MicroBayesAge: A Maximum Likelihood Approach to Predict Epigenetic Age Using Microarray Data DOI Open Access

Nicole Nolan,

Megan Mitchell, Lajoyce Mboning

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 6, 2024

Abstract Certain epigenetic modifications, such as the methylation of CpG sites, can serve biomarkers for chronological age. Previously, we introduced our BayesAge frameworks accurate age prediction through use locally weighted scatterplot smoothing (LOWESS) to capture non-linear relationship between or gene expression and age, Maximum Likelihood Estimation (MLE) bulk bisulfite RNA sequencing data. Here now introduce MicroBayesAge, a framework that enhances accuracy by subdividing input data into age-specific co-horts employing new two-stage process training testing. Age younger patients was significantly improved. MicroBayesAge also exhibited minimal bias in its predictions. Additionally, explored performance model sex-specific which revealed slight improvements male patients, while no changes were observed female patients. provides more predictions accounting variations markers aging among different subgroups, have been over-looked commonly used models.

Language: Английский

MicroBayesAge: A Maximum Likelihood Approach to Predict Epigenetic Age Using Microarray Data DOI Open Access

Nicole Nolan,

Megan Mitchell, Lajoyce Mboning

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 6, 2024

Abstract Certain epigenetic modifications, such as the methylation of CpG sites, can serve biomarkers for chronological age. Previously, we introduced our BayesAge frameworks accurate age prediction through use locally weighted scatterplot smoothing (LOWESS) to capture non-linear relationship between or gene expression and age, Maximum Likelihood Estimation (MLE) bulk bisulfite RNA sequencing data. Here now introduce MicroBayesAge, a framework that enhances accuracy by subdividing input data into age-specific co-horts employing new two-stage process training testing. Age younger patients was significantly improved. MicroBayesAge also exhibited minimal bias in its predictions. Additionally, explored performance model sex-specific which revealed slight improvements male patients, while no changes were observed female patients. provides more predictions accounting variations markers aging among different subgroups, have been over-looked commonly used models.

Language: Английский

Citations

0