Chemoinformatic prioritization of bioactive compounds associated with the bread matrix based on ChEMBL pharmacological annotations and machine learning

Bread and cereal-based products represent not only a source of macronutrients but also a complex food matrix containing low-molecular-weight phenolic, aromatic and fermentation-derived compounds. A number of these molecules have been associated with antioxidant, anti-inflammatory, antifungal and receptor-mediated effects in experimental studies and pharmacological databases. However, these records mainly describe test systems for individual compounds and do not demonstrate the corresponding effects directly in bread products. The objective was to develop a reproducible chemoinformatics framework for internal prioritization of compounds associated with bread and cereal matrices based on structural features and ChEMBL pharmacological annotations. The study included 43 curated compounds. After structural standardization and InChIKey deduplication, 2,058 molecular features were calculated, including physicochemical descriptors and topological fingerprints. Functional labels were generated from ChEMBL records for four activity classes: antioxidant, anti-inflammatory, antifungal, and AhR-modulating. Logistic regression, random forest, CatBoost, and XGBoost were compared using nested repeated multilabel cross-validation; no independent external dataset was used in this study. Random forest showed the best balance of performance and robustness, with a macro average precision of 0.8041 (95 % CI: 0.7766–0.8320) and a macro ROC-AUC of 0.8056. The anti-inflammatory class showed the most stable performance, whereas the antioxidant class was more heterogeneous. The highest-ranking compounds were protocatechuic, caffeic, gallic and ferulic acids, quercetin, and (+)-catechin. Evaluation with molecular scaffold-based splitting reduced macro average precision to 0.6245, indicating limited transferability to structurally distant compounds. The proposed approach should be regarded as a tool for preliminary candidate selection for further external and biological validation, rather than as experimental confirmation of their functional effects in the bread matrix.

1. Boudaoud, S., Sicard, D., Suc, L., Conéjéro, G., Segond, D., Aouf, C. (2021). Ferulic acid content variation from wheat to bread. Food Science and Nutrition, 9(5), 2446–2457. https://doi.org/10.1002/fsn3.2171.

2. Boz, H. (2015). Ferulic acid in cereals — A review. Czech Journal of Food Sciences, 33(1), 1–7. https://doi.org/10.17221/401/2014-CJFS.

3. Skrajda-Brdak, M., Konopka, I., Tańska, M., Czaplicki, S. (2019). Changes in the content of free phenolic acids and antioxidative capacity of wholemeal bread in relation to cereal species and fermentation type. European Food Research and Technology, 245, 2247–2256. https://doi.org/10.1007/s00217-019-03331-y.

4. Abdel-Aal, E.-S.M., Rabalski, I. (2022). Changes in phenolic acids and antioxidant properties during baking of bread and muffin made from blends of hairless canary seed, wheat, and corn. Antioxidants, 11(6), Article 1059. https://doi.org/10.3390/antiox11061059.

5. Dall’Asta, M., Bresciani, L., Calani, L., Cossu, M., Martini, D., Melegari, C. et al. (2016). In vitro bioaccessibility of phenolic acids from a commercial aleuroneenriched bread compared to a whole grain bread. Nutrients, 8(1), Article 42. https://doi.org/10.3390/nu8010042.

6. Arya, S.S., Rookes, J.E., Cahill, D.M., Lenka, S.K. (2021). Vanillin: A review on the therapeutic prospects of a popular flavouring molecule. Advances in Traditional Medicine, 21(3), 1–17. https://doi.org/10.1007/s13596-020-00531-w.

7. Viretto, C., Tlais, A.Z.A., Arora, K., Ameur, H., Tuccillo, F., Polo, A. et al. (2025). Unraveling the functional potential of microbial resources and pulse-based matrices for sourdough breadmaking. Future Foods, 11, Article 100643. https://doi.org/10.1016/j.fufo.2025.100643.

