Zoo: Selecting Transcriptomic and Methylomic Biomarkers by Ensembling Animal-Inspired Swarm Intelligence Feature Selection Algorithms

Biological omics data such as transcriptomes and methylomes have the inherent “large p small n” paradigm, i.e., the number of features is much larger than that of the samples. A feature selection (FS) algorithm selects a subset of the transcriptomic or methylomic biomarkers in order to build a bette...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yuanyuan Han, Lan Huang, Fengfeng Zhou
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	feature selection swarm intelligence machine learning prediction program code Genetics QH426-470
Acceso en línea:	https://doaj.org/article/a333203058734012b20f838f956b4c82
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a333203058734012b20f838f956b4c82
record_format	dspace
spelling	oai:doaj.org-article:a333203058734012b20f838f956b4c822021-11-25T17:42:18ZZoo: Selecting Transcriptomic and Methylomic Biomarkers by Ensembling Animal-Inspired Swarm Intelligence Feature Selection Algorithms10.3390/genes121118142073-4425https://doaj.org/article/a333203058734012b20f838f956b4c822021-11-01T00:00:00Zhttps://www.mdpi.com/2073-4425/12/11/1814https://doaj.org/toc/2073-4425Biological omics data such as transcriptomes and methylomes have the inherent “large p small n” paradigm, i.e., the number of features is much larger than that of the samples. A feature selection (FS) algorithm selects a subset of the transcriptomic or methylomic biomarkers in order to build a better prediction model. The hidden patterns in the FS solution space make it challenging to achieve a feature subset with satisfying prediction performances. Swarm intelligence (SI) algorithms mimic the target searching behaviors of various animals and have demonstrated promising capabilities in selecting features with good machine learning performances. Our study revealed that different SI-based feature selection algorithms contributed complementary searching capabilities in the FS solution space, and their collaboration generated a better feature subset than the individual SI feature selection algorithms. Nine SI-based feature selection algorithms were integrated to vote for the selected features, which were further refined by the dynamic recursive feature elimination framework. In most cases, the proposed Zoo algorithm outperformed the existing feature selection algorithms on transcriptomics and methylomics datasets.Yuanyuan HanLan HuangFengfeng ZhouMDPI AGarticlefeature selectionswarm intelligencemachine learningpredictionprogram codeGeneticsQH426-470ENGenes, Vol 12, Iss 1814, p 1814 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	feature selection swarm intelligence machine learning prediction program code Genetics QH426-470
spellingShingle	feature selection swarm intelligence machine learning prediction program code Genetics QH426-470 Yuanyuan Han Lan Huang Fengfeng Zhou Zoo: Selecting Transcriptomic and Methylomic Biomarkers by Ensembling Animal-Inspired Swarm Intelligence Feature Selection Algorithms
description	Biological omics data such as transcriptomes and methylomes have the inherent “large p small n” paradigm, i.e., the number of features is much larger than that of the samples. A feature selection (FS) algorithm selects a subset of the transcriptomic or methylomic biomarkers in order to build a better prediction model. The hidden patterns in the FS solution space make it challenging to achieve a feature subset with satisfying prediction performances. Swarm intelligence (SI) algorithms mimic the target searching behaviors of various animals and have demonstrated promising capabilities in selecting features with good machine learning performances. Our study revealed that different SI-based feature selection algorithms contributed complementary searching capabilities in the FS solution space, and their collaboration generated a better feature subset than the individual SI feature selection algorithms. Nine SI-based feature selection algorithms were integrated to vote for the selected features, which were further refined by the dynamic recursive feature elimination framework. In most cases, the proposed Zoo algorithm outperformed the existing feature selection algorithms on transcriptomics and methylomics datasets.
format	article
author	Yuanyuan Han Lan Huang Fengfeng Zhou
author_facet	Yuanyuan Han Lan Huang Fengfeng Zhou
author_sort	Yuanyuan Han
title	Zoo: Selecting Transcriptomic and Methylomic Biomarkers by Ensembling Animal-Inspired Swarm Intelligence Feature Selection Algorithms
title_short	Zoo: Selecting Transcriptomic and Methylomic Biomarkers by Ensembling Animal-Inspired Swarm Intelligence Feature Selection Algorithms
title_full	Zoo: Selecting Transcriptomic and Methylomic Biomarkers by Ensembling Animal-Inspired Swarm Intelligence Feature Selection Algorithms
title_fullStr	Zoo: Selecting Transcriptomic and Methylomic Biomarkers by Ensembling Animal-Inspired Swarm Intelligence Feature Selection Algorithms
title_full_unstemmed	Zoo: Selecting Transcriptomic and Methylomic Biomarkers by Ensembling Animal-Inspired Swarm Intelligence Feature Selection Algorithms
title_sort	zoo: selecting transcriptomic and methylomic biomarkers by ensembling animal-inspired swarm intelligence feature selection algorithms
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/a333203058734012b20f838f956b4c82
work_keys_str_mv	AT yuanyuanhan zooselectingtranscriptomicandmethylomicbiomarkersbyensemblinganimalinspiredswarmintelligencefeatureselectionalgorithms AT lanhuang zooselectingtranscriptomicandmethylomicbiomarkersbyensemblinganimalinspiredswarmintelligencefeatureselectionalgorithms AT fengfengzhou zooselectingtranscriptomicandmethylomicbiomarkersbyensemblinganimalinspiredswarmintelligencefeatureselectionalgorithms
_version_	1718412121380749312

Zoo: Selecting Transcriptomic and Methylomic Biomarkers by Ensembling Animal-Inspired Swarm Intelligence Feature Selection Algorithms

Ejemplares similares