Do high-protein diets have the potential to reduce gut barrier function in a sex-dependent manner?

Abstract

Purpose: Impaired gut barrier function is associated with systemic inflammation and many chronic diseases. Undigested dietary proteins are fermented in the colon by the gut microbiota which produces nitrogenous metabolites shown to reduce barrier function in vitro. With growing evidence of sex-based differences in gut microbiotas, we determined whether there were sex by dietary protein interactions which could differentially impact barrier function via microbiota modification.

Methods: Fermentation systems were inoculated with faeces from healthy males (n = 5) and females (n = 5) and supplemented with 0.9 g of non-hydrolysed proteins sourced from whey, fish, milk, soya, egg, pea, or mycoprotein. Microbial populations were quantified using fluorescence in situ hybridisation with flow cytometry. Metabolite concentrations were analysed using gas chromatography, solid phase microextraction coupled with gas chromatography-mass spectrometry and ELISA.

Results: Increased protein availability resulted in increased proteolytic Bacteroides spp (p < 0.01) and Clostridium coccoides (p < 0.01), along with increased phenol (p < 0.01), p-cresol (p < 0.01), indole (p = 0.018) and ammonia (p < 0.01), varying by protein type. Counts of Clostridium cluster IX (p = 0.03) and concentration of p-cresol (p = 0.025) increased in males, while females produced more ammonia (p = 0.02), irrespective of protein type. Further, we observed significant sex-protein interactions affecting bacterial populations and metabolites (p < 0.005).

Conclusions: Our findings suggest that protein fermentation by the gut microbiota in vitro is influenced by both protein source and the donor's sex. Should these results be confirmed through human studies, they could have major implications for developing dietary recommendations tailored by sex to prevent chronic illnesses.

Keywords: Dietary protein; Gut microbiota; In vitro gut systems; Microbial-derived metabolic end products; Sexual dimorphisms.

Fig. 1

Effects of fermentation of proteins extracted from different sources (pea, whey, egg, milk, fish meal, soy and mycoprotein), inulin and negative control (no substrate) on bacterial populations from human faeces following inoculation of anaerobic, pH controlled, batch culture systems and quantification by FISHflow at 0, 8 and 24 h. Averages of the results of all protein samples for each individual volunteer were calculated to generate the “total protein” values. Bacterial groups quantified were total prokaryotes (EUB, a), Bacteroidaceae and Prevotellaceae (BAC,b), Clostridium coccoides-Eubacterium rectale group (EREC, c), Roseburia cluster (RREC, d), Atopobium Cluster (ATO, e), Clostridium Cluster IX (PRO, f), Lactobacillus spp. (LAB, g), Bifidobacterium spp. (BIF, h). Data shown are means of 10 independent experiments (n = 5 males and 5 females) ± SEM. General liner modelling was used and LSD multiple testing correction was applied to generate the table of significances for the model. Significances of p < 0.05 are highlighted. Significance of individual differences can be viewed in Supplementary Table 1

Fig. 2

Proteins isolated from different sources (pea, whey, milk, fish meal, egg, soy and mycoprotein), and inulin, were fermentable substrates utilised by faecal bacteria in anaerobic batch culture systems, along with a negative control (no substrate). These results are from the 24 h timepont in Fig. 1. The results of all the proteins from each individual participants were averaged and labelled as total protein (TP). This was used to compare the effect of overall protein fermentation on bacterial populations against the negative control. FISHflow was used to quantify the following bacterial populations: total prokaryotes (EUB, a), Bacteroidacea and Prevotellaceae (BAC, b), Clostridium coccoides-Eubacterium rectale group (EREC, c), Roseburia cluster (RREC, d), Atopobium Cluster (ATO, e), Clostridium Cluster IX (PRO, f), Bifidobacterium spp. (BIF, g), Lactobacillus spp. (LAB, h). Letters denote a significant difference between conditions: a = significantly different to control, b = significantly different to inulin, c = significantly different to egg, d = significantly different to whey, e = significantly different to milk. Data shown are means of 10 independent experiments (5 males; 5 females) ± SEM

Fig. 3

Sex differences in the effect of fermentation of proteins isolated from different sources and negative control (no substrate) in the abundance of bacterial groups Clostridium cluster IX (PRO) at 8 and 24 h, Lactobacillus-Enterococcus group (LAB) at 24 h, and total bacteria at 8 h (d)) from healthy human faeces inoculated into anaerobic, pH controlled, batch culture systems. MP = Mycoprotein. Samples from 0, 8 and 24 h were quantified by FISHflow. Values are means from 5 males and 5 females ± SEM. * = p < 0.05, ** = p < 0.01

