Graph-Based Link Prediction for Epilepsy Drug Discovery

Epilepsy is one of the most prevalent neurological disorders, affecting approximately 23 million people in Asia alone. It isa disorder with severe social impacts and is going to progressively damage the brain. It encompasses a wide range ofsyndromes and each one of them differs significantly in treatment options. seizures is the common symptom in all of them.Despite being one of the most researched clinical conditions, the exact mechanism is still unknown, and this poses challengesfor coming up with an effective treatment mechanism. Conventional treatment which includes Anti-Epileptic Drugs (AEDs)come with a lot of limitations. Inspired by Ayurveda, we propose a computational framework to predict phytochemical-proteininteractions for potential epilepsy treatment. We propose that the interaction can be modelled as a bipartite graph, wherenodes represent phytochemicals and proteins and edges are represented by interactions. We employ Graph neural networksto capture both local and global information about the graph. Initially, the entire graph was trained using Graph ConvolutionalNetwork (GCN), Graph Attention Network (GAT), and GraphSAGE. To enhance predictive performance, we then constructedone-hop enclosing subgraphs for both positive and negative samples and trained the same three models on this refined dataset.Our best-performing model achieved an accuracy of 0.9778, precision of 0.9574, F1-score of 0.9782, and ROC-AUC score of0.9994.