You are here

A Bayesian integration model of high-throughput proteomics and metabolomics data for improved early detection of microbial infections.

TitleA Bayesian integration model of high-throughput proteomics and metabolomics data for improved early detection of microbial infections.
Publication TypeJournal Article
Year of Publication2009
AuthorsWebb-Robertson, B-JM, McCue, LAnn, Beagley, N, McDermott, JE, Wunschel, DS, Varnum, SM, Hu, JZhi, Isern, NG, Buchko, GW, Mcateer, K, Pounds, JG, Skerrett, SJ, Liggitt, D, Frevert, CW
JournalPac Symp Biocomput
Pagination451-63
Date Published2009
ISSN2335-6936
KeywordsAlgorithms, Animals, Bayes Theorem, Biological Markers, Biometry, Data Interpretation, Statistical, Francisella, Genes, Bacterial, Gram-Negative Bacterial Infections, Infection, Least-Squares Analysis, Magnetic Resonance Spectroscopy, Male, Metabolomics, Mice, Mice, Inbred C57BL, Models, Biological, Mutation, Proteomics, Pseudomonas Infections, Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization, Tandem Mass Spectrometry, Virulence
Abstract

High-throughput (HTP) technologies offer the capability to evaluate the genome, proteome, and metabolome of an organism at a global scale. This opens up new opportunities to define complex signatures of disease that involve signals from multiple types of biomolecules. However, integrating these data types is difficult due to the heterogeneity of the data. We present a Bayesian approach to integration that uses posterior probabilities to assign class memberships to samples using individual and multiple data sources; these probabilities are based on lower-level likelihood functions derived from standard statistical learning algorithms. We demonstrate this approach on microbial infections of mice, where the bronchial alveolar lavage fluid was analyzed by three HTP technologies, two proteomic and one metabolomic. We demonstrate that integration of the three datasets improves classification accuracy to approximately 89% from the best individual dataset at approximately 83%. In addition, we present a new visualization tool called Visual Integration for Bayesian Evaluation (VIBE) that allows the user to observe classification accuracies at the class level and evaluate classification accuracies on any subset of available data types based on the posterior probability models defined for the individual and integrated data.

Alternate JournalPac Symp Biocomput
PubMed ID19209722
Grant ListU54 AI057141 / AI / NIAID NIH HHS / United States