Desarrollo de modelos QSAR por redes neuronales para la estimación de potenciales inhibidores de a-glucosidasa de fenólicos encontrados en matrices alimentarias
DOI:
https://doi.org/10.29059/cienciauat.v20i1.2041Palabras clave:
red neuronal, modelo de predicción, acoplamiento molecular, compuestos fenólicos, inhibición enzimáticaResumen
La a-glucosidasa es una enzima clave en la digestión de carbohidratos, y su inhibición representa una estrategia terapéutica para el control de la diabetes tipo 2. El objetivo del presente estudio fue desarrollar un modelo QSAR mediante una red neuronal (RNA) y acoplamiento molecular para estimar la inhibición de a-glucosidasa por compuestos fenólicos encontrados en matrices alimentarias (CF-MA). La RNA se construyó para estimar el valor de pIC50 a partir de CF-MA, utilizando distintas configuraciones de neuronas en la capa oculta. La mejor estimación de pIC50 se logró empleando un diseño de RNA con 7 neuronas en la capa oculta y dos descriptores moleculares (SpMin7_Bhm, AATSC5s). El acoplamiento molecular se realizó entre la a-glucosidasa (isomaltasa) y las móleculas de compuestos fenólicos que presentaron valores de pIC50 iguales o superiores a la acarbosa (n = 17). El modelo estimó que la naringina (-1.96) y la quercetina 3,4'-O-diglucósido diglucósido (-1.96) presentaron mayor energía libre de afinidad (-10.6 kcal/mol y -10.4 kcal/mol, respectivamente) frente a la a-glucosidasa, superando al control acarbosa (pIC50 = -2.00; y energía libre de afinidad -9.8 kcal/mol). La combinación de RNA y acoplamiento molecular permitió desarrollar una herramienta valiosa para estimar el potencial inhibitorio de los compuestos fenólicos frente a la enzima de a-glucosidasa.
Citas
Alongi, M., Frías-Celayeta, J. M., Vriz, R., Kinsella, G. K., Rulikowska, A., & Anese, M. (2021). In vitro digestion nullified the differences triggered by roasting in phenolic composition and a-glucosidase inhibitory capacity of coffee. Food Chemistry, 342, 128289. https://doi.org/10.1016/j.foodchem.2020.128289
Burden, F. R. (1989). Molecular identification number for substructure searches. Journal of Chemical Information and Computer Sciences, 29(3), 225-227. https://doi.org/10.1021/ci00063a011
Chapman, J., Truong, V. K., & Cozzolino, D. (2022). Artificial intelligence applied to healthcare and biotechnology. In D. Barh (Ed.), Biotechnology in Healthcare: Technologies and Innovations (pp. 249-257). Elsevier. https://doi.org/10.1016/B978-0-323-89837-9.00001-2
Chen, J. G., Wu, S. F., Zhang, Q. F., Yin, Z. P., & Zhang, L. (2020). a-Glucosidase inhibitory effect of anthocyanins from Cinnamomum camphora fruit: Inhibition kinetics and mechanistic insights through in vitro and in silico studies. International Journal of Biological Macromolecules, 143, 696-703. https://doi.org/10.1016/j.ijbiomac.2019.09.091
Cherkasov, A., Muratov, E. N., Fourches, D., Varnek, A., Baskin, I. I., Cronin, M., Dearden, J., Gramatica, P., Martin, Y. C., Todeschini, R., Consonni, V., Kuz’Min, V. E., Cramer, R., Benigni, R., Yang, C., Rathman, J., Terfloth, L., Gasteiger, J., Richard, A., & Tropsha, A. (2014). QSAR modeling: Where have you been? Where are you going to? Journal of Medicinal Chemistry, 57(12), 4977-5010. https://doi.org/10.1021/jm4004285
Daoui, O., Mkhayar, K., Elkhattabi, S., Chtita, S., Zgou, H., & Elkhalabi, R. (2022). Design of novel carbocycle-fused quinoline derivatives as potential inhibitors of lymphoblastic leukemia cell line MOLT-3 using 2D-QSAR and ADME-Tox studies. RHAZES: Green and Applied Chemistry, 14(0), 36-61. https://doi.org/10.48419/IMIST.PRSM/RHAZES-V14.31152
Doungwichitrkul, T., Damsud, T., & Phuwapraisirisan, P. (2024). a-Glucosidase Inhibitors from Cold-Pressed Black Sesame (Sesamum indicum) Meal: Characterization of New Furofuran Lignans, Kinetic Study, and In Vitro Gastrointestinal Digestion. Journal of Agricultural and Food Chemistry, 72(2), 1044-1054. https://doi.org/10.1021/acs.jafc.3c04159
El-fadili, M., Er-rajy, M., Imtara, H., Noman, O. M., Mothana, R. A., Abdullah, S., Zerougui, S., & Elhallaoui, M. (2023). QSAR, ADME-Tox, molecular docking and molecular dynamics simulations of novel selective glycine transporter type 1 inhibitors with memory enhancing properties. Heliyon, 9(2), e13706. https://doi.org/10.1016/j.heliyon.2023.e13706
Emonts, J. & Buyel, J. F. (2023). An overview of descriptors to capture protein properties – Tools and perspectives in the context of QSAR modeling. Computational and Structural Biotechnology Journal, 21, 3234–3247. https://doi.org/10.1016/J.CSBJ.2023.05.022
European Bioinformatics Institute (2025). Base de datos ChEMBL. [En línea]. Disponible en: https://www.ebi.ac.uk/chembl/. Fecha de consulta: 15 de marzo de 2025.
