泡菜中代谢物的季节性变化:利用基于代谢组学的机器学习进行栽培季节和口味鉴别

IF 2.4 3区 农林科学 Q1 Agricultural and Biological Sciences
WooChul Ju, Sung Jin Park, Min Jung Lee, Sung Hee Park, Sung Gi Min, Kang-Mo Ku
{"title":"泡菜中代谢物的季节性变化:利用基于代谢组学的机器学习进行栽培季节和口味鉴别","authors":"WooChul Ju, Sung Jin Park, Min Jung Lee, Sung Hee Park, Sung Gi Min, Kang-Mo Ku","doi":"10.1007/s13580-024-00624-4","DOIUrl":null,"url":null,"abstract":"<p>Kimchi cabbage, a staple in South Korean cuisine, exhibits taste variations depending on the season of cultivation, with significant implications for kimchi production quality. In this study, we conducted comprehensive metabolomic analyses of kimchi cabbage grown in diverse environments throughout the year. We identified 15 primary metabolites, 10 glucosinolates, and 12 hydrolysates, providing valuable insights into the metabolic composition of kimchi cabbage. Using this data, we developed predictive models for taste and quality differentiation in kimchi cabbage based on the season of cultivation. Three regression models, including Orthogonal Partial Least Squares regression (OPLS), Partial Least Squares (PLS) regression, and Random Forest regression, were employed to predict seasonal variation. The models exhibited high accuracy, with R<sup>2</sup> values ranging from 0.77 to 0.95, indicating their potential for distinguishing seasonal differences. Notably, hydroxyglucobrassicin, 5-oxoproline, and inositol consistently emerged as significant metabolites across all models. Additionally, we developed regression models for predicting sweetness and bitterness in kimchi cabbage. Metabolites such as malic acid, fructose, and glucose were positively correlated with sweetness, while neoglucobrassicin and glucobrassicin were negatively correlated. Conversely, metabolites like glucoerucin and glucobrassicin were positively correlated with bitterness, while malic acid and sucrose were negatively correlated. These findings provide a valuable foundation for understanding the metabolic basis of taste variation in kimchi cabbage and offer practical applications for improving kimchi production quality. By incorporating more varieties and multi-year data, future research aims to develop even more accurate predictive models for kimchi cabbage taste and quality, ultimately contributing to the consistency of kimchi production.</p><h3 data-test=\"abstract-sub-heading\">Graphical Abstract</h3>","PeriodicalId":13123,"journal":{"name":"Horticulture Environment and Biotechnology","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2024-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Seasonal variation of metabolites in Kimchi cabbage: utilizing metabolomics based machine learning for cultivation season and taste discrimination\",\"authors\":\"WooChul Ju, Sung Jin Park, Min Jung Lee, Sung Hee Park, Sung Gi Min, Kang-Mo Ku\",\"doi\":\"10.1007/s13580-024-00624-4\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Kimchi cabbage, a staple in South Korean cuisine, exhibits taste variations depending on the season of cultivation, with significant implications for kimchi production quality. In this study, we conducted comprehensive metabolomic analyses of kimchi cabbage grown in diverse environments throughout the year. We identified 15 primary metabolites, 10 glucosinolates, and 12 hydrolysates, providing valuable insights into the metabolic composition of kimchi cabbage. Using this data, we developed predictive models for taste and quality differentiation in kimchi cabbage based on the season of cultivation. Three regression models, including Orthogonal Partial Least Squares regression (OPLS), Partial Least Squares (PLS) regression, and Random Forest regression, were employed to predict seasonal variation. The models exhibited high accuracy, with R<sup>2</sup> values ranging from 0.77 to 0.95, indicating their potential for distinguishing seasonal differences. Notably, hydroxyglucobrassicin, 5-oxoproline, and inositol consistently emerged as significant metabolites across all models. Additionally, we developed regression models for predicting sweetness and bitterness in kimchi cabbage. Metabolites such as malic acid, fructose, and glucose were positively correlated with sweetness, while neoglucobrassicin and glucobrassicin were negatively correlated. Conversely, metabolites like glucoerucin and glucobrassicin were positively correlated with bitterness, while malic acid and sucrose were negatively correlated. These findings provide a valuable foundation for understanding the metabolic basis of taste variation in kimchi cabbage and offer practical applications for improving kimchi production quality. By incorporating more varieties and multi-year data, future research aims to develop even more accurate predictive models for kimchi cabbage taste and quality, ultimately contributing to the consistency of kimchi production.</p><h3 data-test=\\\"abstract-sub-heading\\\">Graphical Abstract</h3>\",\"PeriodicalId\":13123,\"journal\":{\"name\":\"Horticulture Environment and Biotechnology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2024-05-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Horticulture Environment and Biotechnology\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://doi.org/10.1007/s13580-024-00624-4\",\"RegionNum\":3,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"Agricultural and Biological Sciences\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Horticulture Environment and Biotechnology","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1007/s13580-024-00624-4","RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Agricultural and Biological Sciences","Score":null,"Total":0}
引用次数: 0

