Cargando…
DeepMAge: A Methylation Aging Clock Developed with Deep Learning
DNA methylation aging clocks have become an invaluable tool in biogerontology research since their inception in 2013. Today, a variety of machine learning approaches have been tested for the purpose of predicting human age based on molecular-level features. Among these, deep learning, or neural netw...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
JKL International LLC
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8279523/ https://www.ncbi.nlm.nih.gov/pubmed/34341706 http://dx.doi.org/10.14336/AD.2020.1202 |
_version_ | 1783722474729373696 |
---|---|
author | Galkin, Fedor Mamoshina, Polina Kochetov, Kirill Sidorenko, Denis Zhavoronkov, Alex |
author_facet | Galkin, Fedor Mamoshina, Polina Kochetov, Kirill Sidorenko, Denis Zhavoronkov, Alex |
author_sort | Galkin, Fedor |
collection | PubMed |
description | DNA methylation aging clocks have become an invaluable tool in biogerontology research since their inception in 2013. Today, a variety of machine learning approaches have been tested for the purpose of predicting human age based on molecular-level features. Among these, deep learning, or neural networks, is an especially promising approach that has been used to construct accurate clocks using blood biochemistry, transcriptomics, and microbiomics data—feats unachieved by other algorithms. In this article, we explore how deep learning performs in a DNA methylation setting and compare it to the current industry standard—the 353 CpG clock published in 2013. The aging clock we are presenting (DeepMAge) is a neural network regressor trained on 4,930 blood DNA methylation profiles from 17 studies. Its absolute median error was 2.77 years in an independent verification set of 1,293 samples from 15 studies. DeepMAge shows biological relevance by assigning a higher predicted age to people with various health-related conditions, such as ovarian cancer, irritable bowel diseases, and multiple sclerosis. |
format | Online Article Text |
id | pubmed-8279523 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | JKL International LLC |
record_format | MEDLINE/PubMed |
spelling | pubmed-82795232021-08-01 DeepMAge: A Methylation Aging Clock Developed with Deep Learning Galkin, Fedor Mamoshina, Polina Kochetov, Kirill Sidorenko, Denis Zhavoronkov, Alex Aging Dis Orginal Article DNA methylation aging clocks have become an invaluable tool in biogerontology research since their inception in 2013. Today, a variety of machine learning approaches have been tested for the purpose of predicting human age based on molecular-level features. Among these, deep learning, or neural networks, is an especially promising approach that has been used to construct accurate clocks using blood biochemistry, transcriptomics, and microbiomics data—feats unachieved by other algorithms. In this article, we explore how deep learning performs in a DNA methylation setting and compare it to the current industry standard—the 353 CpG clock published in 2013. The aging clock we are presenting (DeepMAge) is a neural network regressor trained on 4,930 blood DNA methylation profiles from 17 studies. Its absolute median error was 2.77 years in an independent verification set of 1,293 samples from 15 studies. DeepMAge shows biological relevance by assigning a higher predicted age to people with various health-related conditions, such as ovarian cancer, irritable bowel diseases, and multiple sclerosis. JKL International LLC 2021-08-01 /pmc/articles/PMC8279523/ /pubmed/34341706 http://dx.doi.org/10.14336/AD.2020.1202 Text en copyright: © 2021 Galkin et al. https://creativecommons.org/licenses/by/2.0/this is an open access article distributed under the terms of the creative commons attribution license, which permits unrestricted use, distribution and reproduction in any medium provided that the original work is properly attributed. |
spellingShingle | Orginal Article Galkin, Fedor Mamoshina, Polina Kochetov, Kirill Sidorenko, Denis Zhavoronkov, Alex DeepMAge: A Methylation Aging Clock Developed with Deep Learning |
title | DeepMAge: A Methylation Aging Clock Developed with Deep Learning |
title_full | DeepMAge: A Methylation Aging Clock Developed with Deep Learning |
title_fullStr | DeepMAge: A Methylation Aging Clock Developed with Deep Learning |
title_full_unstemmed | DeepMAge: A Methylation Aging Clock Developed with Deep Learning |
title_short | DeepMAge: A Methylation Aging Clock Developed with Deep Learning |
title_sort | deepmage: a methylation aging clock developed with deep learning |
topic | Orginal Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8279523/ https://www.ncbi.nlm.nih.gov/pubmed/34341706 http://dx.doi.org/10.14336/AD.2020.1202 |
work_keys_str_mv | AT galkinfedor deepmageamethylationagingclockdevelopedwithdeeplearning AT mamoshinapolina deepmageamethylationagingclockdevelopedwithdeeplearning AT kochetovkirill deepmageamethylationagingclockdevelopedwithdeeplearning AT sidorenkodenis deepmageamethylationagingclockdevelopedwithdeeplearning AT zhavoronkovalex deepmageamethylationagingclockdevelopedwithdeeplearning |