Cargando…

An Improved Stacked Autoencoder for Metabolomic Data Classification

Naru3 (NR) is a traditional Mongolian medicine with high clinical efficacy and low incidence of side effects. Metabolomics is an approach that can facilitate the development of traditional drugs. However, metabolomic data have a high throughput, sparse, high-dimensional, and small sample nature, and...

Descripción completa

Detalles Bibliográficos
Autores principales: Fan, Xiaojing, Wang, Xiye, Jiang, Mingyang, Pei, Zhili, Qiao, Shicheng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8382558/
https://www.ncbi.nlm.nih.gov/pubmed/34434226
http://dx.doi.org/10.1155/2021/1051172
_version_ 1783741558425649152
author Fan, Xiaojing
Wang, Xiye
Jiang, Mingyang
Pei, Zhili
Qiao, Shicheng
author_facet Fan, Xiaojing
Wang, Xiye
Jiang, Mingyang
Pei, Zhili
Qiao, Shicheng
author_sort Fan, Xiaojing
collection PubMed
description Naru3 (NR) is a traditional Mongolian medicine with high clinical efficacy and low incidence of side effects. Metabolomics is an approach that can facilitate the development of traditional drugs. However, metabolomic data have a high throughput, sparse, high-dimensional, and small sample nature, and their classification is challenging. Although deep learning methods have a wide range of applications, deep learning-based metabolomic studies have not been widely performed. We aimed to develop an improved stacked autoencoder (SAE) for metabolomic data classification. We established an NR-treated rheumatoid arthritis (RA) mouse model and classified the obtained metabolomic data using the Hessian-free SAE (HF-SAE) algorithm. During training, the unlabeled data were used for pretraining, and the labeled data were used for fine-tuning based on the HF algorithm for gradient descent optimization. The hybrid algorithm successfully classified the data. The results were compared with those of the support vector machine (SVM), k-nearest neighbor (KNN), and gradient descent SAE (GD-SAE) algorithms. A five-fold cross-validation was used to complete the classification experiment. In each fine-tuning process, the mean square error (MSE) and misclassification rates of the training and test data were recorded. We successfully established an NR animal model and an improved SAE for metabolomic data classification.
format Online
Article
Text
id pubmed-8382558
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-83825582021-08-24 An Improved Stacked Autoencoder for Metabolomic Data Classification Fan, Xiaojing Wang, Xiye Jiang, Mingyang Pei, Zhili Qiao, Shicheng Comput Intell Neurosci Research Article Naru3 (NR) is a traditional Mongolian medicine with high clinical efficacy and low incidence of side effects. Metabolomics is an approach that can facilitate the development of traditional drugs. However, metabolomic data have a high throughput, sparse, high-dimensional, and small sample nature, and their classification is challenging. Although deep learning methods have a wide range of applications, deep learning-based metabolomic studies have not been widely performed. We aimed to develop an improved stacked autoencoder (SAE) for metabolomic data classification. We established an NR-treated rheumatoid arthritis (RA) mouse model and classified the obtained metabolomic data using the Hessian-free SAE (HF-SAE) algorithm. During training, the unlabeled data were used for pretraining, and the labeled data were used for fine-tuning based on the HF algorithm for gradient descent optimization. The hybrid algorithm successfully classified the data. The results were compared with those of the support vector machine (SVM), k-nearest neighbor (KNN), and gradient descent SAE (GD-SAE) algorithms. A five-fold cross-validation was used to complete the classification experiment. In each fine-tuning process, the mean square error (MSE) and misclassification rates of the training and test data were recorded. We successfully established an NR animal model and an improved SAE for metabolomic data classification. Hindawi 2021-08-15 /pmc/articles/PMC8382558/ /pubmed/34434226 http://dx.doi.org/10.1155/2021/1051172 Text en Copyright © 2021 Xiaojing Fan et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Fan, Xiaojing
Wang, Xiye
Jiang, Mingyang
Pei, Zhili
Qiao, Shicheng
An Improved Stacked Autoencoder for Metabolomic Data Classification
title An Improved Stacked Autoencoder for Metabolomic Data Classification
title_full An Improved Stacked Autoencoder for Metabolomic Data Classification
title_fullStr An Improved Stacked Autoencoder for Metabolomic Data Classification
title_full_unstemmed An Improved Stacked Autoencoder for Metabolomic Data Classification
title_short An Improved Stacked Autoencoder for Metabolomic Data Classification
title_sort improved stacked autoencoder for metabolomic data classification
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8382558/
https://www.ncbi.nlm.nih.gov/pubmed/34434226
http://dx.doi.org/10.1155/2021/1051172
work_keys_str_mv AT fanxiaojing animprovedstackedautoencoderformetabolomicdataclassification
AT wangxiye animprovedstackedautoencoderformetabolomicdataclassification
AT jiangmingyang animprovedstackedautoencoderformetabolomicdataclassification
AT peizhili animprovedstackedautoencoderformetabolomicdataclassification
AT qiaoshicheng animprovedstackedautoencoderformetabolomicdataclassification
AT fanxiaojing improvedstackedautoencoderformetabolomicdataclassification
AT wangxiye improvedstackedautoencoderformetabolomicdataclassification
AT jiangmingyang improvedstackedautoencoderformetabolomicdataclassification
AT peizhili improvedstackedautoencoderformetabolomicdataclassification
AT qiaoshicheng improvedstackedautoencoderformetabolomicdataclassification