Open access
Jan 2026
engGNN: A Dual-Graph Neural Network for Omics-Based Disease Classification and Feature Selection
The proposed engGNN is highlighted as a robust, flexible, and interpretable framework for disease classification and biomarker discovery in high-dimensional omics contexts and provides interpretable feature importance scores that facilitate biologically meaningful discoveries, such as pathway enrichment analysis.
Tian-Tian Yang, Yuxuan Wang, Zhen-Wei Zhou et al.
· Briefings in Bioinformatics · 0 citations