Metabolomic Selection for Enhanced Fruit Flavor

Abstract

Although they are staple foods in cuisines globally, commercial fruit varieties have become progressively less flavorful over time. Due to the cost and difficulty associated with flavor phenotyping, many breeding programs have long been challenged in selecting for this complex trait. To address this issue, we leveraged targeted metabolomics of diverse tomato and blueberry accessions and their corresponding consumer panel ratings to create statistical and machine learning models that can predict sensory perceptions of fruit flavor. Using these models, a breeding program can assess flavor ratings for a large number of varieties, previously limited by the low-throughput and high cost of consumer sensory panels. The ability to predict consumer ratings of liking, sweet, sour, umami, and flavor intensity was evaluated by a 10-fold cross-validation and the accuracies of 18 different models are assessed. The best performing models were used to infer the flavor compounds (sugars, acids, and volatiles) that contribute most to each flavor attribute. The prediction accuracies were high for most attributes in both blueberries and tomatoes. We expect that these models will enable an earlier incorporation of flavor as breeding targets and encourage selection and release of more flavorful fruit varieties.

Plant phenotyping relevance

果実フレーバーという植物形質を、標的メタボロームと機械学習で予測する手法を開発し、交差検証で性能評価しており、表現型取得・推定が研究の中心である。

Code and data availability

The supplied blocks describe metabolomic and sensory panel data for tomato and blueberry and prediction modeling, but contain no data or code availability statement, no public repository deposit, and no authors' URL for datasets, models, or scripts. Data are described as partly from previously published sources (cited,

No evidence-backed public reproduction asset is currently recorded.