A disentangled transformer-based transfer learning framework to predict patient drug response from tumor single-cell transcriptomics
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag269 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Xinliang Sun und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, China. Hauptthemen laut MEDLINE: Single-Cell Analysis, Neoplasms, Transcriptome, Antineoplastic Agents. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hunan Province, Academy of Finland.
Abstract (Originalsprache)
Motivation Intratumoral cellular heterogeneity limits therapeutic efficacy in cancer patients. Although single-cell transcriptomics offers high-resolution profiling, translating these insights into clinical drug response prediction remains challenging. Recently, transfer learning approaches have attempted to predict patient drug response by leveraging pre-clinical data. However, these approaches operate at the bulk level, often masking the cellular heterogeneity essential for prediction. Results In this study, we propose scTAPE, a disentangled transfer learning framework to predict patient drug response using tumor single-cell transcriptomics. scTAPE follows a pre-training and fine-tuning paradigm. During the pre-training stage, scTAPE uses a disentangled learning strategy to extract intrinsic pharmacological signals masked by confounding factors from the matched bulk and single-cell expression profiles. Subsequently, a supervised drug response model is trained on labeled cell-line data to fine-tune the aligned common embedding, thereby achieving cross-domain generalization to unseen datasets. Experimental results demonstrate that scTAPE successfully predicts drug response across cell-line datasets and two independent clinical cohorts, outperforming state-of-the-art single-cell-based predictors. Furthermore, by analyzing tumor cell subpopulations, scTAPE not only predicts patient drug response to both single and combination treatments but also identifies potential therapeutic agents targeting drug-resistant subpopulations. Availability and implementation The implementation of scTAPE is available via https://github.com/xinliangSun/scTAPE.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, China.
- Research Program in Systems Oncology, Faculty of Medicine, University of Helsinki, Helsinki 00290, Finland.
- School of Automation, Central South University, Changsha, Hunan 410083, China.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Hunan Province
- Academy of Finland
- iCAN Digital Precision Cancer Medicine Finland
Zitieren
APA
Sun, X., Shen, L., Wang, L., Zhang, X., Lu, Z., Tang, J., & Li, M. (2026). A disentangled transformer-based transfer learning framework to predict patient drug response from tumor single-cell transcriptomics. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag269
Vancouver
Sun X, Shen L, Wang L, Zhang X, Lu Z, Tang J, et al. A disentangled transformer-based transfer learning framework to predict patient drug response from tumor single-cell transcriptomics. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag269
BibTeX
@article{Sun2026,
author = {Sun, Xinliang and Shen, Li and Wang, Linconghua and Zhang, Xinyi and Lu, Zhangli and Tang, Jing and Li, Min},
title = {A disentangled transformer-based transfer learning framework to predict patient drug response from tumor single-cell transcriptomics},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag269}
}
EUVIMED