摘要

泡菜卷心菜是韩国的主食,其口味随种植季节的不同而变化,这对泡菜的生产质量有着重要影响。在这项研究中,我们对全年在不同环境中生长的泡菜白菜进行了全面的代谢组学分析。我们鉴定了 15 种初级代谢物、10 种葡萄糖苷酸盐和 12 种水解物,为了解泡菜卷心菜的代谢组成提供了宝贵的信息。利用这些数据,我们建立了基于栽培季节的泡菜口味和品质差异预测模型。我们采用了正交偏最小二乘回归(OPLS)、偏最小二乘回归(PLS)和随机森林回归等三种回归模型来预测季节变化。这些模型具有很高的准确性,R2 值在 0.77 到 0.95 之间,表明它们具有区分季节性差异的潜力。值得注意的是,在所有模型中,羟基葡萄糖苷、5-氧代脯氨酸和肌醇始终是重要的代谢物。此外,我们还建立了预测泡菜甜度和苦味的回归模型。苹果酸、果糖和葡萄糖等代谢物与甜味呈正相关,而新葡萄糖苷和葡萄糖苷呈负相关。相反,葡萄糖醛酸和葡萄糖苦味素等代谢物与苦味呈正相关,而苹果酸和蔗糖呈负相关。这些发现为了解泡菜口味变化的代谢基础奠定了宝贵的基础,并为提高泡菜生产质量提供了实际应用。通过纳入更多的品种和多年数据,未来的研究旨在开发更准确的泡菜卷心菜口味和质量预测模型,最终促进泡菜生产的一致性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Seasonal variation of metabolites in Kimchi cabbage: utilizing metabolomics based machine learning for cultivation season and taste discrimination

Seasonal variation of metabolites in Kimchi cabbage: utilizing metabolomics based machine learning for cultivation season and taste discrimination

Kimchi cabbage, a staple in South Korean cuisine, exhibits taste variations depending on the season of cultivation, with significant implications for kimchi production quality. In this study, we conducted comprehensive metabolomic analyses of kimchi cabbage grown in diverse environments throughout the year. We identified 15 primary metabolites, 10 glucosinolates, and 12 hydrolysates, providing valuable insights into the metabolic composition of kimchi cabbage. Using this data, we developed predictive models for taste and quality differentiation in kimchi cabbage based on the season of cultivation. Three regression models, including Orthogonal Partial Least Squares regression (OPLS), Partial Least Squares (PLS) regression, and Random Forest regression, were employed to predict seasonal variation. The models exhibited high accuracy, with R2 values ranging from 0.77 to 0.95, indicating their potential for distinguishing seasonal differences. Notably, hydroxyglucobrassicin, 5-oxoproline, and inositol consistently emerged as significant metabolites across all models. Additionally, we developed regression models for predicting sweetness and bitterness in kimchi cabbage. Metabolites such as malic acid, fructose, and glucose were positively correlated with sweetness, while neoglucobrassicin and glucobrassicin were negatively correlated. Conversely, metabolites like glucoerucin and glucobrassicin were positively correlated with bitterness, while malic acid and sucrose were negatively correlated. These findings provide a valuable foundation for understanding the metabolic basis of taste variation in kimchi cabbage and offer practical applications for improving kimchi production quality. By incorporating more varieties and multi-year data, future research aims to develop even more accurate predictive models for kimchi cabbage taste and quality, ultimately contributing to the consistency of kimchi production.

Graphical Abstract

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Horticulture Environment and Biotechnology
Horticulture Environment and Biotechnology Agricultural and Biological Sciences-Horticulture
CiteScore
4.30
自引率
4.20%
发文量
0
审稿时长
6 months
期刊介绍: Horticulture, Environment, and Biotechnology (HEB) is the official journal of the Korean Society for Horticultural Science, was launched in 1965 as the "Journal of Korean Society for Horticultural Science". HEB is an international journal, published in English, bimonthly on the last day of even number months, and indexed in Biosys Preview, SCIE, and CABI. The journal is devoted for the publication of original research papers and review articles related to vegetables, fruits, ornamental and herbal plants, and covers all aspects of physiology, molecular biology, biotechnology, protected cultivation, postharvest technology, and research in plants related to environment.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信