{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T10:54:55Z","timestamp":1791284095937,"version":"4.1.0"},"reference-count":33,"publisher":"Aboutscience Srl","issue":"1","license":[{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["dti"],"abstract":"<jats:p>Introduction: \u03b1-Glucosidase inhibitors (AGIs) are essential for controlling postprandial hyperglycemia, with flavonoids representing a major class of natural AGIs. However, conventional quantitative structure\u2013activity relationship (QSAR) models trained on structurally diverse datasets often exhibit limited predictive reliability for natural flavonoids due to chemical space mismatch. This study aimed to develop and optimize Random Forest\u2013based QSAR models derived from ChEMBL AGIs and to evaluate their chemotype-specific applicability to natural flavonoids.Methods: ChEMBL-derived inhibitors were curated into two datasets: (i) a general scaffold-diverse dataset and (ii) a flavonoid-specific dataset. A custom RDKit-based pipeline employing SMARTS pattern recognition and fingerprint similarity automatically classified flavonoid chemotypes while excluding nonphenolic compounds. Molecular descriptors were calculated using Mordred. Regression and classification models were constructed with 10-fold cross-validation. External validation was performed using 15 literature-reported natural flavonoids categorized into flavones\/flavonols (aglycones), flavonol glycosides, isoflavones, and flavan-3-ols.Results: The general model (n = 563) demonstrated strong regression performance (R2 = 0.837) and classification accuracy (0.915). The flavonoid-specific model showed moderate regression (R2 = 0.564) and classification accuracy (0.880). However, external validation revealed superior predictive reliability of the flavonoid-specific model, particularly for catechins (MAE = 0.182) and aglycones (MAE = 0.233). Predictive performance decreased for glycosides and isoflavones.Conclusion: Chemotype-focused QSAR modeling enhances predictive reliability for natural flavonoids. The optimized flavonoid-specific model is suitable for predicting pIC50 of flavones and flavonols but should be applied cautiously to glycosylated or structurally divergent subclasses.<\/jats:p>","DOI":"10.33393\/dti.2026.3763","type":"journal-article","created":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T10:31:20Z","timestamp":1791282680000},"page":"46-54","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing ChEMBL-derived QSAR models for natural flavonoid screening: chemotype-specific predictive reliability in \u03b1-glucosidase-inhibition"],"prefix":"10.33393","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0350-6819","authenticated-orcid":false,"given":"Radhiah","family":"Zakaria","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8060-7088","authenticated-orcid":false,"given":"Muhammad","family":"Iqhrammullah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8272-754X","authenticated-orcid":false,"given":"Bryan Gervais","family":"De Liyis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9915-3749","authenticated-orcid":false,"given":"Anggi","family":"Susilawati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0254-1920","authenticated-orcid":false,"given":"Nizam","family":"Albar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1081-3758","authenticated-orcid":false,"given":"Andriy Anta","family":"Kacaribu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6372-8240","authenticated-orcid":false,"given":"Muhammad","family":"Habiburrahman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"18642","published-online":{"date-parts":[[2026,10,5]]},"reference":[{"key":"21059","doi-asserted-by":"crossref","unstructured":"Mushtaq A, Azam U, Mehreen S, et al. Synthetic \u03b1-glucosidase inhibitors as promising anti-diabetic agents: recent developments and future challenges. Eur J Med Chem. 2023;249:115119. https:\/\/doi.org\/10.1016\/j.ejmech.2023.115119 PMID:36680985","DOI":"10.1016\/j.ejmech.2023.115119"},{"key":"21060","doi-asserted-by":"crossref","unstructured":"Agrawal