Human Age Prediction Based on DNA Methylation Using a Gradient Boosting Regressor
All tissues of organisms will become old as time goes on. In recent years, epigenetic investigations have found that there is a close correlation between DNA methylation and aging. With the development of DNA methylation research, a quantitative statistical relationship between DNA methylation and d...
Gespeichert in:
Veröffentlicht in: | Genes 2018-08, Vol.9 (9), p.424 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | 9 |
container_start_page | 424 |
container_title | Genes |
container_volume | 9 |
creator | Li, Xingyan Li, Weidong Xu, Yan |
description | All tissues of organisms will become old as time goes on. In recent years, epigenetic investigations have found that there is a close correlation between DNA methylation and aging. With the development of DNA methylation research, a quantitative statistical relationship between DNA methylation and different ages was established based on the change rule of methylation with age, it is then possible to predict the age of individuals. All the data in this work were retrieved from the Illumina HumanMethylation BeadChip platform (27K or 450K). We analyzed 16 sets of healthy samples and 9 sets of diseased samples. The healthy samples included a total of 1899 publicly available blood samples (0⁻103 years old) and the diseased samples included 2395 blood samples. Six age-related CpG sites were selected through calculating Pearson correlation coefficients between age and DNA methylation values. We built a gradient boosting regressor model for these age-related CpG sites. 70% of the data was randomly selected as training data and the other 30% as independent data in each dataset for 25 runs in total. In the training dataset, the healthy samples showed that the correlation between predicted age and DNA methylation was 0.97, and the mean absolute deviation (MAD) was 2.72 years. In the independent dataset, the MAD was 4.06 years. The proposed model was further tested using the diseased samples. The MAD was 5.44 years for the training dataset and 7.08 years for the independent dataset. Furthermore, our model worked well when it was applied to saliva samples. These results illustrated that the age prediction based on six DNA methylation markers is very effective using the gradient boosting regressor. |
doi_str_mv | 10.3390/genes9090424 |
format | Article |
fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_6162650</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2092541410</sourcerecordid><originalsourceid>FETCH-LOGICAL-c384t-16f8a77932c5aba582a7773be4c11dea2197a2be4ce76850f54c65bdd37de7723</originalsourceid><addsrcrecordid>eNpVUU1PwkAQ3RiNEOTm2fTowep-dunFBFDBBD8j5822nZaatou7rQn_3laQ4Fzm4728mcxD6Jzga8ZCfJNBBS7EIeaUH6E-xZL5nFNxfFD30NC5T9wGxxRjcYp6DBPGA8r66G3elLryxhl4rxaSPK5zU3kT7SDx2uLueew9Qb3aFPoXWLq8yjztzaxOcqhqb2KMq7vZO2QWnDP2DJ2kunAw3OUBWj7cf0zn_uJl9jgdL_yYjXjtkyAdaSlDRmOhIy1GtO0ki4DHhCSgKQmlpl0LMhgJnAoeByJKEiYTkJKyAbrd6q6bqIQkbq-xulBrm5fabpTRufqPVPlKZeZbBSSggcCtwOVOwJqvBlytytzFUBS6AtM4RXFIBSecdNSrLTW2xjkL6X4NwaozQh0a0dIvDk_bk__ezn4APUWEgw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2092541410</pqid></control><display><type>article</type><title>Human Age Prediction Based on DNA Methylation Using a Gradient Boosting Regressor</title><source>PubMed Central Open Access</source><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><creator>Li, Xingyan ; Li, Weidong ; Xu, Yan</creator><creatorcontrib>Li, Xingyan ; Li, Weidong ; Xu, Yan</creatorcontrib><description>All tissues of organisms will become old as time goes on. In recent years, epigenetic investigations have found that there is a close correlation between DNA methylation and aging. With the development of DNA methylation research, a quantitative statistical relationship between DNA methylation and different ages was established based on the change rule of methylation with age, it is then possible to predict the age of individuals. All the data in this work were retrieved from the Illumina HumanMethylation BeadChip platform (27K or 450K). We analyzed 16 sets of healthy samples and 9 sets of diseased samples. The healthy samples included a total of 1899 publicly available blood samples (0⁻103 years old) and the diseased samples included 2395 blood samples. Six age-related CpG sites were selected through calculating Pearson correlation coefficients between age and DNA methylation values. We built a gradient boosting regressor model for these age-related CpG sites. 