Cargando…

Biologically-informed neural networks guide mechanistic modeling from sparse experimental data

Biologically-informed neural networks (BINNs), an extension of physics-informed neural networks [1], are introduced and used to discover the underlying dynamics of biological systems from sparse experimental data. In the present work, BINNs are trained in a supervised learning framework to approxima...

Descripción completa

Detalles Bibliográficos
Autores principales: Lagergren, John H., Nardini, John T., Baker, Ruth E., Simpson, Matthew J., Flores, Kevin B.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7732115/
https://www.ncbi.nlm.nih.gov/pubmed/33259472
http://dx.doi.org/10.1371/journal.pcbi.1008462
_version_ 1783622024822784000
author Lagergren, John H.
Nardini, John T.
Baker, Ruth E.
Simpson, Matthew J.
Flores, Kevin B.
author_facet Lagergren, John H.
Nardini, John T.
Baker, Ruth E.
Simpson, Matthew J.
Flores, Kevin B.
author_sort Lagergren, John H.
collection PubMed
description Biologically-informed neural networks (BINNs), an extension of physics-informed neural networks [1], are introduced and used to discover the underlying dynamics of biological systems from sparse experimental data. In the present work, BINNs are trained in a supervised learning framework to approximate in vitro cell biology assay experiments while respecting a generalized form of the governing reaction-diffusion partial differential equation (PDE). By allowing the diffusion and reaction terms to be multilayer perceptrons (MLPs), the nonlinear forms of these terms can be learned while simultaneously converging to the solution of the governing PDE. Further, the trained MLPs are used to guide the selection of biologically interpretable mechanistic forms of the PDE terms which provides new insights into the biological and physical mechanisms that govern the dynamics of the observed system. The method is evaluated on sparse real-world data from wound healing assays with varying initial cell densities [2].
format Online
Article
Text
id pubmed-7732115
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-77321152020-12-17 Biologically-informed neural networks guide mechanistic modeling from sparse experimental data Lagergren, John H. Nardini, John T. Baker, Ruth E. Simpson, Matthew J. Flores, Kevin B. PLoS Comput Biol Research Article Biologically-informed neural networks (BINNs), an extension of physics-informed neural networks [1], are introduced and used to discover the underlying dynamics of biological systems from sparse experimental data. In the present work, BINNs are trained in a supervised learning framework to approximate in vitro cell biology assay experiments while respecting a generalized form of the governing reaction-diffusion partial differential equation (PDE). By allowing the diffusion and reaction terms to be multilayer perceptrons (MLPs), the nonlinear forms of these terms can be learned while simultaneously converging to the solution of the governing PDE. Further, the trained MLPs are used to guide the selection of biologically interpretable mechanistic forms of the PDE terms which provides new insights into the biological and physical mechanisms that govern the dynamics of the observed system. The method is evaluated on sparse real-world data from wound healing assays with varying initial cell densities [2]. Public Library of Science 2020-12-01 /pmc/articles/PMC7732115/ /pubmed/33259472 http://dx.doi.org/10.1371/journal.pcbi.1008462 Text en © 2020 Lagergren et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://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
Lagergren, John H.
Nardini, John T.
Baker, Ruth E.
Simpson, Matthew J.
Flores, Kevin B.
Biologically-informed neural networks guide mechanistic modeling from sparse experimental data
title Biologically-informed neural networks guide mechanistic modeling from sparse experimental data
title_full Biologically-informed neural networks guide mechanistic modeling from sparse experimental data
title_fullStr Biologically-informed neural networks guide mechanistic modeling from sparse experimental data
title_full_unstemmed Biologically-informed neural networks guide mechanistic modeling from sparse experimental data
title_short Biologically-informed neural networks guide mechanistic modeling from sparse experimental data
title_sort biologically-informed neural networks guide mechanistic modeling from sparse experimental data
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7732115/
https://www.ncbi.nlm.nih.gov/pubmed/33259472
http://dx.doi.org/10.1371/journal.pcbi.1008462
work_keys_str_mv AT lagergrenjohnh biologicallyinformedneuralnetworksguidemechanisticmodelingfromsparseexperimentaldata
AT nardinijohnt biologicallyinformedneuralnetworksguidemechanisticmodelingfromsparseexperimentaldata
AT bakerruthe biologicallyinformedneuralnetworksguidemechanisticmodelingfromsparseexperimentaldata
AT simpsonmatthewj biologicallyinformedneuralnetworksguidemechanisticmodelingfromsparseexperimentaldata
AT floreskevinb biologicallyinformedneuralnetworksguidemechanisticmodelingfromsparseexperimentaldata