Cargando…

Human disease prediction from microbiome data by multiple feature fusion and deep learning

Human disease prediction from microbiome data has broad implications in metagenomics. It is rare for the existing methods to consider abundance profiles from both known and unknown microbial organisms, or capture the taxonomic relationships among microbial taxa, leading to significant information lo...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Xingjian, Zhu, Zifan, Zhang, Weitong, Wang, Yuchen, Wang, Fuzhou, Yang, Jianyi, Wong, Ka-Chun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8971930/
https://www.ncbi.nlm.nih.gov/pubmed/35372808
http://dx.doi.org/10.1016/j.isci.2022.104081
_version_ 1784679742814814208
author Chen, Xingjian
Zhu, Zifan
Zhang, Weitong
Wang, Yuchen
Wang, Fuzhou
Yang, Jianyi
Wong, Ka-Chun
author_facet Chen, Xingjian
Zhu, Zifan
Zhang, Weitong
Wang, Yuchen
Wang, Fuzhou
Yang, Jianyi
Wong, Ka-Chun
author_sort Chen, Xingjian
collection PubMed
description Human disease prediction from microbiome data has broad implications in metagenomics. It is rare for the existing methods to consider abundance profiles from both known and unknown microbial organisms, or capture the taxonomic relationships among microbial taxa, leading to significant information loss. On the other hand, deep learning has shown unprecedented advantages in classification tasks for its feature-learning ability. However, it encounters the opposite situation in metagenome-based disease prediction since high-dimensional low-sample-size metagenomic datasets can lead to severe overfitting; and black-box model fails in providing biological explanations. To circumvent the related problems, we developed MetaDR, a comprehensive machine learning-based framework that integrates various information and deep learning to predict human diseases. Experimental results indicate that MetaDR achieves competitive prediction performance with a reduction in running time, and effectively discovers the informative features with biological insights.
format Online
Article
Text
id pubmed-8971930
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-89719302022-04-02 Human disease prediction from microbiome data by multiple feature fusion and deep learning Chen, Xingjian Zhu, Zifan Zhang, Weitong Wang, Yuchen Wang, Fuzhou Yang, Jianyi Wong, Ka-Chun iScience Article Human disease prediction from microbiome data has broad implications in metagenomics. It is rare for the existing methods to consider abundance profiles from both known and unknown microbial organisms, or capture the taxonomic relationships among microbial taxa, leading to significant information loss. On the other hand, deep learning has shown unprecedented advantages in classification tasks for its feature-learning ability. However, it encounters the opposite situation in metagenome-based disease prediction since high-dimensional low-sample-size metagenomic datasets can lead to severe overfitting; and black-box model fails in providing biological explanations. To circumvent the related problems, we developed MetaDR, a comprehensive machine learning-based framework that integrates various information and deep learning to predict human diseases. Experimental results indicate that MetaDR achieves competitive prediction performance with a reduction in running time, and effectively discovers the informative features with biological insights. Elsevier 2022-03-16 /pmc/articles/PMC8971930/ /pubmed/35372808 http://dx.doi.org/10.1016/j.isci.2022.104081 Text en © 2022 The Author(s) https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Article
Chen, Xingjian
Zhu, Zifan
Zhang, Weitong
Wang, Yuchen
Wang, Fuzhou
Yang, Jianyi
Wong, Ka-Chun
Human disease prediction from microbiome data by multiple feature fusion and deep learning
title Human disease prediction from microbiome data by multiple feature fusion and deep learning
title_full Human disease prediction from microbiome data by multiple feature fusion and deep learning
title_fullStr Human disease prediction from microbiome data by multiple feature fusion and deep learning
title_full_unstemmed Human disease prediction from microbiome data by multiple feature fusion and deep learning
title_short Human disease prediction from microbiome data by multiple feature fusion and deep learning
title_sort human disease prediction from microbiome data by multiple feature fusion and deep learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8971930/
https://www.ncbi.nlm.nih.gov/pubmed/35372808
http://dx.doi.org/10.1016/j.isci.2022.104081
work_keys_str_mv AT chenxingjian humandiseasepredictionfrommicrobiomedatabymultiplefeaturefusionanddeeplearning
AT zhuzifan humandiseasepredictionfrommicrobiomedatabymultiplefeaturefusionanddeeplearning
AT zhangweitong humandiseasepredictionfrommicrobiomedatabymultiplefeaturefusionanddeeplearning
AT wangyuchen humandiseasepredictionfrommicrobiomedatabymultiplefeaturefusionanddeeplearning
AT wangfuzhou humandiseasepredictionfrommicrobiomedatabymultiplefeaturefusionanddeeplearning
AT yangjianyi humandiseasepredictionfrommicrobiomedatabymultiplefeaturefusionanddeeplearning
AT wongkachun humandiseasepredictionfrommicrobiomedatabymultiplefeaturefusionanddeeplearning