Deep convolutional neural networks for annotating gene expression patterns in the mouse brain

Tao Zeng, Rongjian Li, Ravi Mukkamala, Jieping Ye, Shuiwang Ji

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

Background: Profiling gene expression in brain structures at various spatial and temporal scales is essential to understanding how genes regulate the development of brain structures. The Allen Developing Mouse Brain Atlas provides high-resolution 3-D in situ hybridization (ISH) gene expression patterns in multiple developing stages of the mouse brain. Currently, the ISH images are annotated with anatomical terms manually. In this paper, we propose a computational approach to annotate gene expression pattern images in the mouse brain at various structural levels over the course of development. Results: We applied deep convolutional neural network that was trained on a large set of natural images to extract features from the ISH images of developing mouse brain. As a baseline representation, we applied invariant image feature descriptors to capture local statistics from ISH images and used the bag-of-words approach to build image-level representations. Both types of features from multiple ISH image sections of the entire brain were then combined to build 3-D, brain-wide gene expression representations. We employed regularized learning methods for discriminating gene expression patterns in different brain structures. Results show that our approach of using convolutional model as feature extractors achieved superior performance in annotating gene expression patterns at multiple levels of brain structures throughout four developing ages. Overall, we achieved average AUC of 0.894 ± 0.014, as compared with 0.820 ± 0.046 yielded by the bag-of-words approach. Conclusions: Deep convolutional neural network model trained on natural image sets and applied to gene expression pattern annotation tasks yielded superior performance, demonstrating its transfer learning property is applicable to such biological image sets.

Original languageEnglish (US)
Article number147
JournalBMC Bioinformatics
Volume16
Issue number1
DOIs
StatePublished - May 7 2015
Externally publishedYes

Fingerprint

Gene expression
Gene Expression
Mouse
Brain
Neural Networks
Neural networks
In Situ Hybridization
3D
Transfer Learning
Extractor
Neural Networks (Computer)
Atlases
Atlas
Gene Expression Profiling
Profiling
Neural Network Model
Large Set
Descriptors
Area Under Curve
Annotation

ASJC Scopus subject areas

  • Applied Mathematics
  • Structural Biology
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications

Cite this

Deep convolutional neural networks for annotating gene expression patterns in the mouse brain. / Zeng, Tao; Li, Rongjian; Mukkamala, Ravi; Ye, Jieping; Ji, Shuiwang.

In: BMC Bioinformatics, Vol. 16, No. 1, 147, 07.05.2015.

Research output: Contribution to journalArticle

Zeng, Tao ; Li, Rongjian ; Mukkamala, Ravi ; Ye, Jieping ; Ji, Shuiwang. / Deep convolutional neural networks for annotating gene expression patterns in the mouse brain. In: BMC Bioinformatics. 2015 ; Vol. 16, No. 1.
@article{d6afd08c5d8d4e36b3cab13c03afd8bf,
title = "Deep convolutional neural networks for annotating gene expression patterns in the mouse brain",
abstract = "Background: Profiling gene expression in brain structures at various spatial and temporal scales is essential to understanding how genes regulate the development of brain structures. The Allen Developing Mouse Brain Atlas provides high-resolution 3-D in situ hybridization (ISH) gene expression patterns in multiple developing stages of the mouse brain. Currently, the ISH images are annotated with anatomical terms manually. In this paper, we propose a computational approach to annotate gene expression pattern images in the mouse brain at various structural levels over the course of development. Results: We applied deep convolutional neural network that was trained on a large set of natural images to extract features from the ISH images of developing mouse brain. As a baseline representation, we applied invariant image feature descriptors to capture local statistics from ISH images and used the bag-of-words approach to build image-level representations. Both types of features from multiple ISH image sections of the entire brain were then combined to build 3-D, brain-wide gene expression representations. We employed regularized learning methods for discriminating gene expression patterns in different brain structures. Results show that our approach of using convolutional model as feature extractors achieved superior performance in annotating gene expression patterns at multiple levels of brain structures throughout four developing ages. Overall, we achieved average AUC of 0.894 ± 0.014, as compared with 0.820 ± 0.046 yielded by the bag-of-words approach. Conclusions: Deep convolutional neural network model trained on natural image sets and applied to gene expression pattern annotation tasks yielded superior performance, demonstrating its transfer learning property is applicable to such biological image sets.",
author = "Tao Zeng and Rongjian Li and Ravi Mukkamala and Jieping Ye and Shuiwang Ji",
year = "2015",
month = "5",
day = "7",
doi = "10.1186/s12859-015-0553-9",
language = "English (US)",
volume = "16",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Deep convolutional neural networks for annotating gene expression patterns in the mouse brain