N, Sharma M, Singh S, et al. Recent advances of \u03b1-glucosidase inhibitors: a comprehensive review. Curr Top Med Chem. 2022;22(25):2069-2086. https:\/\/doi.org\/10.2174\/1568026622666220831092855 PMID:36045528","DOI":"10.2174\/1568026622666220831092855"},{"key":"21061","doi-asserted-by":"crossref","unstructured":"Patel P, Shah D, Bambharoliya T, et al. A review on the development of novel heterocycles as \u03b1-glucosidase inhibitors for the treatment of type-2 diabetes mellitus. Med Chem. 2024;20(5):503-536. https:\/\/doi.org\/10.2174\/0115734064264591231031065639 PMID:38275074","DOI":"10.2174\/0115734064264591231031065639"},{"key":"21062","doi-asserted-by":"crossref","unstructured":"Chen Y, Xiao Y, Lian G, et al. Pneumatosis intestinalis associated with \u03b1-glucosidase inhibitors: a pharmacovigilance study of the FDA adverse event reporting system from 2004 to 2022. Expert Opin Drug Saf. 2023;1-10. https:\/\/doi.org\/10.1080\/14740338.2023.2278708 PMID:37929311","DOI":"10.1080\/14740338.2023.2278708"},{"key":"21063","doi-asserted-by":"crossref","unstructured":"Riyaphan J, Pham DC, Leong MK, et al. In silico approaches to identify polyphenol compounds as \u03b1-glucosidase and \u03b1-amylase inhibitors against type-II diabetes. Biomolecules. 2021;11(12):1877. https:\/\/doi.org\/10.3390\/biom11121877 PMID:34944521","DOI":"10.3390\/biom11121877"},{"key":"21064","doi-asserted-by":"crossref","unstructured":"Benjamin MAZ, Mohd Mokhtar RA, Iqbal M, et al. Medicinal plants of Southeast Asia with anti-\u03b1-glucosidase activity as potential source for type-2 diabetes mellitus treatment. J Ethnopharmacol. 2024;330:118239. https:\/\/doi.org\/10.1016\/j.jep.2024.118239 PMID:38657877","DOI":"10.1016\/j.jep.2024.118239"},{"key":"21065","doi-asserted-by":"crossref","unstructured":"Lam TP, Tran NN, Pham LD, et al. Flavonoids as dual-target inhibitors against \u03b1-glucosidase and \u03b1-amylase: a systematic review of in vitro studies. Nat Prod Bioprospect. 2024;14(1):4. https:\/\/doi.org\/10.1007\/s13659-023-00424-w PMID:38185713","DOI":"10.1007\/s13659-023-00424-w"},{"key":"21066","doi-asserted-by":"crossref","unstructured":"Barber E, Houghton MJ, Williamson G. Flavonoids as human intestinal \u03b1-glucosidase inhibitors. Foods. 2021;10(8):1939. https:\/\/doi.org\/10.3390\/foods10081939 PMID:34441720","DOI":"10.3390\/foods10081939"},{"key":"21067","doi-asserted-by":"crossref","unstructured":"Di\u00e9guez-Santana K, Puris A, Rivera-Borroto OM, et al. A fuzzy system classification approach for QSAR modeling of \u03b1-amylase and \u03b1-Glucosidase Inhibitors. Curr Comput Aided Drug Des. 2022;18(7):469-479. https:\/\/doi.org\/10.2174\/1573409918666220929124820 PMID:36177632","DOI":"10.2174\/1573409918666220929124820"},{"key":"21068","doi-asserted-by":"crossref","unstructured":"Yang T, Yang Z, Pan F, et al. Construction of an MLR-QSAR model based on dietary flavonoids and screening of natural \u03b1-glucosidase inhibitors. Foods. 2022;11(24):4046. https:\/\/doi.org\/10.3390\/foods11244046 PMID:36553788","DOI":"10.3390\/foods11244046"},{"key":"21069","doi-asserted-by":"crossref","unstructured":"Amini F, Abbas KI, Ghasemi JB. Molecular modeling approach in design of new scaffold of \u03b1-glucosidase inhibitor as antidiabetic drug. Biochem Biophys Rep. 2025;42:101995. https:\/\/doi.org\/10.1016\/j.bbrep.2025.101995 PMID:40248138","DOI":"10.1016\/j.bbrep.2025.101995"},{"key":"21070","doi-asserted-by":"crossref","unstructured":"Noviandy TR, Idroes GM, Maulana A, et al. Optimizing hepatitis C virus inhibitor identification with LightGBM and tree-structured parzen estimator sampling. Engineering, Technology & Applied Science Research. 