Cargando…

Integrating a tailored recurrent neural network with Bayesian experimental design to optimize microbial community functions

Microbiomes interact dynamically with their environment to perform exploitable functions such as production of valuable metabolites and degradation of toxic metabolites for a wide range of applications in human health, agriculture, and environmental cleanup. Developing computational models to predic...

Descripción completa

Detalles Bibliográficos
Autores principales: Thompson, Jaron C., Zavala, Victor M., Venturelli, Ophelia S.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10540976/
https://www.ncbi.nlm.nih.gov/pubmed/37773951
http://dx.doi.org/10.1371/journal.pcbi.1011436
_version_ 1785113823880937472
author Thompson, Jaron C.
Zavala, Victor M.
Venturelli, Ophelia S.
author_facet Thompson, Jaron C.
Zavala, Victor M.
Venturelli, Ophelia S.
author_sort Thompson, Jaron C.
collection PubMed
description Microbiomes interact dynamically with their environment to perform exploitable functions such as production of valuable metabolites and degradation of toxic metabolites for a wide range of applications in human health, agriculture, and environmental cleanup. Developing computational models to predict the key bacterial species and environmental factors to build and optimize such functions are crucial to accelerate microbial community engineering. However, there is an unknown web of interactions that determine the highly complex and dynamic behavior of these systems, which precludes the development of models based on known mechanisms. By contrast, entirely data-driven machine learning models can produce physically unrealistic predictions and often require significant amounts of experimental data to learn system behavior. We develop a physically-constrained recurrent neural network that preserves model flexibility but is constrained to produce physically consistent predictions and show that it can outperform existing machine learning methods in the prediction of certain experimentally measured species abundance and metabolite concentrations. Further, we present a closed-loop, Bayesian experimental design algorithm to guide data collection by selecting experimental conditions that simultaneously maximize information gain and target microbial community functions. Using a bioreactor case study, we demonstrate how the proposed framework can be used to efficiently navigate a large design space to identify optimal operating conditions. The proposed methodology offers a flexible machine learning approach specifically tailored to optimize microbiome target functions through the sequential design of informative experiments that seek to explore and exploit community functions.
format Online
Article
Text
id pubmed-10540976
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-105409762023-10-01 Integrating a tailored recurrent neural network with Bayesian experimental design to optimize microbial community functions Thompson, Jaron C. Zavala, Victor M. Venturelli, Ophelia S. PLoS Comput Biol Research Article Microbiomes interact dynamically with their environment to perform exploitable functions such as production of valuable metabolites and degradation of toxic metabolites for a wide range of applications in human health, agriculture, and environmental cleanup. Developing computational models to predict the key bacterial species and environmental factors to build and optimize such functions are crucial to accelerate microbial community engineering. However, there is an unknown web of interactions that determine the highly complex and dynamic behavior of these systems, which precludes the development of models based on known mechanisms. By contrast, entirely data-driven machine learning models can produce physically unrealistic predictions and often require significant amounts of experimental data to learn system behavior. We develop a physically-constrained recurrent neural network that preserves model flexibility but is constrained to produce physically consistent predictions and show that it can outperform existing machine learning methods in the prediction of certain experimentally measured species abundance and metabolite concentrations. Further, we present a closed-loop, Bayesian experimental design algorithm to guide data collection by selecting experimental conditions that simultaneously maximize information gain and target microbial community functions. Using a bioreactor case study, we demonstrate how the proposed framework can be used to efficiently navigate a large design space to identify optimal operating conditions. The proposed methodology offers a flexible machine learning approach specifically tailored to optimize microbiome target functions through the sequential design of informative experiments that seek to explore and exploit community functions. Public Library of Science 2023-09-29 /pmc/articles/PMC10540976/ /pubmed/37773951 http://dx.doi.org/10.1371/journal.pcbi.1011436 Text en © 2023 Thompson et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Thompson, Jaron C.
Zavala, Victor M.
Venturelli, Ophelia S.
Integrating a tailored recurrent neural network with Bayesian experimental design to optimize microbial community functions
title Integrating a tailored recurrent neural network with Bayesian experimental design to optimize microbial community functions
title_full Integrating a tailored recurrent neural network with Bayesian experimental design to optimize microbial community functions
title_fullStr Integrating a tailored recurrent neural network with Bayesian experimental design to optimize microbial community functions
title_full_unstemmed Integrating a tailored recurrent neural network with Bayesian experimental design to optimize microbial community functions
title_short Integrating a tailored recurrent neural network with Bayesian experimental design to optimize microbial community functions
title_sort integrating a tailored recurrent neural network with bayesian experimental design to optimize microbial community functions
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10540976/
https://www.ncbi.nlm.nih.gov/pubmed/37773951
http://dx.doi.org/10.1371/journal.pcbi.1011436
work_keys_str_mv AT thompsonjaronc integratingatailoredrecurrentneuralnetworkwithbayesianexperimentaldesigntooptimizemicrobialcommunityfunctions
AT zavalavictorm integratingatailoredrecurrentneuralnetworkwithbayesianexperimentaldesigntooptimizemicrobialcommunityfunctions
AT venturelliophelias integratingatailoredrecurrentneuralnetworkwithbayesianexperimentaldesigntooptimizemicrobialcommunityfunctions