8. Sanmartín, G., Sánchez-Adriá, I.E., Salvador, A., Prieto, J.A., Estruch, F., Randez- Gil, F. (2024). Quantitative assessment of volatile profile and sensory perception of artisan bread made in the city of Valencia. Foods, 13(23), Article 3872. https://doi.org/10.3390/foods13233872.

9. Huang, C., Huang, J., Zhang, B., Omedi, J.O., Chen, C., Zhou, L. et al. (2023). Rheo-fermentation dough properties, bread-making quality and aroma characteristics of red bean (Vigna angularis) sourdough induced by LAB Weissella confusa QS813 strain fermentation. Foods, 12(3), Article 605. https://doi.org/10.3390/foods12030605.

10. Mărgăoan, R., Cornea-Cipcigan, M., Topal, E., Kösoğlu, M. (2020). Impact of fermentation processes on the bioactive profile and health-promoting properties of bee bread, mead and honey vinegar. Processes, 8(9), Article 1081. https://doi.org/10.3390/pr8091081.

11. Aghababaei, F., Hadidi, M. (2023). Recent advances in potential health benefits of quercetin. Pharmaceuticals, 16(7), Article 1020. https://doi.org/10.3390/ph16071020.

12. Suchowilska, E., Bieńkowska, T., Stuper-Szablewska, K., Wiwart, M. (2020). Concentrations of phenolic acids, flavonoids and carotenoids and the antioxidant activity of the grain, flour and bran of Triticum polonicum as compared with three cultivated wheat species. Agriculture, 10(12), Article 591. https://doi.org/10.3390/agriculture10120591.

13. Wang, M., Firrman, J., Liu, L., Yam, K. (2019). A review on flavonoid apigenin: Dietary intake, ADME, antimicrobial effects, and interactions with human gut microbiota. BioMed Research International, 2019, Article 7010467. https://doi.org/10.1155/2019/7010467.

14. Kim, S.H., Park, J.G., Lee, J., Yang, W.S., Park, G.W., Kim, H.G. et al. (2015). The dietary flavonoid kaempferol mediates anti-inflammatory responses via the Src, Syk, IRAK1, and IRAK4 molecular targets. Mediators of Inflammation, 2015, Article 904142. https://doi.org/10.1155/2015/904142.

15. Ruiz-Álvarez, B.E., Padilla-de la Rosa, J.D., González Avila, M.G., Sandoval, G., Desjardins, Y. (2025). Novel acylated naringin enhances propionate release and stimulates the growth of flavanone-metabolizing bacteria in an in vitro batch fermentation model. Life, 15(6), Article 967. https://doi.org/10.3390/life15060967.

16. Tian, W., Chen, G., Tilley, M., Li, Y. (2021). Changes in phenolic profiles and antioxidant activities during the whole wheat bread-making process. Food Chemistry, 345, Article 128851. https://doi.org/10.1016/j.foodchem.2020.128851.

17. Yu, L., Beta, T. (2015). Identification and antioxidant properties of phenolic compounds during production of bread from purple wheat grains. Molecules, 20(9), 15525–15549. https://doi.org/10.3390/molecules200915525.

18. Czajkowska-González, Y.A., Alvarez-Parrilla, E., Martínez-Ruiz, N.R., Vázquez-Flores, A.A., Gaytán-Martínez, M., de la Rosa, L.A. (2021). Addition of phenolic compounds to bread: Antioxidant benefits and impact on food structure and sensory characteristics. Food Production, Processing and Nutrition, 3, Article 25. https://doi.org/10.1186/s43014-021-00068-8.

19. Liu, Y., Shi, L., Qiu, W., Shi, Y. (2022). Ferulic acid exhibits anti-inflammatory effects by inducing autophagy and blocking NLRP3 inflammasome activation. Molecular and Cellular Toxicology, 18(4), 509–519. https://doi.org/10.1007/s13273-021-00219-5.