2024;14(6):18810-18817. https:\/\/doi.org\/10.48084\/etasr.8947","DOI":"10.48084\/etasr.8947"},{"key":"21071","doi-asserted-by":"crossref","unstructured":"Idroes GM, Noviandy TR, Idroes GM, et al. Prognostication of differentiated thyroid cancer recurrence: an explainable machine learning approach. Narra X. 2024;2(3):e183-e183. https:\/\/doi.org\/10.52225\/narrax.v2i3.183","DOI":"10.52225\/narrax.v2i3.183"},{"key":"21072","doi-asserted-by":"crossref","unstructured":"Priyanto D, Hairani H, Marzuki K, et al. Optimization of Random Forest for health data classification using PCA and K-Means SMOTE-ENN. Engineering, Technology & Applied Science Research. 2025;15(5):27646-27652. https:\/\/doi.org\/10.48084\/etasr.12976","DOI":"10.48084\/etasr.12976"},{"key":"21073","doi-asserted-by":"crossref","unstructured":"Moriwaki H, Tian YS, Kawashita N, et al. Mordred: a molecular descriptor calculator. J Cheminform. 2018;10(1):4. https:\/\/doi.org\/10.1186\/s13321-018-0258-y PMID:29411163","DOI":"10.1186\/s13321-018-0258-y"},{"key":"21074","doi-asserted-by":"crossref","unstructured":"Yang D, Wang L, Zhai J, et al. Characterization of antioxidant, \u03b1-glucosidase and tyrosinase inhibitors from the rhizomes of Potentilla anserina L. and their structure-activity relationship. Food Chem. 2021;336:127714. https:\/\/doi.org\/10.1016\/j.foodchem.2020.127714 PMID:32828014","DOI":"10.1016\/j.foodchem.2020.127714"},{"key":"21075","doi-asserted-by":"crossref","unstructured":"Wang B, Wang C, Duan Y, et al. The effects of Monascus purpureus fermentation on metabolic profile, \u03b1-glucosidase inhibitory action, and in vitro digestion of mulberry leaves flavonoids. Lebensm Wiss Technol. 2023;188:115449. https:\/\/doi.org\/10.1016\/j.lwt.2023.115449","DOI":"10.1016\/j.lwt.2023.115449"},{"key":"21076","doi-asserted-by":"crossref","unstructured":"Kashtoh H, Baek KH. Recent updates on phytoconstituent alpha-glucosidase inhibitors: an approach towards the treatment of type two diabetes. Plants. 2022;11(20):2722. https:\/\/doi.org\/10.3390\/plants11202722 PMID:36297746","DOI":"10.3390\/plants11202722"},{"key":"21077","doi-asserted-by":"crossref","unstructured":"Dej-adisai S, Sakulkeo O, Wattanapiromsakul C, et al. Flavonoid constituents and alpha-glucosidase inhibition of Solanum stramonifolium Jacq. inflorescence with in vitro and in silico studies. Molecules. 2022; 27(23):8189. https:\/\/doi.org\/10.3390\/molecules27238189","DOI":"10.3390\/molecules27238189"},{"key":"21078","doi-asserted-by":"crossref","unstructured":"Han X, Wang P, Zhang J, et al. \u03b1-Glucosidase inhibition mechanism and anti-hyperglycemic effects of flavonoids from astragali radix and their mixture effects. Pharmaceuticals. 2025; 18(5):744. https:\/\/doi.org\/10.3390\/ph18050744","DOI":"10.3390\/ph18050744"},{"key":"21079","doi-asserted-by":"crossref","unstructured":"de Souza Farias SA, da Costa KS, Martins JBL. Analysis of conformational, structural, magnetic, and electronic properties related to antioxidant activity: revisiting flavan, anthocyanidin, flavanone, flavonol, isoflavone, flavone, and flavan-3-ol. ACS Omega. 2021;6(13):8908-8918 https:\/\/doi.org\/10.1021\/acsomega.0c06156","DOI":"10.1021\/acsomega.0c06156"},{"key":"21080","doi-asserted-by":"crossref","unstructured":"Tang H, Huang L, Sun C, et al. Exploring the structure\u2013activity relationship and interaction mechanism of flavonoids and \u03b1-glucosidase based on experimental analysis and molecular docking studies. Food Funct. 2020; 11 (4): 3332\u20133350. https:\/\/doi.org\/10.1039\/c9fo02806d","DOI":"10.1039\/C9FO02806D"},{"key":"21081","doi-asserted-by":"crossref","unstructured":"Proen\u00e7a C, Freitas M, Ribeiro D, et al. \u03b1-Glucosidase inhibition by flavonoids: an in vitro and in silico structure-activity relationship study. J Enzyme Inhib Med Chem. 2017;32(1):1216-1228. https:\/\/doi.org\/10.1080\/14756366.2017.1368503 PMID:28933564","DOI":"10.1080\/14756366.2017.1368503"},{"key":"21082","doi-asserted-by":"crossref","unstructured":"\u015e\u00f6hreto\u011flu D, Sari S. Flavonoids as \u03b1-glucosidase inhibitors: mechanistic approaches merged with enzyme kinetics and molecular modelling. Phytochem Rev. 2020;19:1081-1092. https:\/\/doi.org\/10.1007\/s11101-019-09610-6.","DOI":"10.1007\/s11101-019-09610-6"},{"key":"21083","doi-asserted-by":"crossref","unstructured":"Li J, Zhao T, Yang Q, et al. A review of quantitative structure-activity relationship: the development and current status of data sets, molecular descriptors and mathematical models. Chemom Intell Lab Syst. 2025;256:105278. https:\/\/doi.org\/10.1016\/j.chemolab.2024.105278","DOI":"10.1016\/j.chemolab.2024.105278"},{"key":"21084","doi-asserted-by":"crossref","unstructured":"Duke R, Yang CH, Ganapathysubramanian B, et al. Evaluating molecular similarity measures: do similarity measures reflect electronic structure properties? J Chem Inf Model. 