EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CSGDA: a cell state-guided graph domain adaptation network for single-cell drug response prediction

Fen Yan iD, Donggui Xie, Xiyue Cao, Feiqiao Mao, Zhuhong You, Yitao Chen, Zhihua Du, Yu-An Huang iD

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag726 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Fen Yan und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong 518000, China. Hauptthemen laut MEDLINE: Single-Cell Analysis, Computational Biology, Antineoplastic Agents, Neoplasms. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Intratumoral heterogeneity drives cancer recurrence and metastasis, yet single-cell drug response prediction faces severe “cross-domain” challenges, such as applying in vitro models to in vivo tissues or inferring metastatic resistance from primary tumors. These scenarios trigger distribution shifts arising from heterogeneous sequencing platforms, distinct tissue microenvironments, and metastatic evolution—problems rarely addressed by existing methods. Results We introduce CSGDA, a cell state-guided graph domain adaptation framework designed to predict drug responses across these biological heterogeneities. CSGDA incorporates biological priors to map gene expression into functional cell states, guiding a structure-learning module to construct robust cell topology. To mitigate distribution shifts, the model employs graph domain adaptation combined with a novel overlap penalty mechanism. Extensive benchmarks on five scRNA-seq datasets demonstrate that CSGDA outperforms the state-of-the-art method SSDA4Drug by approximately 6 percentage points in both ACC and AUPR. Beyond prediction accuracy, we employed integrated gradients to effectively pinpoint key genes involved in drug resistance within a challenging cross-metastasis cisplatin dataset. These findings underscore CSGDA’s superior performance in single-cell drug response prediction and its potential in resolving single-cell heterogeneity, paving the way for precision medicine. Availability and implementation Source code is available at https://github.com/yanfen-git/CSGDA-code and archived at https://doi.org/10.5281/zenodo.21759274. Data are available at https://doi.org/10.5281/zenodo.21770737.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Single-Cell AnalysisComputational BiologyAntineoplastic AgentsNeoplasmsSoftwareHumansSingle-Cell Gene Expression AnalysisDrug Resistance, Neoplasm

Substanzen

Antineoplastic Agents

Autor:innen und Institutionen

  • College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong 518000, China.
  • School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi 710000, China.

ORCID-Profile: Fen Yan, Yu-An Huang

Förderung

  • National Natural Science Foundation of China
  • Guangdong Basic and Applied Basic Research Foundation

Zitieren

APA

Yan, F., Xie, D., Cao, X., Mao, F., You, Z., Chen, Y., Du, Z., & Huang, Y. A. (2026). CSGDA: a cell state-guided graph domain adaptation network for single-cell drug response prediction. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag726

Vancouver

Yan F, Xie D, Cao X, Mao F, You Z, Chen Y, et al. CSGDA: a cell state-guided graph domain adaptation network for single-cell drug response prediction. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag726

BibTeX
@article{Yan2026,
  author = {Yan, Fen and Xie, Donggui and Cao, Xiyue and Mao, Feiqiao and You, Zhuhong and Chen, Yitao and Du, Zhihua and Huang, Yu-An},
  title = {CSGDA: a cell state-guided graph domain adaptation network for single-cell drug response prediction},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag726}
}
Kostenlos starten →