Maternal pre-pregnancy BMI and gestational weight gain, offspring DNA methylation and later offspring adiposity: findings from the Avon Longitudinal Study of Parents and Children

Abstract

Background: Evidence suggests that in utero exposure to undernutrition and overnutrition might affect adiposity in later life. Epigenetic modification is suggested as a plausible mediating mechanism.

Methods: We used multivariable linear regression and a negative control design to examine offspring epigenome-wide DNA methylation in relation to maternal and offspring adiposity in 1018 participants.

Results: Compared with neonatal offspring of normal weight mothers, 28 and 1621 CpG sites were differentially methylated in offspring of obese and underweight mothers, respectively [false discovert rate (FDR)-corrected P-value < 0.05), with no overlap in the sites that maternal obesity and underweight relate to. A positive association, where higher methylation is associated with a body mass index (BMI) outside the normal range, was seen at 78.6% of the sites associated with obesity and 87.9% of the sites associated with underweight. Associations of maternal obesity with offspring methylation were stronger than associations of paternal obesity, supporting an intrauterine mechanism. There were no consistent associations of gestational weight gain with offspring DNA methylation. In general, sites that were hypermethylated in association with maternal obesity or hypomethylated in association with maternal underweight tended to be positively associated with offspring adiposity, and sites hypomethylated in association with maternal obesity or hypermethylated in association with maternal underweight tended to be inversely associated with offspring adiposity.

Conclusions: Our data suggest that both maternal obesity and, to a larger degree, underweight affect the neonatal epigenome via an intrauterine mechanism, but weight gain during pregnancy has little effect. We found some evidence that associations of maternal underweight with lower offspring adiposity and maternal obesity with greater offspring adiposity may be mediated via increased DNA methylation.

Keywords: ALSPAC; ARIES; Epigenetic; causality; epigenome-wide association study; longitudinal; overnutrition; overweight; undernutrition.

Figure 1.

A conceptual framework showing the relationships of interest. GWG and maternal BMI are hypothesized to affect offspring adiposity via offspring DNA methylation. Specific hypotheses are: (i) maternal pre-pregnancy BMI and/or GWG is associated with differential methylation at CpG sites in offspring cord blood; (ii) methylation at these sites is also associated with offspring adiposity (we would also expect consistency between different measures of adiposity and age at measurement); and (iii) maternal adiposity is persistently associated with differential methylation in offspring at time points beyond birth.

Figure 2.

Manhattan plots showing the results of epigenome-wide association studies (EWAS) of cord blood DNA methylation in offspring of underweight (n = 24), overweight (n = 94) and obese (n = 32) mothers compared with offspring of normal weight mothers (n = 577). The bottom (blue) line indicates the FDR-adjusted P-value threshold (0.05) and the top (red) line indicates the Bonferroni threshold for genome-wide significance (3.5*10⁻⁷, i.e. 0.05/284972 probes).

Figure 3.

Associations between maternal or paternal obesity and offspring cord blood DNA methylation [mean difference in methylation (%) compared with offspring of normal weight mothers/fathers]. Darker shading indicates a larger effect size (regardless of direction). Models were adjusted for bisulfite conversion batch, and paternal/maternal continuous BMI where indicated, but no other covariates (n obese mothers = 40, n normal weight mothers = 665, n obese fathers = 53, n normal weight fathers = 372). Stars indicate associations with an FDR-adjusted P-value < 0.05.

Figure 4.

Methylation (%) over time for offspring of obese (short dashed (green) line in a) or underweight (short dashed (green) line in b) mothers compared with offspring of normal weight mothers (long dashed (black) line). Ribbons indicate 95% confidence intervals.

Figure 5.

Associations between cord blood DNA methylation and offspring adiposity. The heatmaps are built using effect sizes. Positive associations appear more red and negative associations appear more blue. CpG sites were selected based on their association with maternal underweight or obesity, the effect size for which is indicated in the far right-hand panel. Stars indicate associations with a P-value < 0.05 (before correction for multiple testing).