Therapeutic helminth infection of macaques with idiopathic chronic diarrhea alters the inflammatory signature and mucosal microbiota of the colon

Abstract

Idiopathic chronic diarrhea (ICD) is a leading cause of morbidity amongst rhesus monkeys kept in captivity. Here, we show that exposure of affected animals to the whipworm Trichuris trichiura led to clinical improvement in fecal consistency, accompanied by weight gain, in four out of the five treated monkeys. By flow cytometry analysis of pinch biopsies collected during colonoscopies before and after treatment, we found an induction of a mucosal T(H)2 response following helminth treatment that was associated with a decrease in activated CD4(+) Ki67+ cells. In parallel, expression profiling with oligonucleotide microarrays and real-time PCR analysis revealed reductions in T(H)1-type inflammatory gene expression and increased expression of genes associated with IgE signaling, mast cell activation, eosinophil recruitment, alternative activation of macrophages, and worm expulsion. By quantifying bacterial 16S rRNA in pinch biopsies using real-time PCR analysis, we found reduced bacterial attachment to the intestinal mucosa post-treatment. Finally, deep sequencing of bacterial 16S rRNA revealed changes to the composition of microbial communities attached to the intestinal mucosa following helminth treatment. Thus, the genus Streptophyta of the phylum Cyanobacteria was vastly increased in abundance in three out of five ICD monkeys relative to healthy controls, but was reduced to control levels post-treatment; by contrast, the phylum Tenericutes was expanded post-treatment. These findings suggest that helminth treatment in primates can ameliorate colitis by restoring mucosal barrier functions and reducing overall bacterial attachment, and also by altering the communities of attached bacteria. These results also define ICD in monkeys as a tractable preclinical model for ulcerative colitis in which these effects can be further investigated.

Figure 1. Clinical improvement of juvenile macaques with chronic diarrhea following T. trichiura treatment.

(A) Diarrhea of five macaques was scored daily before and after oral administration of germinated T. trichiura (Tt) ova. Fecal consistency scores (FCS) were based on a standardized 4-point scale; 1 = Well-formed, normal; 1.5 = Normal to semi-solid; 2 = Semi-solid to normal; 2.5 = Semi-solid; 3 = Semi-solid to liquid; 3.5 = Liquid to semi-solid; 4 = Liquid. Semi solid stool is defined as “porridge-like” or able to be picked up with a fork. Each score represents the average of daily scores per week. Subject TC05 (red line) showed no clinical response while four other responder animals (TR01-TR04; black line) had a decrease in FCS. (B) Change in body weight at 14 weeks following T. trichiura treatment, expressed as a percentage of body weight at the time of egg administration. Tt refers to T. trichiura treatment.

Figure 2. Flow cytometric analysis of CD4⁺ T cells from colon biopsies following T. trichiura treatment.

Pinch biopsies collected during colonoscopies pre-treatment (Pre-Tt) and 14 weeks post-treatment (Post-Tt) were compared with samples collected from healthy age-matched controls (Control). Lamina propria mononuclear cells (LPMCs) from biopsies were stimulated ex vivo with PMA and ionomycin for intracellular cytokine staining. (A) Box and whisker plot showing the percentage of IL-4+ cells among CD4+ LPMCs. ***p<0.001, determined by Student's t-test. LPMCs were also stained ex vivo for intranuclear (B) Ki67 and (C) FoxP3. Lines connect paired samples from the same subjects pre- and post-treatment. The non-responding macaque (TC05) is shown in red.

Figure 3. Transcriptional profiling of colon biopsies by macaque whole genome oligonucleotide microarrays.

