A Classification-Based Blood–Brain Barrier Model: A Comparative Approach

Background and Objectives: Drug permeability across the blood–brain barrier (BBB) remains a significant challenge in drug discovery, prompting extensive efforts to develop in silico predictive models. Most existing models rely on molecular descriptors to characterize drug properties. Feature selection algorithms play a crucial role in identifying the most relevant descriptors, thereby enhancing prediction accuracy. Methods: In this study, we compare the effectiveness of sequential feature selection (SFS) and genetic algorithms (GAs) in optimizing descriptor selection for BBB permeability prediction. Five different classifiers were initially trained on a dataset using eight molecular descriptors. Each classifier was then retrained using the descriptors selected by SFS and GA separately. Results: The results indicate that the GA method outperformed SFS, leading to a higher prediction accuracy (96.23%) when combined with a support vector machine (SVM) classifier. Furthermore, the GA approach, utilizing a fitness function based on classifier performance, consistently improved prediction accuracy across all tested models, whereas SFS showed lower effectiveness. Additionally, this study highlights the critical role of polar surface area in determining drug permeability across the BBB. Conclusions: These findings suggest that genetic algorithms provide a more robust approach than sequential feature selection for identifying key molecular descriptors in BBB permeability prediction.

Uncontrolled Keywords

• blood–brain barrier
• classification
• machine learning
• genetic algorithm
• sequential feature selection
• artificial intelligence
• in silico modeling
• drug discovery