Application of Machine Learning Algorithms for Predicting Methylglyoxal Concentration in Processed Packaged Foods
Keywords:
AGEs, Methylglyoxal, predictive MGO concentration, catboost, machine learningAbstract
Background and aim: Methylglyoxal (MGO) is a reactive dicarbonyl metabolite of glucose and plays an important role in processed food products. It is formed by the binding of a sugar molecule to a protein or lipid molecule, inside or outside the body. In this study, a tool called predictive (pMGO) is proposed, which aims to accurately predict MGO formation in foods. Methods: Some machine learning (ML) algorithms were evaluated for pMGO based on food composition data. Models were tested using variables such as glucose, fructose, sucrose, total sugar, carbohydrate, protein, fat, fiber and salt. Results: The highest prediction performance among the models was obtained by the CatBoost model with the values of $R^2 = 0.52 \pm 0.30$ and $RMSE = 156.75 \pm 64.92$. While glucose, fructose and saturated fat stood out as the most effective variables, carbohydrates and protein provided more indirect contributions. Conclusion: Findings suggest that focus on some components, especially sugar type and saturated fat predicting MGO exposure.
References
1. Zheng J, Guo H, Ou J et al. Benefits, deleterious effects and mitigation of methylglyoxal in foods: A critical review. Trends Food Sci Technol 2021; 107: 201–212. doi:10.1016/j.tifs.2020.10.031
2. Zheng L, Boeren S, Liu C et al. Proteomics-based identification of biomarkers reflecting endogenous and exogenous exposure to the advanced glycation end product precursor methylglyoxal in SH-SY5Y human neuroblastoma cells. Int J Biol Macromol 2024; 258: 132859. doi:10.1016/j.ijbiomac.2024.132859
3. Wang Y, Chen J, Zheng Y et al. Glucose metabolite methylglyoxal induces vascular endothelial cell pyroptosis via NLRP3 inflammasome activation and oxidative stress in vitro and in vivo. Cell Mol Life Sci 2024; 81: 401. doi:10.1007/s00018-024-05432-8
4. Scheijen JLJM, Clevers E, Engelen L et al. Analysis of advanced glycation endproducts in selected food items by ultra-performance liquid chromatography tandem mass spectrometry: Presentation of a dietary AGE database. Food Chem 2016; 190: 1145–1150. doi:10.1016/j.foodchem.2015.06.049
5. Lai SWT, Lopez Gonzalez EDJ, Zoukari T, Ki P, Shuck SC. Methylglyoxal and Its Adducts: Induction, Repair, and Association with Disease. Chem Res Toxicol 2022; 35: 1720–1746. doi:10.1021/acs.chemrestox.2c00160
6. Bellier J, Nokin M-J, Lardé E et al. Methylglyoxal, a potent inducer of AGEs, connects between diabetes and cancer. Diabetes Res Clin Pract 2019; 148: 200–211. doi:10.1016/j.diabres.2019.01.002
7. Yusufoğlu B. Evaluation of the Altmetric Attention Score of Recent Hazard Food-Marker: Advanced Glycation End Products. Celal Bayar Univ J Sci 2025; 21: 105-117. doi:10.18466/cbayarfbe.1580554
8. Maasen K, Scheijen JLJM, Opperhuizen A, Stehouwer CDA, Van Greevenbroek MM, Schalkwijk CG. Quantification of dicarbonyl compounds in commonly consumed foods and drinks; presentation of a food composition database for dicarbonyls. Food Chem 2021; 339: 128063. doi:10.1016/j.foodchem.2020.128063
9. Li C, Zhang L, Gao W, Lai C, Dong H. Robust detection of advanced glycation endproducts in milk powder using ultrahigh performance liquid chromatography tandem mass spectrometry (UHPLC-MS/MS). Food Anal Methods 2021; 14: 1472-1481. doi:10.1007/s12161-021-01986-6
