Optimizing ChEMBL-derived QSAR models for natural flavonoid screening: Chemotype-specific predictive reliability in α-glucosidase-inhibition
File(s)
Accepted version
Author(s)
Type
Journal Article
Abstract
Introduction: α-Glucosidase inhibitors (AGIs) are essential for controlling postprandial hyperglycemia, with flavonoids representing a major class of natural AGIs. However, conventional 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–based QSAR models derived from ChEMBL α-glucosidase inhibitors 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 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.
Keywords: α-glucosidase inhibitor; flavonoids; QSAR; Random Forest; chemotype specificity; Mordred descriptors
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 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.
Keywords: α-glucosidase inhibitor; flavonoids; QSAR; Random Forest; chemotype specificity; Mordred descriptors
Date Acceptance
2026-09-09
Citation
Drug Target Insights
ISSN
1177-3928
Publisher
AboutScience Srl
Journal / Book Title
Drug Target Insights
Copyright Statement
Copyright This paper is embargoed until publication. Once published the Version of Record (VoR) will be available on immediate open access.
License URL
Publication Status
Accepted