EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-view knowledge-guided flow subgraphs with substructure initialization for explainable DDI prediction

Yugui Xu, Zhigan Zhou, Hao Yuan, Siqi Liu, Quan Zou, Yongqing Zhang, Wenqian Zhang

Briefings in Functional Genomics · 09.01.2026 · 25

DOI: 10.1093/bfgp/elag006 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Functional Genomics, online erschienen am 01.07.2026. Verfasst von Yugui Xu und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Chengdu University of Information Technology, No. 24 Block 1, Xuefu Road, Chengdu, 610225, China. Hauptthemen laut MEDLINE: Drug Interactions, Models, Chemical. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Polypharmacy has become essential in managing complex and chronic conditions, yet it introduces significant clinical risks due to potential drug–drug interactions (DDIs). Existing computational models struggle to provide accurate and interpretable predictions, largely due to fragmented integration of molecular structures and biomedical knowledge. These limitations arise from static graph designs, inadequate substructure modeling, and insufficient incorporation of semantic context, highlighting the need for a unified, explainable solution. In this study, we propose MKGFlow-DDI, a multi-view knowledge-guided framework that jointly leverages drug–drug interaction networks and biomedical knowledge graphs to dynamically construct drug-flow subgraphs. The model incorporates a dual-channel encoder designed to capture atom-level information and substructure-level features, integrating them with the global semantic embeddings of the composite network to derive novel feature representations. These representations are fused to initialize node features within each subgraph, which are iteratively optimized through similarity-based edge refinement to reduce noise and enhance biological relevance. To further improve generalization and stability, a contrastive learning module is introduced to align representations of perturbed subgraphs by maximizing consistency across positive and negative sample pairs. Experimental results on DrugBank and TWOSIDES demonstrate that MKGFlow-DDI outperforms state-of-the-art baselines, especially in scenarios involving previously unseen drugs. Additionally, the model produces interpretable semantic pathways that align with known pharmacological mechanisms, enabling clinically meaningful insights. Overall, MKGFlow-DDI establishes a robust and biologically grounded approach to DDI prediction, offering a promising direction for computational pharmacovigilance and personalized therapy optimization.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug InteractionsModels, ChemicalAlgorithms

Stichwörter der Autor:innen

contrastive learningdrug–drug interactiongraph neural networksmulti-view knowledge

Autor:innen und Institutionen

  • School of Computer Science, Chengdu University of Information Technology, No. 24 Block 1, Xuefu Road, Chengdu, 610225, China.
  • Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, No. 2006, Xiyuan Ave, West Hi-Tech Zone, Chengdu 611731, China.
  • Department of Thoracic Surgery, Beijing Chaoyang Hospital, Capital Medical University, XiYuan Campus, 5 Jingyuan Road, Shijingshan District, Beijing, 100043, China.

Zitieren

APA

Xu, Y., Zhou, Z., Yuan, H., Liu, S., Zou, Q., Zhang, Y., & Zhang, W. (2026). Multi-view knowledge-guided flow subgraphs with substructure initialization for explainable DDI prediction. Briefings in Functional Genomics, 25. https://doi.org/10.1093/bfgp/elag006

Vancouver

Xu Y, Zhou Z, Yuan H, Liu S, Zou Q, Zhang Y, et al. Multi-view knowledge-guided flow subgraphs with substructure initialization for explainable DDI prediction. Briefings in Functional Genomics. 2026;25. doi:10.1093/bfgp/elag006

BibTeX
@article{Xu2026,
  author = {Xu, Yugui and Zhou, Zhigan and Yuan, Hao and Liu, Siqi and Zou, Quan and Zhang, Yongqing and Zhang, Wenqian},
  title = {Multi-view knowledge-guided flow subgraphs with substructure initialization for explainable DDI prediction},
  journal = {Briefings in Functional Genomics},
  year = {2026},
  volume = {25},
  doi = {10.1093/bfgp/elag006}
}
Kostenlos starten →