Machine Learning–Driven Discovery of Dietary Polyphenol DPP-4 Inhibitors via Molecular Docking
DOI:
https://doi.org/10.24114/ijcst.v9i2.75390Keywords:
Dietary polyphenols, Machine learning, Virtual screening, Molecular docking, Phenol-ExplorerAbstract
T2DM is a chronic metabolic disorder of rising global prevalence, in which DPP-4 serves as a key therapeutic target through its role in incretin hormone degradation. This study aimed to identify polyphenolic compounds derived from dietary sources as potential DPP-4 inhibitors through an in silico pipeline integrating machine learning (ML) and molecular docking. The bioactivity dataset for DPP-4 was retrieved from ChEMBL (CHEMBL284), processed into a binary classification dataset, and represented using 2048-bit Morgan fingerprints combined with five RDKit descriptors. Six ML models were integrated into a soft-voting ensemble, achieving a Matthews correlation coefficient (MCC) of 0.8334 and an AUC-ROC of 0.9739. Screening of 162 compounds from the Phenol-Explorer database yielded 11 potential active inhibitors. Molecular docking identified hesperetin (−8.548 kcal/mol) as the leading candidate, followed by pelargonidin, daidzein, and naringenin, with key binding residues including Ser209, Glu205/206, Tyr631, Arg125, and Tyr662.
References
1. Ji, Q., Chai, S., Zhang, R., Li, J., Zheng, Y., & Rajpathak, S. (2024). Prevalence and co-prevalence of comorbidities among Chinese adult patients with type 2 diabetes mellitus: a cross-sectional, multicenter, retrospective, observational study based on 3B study database. Frontiers in Endocrinology, 15. https://doi.org/10.3389/fendo.2024.1362433
2. Gheonea, T. C., Șurlin, P., Nicolae, F. M., Gheorghe, D. N., Popescu, D. M., & Rogoveanu, I. (2024). Dipeptidyl-Peptidase-4 and Glucagon-like-Peptide-1, a Link in the Connection between Periodontitis and Diabetes Mellitus—What Do We Know So Far?—A Scoping Review. Journal of Clinical Medicine, 13(3), 903. https://doi.org/10.3390/jcm13030903
3. Alrouji, M., Al-kuraishy, H. M., Al-buhadily, A. K., Al-Gareeb, A. I., Elekhnawy, E., & Batiha, G. E.-S. (2023). DPP-4 inhibitors and type 2 diabetes mellitus in Parkinson’s disease: a mutual relationship. Pharmacological Reports, 75(4), 923–936. https://doi.org/10.1007/s43440-023-00500-5
4. Zhang, J., Xu, S., Liu, X., Zhang, J., Hu, S., Liu, X., Yang, C., & Fang, Y. (2024). Time trends and regional variation in utilization of antidiabetic medicines in China, 2015–2022. Diabetes, Obesity and Metabolism, 26(7), 2752–2760. https://doi.org/10.1111/dom.15594
5. Karagiannis, T., Bekiari, E., & Tsapas, A. (2023). Socioeconomic aspects of incretin-based therapy. Diabetologia, 66(10), 1859–1868. https://doi.org/10.1007/s00125-023-05962-z
6. Aryal, D., Joshi, S., Thapa, N. K., Chaudhary, P., Basaula, S., Joshi, U., Bhandari, D., Rogers, H. M., Bhattarai, S., Sharma, K. R., Regmi, B. P., & Parajuli, N. (2024). Dietary phenolic compounds as promising therapeutic agents for diabetes and its complications: A comprehensive review. Food Science & Nutrition, 12(5), 3025–3045. https://doi.org/10.1002/fsn3.3983
