Profiling biological effects of microbiome metabolites via machine learning.

Human microbiome-derived metabolites are key mediators of host physiology. However, their biological effects remain largely uncharacterized due to limitations of current low-throughput and untargeted experimental approaches that are time intensive and costly. This has hindered the systematic biological characterization of microbiome metabolites. To address this gap and accelerate the identification of biological effects of microbiome metabolites, we developed and experimentally validated a machine learning platform trained on publicly available drug development data to rapidly predict a wide array of chemical and biological properties of microbiome metabolites. Prospective experimental validation confirmed the accuracy of our models and uncovered previously unknown effects of several metabolites. For example, we identified previously unknown interleukin 8 secretion stimulation by the metabolites spermine and spermidine, which have been regarded anti-inflammatory thus far. Our findings demonstrate the potential power of machine learning to accelerate the functional annotations of microbiome-derived metabolites, paving the way for biomarker and therapeutic discovery.

Duke Scholars

Author Daniel Reker Biomedical Engineering