A low-gluten diet induces changes in the intestinal microbiome of healthy Danish adults

Abstract

Adherence to a low-gluten diet has become increasingly common in parts of the general population. However, the effects of reducing gluten-rich food items including wheat, barley and rye cereals in healthy adults are unclear. Here, we undertook a randomised, controlled, cross-over trial involving 60 middle-aged Danish adults without known disorders with two 8-week interventions comparing a low-gluten diet (2 g gluten per day) and a high-gluten diet (18 g gluten per day), separated by a washout period of at least six weeks with habitual diet (12 g gluten per day). We find that, in comparison with a high-gluten diet, a low-gluten diet induces moderate changes in the intestinal microbiome, reduces fasting and postprandial hydrogen exhalation, and leads to improvements in self-reported bloating. These observations suggest that most of the effects of a low-gluten diet in non-coeliac adults may be driven by qualitative changes in dietary fibres.

Fig. 1

Experimental design, data overview and summary of the cross-over trial. a The study was a randomised, controlled, cross-over trial with two 8-week dietary intervention periods separated by a washout period of at least six weeks, comparing the effects of a low-gluten diet and a high-gluten diet on the gut microbiome (predefined primary outcome), untargeted urine metabolome and measures of host physiology. Time points for data collections are indicated by circles in the lower part panel (a). b Effects of a low-gluten diet compared with a high-gluten diet on the intestinal microbiome, urine/faecal metabolome and markers of host physiology in apparently healthy adults. Measured variables that were found to be reduced (red arrow), increased (green arrow) or unchanged (black horizontal arrows) following the low-gluten diet intervention compared with the high-gluten diet intervention are listed. MGS metagenomics species, PYY peptide YY, SCFA short-chain fatty acids. The person icon and molecular structure images for the acetate anion, butyrate ion, propionate ion and kynurenine were obtained from Wikimedia Commons, released under public domain

Fig. 2

A low-gluten diet alters the composition of the gut microbiome. a Scatterplot of the statistical significance of the metagenomic species (MGSs) as assessed by a linear mixed model testing for the difference between the low-gluten and the high-gluten diets adjusted for age, gender, intestinal transit time, participant (n = 51) and carry-over effect. Adjusted P values are displayed on the y-axis (log10 scale) and the effect size (absolute values were log10 transformed) is on the x-axis. Points are sized according to the total abundance (%) and coloured according to the ten most abundant taxonomic families. The ‘Other’ category consists of the remaining families. The horizontal line represents an adjusted P value of 0.05 and the 14 species that changed significantly (FDR < 0.05) between the interventions are labelled with their full taxonomic annotation. Only species that could be annotated to family level and with abundance above 0.02% were included in the plot (255 species). b Bar chart of the 14 significant species showing the log2 fold change (means ± SEM) between baseline and after the low-gluten diet (blue bars) and high-gluten diet (red bars), respectively. The black circles are sized according to the negative log10 of the adjusted P values of comparison between the low-gluten and the high-gluten diet using a linear mixed model adjusted for age, gender, intestinal transit time, participant (n = 51) and carry-over effect. Green circles are scaled according the species abundance. The last column lists the number of participants in whom the given species were measured. Details on the individual species can be found in Supplementary Data 2

Fig. 3

A low-gluten diet alters the functional potential of the gut microbiome. a Microbial genes annotated to Kyoto Encyclopedia of Genes and Genomes (KEGG) orthologs (KOs) were grouped into KEGG modules and manually curated (customised) modules. The bar chart display the median log2 fold change (median ± SEM) of all individual KOs within a module when comparing the relative abundance at baseline to the abundance following the low-gluten diet (blue bars) or the high-gluten diet (red bars), respectively. b Dot plot of the negative log10 of the adjusted P value from the linear mixed model comparing changes in the abundance of modules induced by the low-gluten diet with the changes induced in the high-gluten diet (black dots) adjusting for age, gender, intestinal transit time, participant (n = 51) and carry-over effect. The same analysis was carried out while removing the significant MGSs from the data (grey dots) to elucidate their contribution to the significance. All effect sizes and SEM for each KO can be found in Supplementary Data 3 and 4. c Prevalence of the module across the 1264 MGSs identified from the IGC catalogue^,. A module was assessed to be present or partially present in a MGS when at least two KOs from the module were detected in the MGS. d Bar plot showing the fraction of the total abundance of a module contributed by each significantly different MGS in per cent. (Supplementary Data 2)

Fig. 4

A low-gluten diet affects measures of intestinal fermentation. a Breath hydrogen levels following the same standardised meal at all four visits (low-gluten diet start, open blue circles; low-gluten diet end, blue squares; high-gluten diet start, open red triangle; high-gluten diet end, filled red triangle). Data are shown as means ± SEM (n = 51-57). b Plot showing changes in gut bloating as assessed by visual analogue scale (VAS) following the low-gluten diet (blue circles) compared with the high-gluten diet (red squares). Data are shown as means ± SEM (n = 52–53). Changes were assessed by a linear mixed model adjusting for age, gender and intestinal transit time. *P < 0.05, **P < 0.01. c Linear regression network of breath hydrogen levels and the abundance of bacterial species and concentrations of urine metabolites which are significantly responding to the dietary interventions using a linear mixed model adjusted for gender, age and participant (n = 49) (Supplementary Data 5). The dotted line separates the features that were decreased and increased, respectively, when comparing the low-gluten and high-gluten periods. Significant (FDR < 0.05) positive associations are indicated with grey lines; negative associations with red lines. Thickness of lines indicates the significance level. Nodes are coloured according to type; breath hydrogen (cyan), urine metabolites (yellow), Bifidobacterium (red), Dorea longicatena (purple), Blautia wexlerae (orange), Eubacterium hallii (brown), Lachnospiracaea (green), Anaerostipes (blue), Clostridiales (pink) and Unclassified (grey). m/z refers to the mass-to-charge ratio of a given unidentified urine metabolite. BAIBA β-aminoisobutyric acid, DHPPA 3,5-dihydroxy-hydrocinnamic acid

Fig. 5

Low-gluten dieting affects markers of host metabolism. a Plot showing participants’ changes in body weight following the low-gluten (blue circles) and high-gluten (red squares) periods. b Plot showing participants’ plasma concentrations of peptide YY (PYY) following a standardised meal at all four visits (low-gluten diet start, open blue circles; low-gluten diet end, blue squares; high-gluten diet start, open red triangle; high-gluten diet end, filled red triangle). c Plot showing log2 fold changes in participants’ urine concentrations of β-aminoisobutyric acid (BAIBA) and d faecal concentrations of kynurenine following the low-gluten (blue circles) and high-gluten (red squares) diet, respectively. Data are shown as means ± SEM, n = 50–54. Changes were assessed by a linear mixed model adjusting for age, gender and intestinal transit time. *P < 0.05, **P < 0.01, ***P < 0.001. AUC area under the curve