70% of the data was randomly selected as training data and the other 30% as independent data in each dataset for 25 runs in total. In the training dataset, the healthy samples showed that the correlation between predicted age and DNA methylation was 0.97, and the mean absolute deviation (MAD) was 2.72 years. In the independent dataset, the MAD was 4.06 years. The proposed model was further tested using the diseased samples. The MAD was 5.44 years for the training dataset and 7.08 years for the independent dataset. Furthermore, our model worked well when it was applied to saliva samples. These results illustrated that the age prediction based on six DNA methylation markers is very effective using the gradient boosting regressor.</description><identifier>ISSN: 2073-4425</identifier><identifier>EISSN: 2073-4425</identifier><identifier>DOI: 10.3390/genes9090424</identifier><identifier>PMID: 30134623</identifier><language>eng</language><publisher>Switzerland: MDPI</publisher><ispartof>Genes, 2018-08, Vol.9 (9), p.424</ispartof><rights>2018 by the authors. 2018</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c384t-16f8a77932c5aba582a7773be4c11dea2197a2be4ce76850f54c65bdd37de7723</citedby><cites>FETCH-LOGICAL-c384t-16f8a77932c5aba582a7773be4c11dea2197a2be4ce76850f54c65bdd37de7723</cites><orcidid>0000-0001-9462-580X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC6162650/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC6162650/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,315,728,781,785,886,27929,27930,53796,53798</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/30134623$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Li, Xingyan</creatorcontrib><creatorcontrib>Li, Weidong</creatorcontrib><creatorcontrib>Xu, Yan</creatorcontrib><title>Human Age Prediction Based on DNA Methylation Using a Gradient Boosting Regressor</title><title>Genes</title><addtitle>Genes (Basel)</addtitle><description>All tissues of organisms will become old as time goes on. In recent years, epigenetic investigations have found that there is a close correlation between DNA methylation and aging. With the development of DNA methylation research, a quantitative statistical relationship between DNA methylation and different ages was established based on the change rule of methylation with age, it is then possible to predict the age of individuals. All the data in this work were retrieved from the Illumina HumanMethylation BeadChip platform (27K or 450K). We analyzed 16 sets of healthy samples and 9 sets of diseased samples. The healthy samples included a total of 1899 publicly available blood samples (0⁻103 years old) and the diseased samples included 2395 blood samples. Six age-related CpG sites were selected through calculating Pearson correlation coefficients between age and DNA methylation values. We built a gradient boosting regressor model for these age-related CpG sites. 70% of the data was randomly selected as training data and the other 30% as independent data in each dataset for 25 runs in total. In the training dataset, the healthy samples showed that the correlation between predicted age and DNA methylation was 0.97, and the mean absolute deviation (MAD) was 2.72 years. In the independent dataset, the MAD was 4.06 years. The proposed model was further tested using the diseased samples. The MAD was 5.44 years for the training dataset and 7.08 years for the independent dataset. Furthermore, our model worked well when it was applied to saliva samples. These results illustrated that the age prediction based on six DNA methylation markers is very effective using the gradient boosting regressor.