10. Tareke E, Forslund A, Lindh CH, Fahlgren C, Östman E. Isotope dilution ESI-LC-MS/MS for quantification of free and total Nε-(1-Carboxymethyl)-l-Lysine and free Nε-(1-Carboxyethyl)-l-Lysine: Comparison of total Nε-(1-Carboxymethyl)-l-Lysine levels measured with new method to ELISA assay in gruel samples. Food Chem 2013; 141: 4253-4259. doi:10.1016/j.foodchem.2013.07.003
11. Wei Q, Liu T, Sun DW. Advanced glycation end-products (AGEs) in foods and their detecting techniques and methods: A review. Trends Food Sci Technol 2018; 82: 32-45. doi:10.1016/j.jada.2010.03.018
12. Zhu G, Huang X, Peng X, Xu J, Guo S, Zhang H. A deep learning-based quantitative prediction model for the processing potentials of soybeans as soymilk raw materials. Food Chem 2024; 453: 139671. doi:10.1016/j.foodchem.2024.139671
13. Rabbani N. AGEomics Biomarkers and Machine Learning—Realizing the Potential of Protein Glycation in Clinical Diagnostics. Int J Mol Sci 2022; 23: 4584. doi:10.3390/ijms23094584
14. Yang H, Bai X, Feng B et al. Application of Molecular Transformer approach for predicting the potential reactions to generate advanced glycation end products in infant formula. Food Chem 2023; 407: 135143. doi:10.1016/j.foodchem.2022.135143
15. Qian J, Wang X, Song F et al. ChemSweet: An AI-driven computational platform for next-gen sweetener discovery. Food Chem 2025; 463: 141362. doi:10.1016/j.foodchem.2024.141362
16. Zhu J, Lian S, Zhong H, Sun R, Xiao Z, Li H. Detection of Advanced Glycosylation End Products in the Cornea Based on Molecular Fluorescence and Machine Learning. Biosensors (Basel) 2023; 13: 170. doi:10.3390/bios13020170
17. He H-J, Zhang C, Bian X et al. Improved prediction of vitamin C and reducing sugar content in sweet potatoes using hyperspectral imaging and LARS-enhanced LASSO variable selection. J Food Compos Anal 2024; 132: 106350. doi:10.1016/j.jfca.2024.106350
18. Yamasaki Y, Nakamura K, Kashiwabara N, Chiba S, Akiyama H, Tsutsumi T. Development of a processing factor prediction model for pesticides in processed tomato foods using elastic net regularization. Food Chem 2024; 447: 138943. doi:10.1016/j.foodchem.2024.138943
19. Yıldırım N, Tapan A. Data Mining and Application of Decision Tree Modelling on Electrochemical Data Used for Damaged Starch Detection. Gazi Univ J Sci Part A Eng Innov 2021; 8: Article 4. doi:10.54287/gujsa.997123
20. Yordi E, Koeling R, Mota Y et al. Application of KNN algorithm in determining the total antioxidant capacity of flavonoid-containing foods. Proceedings of the 19th International Electronic Conference on Synthetic Organic Chemistry 2015. doi:10.3390/ecsoc-19-e002
21. Dębska B, Guzowska-Świder B. Application of artificial neural network in food classification. Anal Chim Acta 2011; 705: 283–291. doi:10.1016/j.aca.2011.06.033
22. Feng J, Cui Y, Jiang C et al. Analysis of sediment re-formation factors after ginseng beverage clarification based on XGBoost machine learning algorithm. Food Chem 2025; 463: 141304. doi:10.1016/j.foodchem.2024.141304
23. Chen Q, Li J, Feng J, Qian J. Dynamic comprehensive quality assessment of post-harvest grape in different transportation chains using SAHP–CatBoost machine learning. Food Qual Saf 2024; 8: fyae007. doi:10.1093/fqsafe/fyae007
24. Jin J, Liu Y, Li S, Hu J, Liu S, Chen C. Identification of soy sauce using high-field asymmetric waveform ion mobility spectrometry combined with machine learning. Sens Actuators B Chem 2022; 365: 131966. doi:10.1016/j.snb.2022.131966
25. Mayr A, Binder H, Gefeller O, Schmid M. The Evolution of Boosting Algorithms—From Machine Learning to Statistical Modelling. Methods Inf Med 2014; 53: 419–427. doi:10.3414/ME13-01-0122
