De novo reconstruction of cell interaction landscapes from single-cell spatial transcriptome data with DeepLinc

Based on a deep generative model of variational graph autoencoder (VGAE), we develop a new method, DeepLinc (deep learning framework for Landscapes of Interacting Cells), for the de novo reconstruction of cell interaction networks from single-cell spatial transcriptomic data. DeepLinc demonstrates h...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Genome Biology Ročník 23; číslo 1; s. 124
Hlavní autori: Li, Runze, Yang, Xuerui
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: London BioMed Central 03.06.2022
Springer Nature B.V
BMC
Predmet:
Animal Genetics and Genomics
Bioinformatics
Biomedical and Life Sciences
Cell Communication
Cell interaction
Datasets
Deep learning
Design
Evolutionary Biology
Gene expression
genome
Graph representations
Human Genetics
Life Sciences
Ligands
Method
Microbial Genetics and Genomics
Normal distribution
Physiology
Plant Genetics and Genomics
Single-cell spatial transcriptome
Transcriptome
Transcriptomes
Transcriptomics
Variational graph autoencoder
VGAE
Deep learning
Single-cell spatial transcriptome
Cell interaction
Variational graph autoencoder
VGAE
ISSN:1474-760X, 1474-7596, 1474-760X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Based on a deep generative model of variational graph autoencoder (VGAE), we develop a new method, DeepLinc (deep learning framework for Landscapes of Interacting Cells), for the de novo reconstruction of cell interaction networks from single-cell spatial transcriptomic data. DeepLinc demonstrates high efficiency in learning from imperfect and incomplete spatial transcriptome data, filtering false interactions, and imputing missing distal and proximal interactions. The latent representations learned by DeepLinc are also used for inferring the signature genes contributing to the cell interaction landscapes, and for reclustering the cells based on the spatially coded cell heterogeneity in complex tissues at single-cell resolution.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1474-760X
1474-7596
1474-760X
DOI:10.1186/s13059-022-02692-0