AUTHOR=Lu Andrew Ke-Ming , Hsieh Shulan , Yang Cheng-Ta , Wang Xin-Yu , Lin Sheng-Hsiang 

TITLE=DNA methylation signature of psychological resilience in young adults: Constructing a methylation risk score using a machine learning method

JOURNAL=Frontiers in Genetics

VOLUME=Volume 13 - 2022

YEAR=2023

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2022.1046700

DOI=10.3389/fgene.2022.1046700

ISSN=1664-8021

ABSTRACT=Resilience is a process associated with the ability to recover from difficult life events. We aimed to evaluate the abilities of DNA methylation signatures and methylation risk scores to discriminate between low resilience (LR) versus high resilience (HR) individuals. This study recruited 78 young adults, divided into a discovery set and a validation set. In the discovery set, we conducted genome-wide methylation analysis (human MethylationEPIC 850K BeadChip) on the subject’s blood DNA and discriminated significant methylation signatures. These methylation signatures were then verified by quantitative methylation-specific PCR (qMSP) in the validation set. Based on genome-wide scans of LR versus HR individuals, seventeen significantly differentially methylated probes were identified. Next, we selected nine probes within gene coding regions to conduct verification in the validation set. Finally, we selected three methylation probes which were significant differences between LR and HR, cg18565204 (AARS), cg17682313 (FBXW7), and cg07167608 (LINC01107) in the final model of methylation risk score. This methylation risk score model showed satisfactory discrimination between LR and HR individuals by logistic regression and support vector machine, with an AUC of 0.81 and 0.93, accuracy of 72.3% and 87.1%, sensitivity of 75% and 87.5%, and specificity of 70% and 80%. These findings suggest that methylation signatures may be used as an indicator of LR vulnerability and provide a risk score model that may contribute to the field of psychology.