Predictive metabolomic profiling of microbial communities using amplicon or metagenomic sequences

• Published in: Nature communications Vol. 10; no. 1; pp. 3136 - 11
• Main Authors: Mallick, Himel, Franzosa, Eric A., Mclver, Lauren J., Banerjee, Soumya, Sirota-Madi, Alexandra, Kostic, Aleksandar D., Clish, Clary B., Vlamakis, Hera, Xavier, Ramnik J., Huttenhower, Curtis
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 17.07.2019; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/1305; 631/114/2415; 631/326/2565/2134; 631/326/2565/2142; 631/45/320; Algorithms; Colitis, Ulcerative - microbiology; Communities; Computer applications; Crohn Disease - microbiology; Design of experiments; Experimental design; Gastrointestinal Microbiome - genetics; Humanities and Social Sciences; Humans; Intestinal microflora; Metabolites; Metabolomics; Metagenomics; Microbial activity; Microbiomes; Microbiota - genetics; Microorganisms; Models, Genetic; multidisciplinary; Science; Science (multidisciplinary); Vagina
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-019-10927-1

Microbial community metabolomics, particularly in the human gut, are beginning to provide a new route to identify functions and ecology disrupted in disease. However, these data can be costly and difficult to obtain at scale, while amplicon or shotgun metagenomic sequencing data are readily available for populations of many thousands. Here, we describe a computational approach to predict potentially unobserved metabolites in new microbial communities, given a model trained on paired metabolomes and metagenomes from the environment of interest. Focusing on two independent human gut microbiome datasets, we demonstrate that our framework successfully recovers community metabolic trends for more than 50% of associated metabolites. Similar accuracy is maintained using amplicon profiles of coral-associated, murine gut, and human vaginal microbiomes. We also provide an expected performance score to guide application of the model in new samples. Our results thus demonstrate that this ‘predictive metabolomic’ approach can aid in experimental design and provide useful insights into the thousands of community profiles for which only metagenomes are currently available. Obtaining metabolomic data from microbial communities can be costly and difficult, whereas many microbial community sequence datasets are already available. Here Mallick et al. describe a computational approach to predict metabolic features from microbial DNA sequencing information.