.png){kind=icon}
.png){kind=icon}
Return
A machine learning approach to identify key epigenetic transcripts for ageing research in human blood (Epitage)
.png){kind=icon}
PRE
AI
T
U
DOI：10.1007/s10522-026-10473-6.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
DNA methylation is an established biomarker of human ageing and is used by a variety of tools to identify meaningful epigenetic signals. We investigated whether analysing CpGs grouped by transcript as functional units could generate a ranked list of transcripts most correlated with age that might otherwise be overlooked in genome-wide CpG-based studies. Here we present Epitage ( https://github.com/a00s/epitage ), a continuously updated ranked list of transcripts built from the GSE87571 dataset (714 whole-blood samples, ages 14–94 years) through intensive testing with machine-learning models. To support reproducible analyses, we developed ugPlot ( https://github.com/a00s/ugplot ), an open-source R/Shiny tool with a graphical user interface that automates model training, testing, and comparison. Initially, we identified 48 transcripts across 13 genes, with some transcripts from the genes OBSCN, PRRT1, and SPTBN4 showing better predictive performance when multiple associated CpGs were analysed together rather than individually. In contrast, for the majority of transcripts, a dominant individual CpG still showed a higher Spearman correlation with age, as seen in established ageing genes such as ELOVL2, FHL2, and TRIM59. Epitage is a transcript-ranking list based on the methylation patterns observed in the analysed dataset. It provides a reproducible framework for prioritising transcripts associated with human ageing and for guiding future epigenetic studies.
Keywords:
Ageing
Epigenetics
Machine learning
Transcript-level DNA methylation
Ageing biomarkers.
Journal
IF:
4.1
Papers:
1.7K
Citations:
3.5K
Organization
Cited Papers