Machine Learning Techniques Accurately Classify Microbial Communities by Bacterial Vaginosis Characteristics

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@Article{Beck:2014:PLoSONE,

• author = "Daniel Beck and James A. Foster",
• title = "Machine Learning Techniques Accurately Classify Microbial Communities by Bacterial Vaginosis Characteristics",
• journal = "PLoS ONE",
• year = "2014",
• volume = "9",
• number = "2",
• pages = "e87830",
• month = feb # " 3",
• keywords = "genetic algorithms, genetic programming, Bacterial vaginosis, Microbiome, Lactobacillus, Vagina, Community ecology, Machine learning algorithms",
• keywords = "genetic algorithms, genetic programming",
• bibsource = "OAI-PMH server at www.ncbi.nlm.nih.gov",
• publisher = "Public Library of Science",
• oai = "oai:pubmedcentral.nih.gov:3912131",
• URL = "http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3912131",
• URL = "http://dx.doi.org/10.1371/journal.pone.0087830",
• DOI = "doi:10.1371/journal.pone.0087830",
• size = "8 pages",
• abstract = "Microbial communities are important to human health. Bacterial vaginosis (BV) is a disease associated with the vagina microbiome. While the causes of BV are unknown, the microbial community in the vagina appears to play a role. We use three different machine-learning techniques to classify microbial communities into BV categories. These three techniques include genetic programming (GP), random forests (RF), and logistic regression (LR). We evaluate the classification accuracy of each of these techniques on two different datasets. We then deconstruct the classification models to identify important features of the microbial community. We found that the classification models produced by the machine learning techniques obtained accuracies above 90percent for Nugent score BV and above 80percent for Amsel criteria BV. While the classification models identify largely different sets of important features, the shared features often agree with past research.",
• notes = "16 S rRNA, Random Forests, Logistic Regression. pre-select 15 features. R package glmnet, lasso. ROC. pop15000 14 functions in function set. PMID:24498380",

}

Genetic Programming entries for Daniel Beck James A Foster

Citations