Discover mouse gene coexpression landscapes using dictionary learning and sparse coding

Yujie Li, Hanbo Chen, Xi Jiang, Xiang Li, Jinglei Lv, Hanchuan Peng, Joseph Zhuo Tsien, Tianming Liu

Research output: Contribution to journalArticle

Abstract

Gene coexpression patterns carry rich information regarding enormously complex brain structures and functions. Characterization of these patterns in an unbiased, integrated, and anatomically comprehensive manner will illuminate the higher-order transcriptome organization and offer genetic foundations of functional circuitry. Here using dictionary learning and sparse coding, we derived coexpression networks from the space-resolved anatomical comprehensive in situ hybridization data from Allen Mouse Brain Atlas dataset. The key idea is that if two genes use the same dictionary to represent their original signals, then their gene expressions must share similar patterns, thereby considering them as “coexpressed.” For each network, we have simultaneous knowledge of spatial distributions, the genes in the network and the extent a particular gene conforms to the coexpression pattern. Gene ontologies and the comparisons with published gene lists reveal biologically identified coexpression networks, some of which correspond to major cell types, biological pathways, and/or anatomical regions.

Original languageEnglish (US)
Pages (from-to)4253-4270
Number of pages18
JournalBrain Structure and Function
Volume222
Issue number9
DOIs
StatePublished - Dec 1 2017

Fingerprint

Learning
Genes
Gene Ontology
Atlases
Gene Regulatory Networks
Brain
Transcriptome
In Situ Hybridization
Gene Expression
Datasets

Keywords

  • Gene coexpression network
  • Sparse coding
  • Transcriptome

ASJC Scopus subject areas

  • Anatomy
  • Neuroscience(all)
  • Histology

Cite this

Discover mouse gene coexpression landscapes using dictionary learning and sparse coding. / Li, Yujie; Chen, Hanbo; Jiang, Xi; Li, Xiang; Lv, Jinglei; Peng, Hanchuan; Tsien, Joseph Zhuo; Liu, Tianming.

In: Brain Structure and Function, Vol. 222, No. 9, 01.12.2017, p. 4253-4270.

Research output: Contribution to journalArticle

Li, Yujie ; Chen, Hanbo ; Jiang, Xi ; Li, Xiang ; Lv, Jinglei ; Peng, Hanchuan ; Tsien, Joseph Zhuo ; Liu, Tianming. / Discover mouse gene coexpression landscapes using dictionary learning and sparse coding. In: Brain Structure and Function. 2017 ; Vol. 222, No. 9. pp. 4253-4270.
@article{53ee21cd8b594d469b91e4c64b188571,
title = "Discover mouse gene coexpression landscapes using dictionary learning and sparse coding",
abstract = "Gene coexpression patterns carry rich information regarding enormously complex brain structures and functions. Characterization of these patterns in an unbiased, integrated, and anatomically comprehensive manner will illuminate the higher-order transcriptome organization and offer genetic foundations of functional circuitry. Here using dictionary learning and sparse coding, we derived coexpression networks from the space-resolved anatomical comprehensive in situ hybridization data from Allen Mouse Brain Atlas dataset. The key idea is that if two genes use the same dictionary to represent their original signals, then their gene expressions must share similar patterns, thereby considering them as “coexpressed.” For each network, we have simultaneous knowledge of spatial distributions, the genes in the network and the extent a particular gene conforms to the coexpression pattern. Gene ontologies and the comparisons with published gene lists reveal biologically identified coexpression networks, some of which correspond to major cell types, biological pathways, and/or anatomical regions.",
keywords = "Gene coexpression network, Sparse coding, Transcriptome",
author = "Yujie Li and Hanbo Chen and Xi Jiang and Xiang Li and Jinglei Lv and Hanchuan Peng and Tsien, {Joseph Zhuo} and Tianming Liu",
year = "2017",
month = "12",
day = "1",
doi = "10.1007/s00429-017-1460-9",
language = "English (US)",
volume = "222",
pages = "4253--4270",
journal = "Brain Structure and Function",
issn = "1863-2653",
publisher = "Springer Verlag",
number = "9",

}

TY - JOUR

T1 - Discover mouse gene coexpression landscapes using dictionary learning and sparse coding

AU - Li, Yujie

AU - Chen, Hanbo

AU - Jiang, Xi

AU - Li, Xiang

AU - Lv, Jinglei

AU - Peng, Hanchuan

AU - Tsien, Joseph Zhuo

AU - Liu, Tianming

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Gene coexpression patterns carry rich information regarding enormously complex brain structures and functions. Characterization of these patterns in an unbiased, integrated, and anatomically comprehensive manner will illuminate the higher-order transcriptome organization and offer genetic foundations of functional circuitry. Here using dictionary learning and sparse coding, we derived coexpression networks from the space-resolved anatomical comprehensive in situ hybridization data from Allen Mouse Brain Atlas dataset. The key idea is that if two genes use the same dictionary to represent their original signals, then their gene expressions must share similar patterns, thereby considering them as “coexpressed.” For each network, we have simultaneous knowledge of spatial distributions, the genes in the network and the extent a particular gene conforms to the coexpression pattern. Gene ontologies and the comparisons with published gene lists reveal biologically identified coexpression networks, some of which correspond to major cell types, biological pathways, and/or anatomical regions.

AB - Gene coexpression patterns carry rich information regarding enormously complex brain structures and functions. Characterization of these patterns in an unbiased, integrated, and anatomically comprehensive manner will illuminate the higher-order transcriptome organization and offer genetic foundations of functional circuitry. Here using dictionary learning and sparse coding, we derived coexpression networks from the space-resolved anatomical comprehensive in situ hybridization data from Allen Mouse Brain Atlas dataset. The key idea is that if two genes use the same dictionary to represent their original signals, then their gene expressions must share similar patterns, thereby considering them as “coexpressed.” For each network, we have simultaneous knowledge of spatial distributions, the genes in the network and the extent a particular gene conforms to the coexpression pattern. Gene ontologies and the comparisons with published gene lists reveal biologically identified coexpression networks, some of which correspond to major cell types, biological pathways, and/or anatomical regions.

KW - Gene coexpression network

KW - Sparse coding

KW - Transcriptome

UR - http://www.scopus.com/inward/record.url?scp=85021738633&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021738633&partnerID=8YFLogxK

U2 - 10.1007/s00429-017-1460-9

DO - 10.1007/s00429-017-1460-9

M3 - Article

VL - 222

SP - 4253

EP - 4270

JO - Brain Structure and Function

JF - Brain Structure and Function

SN - 1863-2653

IS - 9

ER -