1. Composition Analysis and Feature Selection of the Oral Microbiota Associated with Periodontal Disease
- Author
-
Chuan Yi Tang, Yaw-Ling Lin, Suh-Jen Jane Tsai, Shih-Hao Chang, Ming-Li Liou, and Wen-Pei Chen
- Subjects
0301 basic medicine ,Article Subject ,Aggregatibacter ,Gingiva ,lcsh:Medicine ,Disease ,medicine.disease_cause ,General Biochemistry, Genetics and Molecular Biology ,03 medical and health sciences ,RNA, Ribosomal, 16S ,medicine ,Humans ,Phylogeny ,Periodontitis ,General Immunology and Microbiology ,biology ,Bacteria ,Campylobacter ,Microbiota ,lcsh:R ,General Medicine ,biology.organism_classification ,medicine.disease ,Capnocytophaga ,030104 developmental biology ,Metagenomics ,Gemella ,Immunology ,Chronic Periodontitis ,Filifactor ,Tooth ,Research Article - Abstract
Periodontitis is an inflammatory disease involving complex interactions between oral microorganisms and the host immune response. Understanding the structure of the microbiota community associated with periodontitis is essential for improving classifications and diagnoses of various types of periodontal diseases and will facilitate clinical decision-making. In this study, we used a 16S rRNA metagenomics approach to investigate and compare the compositions of the microbiota communities from 76 subgingival plagues samples, including 26 from healthy individuals and 50 from patients with periodontitis. Furthermore, we propose a novel feature selection algorithm for selecting features with more information from many variables with a combination of these features and machine learning methods were used to construct prediction models for predicting the health status of patients with periodontal disease. We identified a total of 12 phyla, 124 genera, and 355 species and observed differences between health- and periodontitis-associated bacterial communities at all phylogenetic levels. We discovered that the generaPorphyromonas,Treponema,Tannerella,Filifactor, andAggregatibacterwere more abundant in patients with periodontal disease, whereasStreptococcus,Haemophilus,Capnocytophaga,Gemella,Campylobacter, andGranulicatellawere found at higher levels in healthy controls. Using our feature selection algorithm, random forests performed better in terms of predictive power than other methods and consumed the least amount of computational time.
- Published
- 2018
- Full Text
- View/download PDF