Gálvez, J., Garcia, R., Salabert, M. T., & Soler, R. (2002). Charge Indexes. New Topological Descriptors. Journal of Chemical Information and Computer Sciences, 34(3), 520–525. https://doi.org/10.1021/CI00019A008
Guan, L., Long, H., Ren, F., Li, Y., & Zhang, H. (2022). A Structure—Activity Relationship Study of the Inhibition of a-Amylase by Benzoic Acid and Its Derivatives. Nutrients, 14(9), 1931. https://doi.org/10.3390/NU14091931/S1
Gupta, R., Srivastava, D., Sahu, M., Tiwari, S., Ambasta, R. K., & Kumar, P. (2021). Artificial intelligence to deep learning: machine intelligence approach for drug discovery. Molecular Diversity, 25(3), 13151360. https://doi.org/10.1007/s11030-021-10217-3
Hossain, U., Das, A. K., Ghosh, S., & Sil, P. C. (2020). An overview on the role of bioactive a-glucosidase inhibitors in ameliorating diabetic complications. Food and Chemical Toxicology, 145, 111738. https://doi.org/10.1016/j.fct.2020.111738
Hung, C. & Gini, G. (2021). QSAR modeling without descriptors using graph convolutional neural networks: the case of mutagenicity prediction. Molecular Diversity, 25(3), 1283-1299. https://doi.org/10.1007/s11030-021-10250-2
Javaid, M., Haleem, A., Singh, R. P., & Suman, R. (2022). Artificial Intelligence Applications for Industry 4.0: A Literature-Based Study. Journal of Industrial Integration and Management, 7(1), 83-111. https://doi.org/10.1142/S2424862221300040
Manach, C., Scalbert, A., Morand, C., Rémésy, C., & Jiménez, L. (2004). Polyphenols: food sources and bioavailability. The American Journal of Clinical Nutrition, 79(5), 727-747. https://doi.org/10.1093/AJCN/79.5.727
Mehmood, R., Mughal, E. U., Elkaeed, E. B., Obaid, R. J., Nazir, Y., Al-Ghulikah, H. A., Al-Ghulikah, H., Naeem, N., Munirah M. Al-Rooqi, Ahmed, S. A., Wadood-Shah, A. S., & Sadiq, A. (2022). Synthesis of Novel 2,3-Dihydro-1,5-Benzothiazepines as a-Glucosidase Inhibitors: In Vitro, In Vivo, Kinetic, SAR, Molecular Docking, and QSAR Studies. ACS Omega, 7(34), 30215-30232. https://doi.org/10.1021/acsomega.2c03328
Minitab Support. (2023). Interpretar todos los estadísticos y gráficas para Correlación. Minitab. [En línea]. Disponible en: https://support.minitab.com/es-mx/minitab/help-and-how-to/statistics/basic-statistics/how-to/correlation/interpret-the-results/all-statistics-and-graphs/ Fecha de consulta: 16 de octubre de 2025.
National Library of Medicine (2025). PubChem. [En línea]. Disponible en: https://pubchem.ncbi.nlm.nih.gov. Fecha de consulta: 15 de marzo de 2025.
