Characterization and feature selection of volatile metabolites in Yangxian pigmented rice varieties through GC-MS and machine learning algorithms
IntroductionPigmented rice is fascinated by consumers for its abundant phytochemicals and unique aroma.MethodsIn this study, GC–MS-based metabolomics of Yangxian colored rice varieties were performed to characterize their volatile metabolites through multivariate statistics and machine learning algo...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-05-01
|
| Series: | Frontiers in Nutrition |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnut.2025.1598875/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849736494505263104 |
|---|---|
| author | Kaiqi Cheng Ruonan Dong Fei Pan Wen Su Lingjie Xi Meng Zhang Jingzhang Geng Ruichang Gao Ruichang Gao Wengang Jin A. M. Abd El-Aty A. M. Abd El-Aty |
| author_facet | Kaiqi Cheng Ruonan Dong Fei Pan Wen Su Lingjie Xi Meng Zhang Jingzhang Geng Ruichang Gao Ruichang Gao Wengang Jin A. M. Abd El-Aty A. M. Abd El-Aty |
| author_sort | Kaiqi Cheng |
| collection | DOAJ |
| description | IntroductionPigmented rice is fascinated by consumers for its abundant phytochemicals and unique aroma.MethodsIn this study, GC–MS-based metabolomics of Yangxian colored rice varieties were performed to characterize their volatile metabolites through multivariate statistics and machine learning algorithms.ResultsResults showed that a total of 357 volatile metabolites were detected and segmented into 9 groups, including 96 organooxygen compounds (26.89%), 52 carboxylic acids and derivatives (14.57%), 42 fatty acyls (11.76%), 16 benzene and substituted derivatives (4.48%), and 11 hydroxy acids and derivatives (3.08%). Multivariate statistics screened 127 differentially abundant metabolites via PLS-DA. Principal component analysis revealed that the percentages of PC1 and PC2 were 52.48% and 27.09%, respectively. Based on differential metabolites with great multicollinearity above 0.8 and the chi-square test (20% feature numbers), only 7 metabolites were found to represent the overall metabolites among the several colored rice varieties. Four machine learning models were further used for the classification of various colored rice varieties, and random forest model was the optimum for predicting classification, with an accuracy of 0.97. Moreover, Shapley additive explanations analysis revealed that the 7 metabolites can be used as potential markers for representing the metabolomic profiles.ConclusionsThese results implied that GC–MS-based metabolomics combined with random forest might be effective for extracting key features among different pigmented rice varieties. |
| format | Article |
| id | doaj-art-b3da5fce41d54705a850357bdeefd15e |
| institution | DOAJ |
| issn | 2296-861X |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Nutrition |
| spelling | doaj-art-b3da5fce41d54705a850357bdeefd15e2025-08-20T03:07:16ZengFrontiers Media S.A.Frontiers in Nutrition2296-861X2025-05-011210.3389/fnut.2025.15988751598875Characterization and feature selection of volatile metabolites in Yangxian pigmented rice varieties through GC-MS and machine learning algorithmsKaiqi Cheng0Ruonan Dong1Fei Pan2Wen Su3Lingjie Xi4Meng Zhang5Jingzhang Geng6Ruichang Gao7Ruichang Gao8Wengang Jin9A. M. Abd El-Aty10A. M. Abd El-Aty11Qinba State Key Laboratory of Biological Resources and Ecological Environment, QinLing-Bashan Moun-tains Bioresources Comprehensive Development 2011 C. I. C, Shaanxi Province Key Laboratory of Bio-Resources, College of Bioscience and Bioengineering Shaanxi University of Technology, Hanzhong, ChinaQinba State Key Laboratory of Biological Resources and Ecological Environment, QinLing-Bashan Moun-tains Bioresources Comprehensive Development 2011 C. I. C, Shaanxi Province Key Laboratory of Bio-Resources, College of Bioscience and Bioengineering Shaanxi University of Technology, Hanzhong, ChinaInstitute of Apicultural Research, Chinese Academy of Agricultural Sciences, Beijing, ChinaQinba State Key Laboratory of Biological Resources and Ecological Environment, QinLing-Bashan Moun-tains Bioresources Comprehensive Development 2011 C. I. C, Shaanxi Province Key Laboratory of Bio-Resources, College of Bioscience and Bioengineering Shaanxi University of Technology, Hanzhong, ChinaQinba State Key Laboratory of Biological Resources and Ecological Environment, QinLing-Bashan Moun-tains Bioresources Comprehensive Development 2011 C. I. C, Shaanxi Province Key Laboratory of Bio-Resources, College of Bioscience and Bioengineering Shaanxi University of Technology, Hanzhong, ChinaQinba State Key Laboratory of Biological Resources and Ecological Environment, QinLing-Bashan Moun-tains Bioresources Comprehensive Development 2011 C. I. C, Shaanxi Province Key Laboratory of Bio-Resources, College of Bioscience and Bioengineering Shaanxi University of Technology, Hanzhong, ChinaQinba State Key Laboratory of Biological Resources and Ecological Environment, QinLing-Bashan Moun-tains Bioresources Comprehensive Development 2011 C. I. C, Shaanxi Province Key Laboratory of Bio-Resources, College of Bioscience and Bioengineering Shaanxi University of Technology, Hanzhong, ChinaQinba State Key Laboratory of Biological Resources and Ecological Environment, QinLing-Bashan Moun-tains Bioresources Comprehensive Development 2011 C. I. C, Shaanxi Province Key Laboratory of Bio-Resources, College of Bioscience and Bioengineering Shaanxi University of Technology, Hanzhong, ChinaCollege of Food and