EUVIMEDEUVIMED entdecken
Crossref

Assessing parameter efficient methods for pre-trained language model in annotating scRNA-seq data

Yucheng Xia, Yuhang Liu, Tianhao Li, Sihan He, Hong Chang, Yaqing Wang, Yongqing Zhang, Wenyi Ge

Methods · 2024-08 · 228 · 12-21

DOI: 10.1016/j.ymeth.2024.05.007 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Methods, 2024-08. Verfasst von Yucheng Xia und 7 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, 610209, China. Hauptthemen laut MEDLINE: Single-Cell Analysis, RNA-Seq. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 45 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Annotating cell types of single-cell RNA sequencing (scRNA-seq) data is crucial for studying cellular heterogeneity in the tumor microenvironment. Recently, large-scale pre-trained language models (PLMs) have achieved significant progress in cell-type annotation of scRNA-seq data. This approach effectively addresses previous methods' shortcomings in performance and generalization. However, fine-tuning PLMs for different downstream tasks demands considerable computational resources, rendering it impractical. Hence, a new research branch introduces parameter-efficient fine-tuning (PEFT). This involves optimizing a few parameters while leaving the majority unchanged, leading to substantial reductions in computational expenses. Here, we utilize scBERT, a large-scale pre-trained model, to explore the capabilities of three PEFT methods in scRNA-seq cell type annotation. Extensive benchmark studies across several datasets demonstrate the superior applicability of PEFT methods. Furthermore, downstream analysis using models obtained through PEFT showcases their utility in novel cell type discovery and model interpretability for potential marker genes. Our findings underscore the considerable potential of PEFT in PLM-based cell type annotation, presenting novel perspectives for the analysis of scRNA-seq data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Single-Cell AnalysisRNA-SeqHumansSequence Analysis, RNAComputational BiologyAlgorithmsMolecular Sequence AnnotationSoftwareTumor MicroenvironmentSingle-Cell Gene Expression Analysis

Stichwörter der Autor:innen

BioinformaticsCell type annotationParameter-efficient fine-tuningscRNA-seq analysis

Autor:innen und Institutionen

  • Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, 610209, China.
  • School of Computer Science, Chengdu University of Information Technology, Chengdu, 610225, China.
  • School of Computer Science, Chengdu University of Information Technology, Chengdu, 610225, China. Electronic address: gewenyi15@cuit.edu.cn.

Zitieren

APA

Xia, Y., Liu, Y., Li, T., He, S., Chang, H., Wang, Y., Zhang, Y., & Ge, W. (2024). Assessing parameter efficient methods for pre-trained language model in annotating scRNA-seq data. Methods, 228, 12-21. https://doi.org/10.1016/j.ymeth.2024.05.007

Vancouver

Xia Y, Liu Y, Li T, He S, Chang H, Wang Y, et al. Assessing parameter efficient methods for pre-trained language model in annotating scRNA-seq data. Methods. 2024;228:12-21. doi:10.1016/j.ymeth.2024.05.007

BibTeX
@article{Xia2024,
  author = {Xia, Yucheng and Liu, Yuhang and Li, Tianhao and He, Sihan and Chang, Hong and Wang, Yaqing and Zhang, Yongqing and Ge, Wenyi},
  title = {Assessing parameter efficient methods for pre-trained language model in annotating scRNA-seq data},
  journal = {Methods},
  year = {2024},
  volume = {228},
  pages = {12--21},
  doi = {10.1016/j.ymeth.2024.05.007}
}
Kostenlos starten →