Yardjouma Silue, Olaniyi A. Fawole, Taongashe Majoni, Umezuruike L. Opara, Jude A. Okolie
{"title":"基于代谢物图谱的日本李子栽培品种的机器学习分化","authors":"Yardjouma Silue, Olaniyi A. Fawole, Taongashe Majoni, Umezuruike L. Opara, Jude A. Okolie","doi":"10.1007/s11483-024-09870-6","DOIUrl":null,"url":null,"abstract":"<div><p>This study investigates the metabolite diversity of twelve Japanese plum cultivars grown in South Africa to understand their differential organoleptic characteristics and nutritional properties. The goal is to differentiate or associate these plum cultivars based on their metabolic profiles. Metabolite profiling was conducted using gas chromatography-mass spectrometry (GC-MS) at different postharvest ripening stages. Different unsupervised machine learning algorithms were applied: hierarchical clustering, K-means clustering, Density-Based Spatial Applications with Noise, and principal component analysis (PCA). Results revealed that each cultivar contains a unique combination of 13 amino acids, 4 sugars (contributing to organoleptic characteristics), and numerous phenolic compounds and antioxidant activities (contributing to nutritional value). The levels of these compounds are cultivar-dependent and vary with postharvest stages. The number of clusters of plum cultivars varied with both the clustering algorithm and postharvest stages. However, certain cultivars were consistently grouped regardless of the clustering method, indicating similar characteristics and responses to storage and shelf-life conditions. Similar consistent groupings were observed after cold storage and shelf life. Our findings also showed that K-means clustering is the most effective model for plum cultivar differentiation based on the Silhouette Score and Davies-Bouldin Index. This study enhances our understanding of how metabolites evolve over different postharvest stages and provides a robust framework for differentiating plum cultivars, which can aid in sorting and grading operations. The research offers actionable insights to improve postharvest handling and storage practices, which are critical for maintaining the nutritional quality of plums, an important fruit for human health.</p></div>","PeriodicalId":564,"journal":{"name":"Food Biophysics","volume":"19 4","pages":"955 - 972"},"PeriodicalIF":2.8000,"publicationDate":"2024-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s11483-024-09870-6.pdf","citationCount":"0","resultStr":"{\"title\":\"Machine Learning-based Differentiation of Japanese Plum Cultivars Based on Metabolite Profiling\",\"authors\":\"Yardjouma Silue, Olaniyi A. Fawole, Taongashe Majoni, Umezuruike L. Opara, Jude A. Okolie\",\"doi\":\"10.1007/s11483-024-09870-6\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>This study investigates the metabolite diversity of twelve Japanese plum cultivars grown in South Africa to understand their differential organoleptic characteristics and nutritional properties. The goal is to differentiate or associate these plum cultivars based on their metabolic profiles. Metabolite profiling was conducted using gas chromatography-mass spectrometry (GC-MS) at different postharvest ripening stages. Different unsupervised machine learning algorithms were applied: hierarchical clustering, K-means clustering, Density-Based Spatial Applications with Noise, and principal component analysis (PCA). Results revealed that each cultivar contains a unique combination of 13 amino acids, 4 sugars (contributing to organoleptic characteristics), and numerous phenolic compounds and antioxidant activities (contributing to nutritional value). The levels of these compounds are cultivar-dependent and vary with postharvest stages. The number of clusters of plum cultivars varied with both the clustering algorithm and postharvest stages. However, certain cultivars were consistently grouped regardless of the clustering method, indicating similar characteristics and responses to storage and shelf-life conditions. Similar consistent groupings were observed after cold storage and shelf life. Our findings also showed that K-means clustering is the most effective model for plum cultivar differentiation based on the Silhouette Score and Davies-Bouldin Index. This study enhances our understanding of how metabolites evolve over different postharvest stages and provides a robust framework for differentiating plum cultivars, which can aid in sorting and grading operations. The research offers actionable insights to improve postharvest handling and storage practices, which are critical for maintaining the nutritional quality of plums, an important fruit for human health.</p></div>\",\"PeriodicalId\":564,\"journal\":{\"name\":\"Food Biophysics\",\"volume\":\"19 4\",\"pages\":\"955 - 972\"},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2024-08-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://link.springer.com/content/pdf/10.1007/s11483-024-09870-6.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Food Biophysics\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s11483-024-09870-6\",\"RegionNum\":4,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"FOOD SCIENCE & TECHNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Food Biophysics","FirstCategoryId":"97","ListUrlMain":"https://link.springer.com/article/10.1007/s11483-024-09870-6","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"FOOD SCIENCE & TECHNOLOGY","Score":null,"Total":0}
Machine Learning-based Differentiation of Japanese Plum Cultivars Based on Metabolite Profiling
This study investigates the metabolite diversity of twelve Japanese plum cultivars grown in South Africa to understand their differential organoleptic characteristics and nutritional properties. The goal is to differentiate or associate these plum cultivars based on their metabolic profiles. Metabolite profiling was conducted using gas chromatography-mass spectrometry (GC-MS) at different postharvest ripening stages. Different unsupervised machine learning algorithms were applied: hierarchical clustering, K-means clustering, Density-Based Spatial Applications with Noise, and principal component analysis (PCA). Results revealed that each cultivar contains a unique combination of 13 amino acids, 4 sugars (contributing to organoleptic characteristics), and numerous phenolic compounds and antioxidant activities (contributing to nutritional value). The levels of these compounds are cultivar-dependent and vary with postharvest stages. The number of clusters of plum cultivars varied with both the clustering algorithm and postharvest stages. However, certain cultivars were consistently grouped regardless of the clustering method, indicating similar characteristics and responses to storage and shelf-life conditions. Similar consistent groupings were observed after cold storage and shelf life. Our findings also showed that K-means clustering is the most effective model for plum cultivar differentiation based on the Silhouette Score and Davies-Bouldin Index. This study enhances our understanding of how metabolites evolve over different postharvest stages and provides a robust framework for differentiating plum cultivars, which can aid in sorting and grading operations. The research offers actionable insights to improve postharvest handling and storage practices, which are critical for maintaining the nutritional quality of plums, an important fruit for human health.
期刊介绍:
Biophysical studies of foods and agricultural products involve research at the interface of chemistry, biology, and engineering, as well as the new interdisciplinary areas of materials science and nanotechnology. Such studies include but are certainly not limited to research in the following areas: the structure of food molecules, biopolymers, and biomaterials on the molecular, microscopic, and mesoscopic scales; the molecular basis of structure generation and maintenance in specific foods, feeds, food processing operations, and agricultural products; the mechanisms of microbial growth, death and antimicrobial action; structure/function relationships in food and agricultural biopolymers; novel biophysical techniques (spectroscopic, microscopic, thermal, rheological, etc.) for structural and dynamical characterization of food and agricultural materials and products; the properties of amorphous biomaterials and their influence on chemical reaction rate, microbial growth, or sensory properties; and molecular mechanisms of taste and smell.
A hallmark of such research is a dependence on various methods of instrumental analysis that provide information on the molecular level, on various physical and chemical theories used to understand the interrelations among biological molecules, and an attempt to relate macroscopic chemical and physical properties and biological functions to the molecular structure and microscopic organization of the biological material.