GCNG: graph convolutional networks for inferring gene interaction from spatial transcriptomics data.
PMID:33303016
|
IF: 17.906
|
Cited by: 65
|
Download citation

Abstract

Most methods for inferring gene-gene interactions from expression data focus on intracellular interactions. The availability of high-throughput spatial expression data opens the door to methods that can infer such interactions both within and between cells. To achieve this, we developed Graph Convolutional Neural networks for Genes (GCNG). GCNG encodes the spatial information as a graph and combines it with expression data using supervised training. GCNG improves upon prior methods used to analyze spatial transcriptomics data and can propose novel pairs of extracellular interacting genes. The output of GCNG can also be used for downstream analysis including functional gene assignment.Supporting website with software and data: https://github.com/xiaoyeye/GCNG .

Keywords

Spatial Transcriptomics
Extracellular gene interactions
Graph convolutional networks
Spatial transcriptomics

MeSH terms

Animals
Computational Biology
Epistasis, Genetic
Gene Expression
Humans
Ligands
Mice
Neural Networks, Computer
Software
Transcriptome

Authors

Yuan, Ye
Bar-Joseph, Ziv

Recommend literature

1. SpaGCN: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network.
2. DSTG: deconvoluting spatial transcriptomics data through graph-based artificial intelligence.
3. SpaCell: integrating tissue morphology and spatial gene expression to predict disease cells.
4. Deep learning of gene relationships from single cell time-course expression data.
5. ST viewer: a tool for analysis and visualization of spatial transcriptomics datasets.

Similar data

1. Molecular, Spatial and Functional Single-Cell Profiling of the Hypothalamic Preoptic Region
2. Single cell RNA-seq and ATAC-seq of EMT induced by TGFbeta stimulation and Zeb1 overexpression
3. Comparative gene expression profiling of human PGP1 iPS, lymphocyte, donor fibroblasts
4. Exploiting single-cell expression to characterize co-expression replicability
5. Genome-wide long non-coding RNAs and mRNAs analysis of the tissues related to ovarian endometriosis