Quantitative structure and bioactivity relationship study on human acetylcholinesterase inhibitors

Area of Science:

• Medicinal Chemistry
• Computational Chemistry
• Pharmacology

Background:

• Acetylcholinesterase (AChE) inhibitors are crucial for treating neurological disorders.
• Developing accurate predictive models for AChE inhibitors is essential for drug discovery.
• Quantitative Structure-Activity Relationships (QSAR) offer a computational approach to predict biological activity.

Purpose of the Study:

• To develop and validate QSAR models for predicting the inhibitory activity of 404 Acetylcholinesterase inhibitors.
• To compare the performance of Multilinear Regression (MLR) and Support Vector Machine (SVM) for QSAR modeling.
• To ensure the robustness and reliability of the developed QSAR models.

Main Methods:

• Dataset of 404 Acetylcholinesterase inhibitors was curated.
• Data splitting using random selection and Kohonen's self-organizing map.
• Development of QSAR models using MLR and SVM.
• Model validation through Y-randomization tests and docking simulations.

Main Results:

• QSAR models were successfully developed for predicting Acetylcholinesterase inhibitory activity.
• High correlation coefficients (over 0.90) were achieved for all models on test sets.
• Y-randomization tests confirmed the robustness of the models.
• Docking simulations supported the validity of the descriptors used.

Conclusions:

• The developed QSAR models accurately predict the inhibitory activity of Acetylcholinesterase inhibitors.
• Both MLR and SVM are effective methods for QSAR modeling in this context.
• The validated models can aid in the design and discovery of novel Acetylcholinesterase inhibitors.