BoostSweet: Learning molecular perceptual representations of sweeteners. (30th July 2022)

• Record Type: Journal Article
• Authors: Lee, Junho; Song, Seon Bin; Chung, You Kyoung; Jang, Jee Hwan; Huh, Joonsuk
• Is Part Of: Food chemistry. Volume 383(2022)
• Publication Date: 2022-07-30
• Subjects: Sweetener prediction -- Machine learning -- Quantitative structure-activity relationship -- Ligand-binding approach -- Feature analysis; Food -- Analysis -- Periodicals; Food -- Composition -- Periodicals; 664
• DOI: 10.1016/j.foodchem.2022.132435
• Languages: English
• ISSNs: 0308-8146

Abstract

Graphical abstract: Highlights: Our sweetness prediction model demonstrates state-of-the-art performance. Feature importance analysis was used to identify key features for determining sweetness. We chemically analyzed molecular sweetness descriptors. The proposed key molecular descriptors can be utilized to design new sweeteners. Abstract: The development of safe artificial sweeteners has attracted considerable interest in the food industry. Previous machine learning (ML) studies based on quantitative structure–activity relationships have provided some molecular principles for predicting sweetness, but these models can be improved via the chemical recognition of sweetness active factors. Our ML model, a soft-vote ensemble model that has a light gradient boosting machine and uses both layered fingerprints and alvaDesc molecular descriptor features, demonstrates state-of-the-art performance, with an AUROC score of 0.961. Based on an analysis of feature importance and dataset, we identified that the number of nitrogen atoms that serve as hydrogen bond donors in molecules can play an essential role in determining sweetness. These results potentially provide an advanced understanding of the relationship between molecular structure and sweetness, which can be used to design new sweeteners based on molecular structural dependence.