Scientific Reports · 2016 · 76 citations · 46 references
Life SciencesMicrobiologyUrologyMedical MicrobiologyMetagenomicsMicrobiome ResearchInterstitial CystitisMicrobial IdentificationMicrobiome BiomarkersMicrobiome Data AnalysisPelvic Pain SyndromesUrogenital MicrobiomeBacterial Operational Taxonomic UnitsBiomarkersDiagnostic BiomarkersFecal BiomarkersMicrobial Biomarker DiscoveryOperational Taxonomic Unit ProfilingReceiver Operating Characteristic AnalysisStool Biomarkers
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.
46
Leo Breiman · Machine Learning · 2001 · 126.2K citations · Full text
Greedy function approximation: A gradient boosting machine.
Jerome H. Friedman · The Annals of Statistics · 2001 · 29K citations · Full text
Structure, function and diversity of the healthy human microbiome
Curtis Huttenhower, J. Fah Sathirapongsasuti, Nicola Segata et al. · Nature · 2012 · 11.9K citations · Full text
Life Sciences, Biology, Microbiology +17
Harry Sokol, Bénédicte Pigneur, Laurie Watterlot et al. · Proceedings of the National Academy of Sciences · 2008 · 4.3K citations · Full text