Antibiotic-induced perturbations in microbial diversity during post-natal development alters amyloid pathology in an aged APPSWE/PS1ΔE9 murine model of Alzheimer's disease

Abstract

Recent evidence suggests the commensal microbiome regulates host immunity and influences brain function; findings that have ramifications for neurodegenerative diseases. In the context of Alzheimer's disease (AD), we previously reported that perturbations in microbial diversity induced by life-long combinatorial antibiotic (ABX) selection pressure in the APP_SWE/PS1_ΔE9 mouse model of amyloidosis is commensurate with reductions in amyloid-β (Aβ) plaque pathology and plaque-localised gliosis. Considering microbiota-host interactions, specifically during early post-natal development, are critical for immune- and neuro-development we now examine the impact of microbial community perturbations induced by acute ABX exposure exclusively during this period in APP_SWE/PS1_ΔE9 mice. We show that early post-natal (P) ABX treatment (P14-P21) results in long-term alterations of gut microbial genera (predominantly Lachnospiraceae and S24-7) and reduction in brain Aβ deposition in aged APP_SWE/PS1_ΔE9 mice. These mice exhibit elevated levels of blood- and brain-resident Foxp3⁺ T-regulatory cells and display an alteration in the inflammatory milieu of the serum and cerebrospinal fluid. Finally, we confirm that plaque-localised microglia and astrocytes are reduced in ABX-exposed mice. These findings suggest that ABX-induced microbial diversity perturbations during post-natal stages of development coincide with altered host immunity mechanisms and amyloidosis in a murine model of AD.

Figure 1

Alterations in gut microbial diversity induced by 1 wk post-natal ABX gvg treatment of aged APP_SWE/PS1_ΔE9 mice. (A) Treatment regime schematic detailing the antibiotic (ABX) treatment of APP_SWE/PS1_ΔE9 mice used in the current and previous study. (B) Phylogenetic tree describing taxonomy assignment of the (C) bacterial diversity histogram generated from Illumina® MiSeq based V4-V5 amplicon sequencing of the 16 s rRNA gene from caecal and faecal contents of 6.5 month old male APP_SWE/PS1_ΔE9 mice. Only quality-controlled OTU reads corresponding to bacterial families with relative abundance >0.5% were included. (D) Relative abundance comparisons of Lachnospiraceae, S24-7 and Akkermansia, the top three differentially expressed bacterial genus’ identified by V4-V5 amplicon sequencing of the 16 s rRNA gene (n = 10–12, *p < 0.05, ***p < 0.001, one-way ANOVA with Tukey’s multiple comparison post-hoc test). (E) Shannon index analysis of the V4-V5 amplicon 16 s rRNA gene sequencing as a measure of microbial α-diversity in vehicle, 1 wk ABX gvg and ABX-treated 6.5 month old APP_SWE/PS1_ΔE9 mice (n = 10–12, *p < 0.05, one-way ANOVA with Tukey’s multiple comparison post-hoc test). Unifrac principal co-ordinate analysis of (F) un-weighted, accounting for presence of OTUs only, and (G) weighted β-diversity, accounting for both presence and relative abundance of OTUs, in vehicle, 1 wk ABX gvg and ABX-treated APP_SWE/PS1_ΔE9 mice (n = 10–12 mice, caecal and faecal sequencing, ellipses represent treatment groupings). The percentage of data variance explained by each IPCA is displayed. Data are displayed as X/Y scatter, mean or mean ± SEM. All data from the ABX treatment group is reproduced from Minter M. R. et al. and is included here solely for sake of comparison. See Supp. Figs 1, 3, Supp. Table 1 and statistical Table 2 for additional information.

Figure 2

1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice display altered peripheral and brain inflammatory profiles. (A) Representative density dot plots of T-bet and Foxp3 intracellular expression in TCRβ⁺ CD4⁺ T cell populations isolated from MLN, blood and brain tissue of vehicle and 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice analysed by flow cytometry. Quantified percentages of (B) Foxp3⁺ and (C) T-bet⁺ CD4⁺ T cells, representative of a T-reg and Th1 T cell phenotype respectively, are expressed relative to total live CD4⁺ T cell counts (n = 5–6, *p < 0.05, **p < 0.01, un-paired two-tailed Student’s t-test). (D) Immunoblot-based array of inflammatory mediators present in the serum of vehicle and 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice (n = 10 pooled sera). (E) Immunoblot-based array of inflammatory mediators present in the CSF of vehicle and 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice (n = 10 pooled CSF). (F) Heat map analysis of inflammatory mediator fold change expression in 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice relative to control. Data are displayed as log_e(mean) or mean ± SEM. See Supp. Figs 2, 4, 5, 6, and statistical Table 2 for additional information.

