Plasma proteomic biomarkers as mediators or moderators for the association between poor cardiovascular health and white matter microstructural integrity: The UK Biobank study

Abstract

Introduction: The plasma proteome's mediating or moderating roles in the association between poor cardiovascular health (CVH) and brain white matter (WM) microstructural integrity are largely unknown.

Methods: Data from 3953 UK Biobank participants were used (40-70 years, 2006-2010), with a neuroimaging visit between 2014 and 2021. Poor CVH was determined using Life's Essential 8 (LE8) and reversing standardized z-scores (LE8_{z _rev}). The plasma proteome was examined as a potential mediator or moderator of LE8_{z _rev}'s effects on quantitative diffusion-weighted magnetic resonance imaging (dMRI) metrics.

Results: LE8_{z_rev} was significantly associated with deteriorated WM microstructural integrity, as reflected by lower tract-averaged fractional anisotropy (dMRI-FA_mean), (β ± standared error (SE): -0.00152 ± 0.0003, p < 0.001) and higher tract-averaged orientation dispersion (dMRI-OD_mean), (β ± SE:+0.00081 ± 0.00017, p < 0.001). Ten strongly mediating plasma proteins of 1463 were identified, with leptin as the principal driver.

Discussion: Poor CVH is linked to poor WM microstructural integrity measures (lower FA_mean and higher OD_mean), mostly mediated through leptin.

Highlights: Up to 3953 UK Biobank participants were selected for this study. Poor cardiovascular health (CVH) was determined using Life's Essential 8. The plasma proteome was examined as a potential mediator or moderator of poor CVH's effect on dMRI metrics. Ten plasma proteins were identified with strong mediating effects, with leptin being the principal driver.

Keywords: Life's Essential 8; aging; cardiovascular health; diffusion‐weighted magnetic resonance imaging; plasma proteomic biomarkers; white matter microstructural integrity.

FIGURE 1

Poor cardiovascular health (LE8 _{z _rev_total}) and tract‐specific and mean dMRI metrics (FA, MD, ICVF, ISOVF, OD, standardized z‐scores) in final selected sample (N = 3953), multiple linear regression models: UK Biobank 2006–2021. Based on a series of linear regression models adjusted for age, sex, race (non‐White vs White), time elapsed from baseline to neuroimaging visit (days), and household size. Tract‐specific FA, MD, ISOVF, ICVF, and OD are standardized z‐scores, as is the reverse‐coded LE8 total score. Effect sizes are plotted on a heat map to highlight effect sizes (G), whereas standard Montreal Neurological Institute (MNI) brain images display effect sizes on the brain regions/tracts only when pcorr < 0.05. Light blue (or yellow) color is for effect sizes in absolute values ≥0.04 and dark blue (or red) are for effect sizes in absolute value ≥0.03 but <0.04. Light blue/dark blue are for inverse associations and yellow/red are for positive associations. Those are highlighted rows in supplementary datasheet 1 (B) is for FA and (C) is for MD; (D) is for ISOVF; (E) is for ICVF; (F) is for OD; (A) displays the entire JHU FA skeleton with different colors. Better WM microstructural integrity is linked to higher FA and ICVF and lower MD, ISOVF, and OD. FA, fractional anisotropy; ICVF, intra‐cellular volume fraction; ISOVF, volume fraction of Gaussian isotropic diffusion; MD, mean diffusivity; NODDI, neurite orientation dispersion and density imaging; OD orientation dispersion index.

FIGURE 2

Volcano plot of plasma proteomic biomarkers (standardized z‐scored) in relation to LE8 reverse‐coded z‐scored total score: UK Biobank 2006–2010. Based on a series of multiple linear regression models, with main predictor being LE8 toal score (z‐scored, reverse‐coded by multiplying by −1) and the outcome being each of 1463 plasma proteomic biomarkers (Log2 transformed, z‐scored). The y‐axis is the predictor's associated p‐value on a –log10 scale and the x‐axis is the β coefficient (effect of LE8 exposure on standardized z‐scores of plasma proteomic markers) from the multiple linear regression models. An estimate with a Bonferroni corrected p‐value < 0.05 and an absolute estimate >0.20 is marked by the plasma proteomic marker abbreviation (see UK Biobank showcase URL: https://biobank.ndph.ox.ac.uk/showcase/). Selected proteins (k = 147) for further mediation analysis have a corrected p‐value < 0.05 and a point estimate >0.20 in absolute value (red). Dashed vertical lines are set at −0.20 and +0.20 effect sizes. Dashed horizontal line is set at the Bonferroni corrected p‐value. Details are provided on github: https://github.com/baydounm/UKB‐paper13‐supplementarydata. See list of abbreviations for protein abbreviations: mlog10p, −log₁₀(p‐value); LE8, Life's Essential 8.

FIGURE 3

Four‐way decomposition of the association between poor cardiovascular health as measured by LE8 total score (z‐scored, reverse coded) and FA_mean (z‐scored) by the selected plasma proteomic biomarkers (k = 147): UK Biobank 2006–2021. (A) Heatmap for four‐way decomposition showing no significant pure mediation for 124 proteins: PIE p > 0.05. (B) Heatmap for four‐way decomposition showing inconsistent mediation for 9 proteins: PIE p < 0.05, PIE < 0, TE < CDE. (C) Heatmap for four‐way decomposition showing consistent mediation for 14 proteins: PIE p < 0.05 and/or % PIE of TE >20%, PIE > 0, and TE > CDE. Effects could range from 0 to 0.5. *p < 0.05; **p < 0.010; ***p < 0.001. Protein abbreviations are found at https://www.ncbi.nlm.nih.gov/gene/. ERERI_CDE, excess relative risk due to neither mediation nor interaction or controlled direct effect; ERERI_INTMED, excess relative risk due to mediated interaction or mediated interaction; ERERI_INTREF, excess relative risk due to interaction only or interaction referent; ERERI_PIE, excess relative risk due to mediation only or pure indirect effect; FA, fractional anisotropy; TERERI, total excess relative risk.

FIGURE 4

Four‐way decomposition of the association between poor cardiovascular health as measured by LE8 total score (z‐scored, reverse coded) and OD_mean (z‐scored) by the selected plasma proteomic biomarkers (k = 147): UK Biobank 2006–2021. (A) Heatmap for four‐way decomposition showing no significant or inconsistent mediation for 90 proteins (see A and B of Figure 3). (B) Heatmap for four‐way decomposition showing consistent medition for 57 proteins: PIE p < 0.05 and/or % PIE of TE >20%, PIE > 0, TE > CDE. Effects could range from 0 to 0.5. *p < 0.05; **p < 0.010; ***p < 0.001. Protein abbreviations are found at https://www.ncbi.nlm.nih.gov/gene/. ERERI_CDE, excess relative risk due to neither mediation nor interaction or controlled direct effect; ERERI_INTMED, excess relative risk due to mediated interaction or mediated interaction; ERERI_INTREF, excess relative risk due to interaction only or interaction referent; ERERI_PIE, excess relative risk due to mediation only or pure indirect effect; OD, orientation dispersion; TERERI, total excess relative risk.