EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Topology‐Aware Deep Learning on Higher‐Order Structures for Drug Response Prediction

Cong Shen iD, Guancen Lin, Chuan-Shen Hu, Yong Wang

Advanced Science · 2026-08 · 13 (46)

DOI: 10.1002/advs.75816 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 27.05.2026. Verfasst von Cong Shen und 3 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China. Hauptthemen laut MEDLINE: Deep Learning, Antineoplastic Agents, Neoplasms. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Beijing Natural Science Foundation, Postdoctoral Fellowship Program of CPSF.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of anticancer drug response remains a central challenge in precision oncology. Existing approaches often rely on pairwise modeling, overlooking higher‐order dependencies among drugs and cell lines. We present TopDr, a topology‐aware deep learning framework that encodes both drugs and cell lines as multiscale simplicial complexes, capturing interactions at the 0‐, 1‐, and 2‐simplex levels. By jointly integrating local higher‐order neighborhoods and global topological structures, TopDr generates enriched representations for sensitivity prediction. Across six benchmark datasets, TopDr consistently matches or surpasses state‐of‐the‐art baselines in both regression and classification tasks. Beyond predictive accuracy, TopDr offers mechanism‐level interpretability: attention over 1‐ and 2‐simplices highlights drug pairs and triplets with significant pathway enrichment, while cell line groupings reveal biologically coherent expression modules. These results demonstrate that modeling multiscale higher‐order topology yields predictions that are not only accurate and robust but also biologically interpretable, paving the way for more reliable drug response modeling.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningAntineoplastic AgentsNeoplasmsHumansPrediction Algorithms

Stichwörter der Autor:innen

drug response predictionhigher‐order interactionsinterpretabilitysimplicial complexestopological deep learning

Substanzen

Antineoplastic Agents

Autor:innen und Institutionen

  • State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China.
  • Department of Applied Mathematics, National University of Kaohsiung, Kaohsiung, Taiwan.
  • School of Mathematics, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Beijing, China.
  • Center for Excellence in Animal Evolution and Genetics, Chinese Academy of Sciences, Kunming, Yunnan, China.
  • Key Laboratory of Systems Biology, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Hangzhou, Zhejiang, China.

ORCID-Profile: Cong Shen

Förderung

  • National Key Research and Development Program of China
  • Beijing Natural Science Foundation
  • Postdoctoral Fellowship Program of CPSF
  • Shenzhen Medical Research Fund
  • Strategic Priority Research Program of the Chinese Academy of Sciences
  • Natural Science Foundation of Beijing Municipality

Zitieren

APA

Shen, C., Lin, G., Hu, C. S., & Wang, Y. (2026). Topology‐Aware Deep Learning on Higher‐Order Structures for Drug Response Prediction. Advanced Science, 13(46). https://doi.org/10.1002/advs.75816

Vancouver

Shen C, Lin G, Hu CS, Wang Y. Topology‐Aware Deep Learning on Higher‐Order Structures for Drug Response Prediction. Advanced Science. 2026;13(46). doi:10.1002/advs.75816

BibTeX
@article{Shen2026,
  author = {Shen, Cong and Lin, Guancen and Hu, Chuan-Shen and Wang, Yong},
  title = {Topology‐Aware Deep Learning on Higher‐Order Structures for Drug Response Prediction},
  journal = {Advanced Science},
  year = {2026},
  volume = {13},
  number = {46},
  doi = {10.1002/advs.75816}
}
Kostenlos starten →