Deep learning predicts microbial interactions from self-organized spatiotemporal patterns

Authors

Joon-Yong Lee, Pacific Northwest National LaboratoryFollow
Natalie C. Sadler, Pacific Northwest National LaboratoryFollow
Robert G. Egbert, Pacific Northwest National LaboratoryFollow
Christopher R. Anderton, Pacific Northwest National Laboratory
Kirsten S. Hofmockel, Pacific Northwest National Laboratory & Iowa State University
Janet K. Jansson, Pacific Northwest National LaboratoryFollow
Hyun-Seob Song, Pacific Northwest National Laboratory & University of Nebraska-LincolnFollow

Date of this Version

2020

Citation

Computational and Structural Biotechnology Journal 18 (2020) 1259–1269 https://doi.org/10.1016/j.csbj.2020.05.023

Comments

(c) 2020 published by Elsevier B.V. on behalf of Research Network of Computational and Structural Biotechnology

Abstract

Microbial communities organize into spatial patterns that are largely governed by interspecies interactions. This phenomenon is an important metric for understanding community functional dynamics, yet the use of spatial patterns for predicting microbial interactions is currently lacking. Here we propose supervised deep learning as a new tool for network inference. An agent-based model was used to simulate the spatiotemporal evolution of two interacting organisms under diverse growth and interaction scenarios, the data of which was subsequently used to train deep neural networks. For small-size domains (100 mm x 100 mm) over which interaction coefficients are assumed to be invariant, we obtained fairly accurate predictions, as indicated by an average R2 value of 0.84. In application to relatively larger domains (450 mm x 450 mm) where interaction coefficients are varying in space, deep learning models correctly predicted spatial distributions of interaction coefficients without any additional training. Lastly, we evaluated our model against real biological data obtained using Pseudomonas fluorescens and Escherichia coli co-cultures treated with polymeric chitin or N-acetylglucosamine, the hydrolysis product of chitin. While P. fluorescens can utilize both substrates for growth, E. coli lacked the ability to degrade chitin. Consistent with our expectations, our model predicted context-dependent interactions across two substrates, i.e., degrader-cheater relationship on chitin polymers and competition on monomers. The combined use of the agent-based model and machine learning algorithm successfully demonstrates how to infer microbial interactions from spatially distributed data, presenting itself as a useful tool for the analysis of more complex microbial community interactions