Identifying indicator species in ecological habitats using Deep Optimal Feature Learning.

Much of the current research on supervised modelling is focused on maximizing outcome prediction accuracy. However, in engineering disciplines, an arguably more important goal is that of feature extraction, the identification of relevant features associated with the various outcomes. For instance, i...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yiting Tsai, Susan A Baldwin, Bhushan Gopaluni
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/f505eb73dbce472593e0549e10c3d90d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f505eb73dbce472593e0549e10c3d90d
record_format	dspace
spelling	oai:doaj.org-article:f505eb73dbce472593e0549e10c3d90d2021-12-02T20:14:43ZIdentifying indicator species in ecological habitats using Deep Optimal Feature Learning.1932-620310.1371/journal.pone.0256782https://doaj.org/article/f505eb73dbce472593e0549e10c3d90d2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0256782https://doaj.org/toc/1932-6203Much of the current research on supervised modelling is focused on maximizing outcome prediction accuracy. However, in engineering disciplines, an arguably more important goal is that of feature extraction, the identification of relevant features associated with the various outcomes. For instance, in microbial communities, the identification of keystone species can often lead to improved prediction of future behavioral shifts. This paper proposes a novel feature extractor based on Deep Learning, which is largely agnostic to underlying assumptions regarding the training data. Starting from a collection of microbial species abundance counts, the Deep Learning model first trains itself to classify the selected distinct habitats. It then identifies indicator species associated with the habitats. The results are then compared and contrasted with those obtained by traditional statistical techniques. The indicator species are similar when compared at top taxonomic levels such as Domain and Phylum, despite visible differences in lower levels such as Class and Order. More importantly, when our estimated indicators are used to predict final habitat labels using simpler models (such as Support Vector Machines and traditional Artificial Neural Networks), the prediction accuracy is improved. Overall, this study serves as a preliminary step that bridges modern, black-box Machine Learning models with traditional, domain expertise-rich techniques.Yiting TsaiSusan A BaldwinBhushan GopaluniPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 9, p e0256782 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Yiting Tsai Susan A Baldwin Bhushan Gopaluni Identifying indicator species in ecological habitats using Deep Optimal Feature Learning.
description	Much of the current research on supervised modelling is focused on maximizing outcome prediction accuracy. However, in engineering disciplines, an arguably more important goal is that of feature extraction, the identification of relevant features associated with the various outcomes. For instance, in microbial communities, the identification of keystone species can often lead to improved prediction of future behavioral shifts. This paper proposes a novel feature extractor based on Deep Learning, which is largely agnostic to underlying assumptions regarding the training data. Starting from a collection of microbial species abundance counts, the Deep Learning model first trains itself to classify the selected distinct habitats. It then identifies indicator species associated with the habitats. The results are then compared and contrasted with those obtained by traditional statistical techniques. The indicator species are similar when compared at top taxonomic levels such as Domain and Phylum, despite visible differences in lower levels such as Class and Order. More importantly, when our estimated indicators are used to predict final habitat labels using simpler models (such as Support Vector Machines and traditional Artificial Neural Networks), the prediction accuracy is improved. Overall, this study serves as a preliminary step that bridges modern, black-box Machine Learning models with traditional, domain expertise-rich techniques.
format	article
author	Yiting Tsai Susan A Baldwin Bhushan Gopaluni
author_facet	Yiting Tsai Susan A Baldwin Bhushan Gopaluni
author_sort	Yiting Tsai
title	Identifying indicator species in ecological habitats using Deep Optimal Feature Learning.
title_short	Identifying indicator species in ecological habitats using Deep Optimal Feature Learning.
title_full	Identifying indicator species in ecological habitats using Deep Optimal Feature Learning.
title_fullStr	Identifying indicator species in ecological habitats using Deep Optimal Feature Learning.
title_full_unstemmed	Identifying indicator species in ecological habitats using Deep Optimal Feature Learning.
title_sort	identifying indicator species in ecological habitats using deep optimal feature learning.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/f505eb73dbce472593e0549e10c3d90d
work_keys_str_mv	AT yitingtsai identifyingindicatorspeciesinecologicalhabitatsusingdeepoptimalfeaturelearning AT susanabaldwin identifyingindicatorspeciesinecologicalhabitatsusingdeepoptimalfeaturelearning AT bhushangopaluni identifyingindicatorspeciesinecologicalhabitatsusingdeepoptimalfeaturelearning
_version_	1718374681517490176

Identifying indicator species in ecological habitats using Deep Optimal Feature Learning.

Ejemplares similares