Development of an improved SVMp model for age prediction using DNA methylation data
Year: 2026
Type: conference-paper
Abstract: Background incl. aims This study aimed to improve age prediction in a Danish cohort of 150 individuals by in-depth analyses of DNA methylation sequencing data. Previously, 11 well-known age-associated CpGs on ten PCR amplicons associated with ten distinct genes were selected and a support vector machine model with a polynomial function (SVMp) was developed for age estimation in blood. Every CpG site included within the ten amplicons in the previously described assay was investigated to find a new combination of CpGs that could improve the age prediction. Methods The ten amplicons were previously amplified after bisulphite conversion, and the methylation levels were assessed by massively parallel sequencing. The ten amplicons contained a total of 73 CpG sites, of which 63 CpG sites were shown to be medium to highly associated with age in this work (Pearson correlation coefficient, |r| > 0.3). More than 70,000 SVMp models with various combinations of the 63 CpGs were tested to identify the model with the lowest mean absolute error (MAE) and root mean square error (RMSE) in training and test datasets from the Danish cohort. A final model with 34 CpGs (SVMp-34CpG) was selected. Results The SVMp-34CpG model presented considerable improvement over many other forensic prediction models and achieved MAEs of 1.64 years and 1.76 years for the training and test datasets, respectively. The SVMp- 34CpG model indicated robust generalization and minimal prediction bias across the 18–50 age range (MAE 1.47 years), although slightly higher errors were observed for individuals aged 50–70 years (MAE 2.62 years). Compared to the previous 11-CpG model, the SVMp-34CpG model showed superior accuracy in the Danish cohort by predicting the age of 91% of the individuals within four years of their actual age, versus 68% for the prior model. Conclusions The SVMp-34CpG model represents significant advancement in age prediction using DNA methylation data, offering higher accuracy, better generalization, and reduced overfitting compared to prior models. Its robust performance makes it a valuable tool for applications in forensic science, age estimation research, and clinical studies.
Institution: Aalborg University
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W7167390871