7. Ansari, P., Samia, J. F., Khan, J. T., Rafi, M. R., Rahman, Md. S., Rahman, A. B., Abdel-Wahab, Y. H. A., & Seidel, V. (2023). Protective Effects of Medicinal Plant-Based Foods against Diabetes: A Review on Pharmacology, Phytochemistry, and Molecular Mechanisms. Nutrients, 15(14), 3266. https://doi.org/10.3390/nu15143266
8. Nazir, M., Haq, M. A., Ali, S. A., Ghufran Saeed, S. M., Ajmal, M. A., Nisar, M., Khan, T. A., Tsoupras, A., & Naz, S. (2025). Antioxidants and Antidiabetic Potential of Polyphenolic Fractions and Crude Extracts of Rhus typhina Fruit, Punica granatum L. Peel, and Terminalia catappa L. Leaves: In Vitro and In Vivo Evaluation. Chemistry & Biodiversity, 22(7). https://doi.org/10.1002/cbdv.202500020
9. D’Anna, L., Contino, S., Marinello, R., Fares, J., De Simone, G., Monari, A., Barbault, F., Barone, G., Terenzi, A., & Perricone, U. (2026). AGAPE (Computational G-Quadruplex Stabilization Prediction): The First Machine Learning Workflow for G-Quadruplex Stabilization Prediction. ACS Omega, 11(21), 31744–31756. https://doi.org/10.1021/acsomega.6c03072
10. Gadiya, Y., Genilloud, O., Bilitewski, U., Brönstrup, M., von Berlin, L., Attwood, M., Gribbon, P., & Zaliani, A. (2025). Predicting Antimicrobial Class Specificity of Small Molecules Using Machine Learning. Journal of Chemical Information and Modeling, 65(5), 2416–2431. https://doi.org/10.1021/acs.jcim.4c02347
11. Samanta, P. N., Majumdar, D., & Leszczynski, J. (2023). Elucidating Atomistic Insight into the Dynamical Responses of the SARS-CoV-2 Main Protease for the Binding of Remdesivir Analogues: Leveraging Molecular Mechanics To Decode the Inhibition Mechanism. Journal of Chemical Information and Modeling, 63(11), 3404–3422. https://doi.org/10.1021/acs.jcim.3c00105
12. Seal, S., Mahale, M., García-Ortegón, M., Joshi, C. K., Hosseini-Gerami, L., Beatson, A., Greenig, M., Shekhar, M., Patra, A., Weis, C., Mehrjou, A., Badré, A., Paisley, B., Lowe, R., Singh, S., Shah, F., Johannesson, B., Williams, D., Rouquie, D., … Bender, A. (2025). Machine Learning for Toxicity Prediction Using Chemical Structures: Pillars for Success in the Real World. Chemical Research in Toxicology, 38(5), 759–807. https://doi.org/10.1021/acs.chemrestox.5c00033
13. Rothwell, J. A., Perez-Jimenez, J., Neveu, V., Medina-Remon, A., M’Hiri, N., Garcia-Lobato, P., Manach, C., Knox, C., Eisner, R., Wishart, D. S., & Scalbert, A. (2013). Phenol-Explorer 3.0: a major update of the Phenol-Explorer database to incorporate data on the effects of food processing on polyphenol content. Database, 2013(0), bat070–bat070. https://doi.org/10.1093/database/bat070
14. Neveu, V., Perez-Jimenez, J., Vos, F., Crespy, V., du Chaffaut, L., Mennen, L., Knox, C., Eisner, R., Cruz, J., Wishart, D., & Scalbert, A. (2010). Phenol-Explorer: an online comprehensive database on polyphenol contents in foods. Database, 2010(0), bap024–bap024. https://doi.org/10.1093/database/bap024
15. Müller, S. (2025). How to crack a SMILES: automatic crosschecked chemical structure resolution across multiple services using MoleculeResolver. Journal of Cheminformatics, 17(1), 117. https://doi.org/10.1186/s13321-025-01064-7
