Differential Methylation Profile in Fragile X Syndrome-Prone Offspring Mice after in Utero Exposure to Lactobacillus Reuteri

Abstract

Environmental factors such as diet, gut microbiota, and infections have proven to have a significant role in epigenetic modifications. It is known that epigenetic modifications may cause behavioral and neuronal changes observed in neurodevelopmental disabilities, including fragile X syndrome (FXS) and autism (ASD). Probiotics are live microorganisms that provide health benefits when consumed, and in some cases are shown to decrease the chance of developing neurological disorders. Here, we examined the epigenetic outcomes in offspring mice after feeding of a probiotic organism, Lactobacillus reuteri (L. reuteri), to pregnant mother animals. In this study, we tested a cohort of Western diet-fed descendant mice exhibiting a high frequency of behavioral features and lower FMRP protein expression similar to what is observed in FXS in humans (described in a companion manuscript in this same GENES special topic issue). By investigating 17,735 CpG sites spanning the whole mouse genome, we characterized the epigenetic profile in two cohorts of mice descended from mothers treated and non-treated with L. reuteri to determine the effect of prenatal probiotic exposure on the prevention of FXS-like symptoms. We found several genes involved in different neurological pathways being differentially methylated (p ≤ 0.05) between the cohorts. Among the key functions, synaptogenesis, neurogenesis, synaptic modulation, synaptic transmission, reelin signaling pathway, promotion of specification and maturation of neurons, and long-term potentiation were observed. The results of this study are relevant as they could lead to a better understanding of the pathways involved in these disorders, to novel therapeutics approaches, and to the identification of potential biomarkers for early detection of these conditions.

Keywords: ASD; FXS; Lactobacillus reuteri; epigenetics; in utero; methylation.

Figure 1

Heat map showing both Groups A (TD) and B (FXS-like symptoms) methylation patterns. As the color gets darker, this means more hypermethylation. The heatmap is showing the β values from 570 significant CpGs. CpGs were hierarchically clustered.

Figure 2

Gene Ontology analysis. Volcano plot of results from enrichment analysis of pathways from Gene Ontology. Z-score is defined as the number of hypermethylated genes minus the number of hypomethylated genes in the pathway, divided by the square root of the number of total genes. A positive Z-score indicates hypermethylation in Group B, while a negative Z-score indicates hypomethylation in Group B. Orange vertical line indicates a p-value of 0.01. Gene sets with a p-value less than 0.01 are labeled with GO ids. The point size shows the number of genes with methylation information in each pathway. BP: biological process: CC: cellular component; MF: molecular function.

Figure 3

Protein–protein interactions network. Protein interactome network for the proteins that were shown to be differentially methylated in FXS-like mouse models compared to controls using the STRING software. All the colored nodes represent the query proteins and first shell of interactions. Each node represents all the proteins produced by a single, protein-coding gene locus. Filled nodes mean that the 3D structure of that protein is known or predicted. The colored lines represent different types of associations. The navy-blue line indicates known interactions from curated databases. The fuchsia lines indicate known interactions that are experimentally determined. The dark green lines represent predicted interactions of neighboring genes, the red lines represent gene fusions, and the royal blue line represents gene co-occurrence. The light green line represents text mining, the black line represents co-expression, and the purple line represents protein homology.

Figure 4

(Top): Boxplot charts showing the differential expression levels of SHANK3, AGAP3, and DLG2 in the two groups of mice. The comparison of expression levels of both SHANK3 and AGAP3, although in the right direction relative to the methylation data, did not reach statistical significance. A significant increased expression of DLG2 was observed in Group B compared to Group A. (Bottom): Western blot of representative brain samples from Groups A and B (n = 4) for all three proteins. GADPH was used as a loading control. * Denotes statistical significance (p-value < 0.05).