Cargando…
Predicting lung adenocarcinoma disease progression using methylation-correlated blocks and ensemble machine learning classifiers
Applying the knowledge that methyltransferases and demethylases can modify adjacent cytosine-phosphorothioate-guanine (CpG) sites in the same DNA strand, we found that combining multiple CpGs into a single block may improve cancer diagnosis. However, survival prediction remains a challenge. In this...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
PeerJ Inc.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7894106/ https://www.ncbi.nlm.nih.gov/pubmed/33628643 http://dx.doi.org/10.7717/peerj.10884 |
_version_ | 1783653177414909952 |
---|---|
author | Yu, Xin Yang, Qian Wang, Dong Li, Zhaoyang Chen, Nianhang Kong, De-Xin |
author_facet | Yu, Xin Yang, Qian Wang, Dong Li, Zhaoyang Chen, Nianhang Kong, De-Xin |
author_sort | Yu, Xin |
collection | PubMed |
description | Applying the knowledge that methyltransferases and demethylases can modify adjacent cytosine-phosphorothioate-guanine (CpG) sites in the same DNA strand, we found that combining multiple CpGs into a single block may improve cancer diagnosis. However, survival prediction remains a challenge. In this study, we developed a pipeline named “stacked ensemble of machine learning models for methylation-correlated blocks” (EnMCB) that combined Cox regression, support vector regression (SVR), and elastic-net models to construct signatures based on DNA methylation-correlated blocks for lung adenocarcinoma (LUAD) survival prediction. We used methylation profiles from the Cancer Genome Atlas (TCGA) as the training set, and profiles from the Gene Expression Omnibus (GEO) as validation and testing sets. First, we partitioned the genome into blocks of tightly co-methylated CpG sites, which we termed methylation-correlated blocks (MCBs). After partitioning and feature selection, we observed different diagnostic capacities for predicting patient survival across the models. We combined the multiple models into a single stacking ensemble model. The stacking ensemble model based on the top-ranked block had the area under the receiver operating characteristic curve of 0.622 in the TCGA training set, 0.773 in the validation set, and 0.698 in the testing set. When stratified by clinicopathological risk factors, the risk score predicted by the top-ranked MCB was an independent prognostic factor. Our results showed that our pipeline was a reliable tool that may facilitate MCB selection and survival prediction. |
format | Online Article Text |
id | pubmed-7894106 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | PeerJ Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-78941062021-02-23 Predicting lung adenocarcinoma disease progression using methylation-correlated blocks and ensemble machine learning classifiers Yu, Xin Yang, Qian Wang, Dong Li, Zhaoyang Chen, Nianhang Kong, De-Xin PeerJ Bioinformatics Applying the knowledge that methyltransferases and demethylases can modify adjacent cytosine-phosphorothioate-guanine (CpG) sites in the same DNA strand, we found that combining multiple CpGs into a single block may improve cancer diagnosis. However, survival prediction remains a challenge. In this study, we developed a pipeline named “stacked ensemble of machine learning models for methylation-correlated blocks” (EnMCB) that combined Cox regression, support vector regression (SVR), and elastic-net models to construct signatures based on DNA methylation-correlated blocks for lung adenocarcinoma (LUAD) survival prediction. We used methylation profiles from the Cancer Genome Atlas (TCGA) as the training set, and profiles from the Gene Expression Omnibus (GEO) as validation and testing sets. First, we partitioned the genome into blocks of tightly co-methylated CpG sites, which we termed methylation-correlated blocks (MCBs). After partitioning and feature selection, we observed different diagnostic capacities for predicting patient survival across the models. We combined the multiple models into a single stacking ensemble model. The stacking ensemble model based on the top-ranked block had the area under the receiver operating characteristic curve of 0.622 in the TCGA training set, 0.773 in the validation set, and 0.698 in the testing set. When stratified by clinicopathological risk factors, the risk score predicted by the top-ranked MCB was an independent prognostic factor. Our results showed that our pipeline was a reliable tool that may facilitate MCB selection and survival prediction. PeerJ Inc. 2021-02-16 /pmc/articles/PMC7894106/ /pubmed/33628643 http://dx.doi.org/10.7717/peerj.10884 Text en ©2021 Yu et al. https://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited. |
spellingShingle | Bioinformatics Yu, Xin Yang, Qian Wang, Dong Li, Zhaoyang Chen, Nianhang Kong, De-Xin Predicting lung adenocarcinoma disease progression using methylation-correlated blocks and ensemble machine learning classifiers |
title | Predicting lung adenocarcinoma disease progression using methylation-correlated blocks and ensemble machine learning classifiers |
title_full | Predicting lung adenocarcinoma disease progression using methylation-correlated blocks and ensemble machine learning classifiers |
title_fullStr | Predicting lung adenocarcinoma disease progression using methylation-correlated blocks and ensemble machine learning classifiers |
title_full_unstemmed | Predicting lung adenocarcinoma disease progression using methylation-correlated blocks and ensemble machine learning classifiers |
title_short | Predicting lung adenocarcinoma disease progression using methylation-correlated blocks and ensemble machine learning classifiers |
title_sort | predicting lung adenocarcinoma disease progression using methylation-correlated blocks and ensemble machine learning classifiers |
topic | Bioinformatics |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7894106/ https://www.ncbi.nlm.nih.gov/pubmed/33628643 http://dx.doi.org/10.7717/peerj.10884 |
work_keys_str_mv | AT yuxin predictinglungadenocarcinomadiseaseprogressionusingmethylationcorrelatedblocksandensemblemachinelearningclassifiers AT yangqian predictinglungadenocarcinomadiseaseprogressionusingmethylationcorrelatedblocksandensemblemachinelearningclassifiers AT wangdong predictinglungadenocarcinomadiseaseprogressionusingmethylationcorrelatedblocksandensemblemachinelearningclassifiers AT lizhaoyang predictinglungadenocarcinomadiseaseprogressionusingmethylationcorrelatedblocksandensemblemachinelearningclassifiers AT chennianhang predictinglungadenocarcinomadiseaseprogressionusingmethylationcorrelatedblocksandensemblemachinelearningclassifiers AT kongdexin predictinglungadenocarcinomadiseaseprogressionusingmethylationcorrelatedblocksandensemblemachinelearningclassifiers |