Cargando…

Supervised and Unsupervised End-to-End Deep Learning for Gene Ontology Classification of Neural In Situ Hybridization Images †

In recent years, large datasets of high-resolution mammalian neural images have become available, which has prompted active research on the analysis of gene expression data. Traditional image processing methods are typically applied for learning functional representations of genes, based on their ex...

Descripción completa

Detalles Bibliográficos
Autores principales: Cohen, Ido, David, Eli (Omid), Netanyahu, Nathan S.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7514702/
https://www.ncbi.nlm.nih.gov/pubmed/33266936
http://dx.doi.org/10.3390/e21030221
_version_ 1783586649090818048
author Cohen, Ido
David, Eli (Omid)
Netanyahu, Nathan S.
author_facet Cohen, Ido
David, Eli (Omid)
Netanyahu, Nathan S.
author_sort Cohen, Ido
collection PubMed
description In recent years, large datasets of high-resolution mammalian neural images have become available, which has prompted active research on the analysis of gene expression data. Traditional image processing methods are typically applied for learning functional representations of genes, based on their expressions in these brain images. In this paper, we describe a novel end-to-end deep learning-based method for generating compact representations of in situ hybridization (ISH) images, which are invariant-to-translation. In contrast to traditional image processing methods, our method relies, instead, on deep convolutional denoising autoencoders (CDAE) for processing raw pixel inputs, and generating the desired compact image representations. We provide an in-depth description of our deep learning-based approach, and present extensive experimental results, demonstrating that representations extracted by CDAE can help learn features of functional gene ontology categories for their classification in a highly accurate manner. Our methods improve the previous state-of-the-art classification rate (Liscovitch, et al.) from an average AUC of 0.92 to 0.997, i.e., it achieves 96% reduction in error rate. Furthermore, the representation vectors generated due to our method are more compact in comparison to previous state-of-the-art methods, allowing for a more efficient high-level representation of images. These results are obtained with significantly downsampled images in comparison to the original high-resolution ones, further underscoring the robustness of our proposed method.
format Online
Article
Text
id pubmed-7514702
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-75147022020-11-09 Supervised and Unsupervised End-to-End Deep Learning for Gene Ontology Classification of Neural In Situ Hybridization Images † Cohen, Ido David, Eli (Omid) Netanyahu, Nathan S. Entropy (Basel) Article In recent years, large datasets of high-resolution mammalian neural images have become available, which has prompted active research on the analysis of gene expression data. Traditional image processing methods are typically applied for learning functional representations of genes, based on their expressions in these brain images. In this paper, we describe a novel end-to-end deep learning-based method for generating compact representations of in situ hybridization (ISH) images, which are invariant-to-translation. In contrast to traditional image processing methods, our method relies, instead, on deep convolutional denoising autoencoders (CDAE) for processing raw pixel inputs, and generating the desired compact image representations. We provide an in-depth description of our deep learning-based approach, and present extensive experimental results, demonstrating that representations extracted by CDAE can help learn features of functional gene ontology categories for their classification in a highly accurate manner. Our methods improve the previous state-of-the-art classification rate (Liscovitch, et al.) from an average AUC of 0.92 to 0.997, i.e., it achieves 96% reduction in error rate. Furthermore, the representation vectors generated due to our method are more compact in comparison to previous state-of-the-art methods, allowing for a more efficient high-level representation of images. These results are obtained with significantly downsampled images in comparison to the original high-resolution ones, further underscoring the robustness of our proposed method. MDPI 2019-02-26 /pmc/articles/PMC7514702/ /pubmed/33266936 http://dx.doi.org/10.3390/e21030221 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Cohen, Ido
David, Eli (Omid)
Netanyahu, Nathan S.
Supervised and Unsupervised End-to-End Deep Learning for Gene Ontology Classification of Neural In Situ Hybridization Images †
title Supervised and Unsupervised End-to-End Deep Learning for Gene Ontology Classification of Neural In Situ Hybridization Images †
title_full Supervised and Unsupervised End-to-End Deep Learning for Gene Ontology Classification of Neural In Situ Hybridization Images †
title_fullStr Supervised and Unsupervised End-to-End Deep Learning for Gene Ontology Classification of Neural In Situ Hybridization Images †
title_full_unstemmed Supervised and Unsupervised End-to-End Deep Learning for Gene Ontology Classification of Neural In Situ Hybridization Images †
title_short Supervised and Unsupervised End-to-End Deep Learning for Gene Ontology Classification of Neural In Situ Hybridization Images †
title_sort supervised and unsupervised end-to-end deep learning for gene ontology classification of neural in situ hybridization images †
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7514702/
https://www.ncbi.nlm.nih.gov/pubmed/33266936
http://dx.doi.org/10.3390/e21030221
work_keys_str_mv AT cohenido supervisedandunsupervisedendtoenddeeplearningforgeneontologyclassificationofneuralinsituhybridizationimages
AT davideliomid supervisedandunsupervisedendtoenddeeplearningforgeneontologyclassificationofneuralinsituhybridizationimages
AT netanyahunathans supervisedandunsupervisedendtoenddeeplearningforgeneontologyclassificationofneuralinsituhybridizationimages