Multiple sclerosis patients have a distinct gut microbiota compared to healthy controls

Abstract

Multiple sclerosis (MS) is an immune-mediated disease, the etiology of which involves both genetic and environmental factors. The exact nature of the environmental factors responsible for predisposition to MS remains elusive; however, it's hypothesized that gastrointestinal microbiota might play an important role in pathogenesis of MS. Therefore, this study was designed to investigate whether gut microbiota are altered in MS by comparing the fecal microbiota in relapsing remitting MS (RRMS) (n = 31) patients to that of age- and gender-matched healthy controls (n = 36). Phylotype profiles of the gut microbial populations were generated using hypervariable tag sequencing of the V3-V5 region of the 16S ribosomal RNA gene. Detailed fecal microbiome analyses revealed that MS patients had distinct microbial community profile compared to healthy controls. We observed an increased abundance of Psuedomonas, Mycoplana, Haemophilus, Blautia, and Dorea genera in MS patients, whereas control group showed increased abundance of Parabacteroides, Adlercreutzia and Prevotella genera. Thus our study is consistent with the hypothesis that MS patients have gut microbial dysbiosis and further study is needed to better understand their role in the etiopathogenesis of MS.

Figure 1. Flowchart explaining RRMS patients and controls recruited for the study with exclusion and inclusion criteria.

Figure 2. Gut microbiota of MS patients differs from healthy controls.

(A,B) Rarefaction curves comparing the species richness (observed OTU number) and overall diversity (Shannon index) between controls, remission RRMS and active RRMS. The microbiota of active disease has lower diversity. (C) Principal coordinate plot based on Bray-Curtis distance matrix. The first two coordinates are plotted with the percentage of variability explained indicated on the axis. Each point represents a sample with colors representing different states. The control samples are significantly different from MS samples. The remission phase samples show greater heterogeneity with subsets resembling control or active disease samples. The ellipses do not represent any statistical significance but rather serve a visual guide to group differences. (D) Boxplots comparing Bray-Curtis distances between various groups. The three horizontal lines of the box represent the first, second (median) and third quartiles respectively with the whisk extending to 1.5 inter-quartile range (IQR).

Figure 3. Microbial signatures of the gut microbiota of MS patients.

(A) Barplots comparing the abundances of differentially abundant taxa between MS and control. These “signature” taxa are selected by Wilcoxon rank-sum tests and a false discovery rate of 5%. Error bars represent standard errors. Phylum, family and genus-level taxa are plotted. (B) The “signature” taxa are highlighted on the phylogenetic tree (cladogram) using GraPhlAn with red and green color indicating increase and decreases of abundance in the MS patients. (C) Biplots based on principal component analysis of the abundances of the “signature” genera. The first two components are plotted with the percentage of variability explained indicated. Each point represents a sample. The contribution of each genus to the principal components is indicated by the angle and length of the blue line. (D,E) Barplots comparing the relative abundances of Parabacteroides and Blautia between MS and control. Each bar represents the relative abundance of a sample.

Figure 4. Predictive model based on the genus-level abundance profile using Random Forests (RF).

(A) Comparison of the classification error of the RF trained model to guess, which always predicts the class label based on the majority class in the training data set. The boxplots are based on the results from 500 bootstrap samples. The three horizontal lines of the box represent the first, second (median) and third quartiles respectively with the whisk extending to 1.5 inter-quartile range (IQR). RF achieves significantly lower classification error. (B) Predictive power of individual genera assessed by Boruta feature selection algorithm. Blue boxplots correspond to minimal, average and maximum Z score of shadow genera, which are shuffled version of real genera introduced to RF classifier and act as benchmarks to detect truly predictive genera. Red, yellow and green colors represent rejected, suggestive and confirmed genera by Boruta Selection. (C) Heatmap based on the abundance Boruta selected genera. Hierarchical clustering (Euclidean distance, complete linkage) shows that MS samples tend to cluster together.

Figure 5. Predictive model based on the OTU level abundance profile using Random Forests (RF).

(A) Comparison of the classification error of the RF trained model to guess, which always predicts the class label based on the majority class in the training data set. The boxplots are based on the results from 500 bootstrap samples. The three horizontal lines of the box represent the first, second (median) and third quartile respectively with the whisk extending to 1.5 inter-quartile range (IQR). RF achieves significantly lower classification error. (B) Predictive power of individual genera assessed by Boruta feature selection algorithm. Blue boxplots correspond to minimal, average and maximum Z score of shadow genera, which are shuffled version of real genera introduced to RF classifier and act as benchmarks to detect truly predictive genera. Red, yellow and green colors represent rejected, suggestive and confirmed genera by Boruta Selection. (C) Heatmap based on the abundance Boruta selected genera. Hierarchical clustering (Euclidean distance, complete linkage) shows that MS samples tend to cluster together.

Figure 6. Functional analysis of the MS gut microbiota.

PICRUSt was used to infer the functional content of the gut microbiota based on the 16S data. (A) Log2 fold change of the abundances of COG categories showing significant difference between MS and control at a false discovery rate of 5%. Red and blue colors indicate increase and decrease in the MS samples. (B) Boxplots comparing the abundance distribution of the top 4 differential abundant COG categories. (C) Log2 fold change of the abundances of KEGG categories showing significant difference between MS and control at a false discovery rate of 5%.