CME-KGDTI: integrating clustered mutations into knowledge graph embedding for drug-target interaction prediction

BACKGROUND: Computational prediction of drug-target interaction (DTI) is critical for drug discovery and precision medicine. Herein, we constructed a biologically enriched heterogeneous knowledge graph (KG) integrating clustered mutations, synthetic lethal interactions, drug structures, protein sequences, and functional annotations. This multi-dimensional framework was designed to enable the identification of actionable diagnostic signatures and precision therapeutic strategies by leveraging multi-layered biological network factors. RESULTS: Entities within the KG were embedded into low-dimensional vectors using various graph embedding techniques (TransE, RotatE, DistMult, Node2vec and R-GCN). These multimodal embeddings served as input for deep learning models (DNN, NFM, AutoInt), with standardization and PCA-based dimensionality reduction applied. Under a challenging protein cold-start scenario, the CME-KGDTI model demonstrated a better performance. These results highlight the multi-source biological information in enhancing positive sample identification and overall model generalization. Additionally, the CME-KGDTI platform (https://www.tmliang.cn/cmekgdti/#/home) was developed, integrating resources for clustered mutation identification, cancer-specific SL-based genetic networks, DTI prediction, and multi-omics analysis, enabling users to comprehensively explore mutation detection, target prioritization, and mechanistic insights. CONCLUSIONS: By incorporating biological features, the CME-KGDTI model exhibits high accuracy and robust generalization, highlighting its essential complementary role in drug target discovery. The developed CME-KGDTI platform will serve as a flexible, interactive, and implementable technical support platform, contributing to the advancement of precision oncology research.