Artemis: Harnessing Knowledge Graphs for Next-Generation Drug Target Prioritization

Knowledge graphs (KGs) have become an important asset in biomedical research and drug discovery by enabling the structured integration of heterogeneous biological knowledge. When combined with machine learning (ML), KGs support the identification of novel drug-target relationships, but existing approaches are often KG-centric, relying primarily on graph structure and embeddings while overlooking disease-specific biological and clinical context. Moreover, many high-impact applications depend on proprietary KG infrastructures, limiting accessibility for the broader research community. Here, we introduce Artemis, a practical and generalizable ML framework for indication-aware target prioritization that integrates public biomedical KGs with clinical evidence from the ChEMBL database. Artemis derives graph-based representations of clinically validated drug targets from multiple publicly available KGs and trains supervised ML models using disease-relevant clinical labels derived from ChEMBL. This hybrid feature space is used to train supervised ML models across 7 disease indications, with performance assessed via cross-validation and guided parameter optimization. The framework is further evaluated on emerging breast cancer targets reported at the San Antonio Breast Cancer Symposium 2024, demonstrating its ability to prioritize novel candidates. Overall, this work demonstrates that publicly available KGs can be used for actionable, translational target discovery when coupled with clinical data. Artemis provides an accessible, scalable, and cost-efficient alternative to proprietary KG platforms, thereby offering a practical solution for researchers seeking to prioritize therapeutic targets in real-world drug discovery settings.