Machine Learning Identifies a Parsimonious Differential Equation for Myricetin Degradation from Scarce Data
Abstract
1. Introduction
2. Material and Methods
2.1. Preparation of Stripped Soybean Oil
2.2. Preparation of Samples for Oxidation Study
2.3. Measurement of Myricetin Concentrations
2.4. Machine Learning Approach for Myricetin Degradation
3. Results and Discussion
3.1. Neural Differential Equation
3.2. Sparse Identification of Nonlinear Dynamics
3.3. Model Predictions
4. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
Appendix A. Degradation of Myricetin in Soybean Oil at Different Initial Concentrations
Initial Concentration (M) | ||||
---|---|---|---|---|
Time (Day) | 10 | 25 | 50 | 100 |
3 | ||||
4 | ||||
5 | ||||
6 | ||||
8 | ||||
9 | ||||
10 | ||||
11 | ||||
12 | ||||
13 | ||||
15 | ||||
17 | ||||
19 | ||||
21 | ||||
23 | ||||
24 | ||||
25 | ||||
29 | ||||
34 | ||||
36 | ||||
39 | ||||
42 |
Appendix B. Fitting Myricetin Degradation Data with the Weibull Model
References
- Corradini, M.G. Shelf life of food products: From open labeling to real-time measurements. Annu. Rev. Food Sci. Technol. 2018, 9, 251–269. [Google Scholar] [CrossRef] [PubMed]
- Van Boekel, M.A. Kinetic Modeling of Reactions in Foods; CRC Press: Boca Raton, FL, USA, 2008. [Google Scholar]
- Seilert, J.; Moorthy, A.S.; Kearsley, A.J.; Flöter, E. Revisiting a model to predict pure triglyceride thermodynamic properties: Parameter optimization and performance. J. Am. Oil Chem. Soc. 2021, 98, 837–850. [Google Scholar] [CrossRef]
- Sun, Y.E.; Wang, W.D.; Chen, H.W.; Li, C. Autoxidation of unsaturated lipids in food emulsion. Crit. Rev. Food Sci. Nutr. 2011, 51, 453–466. [Google Scholar] [CrossRef] [PubMed]
- Decker, E.A.; Warner, K.; Richards, M.P.; Shahidi, F. Measuring antioxidant effectiveness in food. J. Agric. Food Chem. 2005, 53, 4303–4310. [Google Scholar] [CrossRef]
- Ghelichi, S.; Hajfathalian, M.; Yesiltas, B.; Sørensen, A.D.M.; García-Moreno, P.J.; Jacobsen, C. Oxidation and oxidative stability in emulsions. Compr. Rev. Food Sci. Food Saf. 2023, 22, 1864–1901. [Google Scholar] [CrossRef]
- Corradini, M.G.; Peleg, M. Shelf-life estimation from accelerated storage data. Trends Food Sci. Technol. 2007, 18, 37–47. [Google Scholar] [CrossRef]
- Wanasundara, U.N.; Shahidi, F. Stabilization of marine oils with flavonoids. J. Food Lipids 1998, 5, 183–196. [Google Scholar] [CrossRef]
- Roedig-Penman, A.; Gordon, M.H. Antioxidant properties of myricetin and quercetin in oil and emulsions. J. Am. Oil Chem. Soc. 1998, 75, 169–180. [Google Scholar] [CrossRef]
- Bayram, I.; Laze, A.; Decker, E.A. Synergistic Mechanisms of Interactions between Myricetin or Taxifolin with α-Tocopherol in Oil-in-Water Emulsions. J. Agric. Food Chem. 2023, 71, 9490–9500. [Google Scholar] [CrossRef]
- Škerget, M.; Kotnik, P.; Hadolin, M.; Hraš, A.R.; Simonič, M.; Knez, Ž. Phenols, proanthocyanidins, flavones and flavonols in some plant materials and their antioxidant activities. Food Chem. 2005, 89, 191–198. [Google Scholar] [CrossRef]
- Mozuraityte, R.; Kristinova, V.; Rustad, T. Oxidation of Food Components. In Encyclopedia of Food and Health; Caballero, B., Finglas, P.M., Toldrá, F., Eds.; Academic Press: Oxford, UK, 2016; pp. 186–190. [Google Scholar]
