Randomized Controlled-Feeding Study of Dietary Emulsifier Carboxymethylcellulose Reveals Detrimental Impacts on the Gut Microbiota and Metabolome

Abstract

Background & aims: Epidemiologic and murine studies suggest that dietary emulsifiers promote development of diseases associated with microbiota dysbiosis. Although the detrimental impact of these compounds on the intestinal microbiota and intestinal health have been demonstrated in animal and in vitro models, impact of these food additives in healthy humans remains poorly characterized.

Methods: To examine this notion in humans, we performed a double-blind controlled-feeding study of the ubiquitous synthetic emulsifier carboxymethylcellulose (CMC) in which healthy adults consumed only emulsifier-free diets (n = 9) or an identical diet enriched with 15 g per day of CMC (n = 7) for 11 days.

Results: Relative to control subjects, CMC consumption modestly increased postprandial abdominal discomfort and perturbed gut microbiota composition in a way that reduced its diversity. Moreover, CMC-fed subjects exhibited changes in the fecal metabolome, particularly reductions in short-chain fatty acids and free amino acids. Furthermore, we identified 2 subjects consuming CMC who exhibited increased microbiota encroachment into the normally sterile inner mucus layer, a central feature of gut inflammation, as well as stark alterations in microbiota composition.

Conclusions: These results support the notion that the broad use of CMC in processed foods may be contributing to increased prevalence of an array of chronic inflammatory diseases by altering the gut microbiome and metabolome (ClinicalTrials.gov, number NCT03440229).

Keywords: Emulsifier; Metabolism; Metabolome; Microbiota.

Figure 1.

Effect of CMC consumption on metabolic parameters. (A) Schematic representation of the inpatient study that enabled daily monitoring and specimen collections before, during, and after CMC consumption, or lack thereof, and presenting timing of oral glucose tolerance tests, intestinal biopsies, and feces collection. (B) Biomorphometric characterization of the study’s participants at the beginning of the study. (C) Effect of dietary emulsifier CMC consumption on various metabolic parameters, measured both pre- and postintervention. (D–F) Effect of dietary emulsifier CMC consumption on weight (D), PROMISE gas/bloating (E), and belly pain (F) scores, measured both pre- and postintervention. OGTT, oral glucose tolerance test. Significance was determined using Mann-Whitney test; *P < 0.05 compared with control group.

Figure 2.

Effect of CMC consumption on microbiota composition. (A) PCoA of the unweighted UniFrac distance matrix of the study participants’ microbiota assessed by 16S rRNA gene sequencing. All time points are included in the representation, and samples are colored by participants. (B) PCoA of the Bray-Curtis distance matrix at days 0, 9, and 14 of study participants’ microbiota composition after normalization of every SV based on day 4 value, with samples colored by group. (C) Changes in the microbial community structure over time, as measured by Bray-Curtis distance from day 4 to subsequent days, for each group. (D) Fecal bacterial load assessed by 16S quantitative polymerase chain reaction (qPCR). (E) Changes in Evenness and Shannon alpha diversity measures for CMC intervention versus control groups, at days 0, 9, and 14. Significance was determined using 2-way ANOVA corrected for multiple comparisons with a Bonferroni posttest (E), multiple t tests (E) or Permanova analysis (A, B).

Figure 3.

Effect of CMC consumption on fecal metagenome. (A) PCoA of the Bray-Curtis dissimilarity of study’s participants metagenome (uniref90 categories) assessed by shotgun sequencing. Days 4 and 14 are included in the representation, and samples are colored by participants. (B, C) PCoA of the Bray-Curtis distance matrix at day 4 (B) and 14 (C) of study’s participants metagenome assessed by shotgun sequencing, with samples colored by group.

Figure 4.

Effect of CMC consumption on the fecal metabolome. (A) Changes of the fecal level of bioactive lipopolysaccharide from day 0 to subsequent days measured with HEK-TLR4 reporter cells. (B) Changes of the fecal level of bioactive flagellin from day 0 to subsequent days measured with HEK-TLR5 reporter cells. (C) Changes of the fecal level of the inflammatory marker Lipocalin-2 from day 0 to subsequent days. (D) PCoA of the Euclidean distance at days 0, 9, and 14 of study participants’ fecal metabolome, with samples colored by group. (E) Heatmap presenting participants fecal metabolome over the course of the study. (F) Changes of the fecal level of CMC from day 0 to subsequent days in both control and CMC-treated groups. (G) Changes of the fecal level of CMC from day 0 to subsequent days in control group. Significance was determined using 2-way ANOVA corrected for multiple comparisons with a Bonferroni posttest or repeated t tests corrected with the false discovery rate approach for (G); *P < .05 compared with control group for (F), *P < .05 compared with day 0 for (G).

Figure 5.

Intersubject variability in the response to CMC consumption. (A) Effect of dietary emulsifier CMC consumption on microbiota localization (distance of the closest bacteria from the surface of the epithelium), measured both pre- and postintervention. (B) Changes of the Bray-Curtis distance matrix, for each study’s participant from the CMC-treated group, from day 4 to subsequent days. (C) Changes of the Bray-Curtis distance matrix, for the CMC-Insensitive and the CMC-Sensitive groups, from day 4 to subsequent days. (D) Changes of the fecal level of bioactive LPS from day 0 to subsequent days measured with HEK-TLR4 reporter cells. (E) Changes of the fecal level of bioactive flagellin from day 0 to subsequent days measured with HEK-TLR5 reporter cells. (F) Changes of the fecal level of the inflammatory marker Lipocalin-2 from day 0 to subsequent days. (G) Effect of dietary emulsifier CMC consumption on fecal metagenome measured through Bray-Curtis distance. (H) Biomorphometric characterization of study’s participants at the beginning of the study and according to CMC sensitivity status. Significance was determined using 1-way ANOVA corrected for multiple comparisons with a Bonferroni posttest (A and G) or 2-way ANOVA corrected for multiple comparisons with a Bonferroni posttest (C, D, E, and F). BMI, body mass index; DBP, diastolic blood pressure; IEC, intestinal epithelial cell; LPS, lipopolysaccharide; NS, not statistically significant; SBP, systolic blood pressure.