Multilayered Epigenetic Analysis Identifies a Molecular Portrait for Psychological Resilience in Patients With Breast Cancer

Abstract

Background: Psychological resilience refers to a person's positive adaptation when faced with adversities, such as a breast cancer (BC) diagnosis. Highly resilient patients are more likely to regain stability and be protected from health conditions such as depression, anxiety, and posttraumatic stress disorder. We aimed to identify epigenetic markers that distinguish high- and low-resilient patients in a BC cohort at time of diagnosis.

Methods: Genome-wide DNA methylation was determined in participants selected from a prospectively collected cohort of 1040 newly diagnosed BC patients with known resilience status. DNA methylation of those displaying the highest and lowest scores (n = 425), as measured by the Connor-Davidson Resilience Scale, was analyzed in whole blood, using a multilayered bioinformatic approach. Sample subsets were created to identify differentially methylated probes (DMPs) and differentially methylated regions (DMRs), and fold change and area size were used to estimate the strength of methylation differences. The key regions associated with psychological resilience allowed us to build a classifier, using a random forest model, which was validated using an independent cohort (n = 80).

Results: DMPs and DMRs that consistently distinguished samples derived from high- and low-resilient patients were identified, and methylation differences followed a dose-response pattern related to resilience levels. DMRs included LY6G5C, ZFP57, CDH9, ZNF727, and C8orf31, where LY6G5C was found to be the most consistent DMR. Psychological resilience status could be predicted in the independent cohort with an area under the curve of 0.74 and a sensitivity and specificity of 0.67 and 0.72, respectively.

Conclusions: LY6G5C was identified as a novel marker for psychological resilience, paving the way for a more conceptual and comprehensive molecular understanding.

Keywords: Bioinformatics; Biomarker; Breast cancer; DNA methylation; Epigenetics; Psychological resilience.

Figure 1

Study outline. Flow of patients and datasets generated for the analysis of the association between methylation patterns and resilience status. ^aMore than 6 of 25 items missing. ^bTwo samples failed QC. ^cOne sample failed QC. CD-RISC, Connor-Davidson Resilience Scale; QC, quality control.

Figure 2

Association of methylation levels at individual CpG sites and resilience status. (A) Number of CpGs identified as DMPs between high- and low-resilient samples when comparing all samples in the discovery set and across its 10 subsets. (B) Volcano plots showing the statistical significance of DMPs relative to the log₂ FC for every CpG site for 3 selected subsets (60%, 30%, and 10%). (C) PC analysis score plots corresponding to (B) based on the CpGs identified as DMPs for the subsets mentioned above, with samples color coded by resilience status. (D) Proportions of DMPs overlapping with promoter and 5′ untranslated genomic regions, with the horizontal reference line corresponding to the proportions of all CpG probes in the methylation array passing quality control. ∗Proportions significantly increased/decreased (p < .05). (E) Bar plot showing the number of subsets in which individual CpGs were identified as DMPs. (F) Visualization of the strength of association (log₂ FC) between resilience and methylation for the 25 top DMPs in the discovery set and its 10 subsets. DMP, differentially methylated probe; FC, fold change; PC, principal component; s, subset.

Figure 3

Association between methylation levels at genomic regions and resilience status. (A) Visualization of the strength of association (DMR area size) between resilience and methylation for the top DMRs in the discovery set and its 10 subsets. (B–D) Examples of DMRs identified when comparing high- and low-resilient samples in the discovery set and representative subsets. Points show methylation measurements in samples obtained from participants with low (red) and high (blue) resilience status. Curves represent the smooth estimate of the methylation profiles in the respective resilience groups. DMR, differentially methylated region; s, subset.

Figure 4

Random forest classifier for distinguishing samples from high- and low-resilient patients based on methylation measurements. (A) Distribution of SP and SN obtained when testing the random forest classifier across 500 runs of splitting the classifier set into train, confirmation, and test sets. (B) AUC as a function of number of features (CpGs) used to construct the random forest model (top) and visualization of the genomic annotations of the features used (bottom) showing the proportions of different differentially methylated regions contributing to the classifier. (C) A receiver operating characteristic curve illustrating the performance of the final random forest classifier assessed on the validation set. AUC, area under the curve; SN, sensitivity; SP, specificity.