(661a) Deep Learning Prediction of Interspecies Interactions from Self-Organized Spatiotemporal Patterns of Co-Evolving Organisms

Microorganisms colonizing natural habits such as soils co-evolve to form specific spatial patterns through interspecies interactions. These self-organized patterns are a key ecological phenotype, which provides critical information on their interaction mechanisms. However, conventional network inference techniques that predict interactions based on population size have yet to be extended to account for such spatial heterogeneity. Here we proposed supervised deep learning as a new network inference tool for predicting interaction networks from spatiotemporal patterns of co-evolving organisms. In the absence of biological imaging data that can be used for training deep learning networks, we used in silico data generated from high-fidelity agent-based models to determine model structure and parameters. Even though networks were trained under simple configurations where interaction coefficients are assumed to be invariant, the resulting model successfully predicted more complex cases where interspecies interactions vary in space. In the further test against real biological data obtained through imaging experiments of a binary consortium (Pseudomonas fluorescens and a mutant of Escherichia coli), our model also predicted the dramatic shifts in interactions across different environmental contexts. Through various successful demonstrations in this work, therefore, the combined use of the agent-based modeling and machine learning techniques provides a means to use new type of data - microscopic images - for extracting microbial interactions, therefore presenting itself as a useful tool for the analysis of more complex microbial community interactions.