16. Dolciami, D., Villasclaras-Fernandez, E., Kannas, C., Meniconi, M., Al-Lazikani, B., & Antolin, A. A. (2022). canSAR chemistry registration and standardization pipeline. Journal of Cheminformatics, 14(1), 28. https://doi.org/10.1186/s13321-022-00606-7
17. Montenegro-Herrera, S. A., Sosa, A., Echeverri-Jiménez, I., Castaño-Valencia, R. S., & Jerez-Valderrama, A. M. (2025). Machine Learning-Based QSAR Screening of Colombian Medicinal Flora for Potential Antiviral Compounds Against Dengue Virus: An In Silico Drug Discovery Approach. Pharmaceuticals, 18(12), 1906. https://doi.org/10.3390/ph18121906
18. Bickerton, G. R., Paolini, G. V., Besnard, J., Muresan, S., & Hopkins, A. L. (2012). Quantifying the chemical beauty of drugs. Nature Chemistry, 4(2), 90–98. https://doi.org/10.1038/nchem.1243
19. Shanbhogue, R. V., Gandhi, N. S., B., S. P., & Navada, S. G. (2026). Machine learning based approaches for structure activity relationship analysis of heparanase inhibitors. Scientific Reports. https://doi.org/10.1038/s41598-026-55098-4
20. Liu, K., Cui, H., Yu, X., Li, W., & Han, W. (2025). Predicting cardiotoxicity in drug development: A deep learning approach. Journal of Pharmaceutical Analysis, 15(8), 101263. https://doi.org/10.1016/j.jpha.2025.101263
21. Xia, X., Zhu, C., Zhong, F., & Liu, L. (2024). TransCDR: a deep learning model for enhancing the generalizability of drug activity prediction through transfer learning and multimodal data fusion. BMC Biology, 22(1), 227. https://doi.org/10.1186/s12915-024-02023-8
22. Han, S., & Jung, H. (2024). NATE: Non-pArameTric approach for Explainable credit scoring on imbalanced class. PLOS ONE, 19(12), e0316454. https://doi.org/10.1371/journal.pone.0316454
23. Al-Ahmari, S., & Nadeem, F. (2025). Improving Surgical Site Infection Prediction Using Machine Learning: Addressing Challenges of Highly Imbalanced Data. Diagnostics, 15(4), 501. https://doi.org/10.3390/diagnostics15040501
24. Almadhoun, M. B., & Burhanuddin, M. (2025). Optimizing Feature Selection and Machine Learning Algorithms for Early Detection of Prediabetes Risk: Comparative Study. JMIR Bioinformatics and Biotechnology, 6, e70621–e70621. https://doi.org/10.2196/70621
25. Burns, J. W., & Rogers, D. M. (2023). QuantumScents: Quantum-Mechanical Properties for 3.5k Olfactory Molecules. Journal of Chemical Information and Modeling, 63(23), 7330–7337. https://doi.org/10.1021/acs.jcim.3c01338
26. Vitalis, A., Parker, D., Radler, F., Vargas‐Rosales, P. A., Zhang, Y., Marchand, J., & Caflisch, A. (2025). Parallelized Tools for the Preparation and Curation of Large Libraries for Virtual Screening. Journal of Computational Chemistry, 46(7). https://doi.org/10.1002/jcc.70074
27. Astigarraga, M., Sánchez-Ruiz, A., & Colmenarejo, G. (2025). Conformal Prediction-based Machine Learning in Cheminformatics: Current Applications and New Challenges. https://doi.org/10.26434/chemrxiv-2025-p36vt
28. Noorunnahar, M., Chowdhury, A. H., & Mila, F. A. (2023). A tree based eXtreme Gradient Boosting (XGBoost) machine learning model to forecast the annual rice production in Bangladesh. PLOS ONE, 18(3), e0283452. https://doi.org/10.1371/journal.pone.0283452
