CSK-DDI: compensating structural incompleteness with knowledge graph world knowledge for drug–drug interaction modeling
Bioinformatics · 02.11.2026 · 42 (11)
DOI: 10.1093/bioinformatics/btag800 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 28.10.2026. Verfasst von Jiayi Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan 410082, China. Hauptthemen laut MEDLINE: Computational Biology. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Yuelushan Laboratory Breeding Program.
Abstract (Originalsprache)
Motivation Drug–drug interaction (DDI) prediction is critical for drug safety, yet existing methods suffer from structural incompleteness in drug representation. Motif and molecular graph encodings capture local substructures and global topology but remain confined to the closed structural space of individual molecules, lacking cross-entity and contextual information and leading to limited generalization, especially in cold-start scenarios. To address this issue, we propose CSK-DDI (Compensating Structural Incompleteness with Knowledge Graph World Knowledge for Drug–Drug Interaction Modeling), a multimodal framework that jointly encodes motif-level chemical patterns, molecular graph topology, and biomedical knowledge graph (KG) context as complementary drug representations. The KG encodes drugs’ contextual positions and relational semantics through multi-entity and multi-relation connections, providing global cross-entity and cross-semantic information that complements structural representations. The resulting fusion captures local chemical patterns, global topology, and biomedical context in a unified embedding. Results CSK-DDI employs a cross-attention mechanism to enable multi-view interaction among motif, molecular graph, and KG representations, producing unified structure-aware and context-aware drug embeddings. To improve robustness under sparse conditions, the model further incorporates a cold-start-oriented representation enhancement strategy. Experiments on benchmark datasets demonstrate consistent improvements over state-of-the-art methods, with particularly notable gains in cold-start scenarios. Availability and implementation Source code and data are available at https://github.com/cgwcbz2/CSK-DDI and on Zenodo at https://doi.org/10.5281/zenodo.21415769.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan 410082, China.
- Yuelushan Laboratory, Changsha, Hunan 410128, China.
ORCID-Profile: Jiayi Wang, Bosheng Song
Förderung
- National Natural Science Foundation of China
- Yuelushan Laboratory Breeding Program
Zitieren
APA
Wang, J., He, Y., Ma, T., & Song, B. (2026). CSK-DDI: compensating structural incompleteness with knowledge graph world knowledge for drug–drug interaction modeling. Bioinformatics, 42(11). https://doi.org/10.1093/bioinformatics/btag800
Vancouver
Wang J, He Y, Ma T, Song B. CSK-DDI: compensating structural incompleteness with knowledge graph world knowledge for drug–drug interaction modeling. Bioinformatics. 2026;42(11). doi:10.1093/bioinformatics/btag800
BibTeX
@article{Wang2026,
author = {Wang, Jiayi and He, Yuqin and Ma, Tengfei and Song, Bosheng},
title = {CSK-DDI: compensating structural incompleteness with knowledge graph world knowledge for drug–drug interaction modeling},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {11},
doi = {10.1093/bioinformatics/btag800}
}
EUVIMED