Cover Image

Gene selection and classification of microarray gene expression data based on a new adaptive L1-norm elastic net penalty

The removal of irrelevant and insignificant genes has always been a major step in microarray data analysis. The application of gene selection methods in biological datasets has greatly increased, supporting expert systems in cancer diagnostic capability with high classification accuracy. Penalized l...

Full description

Saved in:
Bibliographic Details
Main Authors: Alharthi, Aiedh Mrisi, Lee, Muhammad Hisyam, Algamal, Zakariya Yahya
Format: Article
Language:English
Published: Elsevier Ltd 2021
Subjects:
QA Mathematics
Online Access:http://eprints.utm.my/id/eprint/95607/1/MuhammadHisyamLee2021_GeneSelectionAndClassificationOfMicroarrayGene.pdf
http://eprints.utm.my/id/eprint/95607/
http://dx.doi.org/10.1016/j.imu.2021.100622
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.95607
record_format eprints
spelling my.utm.956072022-05-31T13:04:30Z http://eprints.utm.my/id/eprint/95607/ Gene selection and classification of microarray gene expression data based on a new adaptive L1-norm elastic net penalty Alharthi, Aiedh Mrisi Lee, Muhammad Hisyam Algamal, Zakariya Yahya QA Mathematics The removal of irrelevant and insignificant genes has always been a major step in microarray data analysis. The application of gene selection methods in biological datasets has greatly increased, supporting expert systems in cancer diagnostic capability with high classification accuracy. Penalized logistic regression (PLR) using the elastic net (EN) has been widely used in high-dimensional cancer classification in recent years to estimate the gene coefficients and perform gene selection simultaneously. However, the EN estimator does not satisfy the oracle properties. This paper proposes the PLR using the adaptive elastic net (AEN), abbreviated as PLRAEN, to address the inconsistency. Our method employs the ratio (BWR) as an initial weight inside the L1-norm of the EN model. Several experiments were performed on a simulation study for a different number of predictor variables, sample sizes, and correlation coefficients and also on three public gene expression datasets to evaluate the effectiveness. Experimental results demonstrate that the proposed method consistently outperforms two other contemporary penalized methods regarding classification accuracy and the number of selected genes. Therefore, we conclude that PLRAEN is a better method to implement gene selection in the high-dimensional cancer classification field. Elsevier Ltd 2021 Article PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/95607/1/MuhammadHisyamLee2021_GeneSelectionAndClassificationOfMicroarrayGene.pdf Alharthi, Aiedh Mrisi and Lee, Muhammad Hisyam and Algamal, Zakariya Yahya (2021) Gene selection and classification of microarray gene expression data based on a new adaptive L1-norm elastic net penalty. Informatics in Medicine Unlocked, 24 . p. 100622. ISSN 2352-9148 http://dx.doi.org/10.1016/j.imu.2021.100622
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic QA Mathematics
spellingShingle QA Mathematics
Alharthi, Aiedh Mrisi
Lee, Muhammad Hisyam
Algamal, Zakariya Yahya
Gene selection and classification of microarray gene expression data based on a new adaptive L1-norm elastic net penalty
description The removal of irrelevant and insignificant genes has always been a major step in microarray data analysis. The application of gene selection methods in biological datasets has greatly increased, supporting expert systems in cancer diagnostic capability with high classification accuracy. Penalized logistic regression (PLR) using the elastic net (EN) has been widely used in high-dimensional cancer classification in recent years to estimate the gene coefficients and perform gene selection simultaneously. However, the EN estimator does not satisfy the oracle properties. This paper proposes the PLR using the adaptive elastic net (AEN), abbreviated as PLRAEN, to address the inconsistency. Our method employs the ratio (BWR) as an initial weight inside the L1-norm of the EN model. Several experiments were performed on a simulation study for a different number of predictor variables, sample sizes, and correlation coefficients and also on three public gene expression datasets to evaluate the effectiveness. Experimental results demonstrate that the proposed method consistently outperforms two other contemporary penalized methods regarding classification accuracy and the number of selected genes. Therefore, we conclude that PLRAEN is a better method to implement gene selection in the high-dimensional cancer classification field.
format Article
author Alharthi, Aiedh Mrisi
Lee, Muhammad Hisyam
Algamal, Zakariya Yahya
author_facet Alharthi, Aiedh Mrisi
Lee, Muhammad Hisyam
Algamal, Zakariya Yahya
author_sort Alharthi, Aiedh Mrisi
title Gene selection and classification of microarray gene expression data based on a new adaptive L1-norm elastic net penalty
title_short Gene selection and classification of microarray gene expression data based on a new adaptive L1-norm elastic net penalty
title_full Gene selection and classification of microarray gene expression data based on a new adaptive L1-norm elastic net penalty
title_fullStr Gene selection and classification of microarray gene expression data based on a new adaptive L1-norm elastic net penalty
title_full_unstemmed Gene selection and classification of microarray gene expression data based on a new adaptive L1-norm elastic net penalty
title_sort gene selection and classification of microarray gene expression data based on a new adaptive l1-norm elastic net penalty
publisher Elsevier Ltd
publishDate 2021
url http://eprints.utm.my/id/eprint/95607/1/MuhammadHisyamLee2021_GeneSelectionAndClassificationOfMicroarrayGene.pdf
http://eprints.utm.my/id/eprint/95607/
http://dx.doi.org/10.1016/j.imu.2021.100622
_version_ 1735386825088827392
score 13.211869

Similar Items