29. Acosta-Murillo, R., Ortiz-Bayliss, J. C., & Zapata-Morin, P. A. (2026). Enhancing cancer drug discovery: QSAR modeling with machine learning and chemical representations. PLOS One, 21(3), e0343654. https://doi.org/10.1371/journal.pone.0343654
30. Yang, S., Li, S., & Chang, J. (2022). Discovery of Cobimetinib as a novel A-FABP inhibitor using machine learning and molecular docking-based virtual screening. RSC Advances, 12(21), 13500–13510. https://doi.org/10.1039/D2RA01057G
31. Chirila, C.-B., & Crisan, L. (2026). Harnessing machine learning models to repurpose drugs targeting HIV-1 integrase, protease, and reverse transcriptase. Scientific Reports, 16(1), 18146. https://doi.org/10.1038/s41598-026-48926-0
32. Bagdad, Y., Sisquellas, M., Arthur, M., & Miteva, M. A. (2024). Machine Learning and Deep Learning Models for Predicting Noncovalent Inhibitors of AmpC β-Lactamase. ACS Omega, 9(40), 41334–41342. https://doi.org/10.1021/acsomega.4c03834
33. Goldwaser, E., Laurent, C., Lagarde, N., Fabrega, S., Nay, L., Villoutreix, B. O., Jelsch, C., Nicot, A. B., Loriot, M.-A., & Miteva, M. A. (2022). Machine learning-driven identification of drugs inhibiting cytochrome P450 2C9. PLOS Computational Biology, 18(1), e1009820. https://doi.org/10.1371/journal.pcbi.1009820
34. Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research, 16, 321–357. https://doi.org/10.1613/jair.953
35. Rai, M., Singh, A. V., Paudel, N., Kanase, A., Falletta, E., Kerkar, P., Heyda, J., Barghash, R. F., Pratap Singh, S., & Soos, M. (2023). Herbal concoction Unveiled: A computational analysis of phytochemicals’ pharmacokinetic and toxicological profiles using novel approach methodologies (NAMs). Current Research in Toxicology, 5, 100118. https://doi.org/10.1016/j.crtox.2023.100118
36. Abdelrahman, A. H. M., Mekhemer, G. A. H., Sidhom, P. A., El-Tayeb, M. A., Khan, S., & Ibrahim, M. A. A. (2025). Exploration of African natural products as VP35 inhibitors to combat Marburg virus infection: Molecular docking, molecular dynamics, and quantum mechanical computations. PLOS One, 20(10), e0334160. https://doi.org/10.1371/journal.pone.0334160
37. Akinnusi, P. A., Olubode, S. O., Alade, A. A., Ashimi, A. A., Onawola, O. L., Agbolade, A. O., Emeka, A. P., Shodehinde, S. A., & Adeniran, O. Y. (2023). Potential Inhibitory Biomolecular Interactions of Natural Compounds With Different Molecular Targets of Diabetes. Bioinformatics and Biology Insights, 17. https://doi.org/10.1177/11779322231167970
38. Tsahnang Fofack, H. M., Mbah Bake, M., Petry, S., Ateba, B. A., Amoa Onguéné, P., Mohammad-Salim, H., Ntie-Kang, F., Mbaze, L. M., Vakal, S., & Kenfack, C. A. (2024). Identification of potential dipeptidyl peptidase IV inhibitors from the ConMedNP library by virtual screening, and molecular dynamics methods. Heliyon, 10(15), e35191. https://doi.org/10.1016/j.heliyon.2024.e35191
39. Antony, P., Baby, B., Aleissaee, H. M., & Vijayan, R. (2022). A Molecular Modeling Investigation of the Therapeutic Potential of Marine Compounds as DPP-4 Inhibitors. Marine Drugs, 20(12), 777. https://doi.org/10.3390/md20120777
40. Zhao, Z., Ma, R., Ma, Y., Zhao, L., Wang, L., Fang, Y., Zhang, Y., Wu, X., & Wang, X. (2024). Discovery of Nine Dipeptidyl Peptidase-4 Inhibitors from Coptis chinensis Using Virtual Screening, Bioactivity Evaluation, and Binding Studies. Molecules, 29(10), 2304. https://doi.org/10.3390/molecules29102304