RNA was isolated from pinch biopsies collected during colonoscopies for microarray analysis. Hierarchical clustering analysis of samples and genes based on the expression levels of genes differentially expressed (B>0) between (A) pre-treatment colitis samples and healthy controls, where each column represents an individual subject and each row represents a single gene. Black indicates median levels of expression; red, greater than median expression; green, less than median expression. Colored horizontal bars indicate the clustering of samples collected from healthy controls (Controls, orange), clinical responders [pre-treatment (Resp: Pre-Tt, light purple) and post-treatment (Resp: Post-Tt, dark purple)], and subject TC05 [pre-treatment (TC05: Pre-Tt, light blue) and post-treatment (TC05: Post-Tt, dark blue)]. Representative genes are listed in the biological processes that are overrepresented. (B) GO analyses identified biological processes up-regulated in pre-treatment colitis samples. X axis indicates the amount of statistical significance [as −log(P)] in enrichment for the indicated biological process, with the up-regulated genes in this process listed. (C) Hierarchical clustering analysis of samples and genes based on the expression levels of genes differentially expressed (B>0) between colitis samples before and after T. trichiura treatment. The complete list of genes for (A) is shown in Figure S2 and Table S1. The complete list of genes for (C) is shown in Figure S3 and Table S2.

Figure 4. Real-time PCR verification of genes differentially expressed between groups.

(A) Expression levels of genes in pre-treatment (Pre-Tt) colitis subjects are shown relative to the average expression of samples from healthy controls. Red/pink spots denote higher expression and blue spots represent lower expression; differential expression increases with spot intensity. Red spots with black borders represent >10-fold higher expression. (B) Expression levels of genes for samples taken post-treatment (Post-Tt) for each subject are shown relative to pre-treatment levels from the same subject.

Figure 5. T. trichiura treatment reduces bacterial attachment to the colonic mucosa.

(A) DNA samples harvested from colon biopsies taken pre-treatment (Pre-Tt) and post-treatment (Post-Tt) were analyzed by quantitative PCR for the abundance of bacterial taxa based on specific primers for 16S rRNA sequences. Abundance is expressed as a fold-change above the average value of healthy controls. Subject TC05 is shown in red. (B) Plasma levels of soluble CD14 were measured by ELISA.

Figure 6. T. trichiura treatment influences microbial diversity within samples (α-diversity) and community diversity between samples (β-diversity).

(A) Shannon diversity of samples from all treatment groups, where each point represents a subject. The average of ten iterations of rarefied subsets of 5422 sequences was used to calculate each Shannon index. The difference between pre- and post-treatment diversity was determined using a Paired Student's t-test (p = 0.075). (B) Relative abundance of taxonomic groups for each macaque sample. The seven most abundant phyla over all samples are presented. (C) The contribution of different taxonomic groups to the separation of samples based on phylogenetic information. Contributions are represented by the size of the circles (grey) overlaid onto a PCoA of unweighted UniFrac distances of macaques pre-treatment (orange), macaques post-treatment (blue), and controls (red).

Figure 7. T. trichiura treatment recovers several microbial clades reduced in colitic macaques.

Utilizing the LEfSe visualization modules and analytical tools, pre-treatment and post-treatment samples were assigned as classes for comparison. (A) Histogram of LDA scores computed for features differentially abundant between macaques pre- and post-treatment. (B) Cladogram illustrating the taxonomic representation of bacterial taxa with different abundance values in macaques pre- and post-treatment, as determined by LEfSe. Taxa that are more abundant in post-treatment samples are illustrated in red and taxa that are more abundant in pre-treatment samples are illustrated in green. Yellow circles delineate non-significant taxa (C, D) Histograms of relative abundances of Bacteroidetes (C) and of Tenericutes (D) in control macaques and macaques, pre- and post-treatment.

Figure 8. Working model of the immunologic mechanisms underlying the amelioration of colitis in the setting of Trichuris sp. treatment.

(A) Colitis is driven by a T_H1-type inflammatory response to increased bacterial attachment and dysbiosis at the mucosal epithelium as a result of compromised barrier function. (B) Trichuris sp. elicits a mucosal T_H2-type response (including the canonical cytokines IL-4 and IL-13) that promotes mucosal wound healing and mucus production. These functions reduce bacterial attachment and restore microbial homeostasis, removing the inflammatory stimulus.