Neveu, V., Perez-Jiménez, 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 : The Journal of Biological Databases and Curation, 2010. https://doi.org/10.1093/DATABASE/BAP024
Nile, A., Gansukh, E., Park, G. S., Kim, D. H., & Nile, S. H. (2021). Novel insights on the multi-functional properties of flavonol glucosides from red onion (Allium cepa L) solid waste – In vitro and in silico approach. Food Chemistry, 335, 127650. https://doi.org/10.1016/J.FOODCHEM.2020.127650
Nirwan, S., Chahal, V., & Kakkar, R. (2022). A comparative study of different docking methodologies to assess the proteinligand interaction for the E. coli MurB enzyme. Journal of Biomolecular Structure & Dynamics, 40(21), 11229-11238. https://doi.org/10.1080/07391102.2021.1957019
Patra, J. C. & Chua, K. H. K. (2010). Neural network based drug design for diabetes mellitus using QSAR with 2D and 3D descriptors. The 2010 International Joint Conference on Neural Networks (IJCNN), 1-8. https://doi.org/10.1109/IJCNN.2010.5596935
Phenol-Explorer (2025). Base de datos sobre compuestos fenólicos en alimentos. [En línea]. Disponible en: http://phenol-explorer.eu/. Fecha de consulta: 16 de marzo de 2025.
Pinzi, L. & Rastelli, G. (2019). Molecular Docking: Shifting Paradigms in Drug Discovery. International Journal of Molecular Sciences, 20(18), 4331. https://doi.org/10.3390/ijms20184331
Poovitha, S., & Parani, M. (2016). In vitro and in vivo a-amylase and a-glucosidase inhibiting activities of the protein extracts from two varieties of bitter gourd (Momordica charantia L.). BMC Complementary and Alternative Medicine, 16(S1), 185. https://doi.org/10.1186/s12906-016-1085-1
RCSB Protein Data Bank (2025). Banco de Datos de Proteínas RCSB. [En línea]. Disponible en: https://www.rcsb.org. Fecha de consulta: 15 de marzo de 2025.
Rosenfeld, R., Vajda, S., & DeLisi, C. (1995). Flexible docking and design. Annual Review of Biophysics and Biomolecular Structure, 24(1), 677-700.https://doi.org/10.1146/ANNUREV.BB.24.060195.003333/CITE/REFWORKS
Rothwell, J. A., Perez-Jimenez, J., Neveu, V., Medina-Remón, A., M’Hiri, N., García-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. https://doi.org/10.1093/DATABASE/BAT070
Rusinko, A., Rezaei, M., Friedrich, L., Buchstaller, H. P., Kuhn, D., & Ghogare, A. (2024). AIDDISON: Empowering Drug Discovery with AI/ML and CADD Tools in a Secure, Web-Based SaaS Platform. Journal of Chemical Information and Modeling, 64(1), 3-8. https://doi.org/10.1021/acs.jcim.3c01016
Sahnoun, M., Trabelsi, S., & Bejar, S. (2017). Citrus flavonoids collectively dominate the a-amylase and a-glucosidase inhibitions. Biologia (Poland), 72(7), 764-773. https://doi.org/10.1515/biolog-2017-0091
Sim, L., Willemsma, C., Mohan, S., Naim, H. Y., Pinto, B. M., & Rose, D. R. (2010). Structural Basis for Substrate Selectivity in Human Maltase-Glucoamylase and Sucrase-Isomaltase N-terminal Domains. The Journal of Biological Chemistry, 285(23), 17763. https://doi.org/10.1074/JBC.M109.078980
Salazar-López, N. J., López-Rodríguez, C. V., Hernández-Montoya, D. A., & Campos-Vega, R. (2020). Health Benefits of Spent Coffee Grounds. In Food Wastes and By-products, 327-351). https://doi.org/10.1002/9781119534167.ch11
Simeon, S. & Jongkon, N. (2019). Construction of Quantitative Structure Activity Relationship (QSAR) Models to Predict Potency of Structurally Diversed Janus Kinase 2 Inhibitors. Molecules 24(23), 4393 https://doi.org/10.3390/MOLECULES24234393
Singh, P., Kumar, R., Sharma, B. K., & Prabhakar, Y. S. (2009). Topological descriptors in modeling malonyl coenzyme A decarboxylase inhibitory activity: N-Alkyl-N-(1,1,1,3,3,3-hexafluoro-2-hydroxypro-pylphenyl) amide derivatives. Journal of Enzyme Inhibition and Medicinal Chemistry, 24(1), 77–85. https://doi.org/10.1080/14756360801915336
Şöhretoğlu, D., Renda, G., Arroo, R., Xiao, J., & Sari, S. (2023). Advances in the natural a-glucosidase inhibitors. EFood, 4(5). https://doi.org/10.1002/efd2.112
Taiwo, A. E., Okoji, A. I., Eloka-Eboka, A. C., & Musonge, P. (2022). The role of artificial neural networks in bioproduct development: a case of modeling and optimization studies. Current Trends and Advances in Computer-Aided Intelligent Environmental Data Engineering, 417-431. https://doi.org/10.1016/B978-0-323-85597-6.00007-0
Todeschini, R. & Consonni, V. (2009). Molecular Descriptors for Chemoinformatics: Volume I: Alphabetical Listing (Second edition). Wiley-VCH.
