Machine Learning and Your Microbiome

August 24, 2016 | Press Releases & Announcements

Dr. Levi Waldron, professor at the CUNY Graduate School of Public Health and Health Policy and colleagues recently published an article that comprehensively assess approaches to metagenomics-based prediction tasks and for quantitative assessment of microbiome-phenotype associations. The work was published in PLoS Computational Biology.

Dr. Levi Waldron

Dr. Levi Waldron

The human microbiome – the entire set of microbial organisms associated with the human host – interacts closely with host immune and metabolic functions and is crucial for human health. Significant advances in the characterization of the microbiome associated with healthy and diseased individuals have been obtained through next-generation DNA sequencing technologies, which permit accurate estimation of microbial communities directly from uncultured human-associated samples (e.g., stool). In particular, shotgun metagenomics provide data at unprecedented species- and strain- levels of resolution. Several large-scale metagenomic disease-associated datasets are also becoming available, and there have been proposals for disease-predictive models built on metagenomic signatures. There has been no validation of the generalization of resulting prediction models on different cohorts and diseases.

The research team assessed approaches to metagenomics-based prediction tasks and for quantitative assessment of microbiome-phenotype associations. They considered 2424 samples from eight studies and six different diseases to assess the independent prediction accuracy of models built on shotgun metagenomic data and to compare strategies for practical use of the microbiome as a prediction tool.

http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1004977

Please click here to see original article.