Human Age Prediction Based on DNA Methylation Using a Gradient Boosting Regressor.

Xingyan Li,Yan Xu,Weidong Li

doi:10.3390/genes9090424

Abstract

All tissues of organisms will become old as time goes on. In recent years, epigenetic investigations have found that there is a close correlation between DNA methylation and aging. With the development of DNA methylation research, a quantitative statistical relationship between DNA methylation and different ages was established based on the change rule of methylation with age, it is then possible to predict the age of individuals. All the data in this work were retrieved from the Illumina HumanMethylation BeadChip platform (27K or 450K). We analyzed 16 sets of healthy samples and 9 sets of diseased samples. The healthy samples included a total of 1899 publicly available blood samples (0–103 years old) and the diseased samples included 2395 blood samples. Six age-related CpG sites were selected through calculating Pearson correlation coefficients between age and DNA methylation values. We built a gradient boosting regressor model for these age-related CpG sites. 70% of the data was randomly selected as training data and the other 30% as independent data in each dataset for 25 runs in total. In the training dataset, the healthy samples showed that the correlation between predicted age and DNA methylation was 0.97, and the mean absolute deviation (MAD) was 2.72 years. In the independent dataset, the MAD was 4.06 years. The proposed model was further tested using the diseased samples. The MAD was 5.44 years for the training dataset and 7.08 years for the independent dataset. Furthermore, our model worked well when it was applied to saliva samples. These results illustrated that the age prediction based on six DNA methylation markers is very effective using the gradient boosting regressor.

Highlights

Aging is an irreversible natural process in human life which is influenced by many factors, such as genetic factors, living environment and diseases [1,2]
DNA methylation (DNAm) refers to the chemical modification process which transfers the active methyl to the specific base on the DNA chain under the catalysis of DNA methyltransferase (DNMT) [10]
The results showed that the correlation between age and DNA methylation was 0.97 for the gradient boosting regressor, with root mean square error (RMSE) and mean absolute deviation (MAD) being

Summary

Introduction

Aging is an irreversible natural process in human life which is influenced by many factors, such as genetic factors, living environment and diseases [1,2]. Many methods have been used to estimate individual age, the problems of low sensitivity and prediction accuracy still to be improved [4,5,6,7]. Recent studies have shown that human aging is related to the alteration of DNA methylation in genome specific locations, and these epigenetic modifications can be used to estimate the individual age [8,9]. DNA methylation (DNAm) refers to the chemical modification process which transfers the active methyl to the specific base on the DNA chain under the catalysis of DNA methyltransferase (DNMT) [10]. DNA methylation can occur at the N-6 position of adenine, N-7 position of guanine, C-5 position of cytosine and so on. In the mammalian genome, DNA methylation often occurs on C (cytosine) of 5’-CpG-3’ to generate 5-methyldeoxycytidine (5mC).

Methods

Results

Discussion

Conclusion