GEO Logo
   NCBI > GEO > Accession DisplayHelp Not logged in | LoginHelp
GEO help: Mouse over screen elements for information.
Series GSE207605 Query DataSets for GSE207605
Status Public on Jan 20, 2023
Title Accurate age prediction from blood using a small set of DNA methylation sites and a cohort-based machine learning algorithm
Organism Homo sapiens
Experiment type Methylation profiling by array
Third-party reanalysis
Summary Chronological age prediction from DNA methylation sheds light on human aging, indicates poor health and predicts lifespan. Previous studies developed methylation clocks based on linear regression models on methylation array data. While accurate, these models are limited to fixed-rate changes in methylation levels across age. Moreover, the high cost of methylation arrays, compared to targeted-PCR sequencing, hinders widespread utility of such predictors. We present an AI-based alternative termed GP-age, which uses a non-parametric approach based on Gaussian Process Regression of a large cohort of ~12K blood methylomes. Given a new blood sample, methylation levels are compared to the cohort samples, which are then weighted to predict the query age. Using only 30 CpG sites, our approach outperforms state-of-the-art methylation clocks that use hundreds of sites, with a median error of 2.1 years (on held-out data). Our model was also applied to sequencing-based data yielding highly accurate predictions. Overall, we provide an accessible alternative to current array-based methylation clocks, with future applications in aging research, forensic profiling, and monitoring epigenetic processes in transplantation medicine and cancer.
Overall design Re-published data of Bisulphite converted DNA from 11,910 whole-blood samples hybridised to the Illumina Infinium 450k Human Methylation Beadchip. The processed beta values of age-correlated 2,374 CpG sites and the ages of the donors are included.
Web link
Contributor(s) Varshavsky M, Harari G, Glaser B, Dor Y, Shemer R, Kaplan T
Citation(s) 37751697
Submission date Jul 06, 2022
Last update date Oct 19, 2023
Contact name Tommy Kaplan
Organization name Hebrew University
Department School of Computer Science and Engineering
Street address Givat Ram Campus
City Jerusalem
ZIP/Postal code 91904
Country Israel
Reanalysis of GSE55763
Reanalysis of GSE84727
Reanalysis of GSE154566
Reanalysis of GSE51032
Reanalysis of GSE87648
Reanalysis of GSE157131
Reanalysis of GSE73103
Reanalysis of GSE105018
Reanalysis of GSE147221
Reanalysis of GSE72680
Reanalysis of GSE64495
Reanalysis of GSE103657
Reanalysis of GSE42861
Reanalysis of GSE72775
Reanalysis of GSE40279
Reanalysis of GSE69270
Reanalysis of GSE41169
Reanalysis of GSE36054
Reanalysis of GSE30870

Download family Format
SOFT formatted family file(s) SOFTHelp
MINiML formatted family file(s) MINiMLHelp
Series Matrix File(s) TXTHelp

Supplementary file Size Download File type/resource
GSE207605_GSE103657.csv.gz 867.7 Kb (ftp)(http) CSV
GSE207605_GSE105018.csv.gz 2.4 Mb (ftp)(http) CSV
GSE207605_GSE147221.csv.gz 2.3 Mb (ftp)(http) CSV
GSE207605_GSE154566.csv.gz 333.7 Kb (ftp)(http) CSV
GSE207605_GSE157131.csv.gz 3.5 Mb (ftp)(http) CSV
GSE207605_GSE30870.csv.gz 87.9 Kb (ftp)(http) CSV
GSE207605_GSE36054.csv.gz 501.5 Kb (ftp)(http) CSV
GSE207605_GSE40279.csv.gz 2.3 Mb (ftp)(http) CSV
GSE207605_GSE41169.csv.gz 360.4 Kb (ftp)(http) CSV
GSE207605_GSE42861.csv.gz 2.4 Mb (ftp)(http) CSV
GSE207605_GSE51032.csv.gz 2.9 Mb (ftp)(http) CSV
GSE207605_GSE55763.csv.gz 8.3 Mb (ftp)(http) CSV
GSE207605_GSE64495.csv.gz 432.0 Kb (ftp)(http) CSV
GSE207605_GSE69270.csv.gz 283.8 Kb (ftp)(http) CSV
GSE207605_GSE72680.csv.gz 703.4 Kb (ftp)(http) CSV
GSE207605_GSE72775.csv.gz 1.2 Mb (ftp)(http) CSV
GSE207605_GSE73103.csv.gz 556.2 Kb (ftp)(http) CSV
GSE207605_GSE84727.csv.gz 1.0 Mb (ftp)(http) CSV
GSE207605_GSE87648.csv.gz 1.4 Mb (ftp)(http) CSV
Processed data are available on Series record

| NLM | NIH | GEO Help | Disclaimer | Accessibility |
NCBI Home NCBI Search NCBI SiteMap