Format

Send to

Choose Destination
Clin Epigenetics. 2018 Dec 13;10(1):155. doi: 10.1186/s13148-018-0591-z.

Machine learning selected smoking-associated DNA methylation signatures that predict HIV prognosis and mortality.

Author information

1
Department of Psychiatry, Yale School of Medicine, 300 George Street, 950 Campbell Ave, West Haven, New Haven, CT, 06511, USA.
2
VA Connecticut Healthcare System, 950 Campbell Ave, West Haven, CT, 06516, USA.
3
Center for Biomedical Bioinformatics, National Cancer Institute, Rockville, MD, 20852, USA.
4
Bluestone Center for Clinical Research, New York University, New York, NY, 10010, USA.
5
Department of Biostatistics, Yale School of Public Health, New Haven, CT, 065116, USA.
6
Division of Infectious Diseases, Emory University School of Medicine, Atlanta, GA, 30303, USA.
7
Department of Native Hawaiian Health, John A. Burns School of Medicine, University of Hawaii, Suite 1016B, Honolulu, 96813, USA.
8
School of Medicine, Vanderbilt University, Nashville, TN, 37232, USA.
9
National Institute on Alcohol Abuse and Alcoholism, Bethesda, MD, 20852, USA.
10
Yale University School of Medicine, New Haven, CT, 06516, USA.
11
Department of Psychiatry, Yale School of Medicine, 300 George Street, 950 Campbell Ave, West Haven, New Haven, CT, 06511, USA. ke.xu@yale.edu.
12
VA Connecticut Healthcare System, 950 Campbell Ave, West Haven, CT, 06516, USA. ke.xu@yale.edu.

Abstract

BACKGROUND:

The effects of tobacco smoking on epigenome-wide methylation signatures in white blood cells (WBCs) collected from persons living with HIV may have important implications for their immune-related outcomes, including frailty and mortality. The application of a machine learning approach to the analysis of CpG methylation in the epigenome enables the selection of phenotypically relevant features from high-dimensional data. Using this approach, we now report that a set of smoking-associated DNA-methylated CpGs predicts HIV prognosis and mortality in an HIV-positive veteran population.

RESULTS:

We first identified 137 epigenome-wide significant CpGs for smoking in WBCs from 1137 HIV-positive individuals (p < 1.70E-07). To examine whether smoking-associated CpGs were predictive of HIV frailty and mortality, we applied ensemble-based machine learning to build a model in a training sample employing 408,583 CpGs. A set of 698 CpGs was selected and predictive of high HIV frailty in a testing sample [(area under curve (AUC) = 0.73, 95%CI 0.63~0.83)] and was replicated in an independent sample [(AUC = 0.78, 95%CI 0.73~0.83)]. We further found an association of a DNA methylation index constructed from the 698 CpGs that were associated with a 5-year survival rate [HR = 1.46; 95%CI 1.06~2.02, p = 0.02]. Interestingly, the 698 CpGs located on 445 genes were enriched on the integrin signaling pathway (p = 9.55E-05, false discovery rate = 0.036), which is responsible for the regulation of the cell cycle, differentiation, and adhesion.

CONCLUSION:

We demonstrated that smoking-associated DNA methylation features in white blood cells predict HIV infection-related clinical outcomes in a population living with HIV.

KEYWORDS:

DNA methylation; Ensemble machine learning; HIV frailty; Mortality; Tobacco smoking

PMID:
30545403
PMCID:
PMC6293604
DOI:
10.1186/s13148-018-0591-z
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for BioMed Central Icon for PubMed Central
Loading ...
Support Center