41. Dăescu, D.-I., Păușescu, I., Benea, I. C., Peter, F., Todea, A., Zappaterra, F., Alexa, A. A., & Buzatu, A. R. (2024). Natural and Synthetic Flavylium Derivatives: Isolation/Synthesis, Characterization and Application. Molecules, 30(1), 90. https://doi.org/10.3390/molecules30010090
42. Bayanati, M., Ismail Mahboubi Rabbani, M., Sirous Kabiri, S., Mir, B., Rezaee, E., & Tabatabai, S. A. (2024). Dipeptidyl Peptidase-4 Inhibitors: A Systematic Review of Structure-Activity Relationship Studies. Iranian Journal of Pharmaceutical Research, 23(1). https://doi.org/10.5812/ijpr-151581
43. Mkabayi, L., Viljoen, Z., Krause, R. W. M., Lobb, K. A., Pletschke, B. I., & Frost, C. L. (2024). Inhibitory effects of selected cannabinoids against dipeptidyl peptidase IV, an enzyme linked to type 2 diabetes. Heliyon, 10(1), e23289. https://doi.org/10.1016/j.heliyon.2023.e23289
44. Desantis, F., Miotto, M., Di Rienzo, L., Milanetti, E., & Ruocco, G. (2022). Spatial organization of hydrophobic and charged residues affects protein thermal stability and binding affinity. Scientific Reports, 12(1), 12087. https://doi.org/10.1038/s41598-022-16338-5
45. Ayaz, M., Alam, A., Zainab, Elhenawy, A. A., Ahmad, I., Rahman, S. U., Ali, L., Latif, A., Ali, M., & Ahmad, M. (2026). Exploring the anti-diabetic potential of bis-Schiff bases of ibuprofen: insights into the in vitro , molecular docking and density functional theory analyses. RSC Advances, 16(12), 11005–11022. https://doi.org/10.1039/D5RA03358F
46. Khalil, I., Zaman, S., Aliza, I. J., Rahman Tanny, M., Hasan, T., & Uzzaman, M. (2026). Structural tuning of diclofenac for enhanced medicinal efficacy and reduced adverse effects: an integrating computational validation. RSC Advances, 16(26), 23740–23753. https://doi.org/10.1039/D6RA01053A
47. Ojeda‐Montes, M. J., Gimeno, A., Tomas‐Hernández, S., Cereto‐Massagué, A., Beltrán‐Debón, R., Valls, C., Mulero, M., Pujadas, G., & Garcia‐Vallvé, S. (2017). Activity and selectivity cliffs for DPP‐IV inhibitors: Lessons we can learn from SAR studies and their application to virtual screening. Medicinal Research Reviews, 38(6), 1874–1915. https://doi.org/10.1002/med.21499
48. Baziyar, L., Solhjoo, A., Kamran, A., Mardaneh, P., Khabnadideh, S., Emami, M., Emami, L., & Rezaei, Z. (2025). Cytotoxic investigation of some Quinazoline-4 amino piperidine derivatives as DPP4 inhibitors along with molecular dynamic simulation studies. Results in Chemistry, 18, 102779. https://doi.org/10.1016/j.rechem.2025.102779
49. Clemente-Suárez, V. J., Martín-Rodríguez, A., Beltrán-Velasco, A. I., Rubio-Zarapuz, A., Martínez-Guardado, I., Valcárcel-Martín, R., & Tornero-Aguilera, J. F. (2025). Functional and Therapeutic Roles of Plant-Derived Antioxidants in Type 2 Diabetes Mellitus: Mechanisms, Challenges, and Considerations for Special Populations. Antioxidants, 14(6), 725. https://doi.org/10.3390/antiox14060725
50. Sarkar, D., Christopher, A., & Shetty, K. (2022). Phenolic Bioactives From Plant-Based Foods for Glycemic Control. Frontiers in Endocrinology, 12. https://doi.org/10.3389/fendo.2021.727503
