Background: Recent advances in next-generation DNA sequencing enable rapid high-throughput quantitation of microbial community composition in human samples, opening up a new field of microbiomics. One of the promises of this field is linking abundances of microbial taxa to phenotypic and physiological states, which can inform development of new diagnostic, personalized medicine, and forensic modalities. Prior research has demonstrated the feasibility of applying machine learning methods to perform body site and subject classification with microbiomic data. However, it is currently unknown which classifiers perform best among the many available alternatives for classification with microbiomic data. Results: In this work, we performed a systematic comparison of 18 major classification methods, 5 feature selection methods, and 2 accuracy metrics using 8 datasets spanning 1,802 human samples and various classification tasks: body site and subject classification and diagnosis. Conclusions: We found that random forests, support vector machines, kernel ridge regression, and Bayesian logistic regression with Laplace priors are the most effective machine learning techniques for performing accurate classification from these microbiomic data.
Bibliographical noteFunding Information:
This research was supported in part by grants UH2 AR057506-01S1 and UH3 CA140233 from the Human Microbiome Project and 1UL1 RR029893 from the National Center for Research Resources, National Institutes of Health, by the Diane Belfer Program in Human Microbial Ecology, and by the Department of Veterans Affairs, Veterans Health Administration, Office of Research and Development. The authors acknowledge Efstratios Efstathiadis and Eric Peskin for providing access and support with high performance computing and Yingfei Ma for contribution to preparation of the PDX and PBS datasets. The authors also are grateful to Dan Knights and Rob Knight for contributing data from their study  and providing the technical details for reproducing their findings.
- Feature selection
- Machine learning
- Microbiomic data