GraphCVAE: Uncovering cell heterogeneity and therapeutic target discovery through residual and contrastive learning

Advancements in Spatial Transcriptomics (ST) technologies in recent years have transformed the analysis of tissue structure and function within spatial contexts. However, accurately identifying spatial domains remains challenging due to data sparsity and noise. Traditional clustering methods often f...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Life sciences (1973) Jg. 359; S. 123208
Hauptverfasser: Zhang, Zhiwei, Wang, Mengqiu, Dai, Ruoyan, Wang, Zhenghui, Lei, Lixin, Zhao, Xudong, Han, Kaitai, Shi, Chaojing, Guo, Qianjin
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Netherlands Elsevier Inc 15.12.2024
Schlagworte:
colorectal neoplasms
Colorectal Neoplasms - genetics
Colorectal Neoplasms - pathology
Contrastive learning
data collection
Deep learning
domain
extracellular matrix
Gene expression
Gene Expression Profiling - methods
glioblastoma
Glioblastoma - genetics
Glioblastoma - pathology
Humans
Machine Learning
Neural Networks, Computer
Prefrontal Cortex
Spatial clustering
spatial data
Spatial transcriptomics
therapeutics
Transcriptome
transcriptomics
Variational graph autoencoder
Deep learning
Spatial clustering
Gene expression
Spatial transcriptomics
Variational graph autoencoder
Contrastive learning
ISSN:0024-3205, 1879-0631, 1879-0631
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Advancements in Spatial Transcriptomics (ST) technologies in recent years have transformed the analysis of tissue structure and function within spatial contexts. However, accurately identifying spatial domains remains challenging due to data sparsity and noise. Traditional clustering methods often fail to capture spatial dependencies, while spatial clustering methods struggle with batch effects and data integration. We introduce GraphCVAE, a model designed to enhance spatial domain identification by integrating spatial and morphological information, correcting batch effects, and managing heterogeneous data. GraphCVAE employs a multi-layer Graph Convolutional Network (GCN) and a variational autoencoder to improve the representation and integration of spatial information. Through contrastive learning, the model captures subtle differences between cell types and states. Extensive testing on various ST datasets demonstrates GraphCVAE's robustness and biological contributions. In the dorsolateral prefrontal cortex (DLPFC) dataset, it accurately delineates cortical layer boundaries. In glioblastoma, GraphCVAE reveals critical therapeutic targets such as TF and NFIB. In colorectal cancer, it explores the role of the extracellular matrix in colorectal cancer. The model's performance metrics consistently surpass existing methods, validating its effectiveness. GraphCVAE's advanced visualization capabilities further highlight its precision in resolving spatial structures, making it a powerful tool for spatial transcriptomics analysis and offering new insights into disease studies.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0024-3205
1879-0631
1879-0631
DOI:10.1016/j.lfs.2024.123208