Data-Driven Elucidation of Flavor Chemistry

Abstract

Flavor molecules are commonly used in the food industry to enhance product quality and consumer experiences but are associated with potential human health risks, highlighting the need for safer alternatives. To address these health-associated challenges and promote reasonable application, several databases for flavor molecules have been constructed. However, no existing studies have comprehensively summarized these data resources according to quality, focused fields, and potential gaps. Here, we systematically summarized 25 flavor molecule databases published within the last 20 years and revealed that data inaccessibility, untimely updates, and nonstandard flavor descriptions are the main limitations of current studies. We examined the development of computational approaches (e.g., machine learning and molecular simulation) for the identification of novel flavor molecules and discussed their major challenges regarding throughput, model interpretability, and the lack of gold-standard data sets for equitable model evaluation. Additionally, we discussed future strategies for the mining and designing of novel flavor molecules based on multi-omics and artificial intelligence to provide a new foundation for flavor science research.

Enhanced Deep-Learning Model for Carbon Footprints of Chemicals

“…ML models are usually considered “black boxes” due to their poor interpretability. , In response, previous studies have used a SHAP-based approach to identify the most important molecular descriptors that affect the PCFs of chemicals . However, it could not provide clear insights on, for example, PCF-intensive substructures and raw materials to guide the design of more sustainable molecules and processes.…”

“…The contamination of proxy data is transmitted to these pre-LCA tools, compromising their performance. Furthermore, while ML has been successfully applied in many fields, interpretability remains challenging for ML-based models. , Previous tools used Shapley additive explanations (SHAP) to identify the critical molecular descriptors that are relevant to PCFs. However, the detailed correlations between PCFs and functional groups and substructures cannot be distinctly quantified, which limits their application in the design of more sustainable molecules.…”

Mlp4green: A Binary Classification Approach Specifically for Green Odor

“…The data for the article was downloaded from the LRI & Odour Database—Odour Data, Flavornet and The Good Scents Company Information System, as well as the paper by Hatanaka et al [ 2 , 21 ]. We extracted 9944 non-green odor molecules and 642 green odor molecules from the database, as indicated in Figure 1 .…”

Data-Driven Prediction of Molecular Biotransformations in Food Fermentation

“…Given the great potential of fermentation products in antiseptic, antioxidation, immunity regulation, and other aspects, scientists have tried to identify the metabolic products of microorganisms in the fermentation process . A food component may undergo a variety of structural modifications causing unknown changes in biological activity under the action of various fermentation strains . Previous studies have shown that there are thousands of novel metabolites produced in the food fermentation process .…”