Informed classification of sweeteners/bitterants compounds via explainable machine learning

Maroni, Gabriele; Pallante, Lorenzo; Benedetto, G; Deriu, Marco Agostino; Piga, Dario; Grasso, Gianvito

doi:10.1016/j.crfs.2022.11.014

Cited by 8 publications

(4 citation statements)

References 47 publications

(58 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The horizontal axis indicates the impact on the prediction through SHAP values, while the color gradient, ranging from blue to red, signifies the intensity of the corresponding feature value. This plot effectively combines feature importance with the directional relationship between feature values and their impact on predictions ( Parsa et al, 2020 ; Maroni et al, 2022 ). For instance, characteristics such as Ag, K, V, Na and Mg exhibited the most pronounced influence on the predictions for samples from Liaoning ( Fig.…”

Section: Resultsmentioning

confidence: 99%

Explainable machine learning for predicting the geographical origin of Chinese Oysters via mineral elements analysis

Kang,

Zhao,

Yao

et al. 2024

Current Research in Food Science

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Explainable machine learning for predicting the geographical origin of Chinese Oysters via mineral elements analysis

Kang,

Zhao,

Yao

et al. 2024

Current Research in Food Science

View full text Add to dashboard Cite

“…This may also provide a good strategy for its use as a functional sugar or dietary supplement to mask the aftertaste. Meanwhile, the growing interdisciplinary intersection of machine learning and food sensory flavor, such as the Shapley Additive Ex Planations (SHAP) strategy for rational sweetness/bitterness classification, provides new ideas for more rational design and screening of sweeteners/bitters …”

Section: Future Food Market Potentialmentioning

confidence: 99%

Siraitia grosvenorii As a Homologue of Food and Medicine: A Review of Biological Activity, Mechanisms of Action, Synthetic Biology, and Applications in Future Food

Guo,

Chen,

Gong

et al. 2024

J. Agric. Food Chem.

View full text Add to dashboard Cite

Siraitia grosvenorii (SG), also known as Luo Han Guo or Monk fruit, boasts a significant history in food and medicine. This review delves into SG's historical role and varied applications in traditional Chinese culture, examining its phytochemical composition and the health benefits of its bioactive compounds. It further explores SG's biological activities, including antioxidant, anti-inflammatory, and antidiabetic properties and elucidates the mechanisms behind these effects. The review also highlights recent synthetic biology advances in enhancing the production of SG's bioactive compounds, presenting new opportunities for broadening their availability. Ultimately, this review emphasizes SG's value in food and medicine, showcasing its historical and cultural importance, phytochemistry, biological functions, action mechanisms, and the role of synthetic biology in its sustainable use.

show abstract

“…These models establish a correlation between the taste of molecules and their structural characteristics, and their popularity can be attributed to advancements in machine learning (ML) algorithms, particularly deep learning (DL), and the availability of curated datasets. While various studies have focused on developing classification models to differentiate between sweet/non-sweet and bitter/non-bitter compounds [9,10,11,12,13,14,15], aiming to identify novel tastants by screening molecule databases, progress in the realm of umami taste has been comparatively limited. To address this gap, Charoenkwan et al curated the UMP442 peptide database.…”

Section: Introductionmentioning

confidence: 99%

Computational Screening of Umami Tastants Using Deep Learning

Dutta,

Gajula,

Gupta

et al. 2024

Preprint

View full text Add to dashboard Cite

Umami, a fundamental human taste modality, refers to the savory flavors in meats and broths, often associated with monosodium glutamate and protein richness. With limited knowledge of umami molecules, the food industry seeks efficient approaches for identifying novel tastants. In this study, we have devised a virtual screening pipeline for identifying potential novel umami tastants from molecular databases. We first curated a comprehensive classification dataset containing 439 umami and 428 non-umami molecules. A transformer-based architecture was trained to differentiate between the two classes, achieving the best performance to date. Additionally, we built a neural network model for predicting the potency of umami compounds, the first effort of its kind. These two models, in conjunction with similarity analysis and toxicity screening, form an end-to-end framework for the rational discovery of novel tastants. We finally applied this framework to the FooDB database as an illustrative use case. This study demonstrates the potential of data-driven methods in predicting the taste of molecules from structural and chemical features.

show abstract

Informed classification of sweeteners/bitterants compounds via explainable machine learning

Cited by 8 publications

References 47 publications

Explainable machine learning for predicting the geographical origin of Chinese Oysters via mineral elements analysis

Explainable machine learning for predicting the geographical origin of Chinese Oysters via mineral elements analysis

Siraitia grosvenorii As a Homologue of Food and Medicine: A Review of Biological Activity, Mechanisms of Action, Synthetic Biology, and Applications in Future Food

Computational Screening of Umami Tastants Using Deep Learning

Contact Info

Product

Resources

About