In the present study, a Graph Attention Network (GAT) model was applied to predict the human blood-brain barrier (BBB) permeability of different molecules using the BBBP (Predicting Blood-Brain Barrier Penetration) dataset. Each molecule was represented as a graph, with atoms as nodes and bonds as edges. The model achieved an accuracy of 0.75 on the test set, demonstrating that graph-based deep learning models like GAT (Graph Attention Networks) can be used effectively to capture information from molecular graphs to accurately classify molecules as BBB+ and BBB-.
For more details, please refer to this doc.
This project is intended strictly for learning and educational purposes. The paper (dummy) and model architecture (GAT) have been implemented only to understand Graph Neural Networks. The code should not be used for production, deployment, or any critical decision-making.