Complete spatially resolved gene expression is not necessary for identifying spatial domains

Senlin Lin; Yan Cui; Fangyuan Zhao; Zhidong Yang; Jiangning Song; Jianhua Yao; Yu Zhao; Bin-Zhi Qian; Yi Zhao; Zhiyuan Yuan

doi:10.1016/j.xgen.2024.100565

Complete spatially resolved gene expression is not necessary for identifying spatial domains

Senlin Lin, Yan Cui, Fangyuan Zhao, Zhidong Yang, Jiangning Song, Jianhua Yao, Yu Zhao, Bin-Zhi Qian, Yi Zhao, Zhiyuan Yuan

Research output: Contribution to journal › Article › Research › peer-review

Abstract

Spatially resolved transcriptomics (SRT) technologies have revolutionized the study of tissue organization. We introduce a graph convolutional network with an attention and positive emphasis mechanism, termed BINARY, relying exclusively on binarized SRT data to accurately delineate spatial domains. BINARY outperforms existing methods across various SRT data types while using significantly less input information. Our study suggests that precise gene expression quantification may not always be essential, inspiring further exploration of the broader applications of spatially resolved binarized gene expression data.

Original language	English
Article number	100565
Number of pages	15
Journal	Cell Genomics
Volume	4
Issue number	6
DOIs	https://doi.org/10.1016/j.xgen.2024.100565
Publication status	Published - 12 Jun 2024

Keywords

binary spatially resolved gene expression
bioinformatics
computational biology
graph convolutional network
spatial clustering
spatial domain
spatial omics
spatially resolved gene expression
spatially resolved transcriptomics
spatially variable gene

Access to Document

10.1016/j.xgen.2024.100565Licence: CC BY-NC-ND

Cite this

@article{2d20b5ead1784497b6d90ef39839c536,

title = "Complete spatially resolved gene expression is not necessary for identifying spatial domains",

abstract = "Spatially resolved transcriptomics (SRT) technologies have revolutionized the study of tissue organization. We introduce a graph convolutional network with an attention and positive emphasis mechanism, termed BINARY, relying exclusively on binarized SRT data to accurately delineate spatial domains. BINARY outperforms existing methods across various SRT data types while using significantly less input information. Our study suggests that precise gene expression quantification may not always be essential, inspiring further exploration of the broader applications of spatially resolved binarized gene expression data.",

keywords = "binary spatially resolved gene expression, bioinformatics, computational biology, graph convolutional network, spatial clustering, spatial domain, spatial omics, spatially resolved gene expression, spatially resolved transcriptomics, spatially variable gene",

author = "Senlin Lin and Yan Cui and Fangyuan Zhao and Zhidong Yang and Jiangning Song and Jianhua Yao and Yu Zhao and Bin-Zhi Qian and Yi Zhao and Zhiyuan Yuan",

note = "Publisher Copyright: {\textcopyright} 2024 The Authors",

year = "2024",

month = jun,

day = "12",

doi = "10.1016/j.xgen.2024.100565",

language = "English",

volume = "4",

journal = "Cell Genomics",

issn = "2666-979X",

publisher = "Cell Press",

number = "6",

}

TY - JOUR

T1 - Complete spatially resolved gene expression is not necessary for identifying spatial domains

AU - Lin, Senlin

AU - Cui, Yan

AU - Zhao, Fangyuan

AU - Yang, Zhidong

AU - Song, Jiangning

AU - Yao, Jianhua

AU - Zhao, Yu

AU - Qian, Bin-Zhi

AU - Zhao, Yi

AU - Yuan, Zhiyuan

PY - 2024/6/12

Y1 - 2024/6/12

N2 - Spatially resolved transcriptomics (SRT) technologies have revolutionized the study of tissue organization. We introduce a graph convolutional network with an attention and positive emphasis mechanism, termed BINARY, relying exclusively on binarized SRT data to accurately delineate spatial domains. BINARY outperforms existing methods across various SRT data types while using significantly less input information. Our study suggests that precise gene expression quantification may not always be essential, inspiring further exploration of the broader applications of spatially resolved binarized gene expression data.

AB - Spatially resolved transcriptomics (SRT) technologies have revolutionized the study of tissue organization. We introduce a graph convolutional network with an attention and positive emphasis mechanism, termed BINARY, relying exclusively on binarized SRT data to accurately delineate spatial domains. BINARY outperforms existing methods across various SRT data types while using significantly less input information. Our study suggests that precise gene expression quantification may not always be essential, inspiring further exploration of the broader applications of spatially resolved binarized gene expression data.

KW - binary spatially resolved gene expression

KW - bioinformatics

KW - computational biology

KW - graph convolutional network

KW - spatial clustering

KW - spatial domain

KW - spatial omics

KW - spatially resolved gene expression

KW - spatially resolved transcriptomics

KW - spatially variable gene

UR - http://www.scopus.com/inward/record.url?scp=85195418466&partnerID=8YFLogxK

U2 - 10.1016/j.xgen.2024.100565

DO - 10.1016/j.xgen.2024.100565

M3 - Article

C2 - 38781966

AN - SCOPUS:85195418466

SN - 2666-979X

VL - 4

JO - Cell Genomics

JF - Cell Genomics

IS - 6

M1 - 100565

ER -

Complete spatially resolved gene expression is not necessary for identifying spatial domains

Abstract

Keywords

Access to Document

Other files and links

Cite this