Integrating Multiomics Data Using a Correlation Based Graph Attention Network for Subtype Classification in Lower Grade Glioma

This repository provides the official implementation of the BioGAT_LGG framework for biomarker discovery and subtype classification of Lower-Grade Glioma using Graph Attention Networks and multi-omics data integration (mRNA, miRNA, and DNA methylation). The model is trained using LASSO-selected features and correlation-based graphs, evaluated with 10-fold cross-validation.