Multiple-Disease Detection and Classification across Cohorts via Microbiome Search
Xiaoquan Su, Gongchao Jing, Zheng Sun, Lu Liu, Zhenjiang Zech Xu, Daniel McDonald, Zengbin Wang, Honglei Wang, Antonio González, Yufeng Zhang, Shi Huang, Gavin Huttley, Rob Knight, Jian Xu
Abstract
Here, we present a search-based strategy for disease detection and classification, which detects diseased samples via their outlier novelty versus a database of samples from healthy subjects and then compares them to databases of samples from patients. This approach enables the identification of microbiome states associated with disease even in the presence of different cohorts, multiple sequencing platforms, or significant contamination.
Topics & Concepts
MicrobiomeNovelty detectionOutlierNoveltyIdentification (biology)AmpliconDiseaseComputer scienceAmplicon sequencingHuman Microbiome ProjectA priori and a posterioriComputational biologyAnomaly detectionArtificial intelligenceData miningPattern recognition (psychology)BiologyHuman microbiome16S ribosomal RNABioinformaticsGeneMedicineGeneticsPolymerase chain reactionPathologyTheologyBotanyEpistemologyPhilosophyGut microbiota and healthGenomics and Phylogenetic StudiesBiosensors and Analytical Detection