MORGaN: self-supervised multi-relational graph learning for drug target discovery

Identifying therapeutically tractable targets remains difficult, partly because disease biology is distributed across multiple molecular layers and relation types, while labeled data are scarce. We present MORGaN, a self-supervised framework for node classification on multi-omic, multi-relation gene networks that learns structure-aware embeddings and outputs calibrated scores to prioritize therapeutic targets. On a pan-cancer graph integrating TCGA multi-omics and diverse biological relation types, MORGaN outperforms state-of-the-art biological node classification models across metrics (AUPR: 0.815 → 0.888; +9%). Ablation studies highlight that both relation diversity and the in-layer fusion architecture are necessary for these gains. Prioritized targets are biologically coherent: high-confidence hits are enriched for pharmaceutically tractable families and ligand–receptor signaling cascades. Post hoc explainability analyses recover compact, pathway-consistent motifs around both known and putative novel targets, and concordance with external resources further supports plausibility. MORGaN thus delivers label-efficient, interpretable node classification for target discovery and can be readily adapted to other diseases, other species, and other node classification tasks. Code and documentation are available at this link .