AU - Zeng, Tao

AU - Li, Rongjian

AU - Mukkamala, Ravi

AU - Ye, Jieping

AU - Ji, Shuiwang

PY - 2015/5/7

Y1 - 2015/5/7

N2 - Background: Profiling gene expression in brain structures at various spatial and temporal scales is essential to understanding how genes regulate the development of brain structures. The Allen Developing Mouse Brain Atlas provides high-resolution 3-D in situ hybridization (ISH) gene expression patterns in multiple developing stages of the mouse brain. Currently, the ISH images are annotated with anatomical terms manually. In this paper, we propose a computational approach to annotate gene expression pattern images in the mouse brain at various structural levels over the course of development. Results: We applied deep convolutional neural network that was trained on a large set of natural images to extract features from the ISH images of developing mouse brain. As a baseline representation, we applied invariant image feature descriptors to capture local statistics from ISH images and used the bag-of-words approach to build image-level representations. Both types of features from multiple ISH image sections of the entire brain were then combined to build 3-D, brain-wide gene expression representations. We employed regularized learning methods for discriminating gene expression patterns in different brain structures. Results show that our approach of using convolutional model as feature extractors achieved superior performance in annotating gene expression patterns at multiple levels of brain structures throughout four developing ages. Overall, we achieved average AUC of 0.894 ± 0.014, as compared with 0.820 ± 0.046 yielded by the bag-of-words approach. Conclusions: Deep convolutional neural network model trained on natural image sets and applied to gene expression pattern annotation tasks yielded superior performance, demonstrating its transfer learning property is applicable to such biological image sets.

AB - Background: Profiling gene expression in brain structures at various spatial and temporal scales is essential to understanding how genes regulate the development of brain structures. The Allen Developing Mouse Brain Atlas provides high-resolution 3-D in situ hybridization (ISH) gene expression patterns in multiple developing stages of the mouse brain. Currently, the ISH images are annotated with anatomical terms manually. In this paper, we propose a computational approach to annotate gene expression pattern images in the mouse brain at various structural levels over the course of development. Results: We applied deep convolutional neural network that was trained on a large set of natural images to extract features from the ISH images of developing mouse brain. As a baseline representation, we applied invariant image feature descriptors to capture local statistics from ISH images and used the bag-of-words approach to build image-level representations. Both types of features from multiple ISH image sections of the entire brain were then combined to build 3-D, brain-wide gene expression representations. We employed regularized learning methods for discriminating gene expression patterns in different brain structures. Results show that our approach of using convolutional model as feature extractors achieved superior performance in annotating gene expression patterns at multiple levels of brain structures throughout four developing ages. Overall, we achieved average AUC of 0.894 ± 0.014, as compared with 0.820 ± 0.046 yielded by the bag-of-words approach. Conclusions: Deep convolutional neural network model trained on natural image sets and applied to gene expression pattern annotation tasks yielded superior performance, demonstrating its transfer learning property is applicable to such biological image sets.

UR - http://www.scopus.com/inward/record.url?scp=84930203768&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84930203768&partnerID=8YFLogxK

U2 - 10.1186/s12859-015-0553-9

DO - 10.1186/s12859-015-0553-9

M3 - Article

AN - SCOPUS:84930203768

VL - 16

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

IS - 1

M1 - 147

ER -