Fig. 4

Effect of faecal bacteria fermentation of different protein substrates (pea, whey, milk, fish meal, egg, soy and mycoprotein) and inulin on the concentrations of short-chain fatty acids butyrate (a), acetate (b) and propionate (c), and on branched-chain fatty acids iso-valerate (d), iso-butyrate (e), valerate (f) quantified by GC/MS at 0 (baseline), 8, 24 and 48 h. The means of all the protein substrates used were averaged for each individual and labelled as total protein (TP). Human faecal inoculums from 10 healthy donors (5 males; 5 females) were used to inoculate anaerobic, pH and temperature-controlled batch culture systems. Error Bars = SEM General linear modelling using ‘sex’, ‘treatment’ and ‘time’ as factors, with LSD multiple testing correction, was used to analyse the model. Significances of p < 0.05 are highlighted. For individual significant differences, see supplementary Table 2

Fig. 5

Effects of bacterial fermentation of different dietary proteins, inulin and negative control (no substrate) by human faecal microbiota on the concentration of phenol (a), p-cresol (b), indole (c) and ammonia (d) at 24 h in in-vitro, pH controlled, anaerobic, batch culture systems. Phenol, indole and p-cresol were quantified using GC/MS, ammonia was analysed using ammonia assay. The average was determined from the results of all proteins and is labelled as total protein (TP) and was compared against the control. Data shown are means (a, b and c) and mean change from baseline (d) of 10 independent experiments with different donors (n = 5 males and females). Error bars = SEM. Letters denote significant differences between conditions: a = significantly different to control, b = significantly different to inulin, c = significantly different to egg, d = significantly different to whey, e = significantly different to milk

Fig. 6

Anaerobic faecal batch culture systems designed to reflect conditions in the human colon (pH controlled at 6.7–6.9, temperature controlled at 37^oC) were used to explore the production of microbial-derived metabolites following fermentation of different dietary proteins (pea, whey, milk, fish meal, egg, soy and mycoprotein) and inulin compared to a negative control (no substrate). The production of short chain fatty acids butyrate (a), acetate (b) and propionate (c), and branched chain fatty acids iso-valerate (d), iso-butyrate (e) and valerate (f) were quantified using GC/MS. Average was determined from the results of all proteins from each individual and are labelled ‘total protein’ (TP) and were compared against the negative control. Figure 5g presents the aggregated concentrations of SCFAs and BCFAs quantified for each condition at 24 h, alongside the corresponding ratio of SCFAs to BCFAs. Letters denote significant difference between conditions. Data presented are the mean changes from baseline of 10 independent experiments with different donors (n = 5 males and 5 females) at the 24 h time point from Fig. 4 ± SEM. Letters denote a significant difference between conditions: a = significantly different to the negative control, b = significantly different to inulin, c = significantly different to egg, d = significantly different to whey, e = significantly different to mycoprotein, f = significantly different to milk

Fig. 7

The effect of increased dietary protein availability (pea, whey, milk, fish meal, egg, soy and mycoprotein) on the production of metabolites associated with reductions in gut barrier function (phenol (a); p-cresol (b); indole (c); ammonia (d)) was assessed using an in-vitro gut model system (pH controlled at 6.7–6.9, temperature controlled at 37 ^oC). The values for ‘additional protein’ were calculated as an average of the results from the use of each of the proteins fermented individually and compared to the negative control (no substrate). Data presented are from 10 independent experiments with different donors (n = 5 males and 5 females) at the 24 h time point. Error bars ± SEM, * p < 0.05, ** p < 0.01, *** p < 0.001

Fig. 8

Dietary protein isolated from animal (milk, whey, fish meal and egg) and non-animal- based proteins (soy, pea and mycoprotein) were utilised as fermented energy sourced by faecal bacteria in anaerobic gut modelling systems (pH controlled at 6.7–6.9, temperature controlled at 37 ^oC). The production of metabolites potentially detrimental to gut barrier function was analysed after 24 h of fermentation. Each protein was fermented individually and the results from non-animal and animal-based protein were determined from the average of the proteins within the respective categories. These categories were then compared against the negative control (no protein). Data presented are from 10 independent experiments, from n = 5 males and females which are shown together (a & c) or separately (b & d). Error bars ± SEM, * p < 0.05, ** p < 0.01, *** p < 0.001

Fig. 9

Sex differences in the production of metabolites (propionate at 8 h (a), acetate at 8 h (b), iso-valerate at 8 h (c) and ammonia at 24 h (d) following fermentation of different dietary proteins, and control (no substrate) by human faecal microbiota in batch culture systems. Acetate and propionate levels were quantified using GC/MS, and ammonia was quantified with an ELISA. Values are means from 10 independent experiments (n = 5 males and females) ± SEM. * = p < 0.05, ** = p < 0.01