EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Structured multi-view relational learning for drug response prediction

Zengwei Wang, Wanchen Li, Junlin Xu, Yajie Meng, Hao Zhou, Shuting Jin iD

Briefings in Bioinformatics · 02.11.2026 · 27 (6)

DOI: 10.1093/bib/bbag619 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 07.11.2026. Verfasst von Zengwei Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Wuhan University of Science and Technology, 2 Huangjiahuxi Road, Hongshan District, Wuhan 430065, Hubei, C…. Hauptthemen laut MEDLINE: Deep Learning, Computational Biology. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Drug response prediction (DRP) requires models that jointly characterize molecular drug structure and heterogeneous cellular states. Although recent deep learning approaches have integrated multi-omics profiles with drug representations, many treat omics views as parallel feature sources or merge them before relational modeling, which can weaken omics-view-specific cell-line relation structures. Here, we propose MulDR, a structured multi-view relational learning framework that preserves omics-view-specific cell-line relation structures before drug-conditioned cell–drug interaction. MulDR constructs separate relation structures for pathway activity, gene expression, mutation, and DNA methylation, learns view-specific relational cell representations, and uses complementary motif-level, geometry-aware molecular graph, and Morgan fingerprint drug representations to condition their fusion. With this design, cell-line similarity remains view-dependent until the interaction stage, rather than being prematurely compressed into a single feature or relation space. Extensive experiments show that MulDR consistently outperforms representative and recent baselines under the same evaluation protocol, reducing root mean square error by 6.07% relative to the strongest baseline. Cold-start evaluations on unseen drugs and cell lines further show that MulDR generalizes to previously unseen entities, while ablation studies show that removing either view-specific relational modeling or drug-conditioned fusion consistently compromises predictive performance. Together, these results suggest that preserving omics-specific cell-line relations before drug-conditioned interaction modeling provides an effective strategy for robust DRP.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningComputational BiologyHumansAlgorithms

Stichwörter der Autor:innen

cell-line relation modelingdrug response predictionhypergraph learninginteraction modelingmulti-view learning

Autor:innen und Institutionen

  • School of Computer Science and Technology, Wuhan University of Science and Technology, 2 Huangjiahuxi Road, Hongshan District, Wuhan 430065, Hubei, China.
  • School of Computer Science and Artificial Intelligence, Wuhan Textile University, 1 Yangguang Avenue, Jiangxia District, Wuhan 430200, Hubei, China.

ORCID-Profile: Shuting Jin

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, Z., Li, W., Xu, J., Meng, Y., Zhou, H., & Jin, S. (2026). Structured multi-view relational learning for drug response prediction. Briefings in Bioinformatics, 27(6). https://doi.org/10.1093/bib/bbag619

Vancouver

Wang Z, Li W, Xu J, Meng Y, Zhou H, Jin S. Structured multi-view relational learning for drug response prediction. Briefings in Bioinformatics. 2026;27(6). doi:10.1093/bib/bbag619

BibTeX
@article{Wang2026,
  author = {Wang, Zengwei and Li, Wanchen and Xu, Junlin and Meng, Yajie and Zhou, Hao and Jin, Shuting},
  title = {Structured multi-view relational learning for drug response prediction},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  volume = {27},
  number = {6},
  doi = {10.1093/bib/bbag619}
}
Kostenlos starten →