Chronological Age Prediction: Developmental Evaluation of DNA Methylation-Based Machine Learning Models

Abstract

Epigenetic clock, a highly accurate age estimator based on DNA methylation (DNAm) level, is the basis for predicting mortality/morbidity and elucidating the molecular mechanism of aging, which is of great significance in forensics, justice, and social life. Herein, we integrated machine learning (ML) algorithms to construct blood epigenetic clock in Southern Han Chinese (CHS) for chronological age prediction. The correlation coefficient (r) meta-analyses of 7,084 individuals were firstly implemented to select five genes (ELOVL2, C1orf132, TRIM59, FHL2, and KLF14) from a candidate set of nine age-associated DNAm biomarkers. The DNAm-based profiles of the CHS cohort (240 blood samples differing in age from 1 to 81 years) were generated by the bisulfite targeted amplicon pyrosequencing (BTA-pseq) from 34 cytosine-phosphate-guanine sites (CpGs) of five selected genes, revealing that the methylation levels at different CpGs exhibit population specificity. Furthermore, we established and evaluated four chronological age prediction models using distinct ML algorithms: stepwise regression (SR), support vector regression (SVR-eps and SVR-nu), and random forest regression (RFR). The median absolute deviation (MAD) values increased with chronological age, especially in the 61–81 age category. No apparent gender effect was found in different ML models of the CHS cohort (all p > 0.05). The MAD values were 2.97, 2.22, 2.19, and 1.29 years for SR, SVR-eps, SVR-nu, and RFR in the CHS cohort, respectively. Eventually, compared to the MAD range of the meta cohort (2.53–5.07 years), a promising RFR model (ntree = 500 and mtry = 8) was optimized with an MAD of 1.15 years in the 1–60 age categories of the CHS cohort, which could be regarded as a robust epigenetic clock in blood for age-related issues.

Microhaplotype and Y-SNP/STR (MY): A novel MPS-based system for genotype pattern recognition in two-person DNA mixtures

“…The mean values and standard deviations (SDs) of the DoC, N-1 stutter ratio for Y-STRs, and ACR values for MHs were calculated by SAS ® 9.4 software (SAS Institute Inc., Cary, NC, USA). The other relevant forensic parameters were determined as described in our previous studies [88][89][90][91][92][93][94][95][96][97][98][99]. A e was calculated using the formula proposed by Kidd et al [100], A e = 1 ∑…”

Pyrosequencing: Current forensic methodology and future applications—a review

“…Besides the different prediction models employed (such as MLR), additional work has demonstrated the effect of ethnicity/ancestry as a confounding factor on DNA methylation. Depending on the loci selected, different populations may show a variation in age‐specific methylation levels [59]. For instance, Becker et al.…”

“…There are a number of DNA methylation markers that have been shown to correlate with biological age. Among the most common are ELOVL2, C1orf132, TRIM59, FHL2, KLF14, PDE4C, and ASPA [59][60][61][62][63][64]. A variety of algorithms have been exploited to build age prediction models using these and other loci.…”

“…A variety of algorithms have been exploited to build age prediction models using these and other loci. Besides the multivariate linear regression (MLR) model [65][66][67], which is the most common one, quantile regression, gradient boosting regression, ordinary least squares regression, weighted least squares regression [68], random forest [59,69], support vector [59,70], elastic net [71], and generalized regression neural networks [72] have been used. Recently, Hong et al [73] discussed the effect of different DNA sequencing/typing methods on the accuracy of age prediction models, and the need for platform-independent predictions.…”

“…A wide variety of research papers have been published discussing age prediction using DNA methylation markers with different sequencing/typing techniques. These include pyrosequencing [59,60,74], massively parallel sequencing [75][76][77], and SNaPshot assays [78][79][80], with the majority using pyrosequencing. Different population groups were studied, including Chinese [59,81], Japanese [60], German [26,60], Thai [63], Spanish [64], Iraqi [82], Italian [83], and French [84].…”