Modeling of New Agents with Potential Antidiabetic Activity Based on Machine Learning Algorithms
Open Access
- 27 October 2025
- journal article
- research article
- Published by MDPI AG in Appliedchem
- Vol. 5 (4) , 30
Abstract
Type 2 diabetes mellitus (T2DM) is a growing global health challenge, expected to affect over 600 million people by 2045. The discovery of new antidiabetic agents remains resource-intensive, motivating the use of machine learning (ML) for virtual screening based on molecular structure. In this study, we developed a predictive pipeline integrating two distinct descriptor types: high-dimensional numerical features from the Mordred library (>1800 2D/3D descriptors) and categorical ontological annotations from the ClassyFire and ChEBI systems. These encode hierarchical chemical classifications and functional group labels. The dataset included 45 active compounds and thousands of inactive molecules, depending on the descriptor system. To address class imbalance, we applied SMOTE and created balanced training and test sets while preserving independent validation sets. Thirteen ML models—including regression, SVM, naive Bayes, decision trees, ensemble methods, and others—were trained using stratified 12-fold cross-validation and evaluated across training, test, and validation. Ridge Regression showed the best generalization (MCC = 0.814), with Gradient Boosting following (MCC = 0.570). Feature importance analysis highlighted the complementary nature of the descriptors: Ridge Regression emphasized ClassyFire taxonomies such as CHEMONTID:0000229 and CHEBI:35622, while Mordred-based models (e.g., Random Forest) prioritized structural and electronic features like MAXsssCH and ETA_dEpsilon_D. This study is the first to systematically integrate and compare structural and ontological descriptors for antidiabetic compound prediction. The framework offers a scalable and interpretable approach to virtual screening and can be extended to other therapeutic domains to accelerate early-stage drug discovery.Keywords
This publication has 43 references indexed in Scilit:
- Exploring Target Identification for Drug Design with K-Nearest Neighbors’ Algorithm2023
- Evolution of Support Vector Machine and Regression Modeling in Chemoinformatics and Drug DiscoveryJournal of Computer-Aided Molecular Design, 2022
- Drug design by machine-trained elastic networks: predicting Ser/Thr-protein kinase inhibitors’ activitiesMolecular Diversity, 2020
- Multi-linear regression model, molecular binding interactions and ligand-based design of some prominent compounds against Mycobacterium tuberculosisNetwork Modeling Analysis in Health Informatics and Bioinformatics, 2020
- Epidemiology of diabetes mellitus2020
- Screen efficiency comparisons of decision tree and neural network algorithms in machine learning assisted drug designScience China Chemistry, 2019
- SEMI-empirical PM6 method applied in the analysis of thermodynamics properties and molecular orbitals at different temperatures of adsorption drugs on chitosan hydrogels for type 2 diabetesPolymer Bulletin, 2018
- Structure-Activity Relationships: Theory, Uses and Limitations☆2015
- On Exploring Structure–Activity Relationships2013
- Prediction of tyrosinase inhibition for drug design using the genetic algorithm–multiple linear regressionsMedicinal Chemistry Research, 2013