Improving the Classification of Alzheimer’s Disease Using Hybrid Gene Selection Pipeline and Deep Learning

Alzheimer’s is a progressive, irreversible, neurodegenerative brain disease. Even with prominent symptoms, it takes years to notice, decode, and reveal Alzheimer’s. However, advancements in technologies, such as imaging techniques, help in early diagnosis. Still, sometimes the results are inaccurate...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Nivedhitha Mahendran, P. M. Durai Raj Vincent, Kathiravan Srinivasan, Chuan-Yu Chang
Formato: article
Lenguaje:EN
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://doaj.org/article/dc704992286b42d89f8755b3ef2b363e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:dc704992286b42d89f8755b3ef2b363e
record_format dspace
spelling oai:doaj.org-article:dc704992286b42d89f8755b3ef2b363e2021-11-12T05:29:47ZImproving the Classification of Alzheimer’s Disease Using Hybrid Gene Selection Pipeline and Deep Learning1664-802110.3389/fgene.2021.784814https://doaj.org/article/dc704992286b42d89f8755b3ef2b363e2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fgene.2021.784814/fullhttps://doaj.org/toc/1664-8021Alzheimer’s is a progressive, irreversible, neurodegenerative brain disease. Even with prominent symptoms, it takes years to notice, decode, and reveal Alzheimer’s. However, advancements in technologies, such as imaging techniques, help in early diagnosis. Still, sometimes the results are inaccurate, which delays the treatment. Thus, the research in recent times focused on identifying the molecular biomarkers that differentiate the genotype and phenotype characteristics. However, the gene expression dataset’s generated features are huge, 1,000 or even more than 10,000. To overcome such a curse of dimensionality, feature selection techniques are introduced. We designed a gene selection pipeline combining a filter, wrapper, and unsupervised method to select the relevant genes. We combined the minimum Redundancy and maximum Relevance (mRmR), Wrapper-based Particle Swarm Optimization (WPSO), and Auto encoder to select the relevant features. We used the GSE5281 Alzheimer’s dataset from the Gene Expression Omnibus We implemented an Improved Deep Belief Network (IDBN) with simple stopping criteria after choosing the relevant genes. We used a Bayesian Optimization technique to tune the hyperparameters in the Improved Deep Belief Network. The tabulated results show that the proposed pipeline shows promising results.Nivedhitha MahendranP. M. Durai Raj VincentKathiravan SrinivasanChuan-Yu ChangFrontiers Media S.A.articledeep learningAlzheimer’s diseasegene selectiongene expressionmolecular bio-markersGeneticsQH426-470ENFrontiers in Genetics, Vol 12 (2021)
institution DOAJ
collection DOAJ
language EN
topic deep learning
Alzheimer’s disease
gene selection
gene expression
molecular bio-markers
Genetics
QH426-470
spellingShingle deep learning
Alzheimer’s disease
gene selection
gene expression
molecular bio-markers
Genetics
QH426-470
Nivedhitha Mahendran
P. M. Durai Raj Vincent
Kathiravan Srinivasan
Chuan-Yu Chang
Improving the Classification of Alzheimer’s Disease Using Hybrid Gene Selection Pipeline and Deep Learning
description Alzheimer’s is a progressive, irreversible, neurodegenerative brain disease. Even with prominent symptoms, it takes years to notice, decode, and reveal Alzheimer’s. However, advancements in technologies, such as imaging techniques, help in early diagnosis. Still, sometimes the results are inaccurate, which delays the treatment. Thus, the research in recent times focused on identifying the molecular biomarkers that differentiate the genotype and phenotype characteristics. However, the gene expression dataset’s generated features are huge, 1,000 or even more than 10,000. To overcome such a curse of dimensionality, feature selection techniques are introduced. We designed a gene selection pipeline combining a filter, wrapper, and unsupervised method to select the relevant genes. We combined the minimum Redundancy and maximum Relevance (mRmR), Wrapper-based Particle Swarm Optimization (WPSO), and Auto encoder to select the relevant features. We used the GSE5281 Alzheimer’s dataset from the Gene Expression Omnibus We implemented an Improved Deep Belief Network (IDBN) with simple stopping criteria after choosing the relevant genes. We used a Bayesian Optimization technique to tune the hyperparameters in the Improved Deep Belief Network. The tabulated results show that the proposed pipeline shows promising results.
format article
author Nivedhitha Mahendran
P. M. Durai Raj Vincent
Kathiravan Srinivasan
Chuan-Yu Chang
author_facet Nivedhitha Mahendran
P. M. Durai Raj Vincent
Kathiravan Srinivasan
Chuan-Yu Chang
author_sort Nivedhitha Mahendran
title Improving the Classification of Alzheimer’s Disease Using Hybrid Gene Selection Pipeline and Deep Learning
title_short Improving the Classification of Alzheimer’s Disease Using Hybrid Gene Selection Pipeline and Deep Learning
title_full Improving the Classification of Alzheimer’s Disease Using Hybrid Gene Selection Pipeline and Deep Learning
title_fullStr Improving the Classification of Alzheimer’s Disease Using Hybrid Gene Selection Pipeline and Deep Learning
title_full_unstemmed Improving the Classification of Alzheimer’s Disease Using Hybrid Gene Selection Pipeline and Deep Learning
title_sort improving the classification of alzheimer’s disease using hybrid gene selection pipeline and deep learning
publisher Frontiers Media S.A.
publishDate 2021
url https://doaj.org/article/dc704992286b42d89f8755b3ef2b363e
work_keys_str_mv AT nivedhithamahendran improvingtheclassificationofalzheimersdiseaseusinghybridgeneselectionpipelineanddeeplearning
AT pmdurairajvincent improvingtheclassificationofalzheimersdiseaseusinghybridgeneselectionpipelineanddeeplearning
AT kathiravansrinivasan improvingtheclassificationofalzheimersdiseaseusinghybridgeneselectionpipelineanddeeplearning
AT chuanyuchang improvingtheclassificationofalzheimersdiseaseusinghybridgeneselectionpipelineanddeeplearning
_version_ 1718431200524107776