BiGvCL: bipartite graph-based cross-domain contrastive learning model for the predicting drug-gene interactions

Drug-gene interactions (DGIs) influence the toxicity or ineffectiveness of the drug therapy and play an important role in elucidating drug mechanisms, predicting potential adverse effects, and facilitating precision medicine. Existing computational methods typically rely on chemical or genetic sequence features of drugs and genes, limiting their effectiveness for novel entities lacking explicit annotations. To address this, we propose BiGvCL, a framework that predicts DGIs exclusively based on network topology, requiring no explicit feature information for drugs or genes. BiGvCL introduces a lightweight graph attention mechanism (GATLite) to efficiently aggregate local neighborhood information. Additionally, we develop a gated graph convolutional network (GatedGCN) to explicitly learn high-order interactions between drugs and genes, further integrating contrastive learning to enhance the model's generalizability. Comprehensive experiments on DrugBank and DGIdb datasets show that BiGvCL achieves competitive performance across all metrics compared with representative baselines. Cross-domain evaluations on OGB datasets further confirm its adaptability to heterogeneous biomedical networks. Ablation and hyperparameter analyses highlight the key contributions of contrastive and gated mechanisms, while case studies and molecular docking provide supporting evidence for the biological relevance of predictions. Collectively, while BiGvCL is constrained by its reliance on network topology and transductive learning paradigm, it demonstrates the potential of topology-based approaches for discovering novel drug-gene interactions, which may inform drug repurposing and precision medicine efforts.