</description><issn>2073-4425</issn><issn>2073-4425</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><recordid>eNpVUU1PwkAQ3RiNEOTm2fTowep-dunFBFDBBD8j5822nZaatou7rQn_3laQ4Fzm4728mcxD6Jzga8ZCfJNBBS7EIeaUH6E-xZL5nFNxfFD30NC5T9wGxxRjcYp6DBPGA8r66G3elLryxhl4rxaSPK5zU3kT7SDx2uLueew9Qb3aFPoXWLq8yjztzaxOcqhqb2KMq7vZO2QWnDP2DJ2kunAw3OUBWj7cf0zn_uJl9jgdL_yYjXjtkyAdaSlDRmOhIy1GtO0ki4DHhCSgKQmlpl0LMhgJnAoeByJKEiYTkJKyAbrd6q6bqIQkbq-xulBrm5fabpTRufqPVPlKZeZbBSSggcCtwOVOwJqvBlytytzFUBS6AtM4RXFIBSecdNSrLTW2xjkL6X4NwaozQh0a0dIvDk_bk__ezn4APUWEgw</recordid><startdate>20180821</startdate><enddate>20180821</enddate><creator>Li, Xingyan</creator><creator>Li, Weidong</creator><creator>Xu, Yan</creator><general>MDPI</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0001-9462-580X</orcidid></search><sort><creationdate>20180821</creationdate><title>Human Age Prediction Based on DNA Methylation Using a Gradient Boosting Regressor</title><author>Li, Xingyan ; Li, Weidong ; Xu, Yan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c384t-16f8a77932c5aba582a7773be4c11dea2197a2be4ce76850f54c65bdd37de7723</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Li, Xingyan</creatorcontrib><creatorcontrib>Li, Weidong</creatorcontrib><creatorcontrib>Xu, Yan</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Genes</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Xingyan</au><au>Li, Weidong</au><au>Xu, Yan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Human Age Prediction Based on DNA Methylation Using a Gradient Boosting Regressor</atitle><jtitle>Genes</jtitle><addtitle>Genes (Basel)</addtitle><date>2018-08-21</date><risdate>2018</risdate><volume>9</volume><issue>9</issue><spage>424</spage><pages>424-</pages><issn>2073-4425</issn><eissn>2073-4425</eissn><abstract>All tissues of organisms will become old as time goes on. In recent years, epigenetic investigations have found that there is a close correlation between DNA methylation and aging. With the development of DNA methylation research, a quantitative statistical relationship between DNA methylation and different ages was established based on the change rule of methylation with age, it is then possible to predict the age of individuals. All the data in this work were retrieved from the Illumina HumanMethylation BeadChip platform (27K or 450K). We analyzed 16 sets of healthy samples and 9 sets of diseased samples. The healthy samples included a total of 1899 publicly available blood samples (0⁻103 years old) and the diseased samples included 2395 blood samples. Six age-related CpG sites were selected through calculating Pearson correlation coefficients between age and DNA methylation values. We built a gradient boosting regressor model for these age-related CpG sites. 70% of the data was randomly selected as training data and the other 30% as independent data in each dataset for 25 runs in total. In the training dataset, the healthy samples showed that the correlation between predicted age and DNA methylation was 0.97, and the mean absolute deviation (MAD) was 2.72 years. In the independent dataset, the MAD was 4.06 years. The proposed model was further tested using the diseased samples. The MAD was 5.44 years for the training dataset and 7.08 years for the independent dataset. Furthermore, our model worked well when it was applied to saliva samples. These results illustrated that the age prediction based on six DNA methylation markers is very effective using the gradient boosting regressor.</abstract><cop>Switzerland</cop><pub>MDPI</pub><pmid>30134623</pmid><doi>10.3390/genes9090424</doi><orcidid>https://orcid.org/0000-0001-9462-580X</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2073-4425 |
ispartof | Genes, 2018-08, Vol.9 (9), p.424 |
issn | 2073-4425 2073-4425 |
language | eng |
recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_6162650 |
source | PubMed Central Open Access; MDPI - Multidisciplinary Digital Publishing Institute; EZB-FREE-00999 freely available EZB journals; PubMed Central |
title | Human Age Prediction Based on DNA Methylation Using a Gradient Boosting Regressor |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-16T07%3A33%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Human%20Age%20Prediction%20Based%20on%20DNA%20Methylation%20Using%20a%20Gradient%20Boosting%20Regressor&rft.jtitle=Genes&rft.au=Li,%20Xingyan&rft.date=2018-08-21&rft.volume=9&rft.issue=9&rft.spage=424&rft.pages=424-&rft.issn=2073-4425&rft.eissn=2073-4425&rft_id=info:doi/10.3390/genes9090424&rft_dat=%3Cproquest_pubme%3E2092541410%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2092541410&rft_id=info:pmid/30134623&rfr_iscdi=true |