Stool-based biomarkers of interstitial cystitis/bladder pain syndrome

Abstract

Interstitial cystitis/bladder pain syndrome (IC) is associated with significant morbidity, yet underlying mechanisms and diagnostic biomarkers remain unknown. Pelvic organs exhibit neural crosstalk by convergence of visceral sensory pathways, and rodent studies demonstrate distinct bacterial pain phenotypes, suggesting that the microbiome modulates pelvic pain in IC. Stool samples were obtained from female IC patients and healthy controls, and symptom severity was determined by questionnaire. Operational taxonomic units (OTUs) were identified by16S rDNA sequence analysis. Machine learning by Extended Random Forest (ERF) identified OTUs associated with symptom scores. Quantitative PCR of stool DNA with species-specific primer pairs demonstrated significantly reduced levels of E. sinensis, C. aerofaciens, F. prausnitzii, O. splanchnicus, and L. longoviformis in microbiota of IC patients. These species, deficient in IC pelvic pain (DIPP), were further evaluated by Receiver-operator characteristic (ROC) analyses, and DIPP species emerged as potential IC biomarkers. Stool metabolomic studies identified glyceraldehyde as significantly elevated in IC. Metabolomic pathway analysis identified lipid pathways, consistent with predicted metagenome functionality. Together, these findings suggest that DIPP species and metabolites may serve as candidates for novel IC biomarkers in stool. Functional changes in the IC microbiome may also serve as therapeutic targets for treating chronic pelvic pain.

Figure 1. Stool and vaginal microbiomes in IC.

(A) Principle component analysis of pilot cohort suggested segregation of stool microbiome among IC patients and controls (P = 0.055). (B) Principle component analyses of vaginal samples from pilot cohort did not segregate by diagnoses (P = 0.326).

Figure 2. Altered microbiome in IC.

(A) Comparison of phyla abundance between IC patients and controls as determined by 16S reads. (B) Comparison of bacterial order abundance shows numerous orders that are differentially abundant in controls (red) and IC (green; n = 34). Phyla are indicated by colors in the outer ring. Data were compared to M5RNA using a maximum e-value of 1e-20, a minimum identity of 97%, and a minimum alignment length of 15 bp.

Figure 3. ERF identifies significant features of IC microbiome.

Box plot of likelihood of relevance for fecal OTUs by (vertical) and importance (x axis; n = 34).

Figure 4. Specific stool OTUs are associated with IC.

(A) qPCR was performed on healthy control (n = 10) and IC stool DNA (n = 16) using species-specific primers (±SEM). Species with significant, differential abundance are indicated (*P < 0.05). (B) Interactive network diagram integrating qPCR findings with 16S data by MIC analysis to detect relationships between features. (C) ROC curves for C. aerofaciens qPCR data.

Figure 5. Metabolomic and metagenomic comparison in IC.

(A) ROC analysis (left panel) and box-and-whisker plot (right panel) identified glyceraldehyde as significantly elevated in IC and a candidate biomarker (AUM = 0.98, P<0.05). (B) Pathway analysis of stool metabolites in MetaboAnalyst 3.0 identified arachidonic acid signaling as significantly altered in IC (P<0.05). (C) PICRUSt metagenome analyses identified fatty acid biosynthesis, homologous recombination and nicotinate/nicotinamide metabolism as significantly different.