Answers are grounded in this paper and cite their sources.
Abstract Alzheimer's disease (AD) is one of the most prevalent neurodegenerative diseases. Given the multifactorial pathophysiology of AD, monotargeted agents can only alleviate symptoms but not cure AD. Acetylcholinesterase (AChE) and Monoamine oxidase B (MAO-B) are two key targets in the treatment of AD, molecules that inhibiting both targets are considered promising avenue to develop more effective AD therapies. In the present work, a dual inhibition dataset containing 449 molecules was established, based on which six machine-learning algorithms (KNN, SVM, RF, GBDT, LGBM and DNN) four fingerprints (MACCS, ECFP4, RDKitFP, PubChemFP) and DRAGON descriptors were combined to develop 30 classification models in which GBDT model paired with MACCS and especially ECFP4, achieved the best performance across multiple metrics (Accuracy = 0.89, Precision = 0.88, Recall = 0.92, F1 Score = 0.90, MCC = 0.70). Moreover, based on the curated bioactivity datasets of AChE and MAO-B, regression models were developed to predict pIC50 values. For the AChE inhibition task, GBDT and SVM demonstrated the best performance (MSE = 0.43, MAE = 0.47, R² = 0.75). The SVM algorithm emerged as the most effective for MAO-B inhibition (MSE = 0.35, MAE = 0.45, R² = 0.77). The SHAP algorithm was used to interpret the optimal models, identifying and analyzing the key substructures and properties for both dual-target and single-target inhibitors. The interactions of these structural fragments with both targets were further validated using molecular docking.
No takes yet. Share an insight, caveat, or question.
Hou et al. (2024) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: