Deep learning predicts microbial interactions from self-organized spatiotemporal patterns
Abstract
Microorganisms in terrestrial habitats self-organize to form specific spatial patterns through their interactions with each other and with the environment. Spatial patterns of microorganisms can therefore be viewed as a key ecological phenotype. However, their use for predicting microbial interactions is currently lacking, primarily due to an intrinsic limitation of current network inference methods that are based on population-level analyses. To address this gap, here we propose supervised deep learning as a new tool for predicting interspecies interactions from spatial patterns of microbial assembly. In a case study of two interacting organisms, we developed an agent-based model to simulate their spatiotemporal evolution under diverse growth and interaction scenarios. These data were subsequently used as a primary source to train, validate, and test deep neural networks. To do so, we first tested the effectiveness of the deep learning method for small-size domains (100 µm × 100 µm) over which interaction coefficients are assumed to be invariant. We obtained fairly accurate predictions, as indicated by an average R2 value of 0.84. We further tested how deep learning models can be extended to relatively larger domains (450 µm × 450 µm) where interaction coefficients are varying in space. Notably, without any additional training,more »
- Authors:
- Publication Date:
- Research Org.:
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1762535
- Alternate Identifier(s):
- OSTI ID: 1633302
- Report Number(s):
- PNNL-SA-150281
Journal ID: ISSN 2001-0370; S2001037020302865; PII: S2001037020302865
- Grant/Contract Number:
- AC05-76RL01830
- Resource Type:
- Published Article
- Journal Name:
- Computational and Structural Biotechnology Journal
- Additional Journal Information:
- Journal Name: Computational and Structural Biotechnology Journal Journal Volume: 18 Journal Issue: C; Journal ID: ISSN 2001-0370
- Publisher:
- Elsevier
- Country of Publication:
- Sweden
- Language:
- English
- Subject:
- 59 BASIC BIOLOGICAL SCIENCES; 97 MATHEMATICS AND COMPUTING; Machine learning; Agent-based modeling; Soil microbiomes; Microscopy imaging technology; Network inference
Citation Formats
Lee, Joon-Yong, Sadler, Natalie C., Egbert, Robert G., Anderton, Christopher R., Hofmockel, Kirsten S., Jansson, Janet K., and Song, Hyun-Seob. Deep learning predicts microbial interactions from self-organized spatiotemporal patterns. Sweden: N. p., 2020.
Web. doi:10.1016/j.csbj.2020.05.023.
Lee, Joon-Yong, Sadler, Natalie C., Egbert, Robert G., Anderton, Christopher R., Hofmockel, Kirsten S., Jansson, Janet K., & Song, Hyun-Seob. Deep learning predicts microbial interactions from self-organized spatiotemporal patterns. Sweden. https://doi.org/10.1016/j.csbj.2020.05.023
Lee, Joon-Yong, Sadler, Natalie C., Egbert, Robert G., Anderton, Christopher R., Hofmockel, Kirsten S., Jansson, Janet K., and Song, Hyun-Seob. Wed .
"Deep learning predicts microbial interactions from self-organized spatiotemporal patterns". Sweden. https://doi.org/10.1016/j.csbj.2020.05.023.
@article{osti_1762535,
title = {Deep learning predicts microbial interactions from self-organized spatiotemporal patterns},
author = {Lee, Joon-Yong and Sadler, Natalie C. and Egbert, Robert G. and Anderton, Christopher R. and Hofmockel, Kirsten S. and Jansson, Janet K. and Song, Hyun-Seob},
abstractNote = {Microorganisms in terrestrial habitats self-organize to form specific spatial patterns through their interactions with each other and with the environment. Spatial patterns of microorganisms can therefore be viewed as a key ecological phenotype. However, their use for predicting microbial interactions is currently lacking, primarily due to an intrinsic limitation of current network inference methods that are based on population-level analyses. To address this gap, here we propose supervised deep learning as a new tool for predicting interspecies interactions from spatial patterns of microbial assembly. In a case study of two interacting organisms, we developed an agent-based model to simulate their spatiotemporal evolution under diverse growth and interaction scenarios. These data were subsequently used as a primary source to train, validate, and test deep neural networks. To do so, we first tested the effectiveness of the deep learning method for small-size domains (100 µm × 100 µm) over which interaction coefficients are assumed to be invariant. We obtained fairly accurate predictions, as indicated by an average R2 value of 0.84. We further tested how deep learning models can be extended to relatively larger domains (450 µm × 450 µm) where interaction coefficients are varying in space. Notably, without any additional training, our deep neural network model was able to successfully recover the spatial distribution of interaction coefficients. Lastly, we evaluated the applicability of our computational approach to real biological data through imaging experiments of binary interactions between Pseudomonas fluorescens and a mutant of Escherichia coli. These co-culture experiments were designed to control interactions as a function of environmental conditions. For example, P. fluorescens and E. coli develop a degrader-cheater relationship when growing on chitin polymers, which however turns into competition when growing on chitin hydrolysis products (i.e., N-acetyl glucosamine). Consistent with our expectations, the analysis of real images using the deep neural network model correctly predicted the dramatic shifts in interactions of the two organisms in the two different environmental contexts mentioned above. The combined use of the agent-based model and machine learning algorithm developed in this work 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.},
doi = {10.1016/j.csbj.2020.05.023},
journal = {Computational and Structural Biotechnology Journal},
number = C,
volume = 18,
place = {Sweden},
year = {Wed Jan 01 00:00:00 EST 2020},
month = {Wed Jan 01 00:00:00 EST 2020}
}
https://doi.org/10.1016/j.csbj.2020.05.023
Figures / Tables:
Works referenced in this record:
Spatial Ecology of Bacteria at the Microscale in Soil
journal, January 2014
- Raynaud, Xavier; Nunan, Naoise
- PLoS ONE, Vol. 9, Issue 1
Microbial interactions: from networks to models
journal, July 2012
- Faust, Karoline; Raes, Jeroen
- Nature Reviews Microbiology, Vol. 10, Issue 8
Colony analysis and deep learning uncover 5-hydroxyindole as an inhibitor of gliding motility and iridescence in Cellulophaga lytica
journal, March 2018
- Chapelais-Baron, Maylis; Goubet, Isabelle; Péteri, Renaud
- Microbiology, Vol. 164, Issue 3
Deep learning
journal, May 2015
- LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
- Nature, Vol. 521, Issue 7553
Deep learning and process understanding for data-driven Earth system science
journal, February 2019
- Reichstein, Markus; Camps-Valls, Gustau; Stevens, Bjorn
- Nature, Vol. 566, Issue 7743
Chromatic Bacteria – A Broad Host-Range Plasmid and Chromosomal Insertion Toolbox for Fluorescent Protein Expression in Bacteria
journal, December 2018
- Schlechter, Rudolf O.; Jun, Hyunwoo; Bernach, Michał
- Frontiers in Microbiology, Vol. 9
Selection, Succession, and Stabilization of Soil Microbial Consortia
journal, May 2019
- Zegeye, Elias K.; Brislawn, Colin J.; Farris, Yuliya
- mSystems, Vol. 4, Issue 4
Live imaging of root–bacteria interactions in a microfluidics setup
journal, March 2017
- Massalha, Hassan; Korenblum, Elisa; Malitsky, Sergey
- Proceedings of the National Academy of Sciences, Vol. 114, Issue 17
Human-level control through deep reinforcement learning
journal, February 2015
- Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David
- Nature, Vol. 518, Issue 7540
Advancing microbial sciences by individual-based modelling
journal, June 2016
- Hellweger, Ferdi L.; Clegg, Robert J.; Clark, James R.