- Decker, E.A.; McClements, D.J.; Bourlieu-Lacanal, C.; Durand, E.; Figueroa-Espinoza, M.C.; Lecomte, J.; Villeneuve, P. Hurdles in predicting antioxidant efficacy in oil-in-water emulsions. Trends Food Sci. Technol. 2017, 67, 183–194. [Google Scholar] [CrossRef]
- Alamed, J.; Chaiyasit, W.; McClements, D.J.; Decker, E.A. Relationships between free radical scavenging and antioxidant activity in foods. J. Agric. Food Chem. 2009, 57, 2969–2976. [Google Scholar] [CrossRef] [PubMed]
- Chen, R.T.; Rubanova, Y.; Bettencourt, J.; Duvenaud, D.K. Neural ordinary differential equations. In Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada, 3–8 December 2018; Volume 31. [Google Scholar]
- Kidger, P. On Neural Differential Equations. Ph.D. Thesis, University of Oxford, Oxford, UK, 2021. [Google Scholar]
- Haber, E.; Ruthotto, L. Stable architectures for deep neural networks. Inverse Probl. 2017, 34, 014004. [Google Scholar] [CrossRef]
- Maulik, R.; Mohan, A.; Lusch, B.; Madireddy, S.; Balaprakash, P.; Livescu, D. Time-series learning of latent-space dynamics for reduced-order model closure. Phys. D Nonlinear Phenom. 2020, 405, 132368. [Google Scholar] [CrossRef]
- Du, J.; Futoma, J.; Doshi-Velez, F. Model-based reinforcement learning for semi-markov decision processes with neural odes. In Proceedings of the Advances in Neural Information Processing Systems, Online, 6–12 December 2020; Volume 33, pp. 19805–19816. [Google Scholar]
- Udrescu, S.M.; Tegmark, M. AI Feynman: A physics-inspired method for symbolic regression. Sci. Adv. 2020, 6, eaay2631. [Google Scholar] [CrossRef]
- Quade, M.; Abel, M.; Nathan Kutz, J.; Brunton, S.L. Sparse identification of nonlinear dynamics for rapid model recovery. Chaos Interdiscip. J. Nonlinear Sci. 2018, 28, 063116. [Google Scholar] [CrossRef]
- Fasel, U.; Kaiser, E.; Kutz, J.N.; Brunton, B.W.; Brunton, S.L. Sindy with control: A tutorial. In Proceedings of the 2021 60th IEEE Conference on Decision and Control (CDC), Austin, TX, USA, 14–17 December 2021; IEEE: Piscataway, NJ, USA, 2021; pp. 16–21. [Google Scholar]
- Deng, N.; Noack, B.R.; Morzyński, M.; Pastur, L.R. Low-order model for successive bifurcations of the fluidic pinball. J. Fluid Mech. 2020, 884, A37. [Google Scholar] [CrossRef]
- Boon, C.S.; Xu, Z.; Yue, X.; McClements, D.J.; Weiss, J.; Decker, E.A. Factors Affecting Lycopene Oxidation in Oil-in-Water Emulsions. J. Agric. Food Chem. 2008, 56, 1408–1414. [Google Scholar] [CrossRef]
- Bayram, I.; Decker, E.A. Underlying mechanisms of synergistic antioxidant interactions during lipid oxidation. Trends Food Sci. Technol. 2023, 133, 219–230. [Google Scholar] [CrossRef]
- Amari, S.I. Backpropagation and stochastic gradient descent method. Neurocomputing 1993, 5, 185–196. [Google Scholar] [CrossRef]
- Deisenroth, M.P.; Faisal, A.A.; Ong, C.S. Mathematics for Machine Learning; Cambridge University Press: Cambridge, UK, 2020. [Google Scholar]
- Kingma, D.P.; Ba, J. Adam: A method for stochastic optimization. arXiv 2014, arXiv:1412.6980. [Google Scholar]
- Chollet, F.; Keras Team. Keras. 2015. Available online: https://github.com/fchollet/keras (accessed on 15 June 2025).
- Abadi, M.; Agarwal, A.; Barham, P.; Brevdo, E.; Chen, Z.; Citro, C.; Corrado, G.S.; Davis, A.; Dean, J.; Devin, M.; et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. 2015. Available online: https://www.tensorflow.org/ (accessed on 15 June 2025).