26. Zheng R, Jia Y, Ullagaddi C et al. Optimizing feature selection with gradient boosting machines in PLS regression for predicting moisture and protein in multi-country corn kernels via NIR spectroscopy. Food Chem 2024; 456: 140062. doi:10.1016/j.foodchem.2024.140062
27. Durmus Y. High accuracy prediction of Thai rice glycemic index using machine learning. Cogent Food Agric 2024; 10: 2411032. doi:10.1080/23311932.2024.2411032
28. Bisutti V, Mota LFM, Giannuzzi D et al. Infrared spectroscopy coupled with machine learning algorithms for predicting the detailed milk mineral profile in dairy cattle. Food Chem 2024; 461: 140800. doi:10.1016/j.foodchem.2024.140800
29. Gana R, Naha S, Mazumder R, Goldman R, Vasudevan S. Ridge Regression Estimated Linear Probability Model Predictions of N-glycosylation in Proteins with Structural and Sequence Data. arXiv 2018; arXiv:1803.06002. doi:10.48550/arXiv.1803.06002
30. Özboy Ö, Köksel H. An application of linear regression technique for predicting bulgur yield and quality of wheat cultivars. Nahrung 2002; 46: 21–24. doi:10.1002/1521-3803
31. Tarlak F, Şimşek BB, Şahin M, Pérez-Rodríguez F. Next-Generation Predictive Microbiology: A Software Platform Combining Two-Step, One-Step and Machine Learning Modelling. Foods 2025; 14: 3158. doi:10.3390/foods14183158
32. Jović O, Smrečki N, Popović Z. Interval ridge regression (iRR) as a fast and robust method for quantitative prediction and variable selection applied to edible oil adulteration. Talanta 2016; 150: 37–45. doi:10.1016/j.talanta.2015.12.007
33. An D, Wang L, He J, Hua Y. A two-step framework integrating lasso and Relaxed Lasso for resolving multidimensional collinearity in Chinese baijiu aging research. Heliyon 2024; 10: e36871. doi:10.1016/j.heliyon.2024.e36871
34. Amini F, Hu G. A two-layer feature selection method using Genetic Algorithm and Elastic Net. Expert Syst Appl 2021; 166: 114072. doi:10.1016/j.eswa.2020.114072
35. Peng H, Yi L, Fan X, Zhang J, Gu Y, Wang S. Near-infrared spectroscopy assisted by random forest for predicting the physicochemical indicators of yak milk powder. Food Chem 2025; 478: 143555. doi:10.1016/j.foodchem.2025.143555
36. Breda LS, de Melo Nascimento JE, Alves V, de Alencar Arnaut de Toledo V, de Lima VA, Felsner ML. Green and fast prediction of crude protein contents in bee pollen based on digital images combined with Random Forest algorithm. Food Res Int 2024; 179: 113958. doi:10.1016/j.foodres.2024.113958
37. Wiens M, Verone-Boyle A, Henscheid N, Podichetty JT, Burton J. A Tutorial and Use Case Example of the eXtreme Gradient Boosting (XGBoost) Artificial Intelligence Algorithm for Drug Development Applications. Clin Transl Sci 2025; 18: e70172. doi:10.1111/cts.70172
38. Li H, Liu S, Hassan MM et al. Rapid quantitative analysis of Hg2+ residue in dairy products using SERS coupled with ACO-BP-AdaBoost algorithm. Spectrochim Acta A Mol Biomol Spectrosc 2019; 223: 117281. doi:10.1016/j.saa.2019.117281
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Busra Yusufoglu
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by-nc/4.0) which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Transfer of Copyright and Permission to Reproduce Parts of Published Papers.
Authors retain the copyright for their published work. No formal permission will be required to reproduce parts (tables or illustrations) of published papers, provided the source is quoted appropriately and reproduction has no commercial intent. Reproductions with commercial intent will require written permission and payment of royalties.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
