KoMethylNet is a Korean-population DNA methylation clock that predicted chronological age accurately and linked age acceleration to diabetes-related traits.
Evidence
This model-development and validation study trained a neural network on DNAm data from 2,747 KoGES participants and externally validated it in healthy Korean individuals, reporting MAE 2.74 years and R 0.94 in validation.
Caveat
The phenotype findings are regression associations with KoMethylNet , not evidence that the clock or methylation changes cause aging-related disease.
Simplified
BACKGROUND: Epigenetic clocks have been extensively investigated in individuals of European ancestry and may be suboptimal in East Asians. We developed a novel epigenetic clock (KoMethylNet) using neural network analysis of DNA methylation (DNAm) data from the Korean population to predict chronological ages.
METHODS: DNAm data (367,785 CpG sites) from 2,747 participants (Infinium Human Methylation 450 K BeadChip: N = 397; Infinium MethylationEPIC BeadChip: N = 2,350) in the Korean Genome and Epidemiology Study (KoGES) were used to train the neural network on chronological ages. SHapley Additive exPlanation analysis was used to select the optimal number of CpG sites. KoMethylNet- (EAA)-phenotype analysis was conducted with linear regression, to identify aging-related phenotypes in the Korean population.
RESULTS: KoMethylNet, which uses 300 CpG sites, achieved a mean absolute error (MAE) of 2.82 years, a mean squared error (MSE) of 12.68 years, and a Pearson's correlation coefficient (R) of 0.90 with chronological age. In the external validation using healthy Korean individuals, KoMethylNet achieved the highest performance (MAE = 2.74, MSE = 12.29, R = 0.94). Seven phenotypes, including diabetes-related traits (diabetes, HbA1c, and urine glucose), were positively associated with KoMethylNet-EAA.
CONCLUSIONS: We developed a neural network-based DNAm aging clock using Korean population data that enables precise age prediction and offers potential opportunities for advancing aging-related research in Korea.
Key numbers
2.82 years
Mean Absolute Error
Measured in the hold-out validation set.
2.74 years
External Validation MAE
Achieved during external validation.
0.94
Pearson's Correlation Coefficient
Observed in external validation with healthy individuals.
Full Text
We can’t show the full text here under this license.
