Duodenal Microbiota in Stunted Undernourished Children with Enteropathy

Abstract

Background: Environmental enteric dysfunction (EED) is an enigmatic disorder of the small intestine that is postulated to play a role in childhood undernutrition, a pressing global health problem. Defining the incidence of this disorder, its pathophysiological features, and its contribution to impaired linear and ponderal growth has been hampered by the difficulty in directly sampling the small intestinal mucosa and microbial community (microbiota).

Methods: In this study, among 110 young children (mean age, 18 months) with linear growth stunting who were living in an urban slum in Dhaka, Bangladesh, and had not benefited from a nutritional intervention, we performed endoscopy in 80 children who had biopsy-confirmed EED and available plasma and duodenal samples. We quantified the levels of 4077 plasma proteins and 2619 proteins in duodenal biopsy samples obtained from these children. The levels of bacterial strains in microbiota recovered from duodenal aspirate from each child were determined with the use of culture-independent methods. In addition, we obtained 21 plasma samples and 27 fecal samples from age-matched healthy children living in the same area. Young germ-free mice that had been fed a Bangladeshi diet were colonized with bacterial strains cultured from the duodenal aspirates.

Results: Of the bacterial strains that were obtained from the children, the absolute levels of a shared group of 14 taxa (which are not typically classified as enteropathogens) were negatively correlated with linear growth (length-for-age z score, r = -0.49; P = 0.003) and positively correlated with duodenal proteins involved in immunoinflammatory responses. The representation of these 14 duodenal taxa in fecal microbiota was significantly different from that in samples obtained from healthy children (P<0.001 by permutational multivariate analysis of variance). Enteropathy of the small intestine developed in gnotobiotic mice that had been colonized with cultured duodenal strains obtained from children with EED.

Conclusions: These results provide support for a causal relationship between growth stunting and components of the small intestinal microbiota and enteropathy and offer a rationale for developing therapies that target these microbial contributions to EED. (Funded by the Bill and Melinda Gates Foundation and others; ClinicalTrials.gov number, NCT02812615.).

Figure. 1

Correlations between components of the duodenal proteome, the absolute abundances of duodenal bacterial taxa and stunting. (A) The top 10 positive correlations between members of the 14 core taxa and duodenal proteins. The size and color of the circle represents the magnitude of the correlation (larger circle and darker color indicates stronger correlation). (B) Annotations of proteins shown in panels A and G. (C-F) Total duodenal bacterial load, and the abundances of the three organisms most positively correlated with duodenal inflammatory proteins are significantly negatively correlated with LAZ. The least-squares regression line is depicted in blue while shaded regions denote 95% confidence bands. (G) Star network of correlations between plasma REG3A and core taxa-associated duodenal proteins. As indicated by the color key, edge transparency/color corresponds to correlation strength (darker edges denote a stronger correlation). The duodenal protein with the strongest correlation, lipocalin-2 (LCN-2), is indicated by the tail of the arrowhead at 3 o’clock; duodenal proteins with progressively weaker correlations with REG3A are distributed in a counter-clockwise fashion from this position.

Figure. 2

A defined consortium of cultured duodenal bacterial taxa from Bangladeshi children with EED transmits an enteropathy to gnotobiotic mice. (A) Experimental design. The majority of mice gavaged with the EED strains (12/16), and all CONV-D mice (n=10) were euthanized seven days after the final gavage (four mice gavaged with the EED consortium became moribund five days following the second gavage and were euthanized; at this time point they had lost 20% of their starting body weight compared to -4.7% ± 7.7% for all other animals receiving the consortium and -4.9 ± 5.3% for the CONV-D group). (B) Twenty-three bacterial strains that colonized animals at a relative abundance >0.01% at one or more locations along the intestine. See Figure S6 for the biogeographical features of colonization along the length of the intestine. Strains belonging to the 14 core taxa detected in the duodenums of children with EED at the Genus level are highlighted in purple. (C-E) Hematoxylin- and eosin-stained sections showing representative histopathologic changes in the duodenal epithelium and lamina propria of mice colonized with the EED consortium (panels C and D) compared to CONV-D controls (panel E). See Supplementary Results and Supplementary Table S12 for flow cytometry of immune cell populations. Scale bars, 100 µm in panel C, 25 µm in panels D and E. (F) Quantification of crypt length in the proximal 3 cm of the small intestine. The 10 best oriented crypts were measured (n=5 mice/treatment group). Each dot represents one measurement. Horizontal lines denote mean values. ***, p<0.001 (ANOVA). (G) Differential expression of duodenal Reg3β and Reg3γ as determined by DESeq2 (FDR-corrected q<0.001). (H) MMP-8 protein levels in serum and small intestine. *, p=0.01 (serum, unpaired t-test); **, p=0.005 (duodenum), p=0.002 (jejunum), p=0.001 (ileum) (2-way ANOVA with Sidak’s multiple comparisons test). (I) Bacterial translocation from the gut is increased in mice colonized with the EED consortium. Each dot represents a splenic homogenate from one mouse (two independent experiments; n=5 mice/experiment; mean values are shown as horizontal lines; ***, p<0.001). All translocated bacteria recovered from mice gavaged with the EED consortium were identified as Escherichia coli and Enterococcus hirae (the former lacks virulence-associated markers of diarrheagenic strains of E. coli). Rare Enterococcus faecalis, Acinetobacter lwoffii, and Acinetobacter radioresistens were recovered from the spleens of CONV-D controls.