2025;65(9):4311-4319. https:\/\/doi.org\/10.1021\/acs.jcim.5c00175 PMID:40299458","DOI":"10.1021\/acs.jcim.5c00175"},{"key":"21085","doi-asserted-by":"crossref","unstructured":"Li MM, Chen YT, Ruan JC, et al. Structure-activity relationship of dietary flavonoids on pancreatic lipase. Curr Res Food Sci. 2022;6:100424. https:\/\/doi.org\/10.1016\/j.crfs.2022.100424 PMID:36618100","DOI":"10.1016\/j.crfs.2022.100424"},{"key":"21086","doi-asserted-by":"crossref","unstructured":"Uyan\u0131r E, \u0160oral M, Seyhan G, et al. Alpha-glucosidase inhibitory effects of flavonoids, phenolic acids and iridoids isolated from Vinca soneri: in vitro and in silico perspectives. Chem Biodivers. 2024;21(10):e202401386. https:\/\/doi.org\/10.1002\/cbdv.202401386.","DOI":"10.1002\/cbdv.202401386"},{"key":"21087","doi-asserted-by":"crossref","unstructured":"K\u0131z\u0131lcan D\u015e, T\u00fcrkmeno\u011flu B, G\u00fczel Y. Comparison of the performance of different \"local reactive descriptors\" in 3D-QSAR analysis of enantioselective molecules. Struct Chem. 2022;33(2):433-443. https:\/\/doi.org\/10.1007\/s11224-021-01859-y","DOI":"10.1007\/s11224-021-01859-y"},{"key":"21088","doi-asserted-by":"crossref","unstructured":"Edache EI, Uzairu A, Mamza PA, et al. Structure-based simulated scanning of rheumatoid arthritis inhibitors: 2D-QSAR, 3D-QSAR, docking, molecular dynamics simulation, and lipophilicity indices calculation. Sci Afr. 2022;15:e01088. https:\/\/doi.org\/10.1016\/j.sciaf.2021.e01088","DOI":"10.1016\/j.sciaf.2021.e01088"},{"key":"21089","doi-asserted-by":"crossref","unstructured":"Vasilev B, Atanasova M. A (comprehensive) review of the application of quantitative structure\u2013activity relationship (QSAR) in the prediction of new compounds with anti-breast cancer activity. Appl Sci (Basel). 2025;15(3):1206. https:\/\/doi.org\/10.3390\/app15031206","DOI":"10.3390\/app15031206"},{"key":"21090","doi-asserted-by":"crossref","unstructured":"De P, Kar S, Ambure P, et al. Prediction reliability of QSAR models: an overview of various validation tools. Arch Toxicol. 2022;96(5):1279-1295. https:\/\/doi.org\/10.1007\/s00204-022-03252-y PMID:35267067","DOI":"10.1007\/s00204-022-03252-y"},{"key":"21091","doi-asserted-by":"crossref","unstructured":"Zhou Y, Li S, Zhao Y, et al. Quantitative structure\u2013activity relationship (QSAR) model for the severity prediction of drug-induced rhabdomyolysis by using random forest. Chem Res Toxicol. 2021;34(2):514-521. https:\/\/doi.org\/10.1021\/acs.chemrestox.0c00347 PMID:33393765","DOI":"10.1021\/acs.chemrestox.0c00347"}],"container-title":["Drug Target Insights"],"original-title":[],"link":[{"URL":"https:\/\/journals.aboutscience.eu\/index.php\/dti\/article\/download\/3763\/5353","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.aboutscience.eu\/index.php\/dti\/article\/download\/3763\/5354","content-type":"application\/epub+zip","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.aboutscience.eu\/index.php\/dti\/article\/download\/3763\/5353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T10:31:35Z","timestamp":1791282695000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.aboutscience.eu\/index.php\/dti\/article\/view\/3763"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,5]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,7,15]]}},"URL":"https:\/\/doi.org\/10.33393\/dti.2026.3763","relation":{},"ISSN":["1177-3928"],"issn-type":[{"value":"1177-3928","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,5]]}}}