Disruption of gut barrier integrity and host-microbiome interactions underlie MASLD severity in patients with type-2 diabetes mellitus

Abstract

Aberration of the "gut-liver axis" contributes to the development and progression of metabolic dysfunction-associated steatotic liver disease (MASLD). Here, we use multi-omics to analyze the gut microbiota composition and metabolic profile of patients with type-2 diabetes mellitus (T2DM). T2DM patients were screened for liver disease by blood tests, ultrasound, and liver stiffness measurements. Stool microbiota was analyzed by 16S rRNA gene sequencing; metabolomic profiling by Nuclear Magnetic Resonance spectroscopy and Ultra-High Performance-Mass Spectrometry. Microbiome and metabolic signatures were analyzed in the whole cohort and in matched subsets to identify signatures specific for steatosis (MASLD±) or fibrosis (Fibrosis±). Gut permeability was assessed in-vitro using monolayers of MDCK cells and trans-epithelial electric resistance (TEER). Cytokine profile was assessed in serum and stools.Overall, 285 patients were enrolled: 255 serum, 252 urine and 97 stool samples were analyzed. Anaeroplasma and Escherichia/Shigella ASVs were higher, while Butyricicoccus ASVs were lower in those with normal liver. In MASLD±, Butyricicoccus ASV was significantly higher in those with steatosis. In the Fibrosis±, Butyricicoccus ASV was significantly lower in those with fibrosis. Glycochenodeoxycholic acid-3-sulfate (G-UDCA-3S) appeared to be higher in MASLD with fibrosis. Fecal water from patients with MASLD and fibrosis caused the greatest drop in the TEER vs those with normal liver; this was reversed with protease inhibitors. Finally, fecal IL-13 was lower in MASLD with fibrosis. We identified microbiome signatures which were specific for steatosis and fibrosis and independent of other metabolic risk factors. Moreover, we conclude that protease-related gut permeability plays a role in those MASLD patients with fibrosis, and that disease progression is linked to a gut-liver axis which is at least partially independent of T2DM.

Keywords: MASLD; Microbiome; fibrosis; gut permeability; metabolomics; type-2 diabetes mellitus.

Figure 1.

a) Taxonomic features significant across unmatched and matched comparisons. All_noagesex comparison did not include age and sex as covariates in the model. b) Log-fold change of differentially abundant genera shown in panel A, determined with ANCOMBC in MASLD± (left) and Fibrosis± (right) matched analyses. c) Log-fold change of differentially abundant ASVs shown in panel A, determined with ANCOMBC in MASLD± (top) and Fibrosis± (bottom) matched analyses.

Figure 2.

a) relative intensities of differentially abundant bile acids in the MASLD± (left; n = 17 MASLD-; n = 13 MASLD+) and Fibrosis± analyses (right; n = 11 fibrosis-; n = 15 Fibrosis+). b) Pearson correlation heatmap of fecal bile acids relative intensities and significant taxonomic features found in the cohort. P-values were adjusted using Benjamini–Hochberg, with a 10% false discovery rate threshold (Padj <0.1). Only significant correlations with an absolute coefficient value equal or bigger than 0.2 are shown. n = 20 no liver disease; n = 58 MASLD without fibrosis; n = 19 MASLD with fibrosis.

Figure 3.

Effect of uninhibited fecal water, positive and negative controls on TEER of MDCK monolayers. The box plot illustrates median values of triplicate measurements of TEER and corresponding 95%CI and difference between study groups: normal liver (n = 5), MASLD with normal LSM (n = 3) and MASLD with elevated LSM (n = 4). abbreviations: 95%CI: 95% confidence interval, TEER: trans-epithelium electric resistance.