scLEGA: an attention-based deep clustering method with a tendency for low expression of genes on single-cell RNA-seq data
Briefings in Bioinformatics · 2024
DOI: 10.1093/bib/bbae371 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2024. Verfasst von Zhenze Liu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Aulin College, Northeast Forestry University 150040, 26 Hexing Road, Xiangfang District, Harbin, China. Hauptthemen laut MEDLINE: RNA-Seq, Single-Cell Gene Expression Analysis. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R and D Program of China, National Natural Science Foundation of China, National Science Foundation for Distinguished Young Scholars of China.
Abstract (Originalsprache)
Single-cell RNA sequencing (scRNA-seq) enables the exploration of biological heterogeneity among different cell types within tissues at a resolution. Inferring cell types within tissues is foundational for downstream research. Most existing methods for cell type inference based on scRNA-seq data primarily utilize highly variable genes (HVGs) with higher expression levels as clustering features, overlooking the contribution of HVGs with lower expression levels. To address this, we have designed a novel cell type inference method for scRNA-seq data, termed scLEGA. scLEGA employs a novel zero-inflated negative binomial (ZINB) loss function that fully considers the contribution of genes with lower expression levels and combines two distinct scRNA-seq clustering strategies through a multi-head attention mechanism. It utilizes a low-expression optimized denoising autoencoder, based on the novel ZINB model, to extract low-dimensional features and handle dropout events, and a GCN-based graph autoencoder (GAE) that leverages neighbor information to guide dimensionality reduction. The iterative fusion of denoising and topological embedding in scLEGA facilitates the acquisition of cluster-friendly cell representations in the hidden embedding, where similar cells are brought closer together. Compared to 12 state-of-the-art cell type inference methods on 15 scRNA-seq datasets, scLEGA demonstrates superior performance in clustering accuracy, scalability, and stability. Our scLEGA model codes are freely available at https://github.com/Masonze/scLEGA-main.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Aulin College, Northeast Forestry University 150040, 26 Hexing Road, Xiangfang District, Harbin, China.
- Key Laboratory of Hepatosplenic Surgery, Ministry of Education, Department of General Surgery, the First Affiliated Hospital of Harbin Medical University 150001, 23 Postal Street, Nangang District, Harbin, China.
- College of Computer and Control Engineering, Northeast Forestry University 150040, 26 Hexing Road, Xiangfang District, Harbin, China.
- Faculty of Computing, Harbin Institute of Technology 150006, 92 West Dazhi Street, Nangang District, Harbin, China.
ORCID-Profile: Zhenze Liu, Tianjiao Zhang
Förderung
- National Key R and D Program of China
- National Natural Science Foundation of China
- National Science Foundation for Distinguished Young Scholars of China
Zitieren
APA
Liu, Z., Liang, Y., Wang, G., & Zhang, T. (2024). scLEGA: an attention-based deep clustering method with a tendency for low expression of genes on single-cell RNA-seq data. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbae371
Vancouver
Liu Z, Liang Y, Wang G, Zhang T. scLEGA: an attention-based deep clustering method with a tendency for low expression of genes on single-cell RNA-seq data. Briefings in Bioinformatics. 2024. doi:10.1093/bib/bbae371
BibTeX
@article{Liu2024,
author = {Liu, Zhenze and Liang, Yingjian and Wang, Guohua and Zhang, Tianjiao},
title = {scLEGA: an attention-based deep clustering method with a tendency for low expression of genes on single-cell RNA-seq data},
journal = {Briefings in Bioinformatics},
year = {2024},
doi = {10.1093/bib/bbae371}
}
EUVIMED