Academy of Agricultural Sciences; Key Laboratory of Information Traceability for Agricultural Products, Ministry of Agriculture and Rural Affairs of ChinaJiangsu Collaborative Innovation Center of Chinese Medicinal Resources Industrialization, Nanjing University of Chinese MedicineAbstract Euryales Semen (ES, Euryale ferox Salisb.) is a valuable aquatic food in Asia. Its quality and price depend on its geographical origins. To ensure the authenticity of ES, a tracing strategy using stable isotopes, elements, and starch composition with interpretable algorithms was successfully developed. Results indicated that ES from different regions exhibited different chemical fingerprinting profiles. Tree-based intelligent algorithms were introduced for classification, and light gradient boosting machine (LightGBM) achieved the highest accuracy of 97.67%. The SHapley Additive exPlanation (SHAP) interpreted the LightGBM output for feature impact. Notably, the top 10 significant variables, encompassing Na, V, Ba, Sb, Cu, Ti, Mn, %N, amylose, and ratio of amylose to amylopectin (SHAP value >1.0), were selected as the key factors. Moreover, environmental factors were found to be significantly related to these key variables (p < 0.05). Overall, this study offers an effective strategy for the geographical origin traceability of ES or other aquatic crops.https://doi.org/10.1038/s41538-025-00510-y
spellingShingle Daixin Yu
Cheng Qu
Jing Nie
Pei Wen
Yuyang Zhao
Caiyan Dai
Hui Yan
Yuwei Yuan
Qinan Wu
Interpretable AI-driven multidimensional chemical fingerprints for geographical authentication of Euryales Semen
npj Science of Food
title Interpretable AI-driven multidimensional chemical fingerprints for geographical authentication of Euryales Semen
title_full Interpretable AI-driven multidimensional chemical fingerprints for geographical authentication of Euryales Semen
title_fullStr Interpretable AI-driven multidimensional chemical fingerprints for geographical authentication of Euryales Semen
title_full_unstemmed Interpretable AI-driven multidimensional chemical fingerprints for geographical authentication of Euryales Semen
title_short Interpretable AI-driven multidimensional chemical fingerprints for geographical authentication of Euryales Semen
title_sort interpretable ai driven multidimensional chemical fingerprints for geographical authentication of euryales semen
url https://doi.org/10.1038/s41538-025-00510-y
work_keys_str_mv AT daixinyu interpretableaidrivenmultidimensionalchemicalfingerprintsforgeographicalauthenticationofeuryalessemen
AT chengqu interpretableaidrivenmultidimensionalchemicalfingerprintsforgeographicalauthenticationofeuryalessemen
AT jingnie interpretableaidrivenmultidimensionalchemicalfingerprintsforgeographicalauthenticationofeuryalessemen
AT peiwen interpretableaidrivenmultidimensionalchemicalfingerprintsforgeographicalauthenticationofeuryalessemen
AT yuyangzhao interpretableaidrivenmultidimensionalchemicalfingerprintsforgeographicalauthenticationofeuryalessemen
AT caiyandai interpretableaidrivenmultidimensionalchemicalfingerprintsforgeographicalauthenticationofeuryalessemen
AT huiyan interpretableaidrivenmultidimensionalchemicalfingerprintsforgeographicalauthenticationofeuryalessemen
AT yuweiyuan interpretableaidrivenmultidimensionalchemicalfingerprintsforgeographicalauthenticationofeuryalessemen
AT qinanwu interpretableaidrivenmultidimensionalchemicalfingerprintsforgeographicalauthenticationofeuryalessemen