Microglia - mediated immunity partly contributes to the genetic association between Alzheimer's disease and hippocampal volume

Abstract

Genome-wide association studies (GWAS) suggest that Alzheimer's disease (AD) is partly explained by a burden of risk alleles (single nucleotide polymorphisms; SNPs) with relatively small effects. However, the mechanisms by which these loci cumulatively confer susceptibility remain largely unknown. Accumulating evidence suggests an association between increased AD risk allele burden (measured via a polygenic risk profile score; AD-RPS) with reduced hippocampal volume (HV) across a number of independent cohorts. These lines of research suggest that the reduced HV may be a causal mechanism of risk in the development of late-onset Alzheimer's disease (AD). However, as RPS assesses broad, cumulative genetic risk, little is known about the biological processes which may explain this observation. Here, we leverage GWAS data from i) 17,008 late onset AD cases & 37,154 controls and ii) hippocampal volume (N = 12,147; N = 9707) to explore putative pathways that may explain this association. We first demonstrate an association between whole genome AD-RPS and HV (PT < 0.5, Z = -2.07, P = 0.038), confirming previous associations. Second, we restrict our analysis to SNPs within AD genes within a microglia mediated immunity network (N_GENES = 56). A microglia AD-RPS was further associated with HV (PT < 0.01; Z = -2.152, P = 0.031). Last, using a competitive, permutation based approach, we show that the common variation within this candidate gene-set is associated with HV, controlling for SNP set-size (P = 0.024). Together, the observations suggest that the relationship between AD and HV is partially explained by genes within an AD-linked microglia mediated immunity network.

Keywords: Alzhiemer’s disease; GWAS; Hippocampus; MRI; Microglia; Polygenic; Risk profile score.

Fig. 1

All AD-RPS (SNPs across whole genome) regressed on hippocampal volume (across whole genome; red) and microglia AD-RPS (SNPs within 56 microglia-mediated immunity genes (Sims et al., 2017; blue)). Left Y-axis = R²; Right Y axis = beta coefficients (+/− 95% confidence), X-axis = P-Threshold of AD-RPS. All AD-RPS are performed after the removal of the APOE and MHC loci. P values are annotated above each bar that denotes variance explained (R²) at each AD-RPS/P – threshold.

Fig. 2

Variance explained (R²) by microglia AD-RPS (SNPs within 56 microglia-mediated immunity genes (denoted by blue dashed line) compared to 1000, comparably sized random AD RPS SNP sets at P-thresholds where microglia AD-RPS was significant. P value of enrichment at dashed line represents number of random AD-RPS that surpass microglia AD-RPS divided by total number of random AD-RPS permutations.

Fig. 3

Diagnostic plots for microglia SNP sets for ENIGMA (N = 13,163; left: β = −26.9, P = 0.016, N_SNPS = 60) and UK Biobank (N = 9707; right: β = −0.05, P = 0.027, N_SNPS = 61), both constrained to the P-threshold < 0.01. Each SNP is plotted by coefficient in the risk score (x axis) versus estimated effect size for HV in the testing dataset (y axis). The solid black line shows the effect size estimate for the risk score on HV in each of the testing datasets. Grey bar represents 95% confidence intervals.