bioRxiv2018
Microbes affect each others growth in multiple, often elusive ways. The ensuing interdependencies form complex networks, believed to influence taxonomic composition, as well as community-level functional properties and dynamics. Elucidation of these networks is often pursued by measuring pairwise interaction in co-culture experiments. However, combinatorial complexity precludes the exhaustive experimental analysis of pairwise interactions even for moderately sized microbial communities. Here, we use a machine-learning random forest approach to address this challenge. In particular, we show how partial knowledge of a microbial interaction network, combined with trait-level representations of individual microbial species, can provide accurate inference of missing edges in the network and putative mechanisms underlying interactions. We applied our algorithm to two case studies: an experimentally mapped network of interactions between auxotrophic E. coli strains, and a large in silico network of metabolic interdependencies between 100 human gut-associated bacteria. For this last case, 5% of the network is enough to predict the remaining 95% with 80% accuracy, and mechanistic hypotheses produced by the algorithm accurately reflect known metabolic exchanges. Our approach, broadly applicable to any microbial or other ecological network, can drive the discovery of new interactions and new molecular mechanisms, both for therapeutic interventions involving natural communities and for the rational design of synthetic consortia.\n\nImportanceDifferent organisms in a microbial community may drastically affect each others growth phenotype, significantly affecting the community dynamics, with important implications for human and environmental health. Novel culturing methods and decreasing costs of sequencing will gradually enable high-throughput measurements of pairwise interactions in systematic co-culturing studies. However, a thorough characterization of all interactions that occur within a microbial community is greatly limited both by the combinatorial complexity of possible assortments, and by the limited biological insight that interaction measurements typically provide without laborious specific follow-ups. Here we show how a simple and flexible formal representation of microbial pairs can be used for classification of interactions with machine learning. The approach we propose predicts with high accuracy the outcome of yet to be performed experiments, and generates testable hypotheses about the mechanisms of specific interactions.