EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

scATD: a high-throughput and interpretable framework for single-cell cancer drug resistance prediction and biomarker identification

Murong Zhou, Zeyu Luo, Yu-Hang Yin, Qiaoming Liu, Guohua Wang, Yuming Zhao

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf268 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Murong Zhou und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China. Hauptthemen laut MEDLINE: Drug Resistance, Neoplasm, Single-Cell Analysis, Biomarkers, Tumor, Neoplasms. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 62 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)

Transfer learning has been widely applied to drug sensitivity prediction based on single-cell RNA sequencing, leveraging knowledge from large datasets of cancer cell lines or other sources to improve the prediction of drug responses. However, previous studies require model fine-tuning for different patient single-cell datasets, limiting their ability to meet the clinical need for high-throughput rapid prediction. In this research, we introduce single-cell Adaptive Transfer and Distillation model (scATD), a transfer learning framework leveraging large language models for high-throughput drug sensitivity prediction. Based on different large language models (scFoundation and Geneformer) and transfer strategies, scATD includes three distinct sub-models: scATD-sf, scATD-gf, and scATD-sf-dist. scATD-sf and scATD-gf employs an important bidirectional style transfer to enable predictions for new patients without model parameter training. Additionally, scATD-sf-dist uses knowledge distillation from large models to enhance prediction performance, improve efficiency, and reduce resource requirements. Benchmarking across more diverse datasets demonstrates scATD’s superior accuracy, generalization and efficiency. Besides, by rigorously selecting reference background samples for feature attribution algorithms, scATD also provides more meaningful insights into the relationship between gene expression and drug resistance mechanisms. Making scATD more interpretability for addressing critical challenges in precision oncology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug Resistance, NeoplasmSingle-Cell AnalysisBiomarkers, TumorNeoplasmsHumansMachine LearningComputational BiologyAlgorithms

Stichwörter der Autor:innen

cancer drug resistanceknowledge distillationlarge language model (LLM)model interpretationsingle-cell RNA sequencing

Substanzen

Biomarkers, Tumor

Autor:innen und Institutionen

  • College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China.
  • College of Life Science, Northeast Forestry University, Harbin 150040, China.
  • College of Artificial Intelligence, Henan University, Zhengzhou 450000, China.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhou, M., Luo, Z., Yin, Y. H., Liu, Q., Wang, G., & Zhao, Y. (2025). scATD: a high-throughput and interpretable framework for single-cell cancer drug resistance prediction and biomarker identification. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf268

Vancouver

Zhou M, Luo Z, Yin YH, Liu Q, Wang G, Zhao Y. scATD: a high-throughput and interpretable framework for single-cell cancer drug resistance prediction and biomarker identification. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf268

BibTeX
@article{Zhou2025,
  author = {Zhou, Murong and Luo, Zeyu and Yin, Yu-Hang and Liu, Qiaoming and Wang, Guohua and Zhao, Yuming},
  title = {scATD: a high-throughput and interpretable framework for single-cell cancer drug resistance prediction and biomarker identification},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf268}
}
Kostenlos starten →