Recover then aggregate: unified cross-modal deep clustering with global structural information for single-cell data
Briefings in Bioinformatics · 2024
DOI: 10.1093/bib/bbae485 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2024. Verfasst von Ziyi Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Surgical Oncology and General Surgery, First Hospital of China Medical University, Shenyang 110001, PR China. Hauptthemen laut MEDLINE: Single-Cell Analysis. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Technology Program Joint Fund of Liaoning Province.
Abstract (Originalsprache)
Single-cell cross-modal joint clustering has been extensively utilized to investigate the tumor microenvironment. Although numerous approaches have been suggested, accurate clustering remains the main challenge. First, the gene expression matrix frequently contains numerous missing values due to measurement limitations. The majority of existing clustering methods treat it as a typical multi-modal dataset without further processing. Few methods conduct recovery before clustering and do not sufficiently engage with the underlying research, leading to suboptimal outcomes. Additionally, the existing cross-modal information fusion strategy does not ensure consistency of representations across different modes, potentially leading to the integration of conflicting information, which could degrade performance. To address these challenges, we propose the ’Recover then Aggregate’ strategy and introduce the Unified Cross-Modal Deep Clustering model. Specifically, we have developed a data augmentation technique based on neighborhood similarity, iteratively imposing rank constraints on the Laplacian matrix, thus updating the similarity matrix and recovering dropout events. Concurrently, we integrate cross-modal features and employ contrastive learning to align modality-specific representations with consistent ones, enhancing the effective integration of diverse modal information. Comprehensive experiments on five real-world multi-modal datasets have demonstrated this method’s superior effectiveness in single-cell clustering tasks.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Surgical Oncology and General Surgery, First Hospital of China Medical University, Shenyang 110001, PR China.
- Section of Esophageal and Mediastinal Oncology, Department of Thoracic Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union M…
- Department of Thoracic Surgery, The First Hospital of China Medical University, No.155 North Nanjing Street, Shenyang 110001, People's Republic of China.
- Department of Thoracic Surgery, Xinqiao Hospital, Army Medical University, Chongqing 400038, China.
- Department of Pathology, People's Hospital of China Medical University (Liaoning Provincial People's Hospital), Shenyang, Liaoning Province 110015, People's Republic of China.
- Electrical and Computer Engineering, University of Illinois at Chicago, Chicago, IL 60607, United States.
Förderung
- National Natural Science Foundation of China
- Technology Program Joint Fund of Liaoning Province
Zitieren
APA
Wang, Z., Luo, P., Xiao, M., Wang, B., Liu, T., & Sun, X. (2024). Recover then aggregate: unified cross-modal deep clustering with global structural information for single-cell data. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbae485
Vancouver
Wang Z, Luo P, Xiao M, Wang B, Liu T, Sun X. Recover then aggregate: unified cross-modal deep clustering with global structural information for single-cell data. Briefings in Bioinformatics. 2024. doi:10.1093/bib/bbae485
BibTeX
@article{Wang2024,
author = {Wang, Ziyi and Luo, Peng and Xiao, Mingming and Wang, Boyang and Liu, Tianyu and Sun, Xiangyu},
title = {Recover then aggregate: unified cross-modal deep clustering with global structural information for single-cell data},
journal = {Briefings in Bioinformatics},
year = {2024},
doi = {10.1093/bib/bbae485}
}
EUVIMED