Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2015 Dec 4;5:17788. doi: 10.1038/srep17788

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

Copyright © 2015, Macmillan Publishers Limited

This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

PMC Copyright notice

(a) The minimal MAD of predicted age as a function of the number of sites that compose the independent variables. The 11 CpG sites selected from the Sequenom MassARRAY dataset were combined to one to 11 independent variables. SVR model fit on all but one sample, and the minimal MAD of the predicted age was observed for a given number of independent variables. (b) Predicted versus observed age of all 49 subjects, using SVR model by six markers. MAD of 2.8 years was observed, which is slightly higher than that obtained by 11 markers. (c) Predicted versus observed age using multivariate linear regression by three DNA methylation markers obtained from a recent study¹⁸. The original BeadChip data of these three sites were extracted to predict age by using a multivariate linear regression model, and an MAD of 6.27 years was obtained. (d) Predicted versus observed age using SVR by three DNA methylation markers obtained from a recent study¹⁸. MAD of 4.23 years was obtained, which is better than the MAD obtained when using a multivariate linear regression (panel C), and better than the MAD obtained when using a multivariate linear regression based on pyrosequencing data in the published study (5.4 years)¹⁸.