Figure 3

Amyloidosis is altered in 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice. (A) Representative immunohistochemical images of Aβ plaque burden in the cortex and hippocampus of vehicle and 1 wk ABX-gvg 6.5-month-old APP_SWE/PS1_ΔE9 mice using the anti-Aβ mAb, 3D6. Images in set display representative ×60 magnification z-stack maximum projections of individual 3D6⁺ Aβ plaques in these mice. Each immunohistochemical staining run was performed in conjunction with 12-month-old APP_SWE/PS1_ΔE9 mouse sections as a positive staining control and no primary antibody negative staining control. (B) Plaque burden quantification of vehicle and 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice using threshold-limited particle analysis of 3D6⁺ immunostaining (n = 12, *p < 0.05, un-paired two-tailed Student’s t-test). 3D6⁺ area was averaged from 6 sections/mouse (240 µm apart) and expressed relative to total cortical and hippocampal area of each slice. (C) Quantification of 3D6⁺ plaque area using threshold-limited immunofluorescence detection (n = 12, *p < 0.05, un-paired two-tailed Student’s t-test). (D) MSD Mesoscale® analysis of TFA-soluble (TBS-insoluble) Aβ1:40 and Aβ1:42 levels in combined cortical and hippocampal tissue from vehicle and 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice using anti-Aβ mAb, 4G8 (n = 14). (E) MSD Mesoscale® analysis of TBS-soluble Aβ1:40 and Aβ1:42 levels in combined cortical and hippocampal tissue from vehicle and 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice using anti-Aβ mAb, 4G8 (n = 14). Aβ concentrations are expressed relative to total protein concentrations obtained from the total-TBS soluble fraction used in the MSD Mesoscale® assay. (F) Immunoblot of full length APP (APP-FL) and BACE expression in RIPA-soluble brain lysates of vehicle and 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice using anti-APP mAb, 26D6 and an anti-BACE mAb. Samples were run both individually and as pools to confirm expression. Densitometry of (G) APP-FL and (H) BACE expression as detected by immunoblotting (n = 8). All densitometry is expressed as a ratio of APP-FL:β-actin or BACE:β-actin raw pixel intensities. Immuno-detection of β-actin was used to ascertain loading quantities. Full length blots can be viewed in Supp. Fig. 9. Data are displayed as mean ± SEM. See Supp. Figs 7, 8, 9 and statistical Table 2 for additional information.

Figure 4

Plaque-localised glial reactivity is reduced in 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice. (A) Representative ×60 magnification z-stack maximum projection images of IBA-1^+ve Aβ plaque-localised microglia, co-stained with DAPI, in vehicle and 1 wk ABX gvg-treated 6.5-month-old APP_SWE/PS1_ΔE9 mice. (B) Quantification of plaque-localised IBA-1^+ve microglial number in vehicle and 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice (n = 12, *p < 0.05, unpaired two-tailed Student’s t-test). (C) Plaque-localised IBA^+ve microglial number expressed relative to 3D6^+ve Aβ plaque area in vehicle and 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice (n = 12). (D) Representative ×60 magnification z-stack maximum projection images of GFAP^+ve Aβ plaque-localised astrocytes, co-stained with DAPI, in vehicle and 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice. (E) Quantification of plaque-localised GFAP^+ve astrocyte number in vehicle and 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice (n = 12, *p < 0.05, unpaired two-tailed Student’s t-test). (F) Plaque-localised GFAP^+ve astrocyte number expressed relative to 3D6^+ve Aβ plaque area in vehicle and 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice (n = 12). (G) 3D-IMARIS-based reconstructions of IBA-1^+ve plaque-localised microglia and quantification of (H) dendrite length, (I) dendrite number, and (J) terminal points in a subset of vehicle and 1 wk ABX gvg-treated APP_SWE/PS1_ΔE9 mice used for cell counts above (n = 5, **p < 0.01, *p < 0.05, unpaired two-tailed Student’s t-test). (K) 3D-IMARIS-based reconstructions of GFAP^+ve plaque-localised astrocytes and quantification of (H) dendrite length, (I) dendrite number, and (J) terminal points in these same mice (n = 5, *p < 0.05, unpaired two-tailed Student’s t-test). Data are displayed as mean ± SEM. See statistical Table 2 for additional information.