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.