- Champion, K.; Lusch, B.; Kutz, J.N.; Brunton, S.L. Data-driven discovery of coordinates and governing equations. Proc. Natl. Acad. Sci. USA 2019, 116, 22445–22451. [Google Scholar] [CrossRef] [PubMed]
- Tibshirani, R. Regression shrinkage and selection via the lasso. J. R. Stat. Soc. Ser. B Stat. Methodol. 1996, 58, 267–288. [Google Scholar] [CrossRef]
- Zheng, P.; Askham, T.; Brunton, S.L.; Kutz, J.N.; Aravkin, A.Y. A unified framework for sparse relaxed regularized regression: SR3. IEEE Access 2018, 7, 1404–1423. [Google Scholar] [CrossRef]
- Zhang, L.; Schaeffer, H. On the convergence of the SINDy algorithm. Multiscale Model. Simul. 2019, 17, 948–972. [Google Scholar] [CrossRef]
- Friedman, J.H. Greedy function approximation: A gradient boosting machine. Ann. Stat. 2001, 29, 1189–1232. [Google Scholar] [CrossRef]
- Focke, W.W.; van der Westhuizen, I.; Musee, N.; Loots, M.T. Kinetic interpretation of log-logistic dose-time response curves. Sci. Rep. 2017, 7, 2234. [Google Scholar] [CrossRef]
- Heinonen, M.; Haila, K.; Lampi, A.M.; Piironen, V. Inhibition of oxidation in 10% oil-in-water emulsions by β-carotene with α-and γ-tocopherols. J. Am. Oil Chem. Soc. 1997, 74, 1047–1052. [Google Scholar] [CrossRef]
- Labuza, T.P.; Dugan, L.R. Kinetics of lipid oxidation in foods. Crit. Rev. Food Technol. 1971, 2, 355–405. [Google Scholar] [CrossRef]
- Brand-Williams, W.; Cuvelier, M.; Berset, C. Use of a free radical method to evaluate antioxidant activity. LWT-Food Sci. Technol. 1995, 28, 25–30. [Google Scholar] [CrossRef]
- Mcclements, D.; Decker, E. Lipid Oxidation in Oil-in-Water Emulsions: Impact of Molecular Environment on Chemical Reactions in Heterogeneous Food Systems. J. Food Sci. 2000, 65, 1270–1282. [Google Scholar] [CrossRef]
- Burton, G.W.; Ingold, K. β-Carotene: An unusual type of lipid antioxidant. Science 1984, 224, 569–573. [Google Scholar] [CrossRef] [PubMed]
- Zhou, B.; Wu, L.M.; Yang, L.; Liu, Z.L. Evidence for α-tocopherol regeneration reaction of green tea polyphenols in SDS micelles. Free. Radic. Biol. Med. 2005, 38, 78–84. [Google Scholar] [CrossRef] [PubMed]
- Amorati, R.; Ferroni, F.; Lucarini, M.; Pedulli, G.F.; Valgimigli, L. A quantitative approach to the recycling of α-tocopherol by coantioxidants. J. Org. Chem. 2002, 67, 9295–9303. [Google Scholar] [CrossRef]
- Lee, J.; Lee, Y.; Choe, E. Temperature dependence of the autoxidation and antioxidants of soybean, sunflower, and olive oil. Eur. Food Res. Technol. 2007, 226, 239–246. [Google Scholar] [CrossRef]
- Kingsland, S. The Refractory Model: The Logistic Curve and the History of Population Ecology. Q. Rev. Biol. 1982, 57, 29–52. [Google Scholar] [CrossRef]
- Burnham, A.K. Use and misuse of logistic equations for modeling chemical kinetics. J. Therm. Anal. Calorim. 2017, 127, 1107–1116. [Google Scholar] [CrossRef]
- Peleg, M.; Cole, M.B. Reinterpretation of microbial survival curves. Crit. Rev. Food Sci. 1998, 38, 353–380. [Google Scholar] [CrossRef]
- van Boekel, M.A. On the use of the Weibull model to describe thermal inactivation of microbial vegetative cells. Int. J. Food Microbiol. 2002, 74, 139–159. [Google Scholar] [CrossRef]
- Peleg, M.; Normand, M.D.; Corradini, M.G. A new look at kinetics in relation to food storage. Annu. Rev. Food Sci. Technol. 2017, 8, 135–153. [Google Scholar] [CrossRef]
- Bayram, I.; Parra-Escudero, C.; Decker, E.A.; Lu, J. Mathematical Modeling of Alpha-Tocopherol Early Degradation Kinetics to Predict the Shelf-Life of Bulk Oils. J. Agric. Food Chem. 2024, 72, 4939–4946. [Google Scholar] [CrossRef]
Concentration (M) | Rate r () | Capacity K (-) |
---|---|---|
10 | 1.636 | 1.947 |
25 | 0.799 | 1.943 |
50 | 0.533 | 1.960 |
100 | 0.258 | 1.938 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Fulkerson, A.; Bayram, I.; Decker, E.A.; Parra-Escudero, C.; Lu, J.; Corvalan, C.M. Machine Learning Identifies a Parsimonious Differential Equation for Myricetin Degradation from Scarce Data. Foods 2025, 14, 2135. https://doi.org/10.3390/foods14122135
Fulkerson A, Bayram I, Decker EA, Parra-Escudero C, Lu J, Corvalan CM. Machine Learning Identifies a Parsimonious Differential Equation for Myricetin Degradation from Scarce Data. Foods. 2025; 14(12):2135. https://doi.org/10.3390/foods14122135
Chicago/Turabian StyleFulkerson, Andrew, Ipek Bayram, Eric A. Decker, Carlos Parra-Escudero, Jiakai Lu, and Carlos M. Corvalan. 2025. "Machine Learning Identifies a Parsimonious Differential Equation for Myricetin Degradation from Scarce Data" Foods 14, no. 12: 2135. https://doi.org/10.3390/foods14122135
APA StyleFulkerson, A., Bayram, I., Decker, E. A., Parra-Escudero, C., Lu, J., & Corvalan, C. M. (2025). Machine Learning Identifies a Parsimonious Differential Equation for Myricetin Degradation from Scarce Data. Foods, 14(12), 2135. https://doi.org/10.3390/foods14122135