Tolmie, M., Bester, M. J., & Apostolides, Z. (2021). Inhibition of a-glucosidase and a-amylase by her-bal compounds for the treatment of type 2 diabetes: A validation of in silico reverse docking with in vitro enzyme assays. Journal of Diabetes, 13(10), 779-791. https://doi.org/10.1111/1753-0407.13163
Tropsha, A. (2010). Best Practices for QSAR Mo-del Development, Validation, and Exploitation. Molecular Informatics, 29(6-7), 476-488. https://doi.org/10.1002/MINF.201000061
Wang, Z., Li, S., Ge, S., & Lin, S. (2020). Review of Distribution, Extraction Methods, and Health Benefits of Bound Phenolics in Food Plants. Journal of Agricultural and Food Chemistry, 68(11), 3330-3343. https://doi.org/10.1021/acs.jafc.9b06574
Xiangju, Z., Yuqin, C., Zhongping, Y., Qi, L., Jianwei, Z., Daobang, T., Jiguang, C., Xiangju, Z., Yuqin, C., Zhongping, Y., Qi, L., Jianwei, Z., Daobang, T., & Jiguang, C. (2022). Inhibitory Effect of Naringin on a-Glucosidase and Its Mechanism. Science and Technology of Food Industry, 43(8), 157-164. https://doi.org/10.13386/J.ISSN1002-0306.2021080184
Xu, Y. (2022). Deep neural networks for QSAR. In A. Heifetz (Ed.), Artificial intelligence in drug design (pp. 233-260). Humana. https://doi.org/10.1007/978-1-0716-1787-8_10
Yamamoto, K., Miyake, H., Kusunoki, M., & Osaki, S. (2010). Crystal structures of isomaltase from Saccharomyces cerevisiae and in complex with its competitive inhibitor maltose. FEBS Journal, 277(20), 4205-4214. https://doi.org/10.1111/j.1742-4658.2010.07810.x
Yap, C. W. (2011). PaDEL-descriptor: An open source software to calculate molecular descriptors and fingerprints. Journal of Computational Chemistry, 32(7), 1466-1474. https://doi.org/10.1002/JCC.21
707
Yoshikawa, T., Mifune, Y., Inui, A., Nishimoto, H., Yamaura, K., Mukohara, S., Shinohara, I., & Kuroda, R. (2022). Quercetin treatment protects the Achilles tendons of rats from oxidative stress induced by hyperglycemia. BMC Musculoskeletal Disorders, 23(1), 563. https://doi.org/10.1186/s12891-02205513-4
Yue, L. M., Lee, J., Zheng, L., Park, Y. D., Ye, Z. M., & Yang, J. M. (2017). Computational prediction integrating the inhibition kinetics of gallotannin on a-glucosidase. International Journal of Biological Macromolecules, 103, 829-838. https://doi.org/10.1016/j.ijbiomac.2017.05.106
Zdrazil, B., Felix, E., Hunter, F., Manners, E. J., Blackshaw, J., Corbett, S., de-Veij, M., Ioannidis, H., Lopez, D. M., Mosquera, J. F., Magarinos, M. P., Bosc, N., Arcila, R., Kizilören, T., Gaulton, A., Bento, A. P., Adasme, M. F., Monecke, P., Landrum, G. A., & Leach, A. R. (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
Zerroug, E., Belaidi, S., & Chtita, S. (2021). Artificial neural network-based quantitative structure–activity relationships model and molecular docking for virtual screening of novel potent acetylcholines-terase inhibitors. Journal of the Chinese Chemical Society, 68(8), 1379-1399. https://doi.org/10.1002/jccs.202000457
Publicado
Cómo citar
Número
Sección
Categorías
Licencia
Derechos de autor 2025 Universidad Autónoma de Tamaulipas
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
Aceptado 2025-11-13
Publicado 2025-11-19
