Analysis of Microbiome Data across Inflammatory Bowel Disease Patients

The interaction and inter-play of microbes with human host cells is responsible for several disease conditions and of criticality to human health. In this study we analyze the microbial communities within the human gut and their roles in Inflammatory Bowel Disease (IBD). These microbial communities can be profiled using either Length Heterogeneity PCR (LH-PCR) or small subunit (SSU) rRNA sequences. Classification methods based on support vector machines (SVM) and k-nearest neighbor (KNN) were developed to differentiate between healthy controls and IBD patients at various intestinal locations using those profiles. The results show that there exist significant operational taxonomic units (OTUs) or microbial species that are differentially abundant between IBD and healthy control state at specific intestinal locations. Moreover, the classification performances of the sequence data outperform those of LH-PCR profiles and the lowest taxonomic level (Genus-Species) is more likely to have superior classification performances than the higher taxonomic levels.