Biotechnology, Jiangsu University, Zhenjiang, ChinaQinba State Key Laboratory of Biological Resources and Ecological Environment, QinLing-Bashan Moun-tains Bioresources Comprehensive Development 2011 C. I. C, Shaanxi Province Key Laboratory of Bio-Resources, College of Bioscience and Bioengineering Shaanxi University of Technology, Hanzhong, ChinaDepartment of Pharmacology, Faculty of Veterinary Medicine, Cairo University, Giza, EgyptDepartment of Medical Pharmacology, Medical Faculty, Ataturk University, Erzurum, TürkiyeIntroductionPigmented rice is fascinated by consumers for its abundant phytochemicals and unique aroma.MethodsIn this study, GC–MS-based metabolomics of Yangxian colored rice varieties were performed to characterize their volatile metabolites through multivariate statistics and machine learning algorithms.ResultsResults showed that a total of 357 volatile metabolites were detected and segmented into 9 groups, including 96 organooxygen compounds (26.89%), 52 carboxylic acids and derivatives (14.57%), 42 fatty acyls (11.76%), 16 benzene and substituted derivatives (4.48%), and 11 hydroxy acids and derivatives (3.08%). Multivariate statistics screened 127 differentially abundant metabolites via PLS-DA. Principal component analysis revealed that the percentages of PC1 and PC2 were 52.48% and 27.09%, respectively. Based on differential metabolites with great multicollinearity above 0.8 and the chi-square test (20% feature numbers), only 7 metabolites were found to represent the overall metabolites among the several colored rice varieties. Four machine learning models were further used for the classification of various colored rice varieties, and random forest model was the optimum for predicting classification, with an accuracy of 0.97. Moreover, Shapley additive explanations analysis revealed that the 7 metabolites can be used as potential markers for representing the metabolomic profiles.ConclusionsThese results implied that GC–MS-based metabolomics combined with random forest might be effective for extracting key features among different pigmented rice varieties.https://www.frontiersin.org/articles/10.3389/fnut.2025.1598875/fullpigmented ricemetabolitesmultivariate statisticsmachine learningvolatiles |
| spellingShingle | Kaiqi Cheng Ruonan Dong Fei Pan Wen Su Lingjie Xi Meng Zhang Jingzhang Geng Ruichang Gao Ruichang Gao Wengang Jin A. M. Abd El-Aty A. M. Abd El-Aty Characterization and feature selection of volatile metabolites in Yangxian pigmented rice varieties through GC-MS and machine learning algorithms Frontiers in Nutrition pigmented rice metabolites multivariate statistics machine learning volatiles |
| title | Characterization and feature selection of volatile metabolites in Yangxian pigmented rice varieties through GC-MS and machine learning algorithms |
| title_full | Characterization and feature selection of volatile metabolites in Yangxian pigmented rice varieties through GC-MS and machine learning algorithms |
| title_fullStr | Characterization and feature selection of volatile metabolites in Yangxian pigmented rice varieties through GC-MS and machine learning algorithms |
| title_full_unstemmed | Characterization and feature selection of volatile metabolites in Yangxian pigmented rice varieties through GC-MS and machine learning algorithms |
| title_short | Characterization and feature selection of volatile metabolites in Yangxian pigmented rice varieties through GC-MS and machine learning algorithms |
| title_sort | characterization and feature selection of volatile metabolites in yangxian pigmented rice varieties through gc ms and machine learning algorithms |
| topic | pigmented rice metabolites multivariate statistics machine learning volatiles |
| url | https://www.frontiersin.org/articles/10.3389/fnut.2025.1598875/full |
| work_keys_str_mv | AT kaiqicheng characterizationandfeatureselectionofvolatilemetabolitesinyangxianpigmentedricevarietiesthroughgcmsandmachinelearningalgorithms AT ruonandong characterizationandfeatureselectionofvolatilemetabolitesinyangxianpigmentedricevarietiesthroughgcmsandmachinelearningalgorithms AT feipan characterizationandfeatureselectionofvolatilemetabolitesinyangxianpigmentedricevarietiesthroughgcmsandmachinelearningalgorithms AT wensu characterizationandfeatureselectionofvolatilemetabolitesinyangxianpigmentedricevarietiesthroughgcmsandmachinelearningalgorithms AT lingjiexi characterizationandfeatureselectionofvolatilemetabolitesinyangxianpigmentedricevarietiesthroughgcmsandmachinelearningalgorithms AT mengzhang characterizationandfeatureselectionofvolatilemetabolitesinyangxianpigmentedricevarietiesthroughgcmsandmachinelearningalgorithms AT jingzhanggeng characterizationandfeatureselectionofvolatilemetabolitesinyangxianpigmentedricevarietiesthroughgcmsandmachinelearningalgorithms AT ruichanggao characterizationandfeatureselectionofvolatilemetabolitesinyangxianpigmentedricevarietiesthroughgcmsandmachinelearningalgorithms AT ruichanggao characterizationandfeatureselectionofvolatilemetabolitesinyangxianpigmentedricevarietiesthroughgcmsandmachinelearningalgorithms AT wengangjin characterizationandfeatureselectionofvolatilemetabolitesinyangxianpigmentedricevarietiesthroughgcmsandmachinelearningalgorithms AT amabdelaty characterizationandfeatureselectionofvolatilemetabolitesinyangxianpigmentedricevarietiesthroughgcmsandmachinelearningalgorithms AT amabdelaty characterizationandfeatureselectionofvolatilemetabolitesinyangxianpigmentedricevarietiesthroughgcmsandmachinelearningalgorithms |