MORGaN: self-supervised multi-relational graph learning for druggable gene discovery

Accurate identification of druggable targets remains a critical challenge in drug discovery due to the inherent complexity of biology and the scarcity of labeled data. We present MORGaN , the first masked auto-encoder that natively oper-ates on heterogeneous m ulti- o mic g ene n etworks with diverse biological relation types. MORGaN learns structure-aware node embeddings without supervision, leveraging multi-relation topology through a cross-relation message-passing ar-chitecture. We deploy MORGaN for druggable gene discovery , using its repre-sentations to identify candidate therapeutic targets. Despite using no additional labels, MORGaN outperforms state-of-the-art models across all metrics (AUPR: 0.815 0.888; +9%). Ablation studies highlight the importance of both relation diversity and architectural design in achieving these gains. Post-hoc analyses uncover pathway-coherent subgraphs that help explain predictions, supporting biological interpretability. MORGaN enables label-efficient, interpretable, and fast graph learning for drug discovery and other data-scarce biomedical tasks. Code and documentation are available at this link.