Cargando…
Random Forest in Clinical Metabolomics for Phenotypic Discrimination and Biomarker Selection
Metabolomic data analysis becomes increasingly challenging when dealing with clinical samples with diverse demographic and genetic backgrounds and various pathological conditions or treatments. Although many classification tools, such as projection to latent structures (PLS), support vector machine...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi Publishing Corporation
2013
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3594909/ https://www.ncbi.nlm.nih.gov/pubmed/23573122 http://dx.doi.org/10.1155/2013/298183 |
_version_ | 1782262358970728448 |
---|---|
author | Chen, Tianlu Cao, Yu Zhang, Yinan Liu, Jiajian Bao, Yuqian Wang, Congrong Jia, Weiping Zhao, Aihua |
author_facet | Chen, Tianlu Cao, Yu Zhang, Yinan Liu, Jiajian Bao, Yuqian Wang, Congrong Jia, Weiping Zhao, Aihua |
author_sort | Chen, Tianlu |
collection | PubMed |
description | Metabolomic data analysis becomes increasingly challenging when dealing with clinical samples with diverse demographic and genetic backgrounds and various pathological conditions or treatments. Although many classification tools, such as projection to latent structures (PLS), support vector machine (SVM), linear discriminant analysis (LDA), and random forest (RF), have been successfully used in metabolomics, their performance including strengths and limitations in clinical data analysis has not been clear to researchers due to the lack of systematic evaluation of these tools. In this paper we comparatively evaluated the four classifiers, PLS, SVM, LDA, and RF, in the analysis of clinical metabolomic data derived from gas chromatography mass spectrometry platform of healthy subjects and patients diagnosed with colorectal cancer, where cross-validation, R (2)/Q (2) plot, receiver operating characteristic curve, variable reduction, and Pearson correlation were performed. RF outperforms the other three classifiers in the given clinical data sets, highlighting its comparative advantages as a suitable classification and biomarker selection tool for clinical metabolomic data analysis. |
format | Online Article Text |
id | pubmed-3594909 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2013 |
publisher | Hindawi Publishing Corporation |
record_format | MEDLINE/PubMed |
spelling | pubmed-35949092013-04-09 Random Forest in Clinical Metabolomics for Phenotypic Discrimination and Biomarker Selection Chen, Tianlu Cao, Yu Zhang, Yinan Liu, Jiajian Bao, Yuqian Wang, Congrong Jia, Weiping Zhao, Aihua Evid Based Complement Alternat Med Research Article Metabolomic data analysis becomes increasingly challenging when dealing with clinical samples with diverse demographic and genetic backgrounds and various pathological conditions or treatments. Although many classification tools, such as projection to latent structures (PLS), support vector machine (SVM), linear discriminant analysis (LDA), and random forest (RF), have been successfully used in metabolomics, their performance including strengths and limitations in clinical data analysis has not been clear to researchers due to the lack of systematic evaluation of these tools. In this paper we comparatively evaluated the four classifiers, PLS, SVM, LDA, and RF, in the analysis of clinical metabolomic data derived from gas chromatography mass spectrometry platform of healthy subjects and patients diagnosed with colorectal cancer, where cross-validation, R (2)/Q (2) plot, receiver operating characteristic curve, variable reduction, and Pearson correlation were performed. RF outperforms the other three classifiers in the given clinical data sets, highlighting its comparative advantages as a suitable classification and biomarker selection tool for clinical metabolomic data analysis. Hindawi Publishing Corporation 2013 2013-02-02 /pmc/articles/PMC3594909/ /pubmed/23573122 http://dx.doi.org/10.1155/2013/298183 Text en Copyright © 2013 Tianlu Chen et al. https://creativecommons.org/licenses/by/3.0/ 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 Chen, Tianlu Cao, Yu Zhang, Yinan Liu, Jiajian Bao, Yuqian Wang, Congrong Jia, Weiping Zhao, Aihua Random Forest in Clinical Metabolomics for Phenotypic Discrimination and Biomarker Selection |
title | Random Forest in Clinical Metabolomics for Phenotypic Discrimination and Biomarker Selection |
title_full | Random Forest in Clinical Metabolomics for Phenotypic Discrimination and Biomarker Selection |
title_fullStr | Random Forest in Clinical Metabolomics for Phenotypic Discrimination and Biomarker Selection |
title_full_unstemmed | Random Forest in Clinical Metabolomics for Phenotypic Discrimination and Biomarker Selection |
title_short | Random Forest in Clinical Metabolomics for Phenotypic Discrimination and Biomarker Selection |
title_sort | random forest in clinical metabolomics for phenotypic discrimination and biomarker selection |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3594909/ https://www.ncbi.nlm.nih.gov/pubmed/23573122 http://dx.doi.org/10.1155/2013/298183 |
work_keys_str_mv | AT chentianlu randomforestinclinicalmetabolomicsforphenotypicdiscriminationandbiomarkerselection AT caoyu randomforestinclinicalmetabolomicsforphenotypicdiscriminationandbiomarkerselection AT zhangyinan randomforestinclinicalmetabolomicsforphenotypicdiscriminationandbiomarkerselection AT liujiajian randomforestinclinicalmetabolomicsforphenotypicdiscriminationandbiomarkerselection AT baoyuqian randomforestinclinicalmetabolomicsforphenotypicdiscriminationandbiomarkerselection AT wangcongrong randomforestinclinicalmetabolomicsforphenotypicdiscriminationandbiomarkerselection AT jiaweiping randomforestinclinicalmetabolomicsforphenotypicdiscriminationandbiomarkerselection AT zhaoaihua randomforestinclinicalmetabolomicsforphenotypicdiscriminationandbiomarkerselection |