Perception of taste is an emergent phenomenon arising from complex molecular interactions between chemical compounds and specific taste receptors. Among all the taste perceptions, the dichotomy of sweet and bitter tastes has been the subject of several machine learning studies for classification purposes. While previous studies have provided accurate sweeteners/bitterants classifiers, there is ample scope to enhance these models by enriching the understanding of the molecular basis of bitter-sweet tastes. Towards these goals, our study focuses on the development and testing of several machine learning strategies coupled with the novel SHapley Additive exPlanations (SHAP) for a rational sweetness/bitterness classification. This allows the identification of the chemical descriptors of interest by allowing a more informed approach toward the rational design and screening of sweeteners/bitterants. To support future research in this field, we make all datasets and machine learning models publicly available and present an easy-to-use code for bitter-sweet taste prediction.

Informed classification of sweeteners/bitterants compounds via explainable machine learning / Maroni, Gabriele; Pallante, Lorenzo; Di Benedetto, Giacomo; Deriu, Marco A.; Piga, Dario; Grasso, Gianvito. - In: CURRENT RESEARCH IN FOOD SCIENCE. - ISSN 2665-9271. - 5:(2022), pp. 2270-2280. [10.1016/j.crfs.2022.11.014]

Informed classification of sweeteners/bitterants compounds via explainable machine learning

Lorenzo Pallante;Marco A. Deriu;
2022

Abstract

Perception of taste is an emergent phenomenon arising from complex molecular interactions between chemical compounds and specific taste receptors. Among all the taste perceptions, the dichotomy of sweet and bitter tastes has been the subject of several machine learning studies for classification purposes. While previous studies have provided accurate sweeteners/bitterants classifiers, there is ample scope to enhance these models by enriching the understanding of the molecular basis of bitter-sweet tastes. Towards these goals, our study focuses on the development and testing of several machine learning strategies coupled with the novel SHapley Additive exPlanations (SHAP) for a rational sweetness/bitterness classification. This allows the identification of the chemical descriptors of interest by allowing a more informed approach toward the rational design and screening of sweeteners/bitterants. To support future research in this field, we make all datasets and machine learning models publicly available and present an easy-to-use code for bitter-sweet taste prediction.
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S2665927122002179-main.pdf

accesso aperto

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Creative commons
Dimensione 8.64 MB
Formato Adobe PDF
8.64 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2973867