Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Mar 15;8(12):10875-10887.
doi: 10.1021/acsomega.2c07176. eCollection 2023 Mar 28.

Generating Flavor Molecules Using Scientific Machine Learning

Affiliations

Generating Flavor Molecules Using Scientific Machine Learning

Luana P Queiroz et al. ACS Omega. .

Abstract

Flavor is an essential component in the development of numerous products in the market. The increasing consumption of processed and fast food and healthy packaged food has upraised the investment in new flavoring agents and consequently in molecules with flavoring properties. In this context, this work brings up a scientific machine learning (SciML) approach to address this product engineering need. SciML in computational chemistry has opened paths in the compound's property prediction without requiring synthesis. This work proposes a novel framework of deep generative models within this context to design new flavor molecules. Through the analysis and study of the molecules obtained from the generative model training, it was possible to conclude that even though the generative model designs the molecules through random sampling of actions, it can find molecules that are already used in the food industry, not necessarily as a flavoring agent, or in other industrial sectors. Hence, this corroborates the potential of the proposed methodology for the prospecting of molecules to be applied in the flavor industry.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing financial interest.

Figures

Figure 1
Figure 1
Bar plot of the 20 most common flavor’s descriptors’ frequency in the database.
Figure 2
Figure 2
Co-occurrence heat map for the 20 most common flavor’s descriptors in the database.
Figure 3
Figure 3
DGM methodology scheme.
Figure 4
Figure 4
Logarithm of time in minutes for each training epoch.
Figure 5
Figure 5
New designed molecules from DGM part 1.
Figure 6
Figure 6
New designed molecules from DGM part 2.
Figure 7
Figure 7
Generative model’s learning rate.
Figure 8
Figure 8
Average train and valid loss for the 1000 training epochs.
Figure 9
Figure 9
Average likelihood per molecule in training and in validation for the 1000 training epochs.
Figure 10
Figure 10
Average number of edges and nodes for the 1000 training epochs.
Figure 11
Figure 11
Image obtained as the output of the generative model of the 2-hydroxy-6-propan-2-ylcyclohepta-2,4,6-trien-1-one.
Figure 12
Figure 12
Image obtained as the output of the generative model of 1,3-benzodioxole-5-carboxylic acid.
Figure 13
Figure 13
Image obtained as the output of the generative model of 7,7-dimethyl-3-methylene-bicyclo[4.1.0]heptane.
Figure 14
Figure 14
Image obtained as the output of the generative model of 2-methylbenzaldehyde.

References

    1. Berenstein N.Flavor Added: The Sciences of Flavor and the Industrialization of Taste in America. ProQuest Dissertations and Theses, 2018, p 556.
    1. Ulloa A. M. The aesthetic life of artificial flavors. Senses Soc. 2018, 13, 60–74. 10.1080/17458927.2017.1420026. - DOI
    1. Rodrigues A. E.; Nogueira I.; Faria R. P. V. Perfume and flavor engineering: A chemical engineering perspective. Molecules 2021, 26, 3095.10.3390/molecules26113095. - DOI - PMC - PubMed
    1. Monteiro A.; Costa P.; Loureiro J. M.; Rodrigues A. E. Flavor Engineering-A Methodology to Predict Sensory Qualities of Flavored Products. Ind. Eng. Chem. Res. 2018, 57, 8115–8123. 10.1021/acs.iecr.8b00527. - DOI
    1. Vanderhaegen B.; Neven H.; Coghe S.; Verstrepen K. J.; Derdelinckx G.; Verachtert H. Bioflavoring and beer refermentation. Appl. Microbiol. Biotechnol. 2003, 62, 140–150. 10.1007/s00253-003-1340-5. - DOI - PubMed