20. Goya-Jorge, E., Jorge Rodríguez, M.E., Sylla-Iyarreta Veitía, M., Giner, R.M. (2021). Plant occurring flavonoids as modulators of the aryl hydrocarbon receptor. Molecules, 26(8), Article 2315. https://doi.org/10.3390/molecules26082315.

21. Jin, U.-H., Park, H., Li, X., Davidson, L.A., Allred, C., Patil, B. et al. (2018). Structure-dependent modulation of aryl hydrocarbon receptor-mediated activities by flavonoids. Toxicological Sciences, 164(1), 205–217. https://doi.org/10.1093/toxsci/kfy075.

22. Zhang, S., Qin, C., Safe, S.H. (2003). Flavonoids as aryl hydrocarbon receptor agonists/antagonists: Effects of structure and cell context. Environmental Health Perspectives, 111(16), 1877–1882. https://doi.org/10.1289/ehp.6322.

23. Zdrazil, B., Felix, E., Hunter, F., Manners, E.J., Blackshaw, J., Corbett, S. et al. (2024). The ChEMBL Database in 2023: A drug discovery platform spanning multiple bioactivity data types and time periods. Nucleic Acids Research, 52(D1), D1180-D1192. https://doi.org/10.1093/nar/gkad1004.

24. Rogers, D., Hahn, M. (2010). Extended-connectivity fingerprints. Journal of Chemical Information and Modeling, 50(5), 742–754. https://doi.org/10.1021/ci100050t.

25. Mayr, A., Klambauer, G., Unterthiner, T., Steijaert, M., Wegner, J.K., Ceulemans, H. et al. (2018). Large-scale comparison of machine learning methods for drug target prediction on ChEMBL. Chemical Science, 9(24), 5441–5451. https://doi.org/10.1039/c8sc00148k

26. Varma, S., Simon, R. (2006). Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics, 7, Article 91. https://doi.org/10.1186/1471-2105-7-91.

27. Westerman, K.E., Harrington, S., Ordovas, J.M., Parnell, L.D. (2020). PhyteByte: Identification of foods containing compounds with specific pharmacological properties. BMC Bioinformatics, 21, Article 238. https://doi.org/10.1186/s12859-020-03582-7.

28. Reker, D., Shi, Y., Kirtane, A.R., Hess, K., Zhong, G.J., Crane, E. et al. (2020). Machine learning uncovers food- and excipient-drug interactions. Cell Reports, 30(11), 3710–3716. https://doi.org/10.1016/j.celrep.2020.02.094.

29. Sanchez-Ruiz, A., Colmenarejo, G. (2022). Systematic Analysis and Prediction of the Target Space of Bioactive Food Compounds: Filling the Chemobiological Gaps. Journal of Chemical Information and Modeling, 62(16), 3734–3751. https://doi.org/10.1021/acs.jcim.2c00888

30. Periwal, V., Bassler, S., Andrejev, S., Gabrielli, N., Patil, K.R., Typas, A. et al. (2022). Bioactivity assessment of natural compounds using machine learning models trained on target similarity between drugs. PLoS Computational Biology, 18(4), Article e1010029. https://doi.org/10.1371/journal.pcbi.1010029.

31. Kuznetsov, M., Chernyavskaya, O., Kutuzov, M., Vilkova, D., Novichenko, O., Stolyarova, A. et al. (2025). Development of a predictive model for the biological activity of food and microbial metabolites toward estrogen receptor alpha (erα) using machine learning. Big Data and Cognitive Computing, 9(4), Article 86. https://doi.org/10.3390/bdcc9040086.

32. Kuznetsov, M., Klein, E., Velina, D., Mutallibzoda, S., Orlovtseva, O., Tefikova, S. et al. (2025). Using Machine learning for the discovery and development of multitarget flavonoid-based functional products in MASLD. Molecules, 30(21), Article 4159. https://doi.org/10.3390/molecules30214159.

33. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324