Yui Tomo

This study predicts biological age and clinical biomarkers from cheek mucosa DNA methylation data, showing high accuracy for age and multiple biomarkers compared to blood-derived data.

This paper calibrates epigenetic age between EPICv2 and MSA arrays using linear regression models to reduce cross-platform differences in six epigenetic clocks.

The paper introduces an incremental batch effect correction framework for DNA methylation data, allowing new data to be corrected without reprocessing existing data.

The paper develops Transfer Elastic Net, a transfer learning method to create epigenetic clocks for the Japanese population with smaller sample sizes, achieving lower prediction errors than existing models.