- Nature Reviews Microbiology, Vol. 14, Issue 7
Automatic early stopping using cross validation: quantifying the criteria
journal, June 1998
- Prechelt, Lutz
- Neural Networks, Vol. 11, Issue 4
Deciphering links between bacterial interactions and spatial organization in multispecies biofilms
journal, August 2019
- Liu, Wenzheng; Jacquiod, Samuel; Brejnrod, Asker
- The ISME Journal, Vol. 13, Issue 12
Construction of Escherichia coli K-12 in-frame, single-gene knockout mutants the Keio collection
journal, February 2006
- Baba, Tomoya; Ara, Takeshi; Hasegawa, Miki
- Molecular Systems Biology, Vol. 2, Article No. 2006.0008
Minimal Interspecies Interaction Adjustment (MIIA): Inference of Neighbor-Dependent Interactions in Microbial Communities
journal, June 2019
- Song, Hyun-Seob; Lee, Joon-Yong; Haruta, Shin
- Frontiers in Microbiology, Vol. 10
Cross-biome patterns in soil microbial respiration predictable from evolutionary theory on thermal adaptation
journal, January 2019
- Bradford, Mark A.; McCulley, Rebecca L.; Crowther, Thomas. W.
- Nature Ecology & Evolution, Vol. 3, Issue 2
Soil biofilms: microbial interactions, challenges, and advanced techniques for ex-situ characterization
journal, July 2019
- Cai, Peng; Sun, Xiaojie; Wu, Yichao
- Soil Ecology Letters, Vol. 1, Issue 3-4
Microbial interactions and community assembly at microscales
journal, June 2016
- Cordero, Otto X.; Datta, Manoshi S.
- Current Opinion in Microbiology, Vol. 31
Exact stochastic simulation of coupled chemical reactions
journal, December 1977
- Gillespie, Daniel T.
- The Journal of Physical Chemistry, Vol. 81, Issue 25
Mathematical Modeling of Microbial Community Dynamics: A Methodological Review
journal, October 2014
- Song, Hyun-Seob; Cannon, William; Beliaev, Alexander
- Processes, Vol. 2, Issue 4
Micro-scale determinants of bacterial diversity in soil
journal, November 2013
- Vos, Michiel; Wolf, Alexandra B.; Jennings, Sarah J.
- FEMS Microbiology Reviews, Vol. 37, Issue 6
A microfluidics-based in situ chemotaxis assay to study the behaviour of aquatic microbial communities
journal, August 2017
- Lambert, Bennett S.; Raina, Jean-Baptiste; Fernandez, Vicente I.
- Nature Microbiology, Vol. 2, Issue 10
Modeling and Simulating Chemical Reactions
journal, January 2008
- Higham, Desmond J.
- SIAM Review, Vol. 50, Issue 2
Phenotypic responses to interspecies competition and commensalism in a naturally-derived microbial co-culture
journal, January 2018
- Khan, Nymul; Maezato, Yukari; McClure, Ryan S.
- Scientific Reports, Vol. 8, Issue 1
A primer on deep learning in genomics
journal, November 2018
- Zou, James; Huss, Mikael; Abid, Abubakar
- Nature Genetics, Vol. 51, Issue 1
A Microfluidics and Agent-Based Modeling Framework for Investigating Spatial Organization in Bacterial Colonies: The Case of Pseudomonas Aeruginosa and H1-Type VI Secretion Interactions
journal, February 2018
- Wilmoth, Jared L.; Doak, Peter W.; Timm, Andrea
- Frontiers in Microbiology, Vol. 9
Systems-level analysis of microbial community organization through combinatorial labeling and spectral imaging
journal, February 2011
- Valm, A. M.; Welch, J. L. M.; Rieken, C. W.
- Proceedings of the National Academy of Sciences, Vol. 108, Issue 10
Cell-to-cell bacterial interactions promoted by drier conditions on soil surfaces
journal, September 2018
- Tecon, Robin; Ebrahimi, Ali; Kleyer, Hannah
- Proceedings of the National Academy of Sciences, Vol. 115, Issue 39
A general method for numerically simulating the stochastic time evolution of coupled chemical reactions
journal, December 1976
- Gillespie, Daniel T.
- Journal of Computational Physics, Vol. 22, Issue 4
A guide to deep learning in healthcare
journal, January 2019
- Esteva, Andre; Robicquet, Alexandre; Ramsundar, Bharath
- Nature Medicine, Vol. 25, Issue 1
Strong inter-population cooperation leads to partner intermixing in microbial communities
journal, January 2013
- Momeni, Babak; Brileya, Kristen A.; Fields, Matthew W.
- eLife, Vol. 2
Figures / Tables found in this record: