Reconstructing the landscape of gut microbial species across 29,000 diverse individuals.

The human gut microbiome has been linked to health and disease. Investigation of the human microbiome has largely employed 16S amplicon sequencing, with limited ability to distinguish microbes at the species level. Herein, we describe the development of Reference-based Exact Mapping (RExMap) of microbial amplicon variants that enables mapping of microbial species from standard 16S sequencing data. RExMap analysis of 16S data captures ∼75% of microbial species identified by whole-genome shotgun sequencing, despite hundreds-fold less sequencing depth. RExMap re-analysis of existing 16S data from 29,349 individuals across 16 regions from around the world reveals a detailed landscape of gut microbial species across populations and geography. Moreover, RExMap identifies a core set of fifteen gut microbes shared by humans. Core microbes are established soon after birth and closely associate with BMI across multiple independent studies. RExMap and the human microbiome dataset are presented as resources with which to explore the role of the human microbiome.

Deep Neural Networks for Classification of LC-MS Spectral Peaks.

Liquid chromatography-mass spectrometry (LC-MS)-based metabolomics has emerged as a valuable tool for biological discovery, capable of assaying thousands of diverse chemical entities in a single biospecimen. Processing of nontargeted LC-MS spectral data requires identification and isolation of true spectral features from the random, false noise peaks that comprise a significant portion of total signals, using inexact peak selection algorithms and time-consuming visual inspection of data. To increase the fidelity and speed of data processing, herein we establish, optimize, and evaluate a machine learning pipeline employing deep neural networks as well as a simpler multiple logistic regression model for classification of spectral features from nontargeted LC-MS metabolomics data. Machine learning-based approaches were found to remove up to 90% of false peaks from complex nontargeted LC-MS data sets without reducing true positive signals and exhibit excellent reproducibility across multiple data sets. Application of machine learning for nontargeted LC-MS-based peak selection provides for robust and scalable peak classification and data filtering, enabling handling and processing of large scale, complex metabolomics data sets.