Cargando…

Machine learning meets Monte Carlo methods for models of muscle’s molecular machinery to classify mutations

The timing and magnitude of force generation by a muscle depend on complex interactions in a compliant, contractile filament lattice. Perturbations in these interactions can result in cardiac muscle diseases. In this study, we address the fundamental challenge of connecting the temporal features of...

Descripción completa

Detalles Bibliográficos
Autores principales: Asencio, Anthony, Malingen, Sage, Kooiker, Kristina B., Powers, Joseph D., Davis, Jennifer, Daniel, Thomas, Moussavi-Harami, Farid
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Rockefeller University Press 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10067704/
https://www.ncbi.nlm.nih.gov/pubmed/37000171
http://dx.doi.org/10.1085/jgp.202213291
_version_ 1785018532062298112
author Asencio, Anthony
Malingen, Sage
Kooiker, Kristina B.
Powers, Joseph D.
Davis, Jennifer
Daniel, Thomas
Moussavi-Harami, Farid
author_facet Asencio, Anthony
Malingen, Sage
Kooiker, Kristina B.
Powers, Joseph D.
Davis, Jennifer
Daniel, Thomas
Moussavi-Harami, Farid
author_sort Asencio, Anthony
collection PubMed
description The timing and magnitude of force generation by a muscle depend on complex interactions in a compliant, contractile filament lattice. Perturbations in these interactions can result in cardiac muscle diseases. In this study, we address the fundamental challenge of connecting the temporal features of cardiac twitches to underlying rate constants and their perturbations associated with genetic cardiomyopathies. Current state-of-the-art metrics for characterizing the mechanical consequence of cardiac muscle disease do not utilize information embedded in the complete time course of twitch force. We pair dimension reduction techniques and machine learning methods to classify underlying perturbations that shape the timing of twitch force. To do this, we created a large twitch dataset using a spatially explicit Monte Carlo model of muscle contraction. Uniquely, we modified the rate constants of this model in line with mouse models of cardiac muscle disease and varied mutation penetrance. Ultimately, the results of this study show that machine learning models combined with biologically informed dimension reduction techniques can yield excellent classification accuracy of underlying muscle perturbations.
format Online
Article
Text
id pubmed-10067704
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Rockefeller University Press
record_format MEDLINE/PubMed
spelling pubmed-100677042023-09-30 Machine learning meets Monte Carlo methods for models of muscle’s molecular machinery to classify mutations Asencio, Anthony Malingen, Sage Kooiker, Kristina B. Powers, Joseph D. Davis, Jennifer Daniel, Thomas Moussavi-Harami, Farid J Gen Physiol Article The timing and magnitude of force generation by a muscle depend on complex interactions in a compliant, contractile filament lattice. Perturbations in these interactions can result in cardiac muscle diseases. In this study, we address the fundamental challenge of connecting the temporal features of cardiac twitches to underlying rate constants and their perturbations associated with genetic cardiomyopathies. Current state-of-the-art metrics for characterizing the mechanical consequence of cardiac muscle disease do not utilize information embedded in the complete time course of twitch force. We pair dimension reduction techniques and machine learning methods to classify underlying perturbations that shape the timing of twitch force. To do this, we created a large twitch dataset using a spatially explicit Monte Carlo model of muscle contraction. Uniquely, we modified the rate constants of this model in line with mouse models of cardiac muscle disease and varied mutation penetrance. Ultimately, the results of this study show that machine learning models combined with biologically informed dimension reduction techniques can yield excellent classification accuracy of underlying muscle perturbations. Rockefeller University Press 2023-03-31 /pmc/articles/PMC10067704/ /pubmed/37000171 http://dx.doi.org/10.1085/jgp.202213291 Text en © 2023 Asencio et al. https://creativecommons.org/licenses/by-nc-sa/4.0/http://www.rupress.org/terms/This article is distributed under the terms of an Attribution–Noncommercial–Share Alike–No Mirror Sites license for the first six months after the publication date (see http://www.rupress.org/terms/). After six months it is available under a Creative Commons License (Attribution–Noncommercial–Share Alike 4.0 International license, as described at https://creativecommons.org/licenses/by-nc-sa/4.0/).
spellingShingle Article
Asencio, Anthony
Malingen, Sage
Kooiker, Kristina B.
Powers, Joseph D.
Davis, Jennifer
Daniel, Thomas
Moussavi-Harami, Farid
Machine learning meets Monte Carlo methods for models of muscle’s molecular machinery to classify mutations
title Machine learning meets Monte Carlo methods for models of muscle’s molecular machinery to classify mutations
title_full Machine learning meets Monte Carlo methods for models of muscle’s molecular machinery to classify mutations
title_fullStr Machine learning meets Monte Carlo methods for models of muscle’s molecular machinery to classify mutations
title_full_unstemmed Machine learning meets Monte Carlo methods for models of muscle’s molecular machinery to classify mutations
title_short Machine learning meets Monte Carlo methods for models of muscle’s molecular machinery to classify mutations
title_sort machine learning meets monte carlo methods for models of muscle’s molecular machinery to classify mutations
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10067704/
https://www.ncbi.nlm.nih.gov/pubmed/37000171
http://dx.doi.org/10.1085/jgp.202213291
work_keys_str_mv AT asencioanthony machinelearningmeetsmontecarlomethodsformodelsofmusclesmolecularmachinerytoclassifymutations
AT malingensage machinelearningmeetsmontecarlomethodsformodelsofmusclesmolecularmachinerytoclassifymutations
AT kooikerkristinab machinelearningmeetsmontecarlomethodsformodelsofmusclesmolecularmachinerytoclassifymutations
AT powersjosephd machinelearningmeetsmontecarlomethodsformodelsofmusclesmolecularmachinerytoclassifymutations
AT davisjennifer machinelearningmeetsmontecarlomethodsformodelsofmusclesmolecularmachinerytoclassifymutations
AT danielthomas machinelearningmeetsmontecarlomethodsformodelsofmusclesmolecularmachinerytoclassifymutations
AT moussaviharamifarid machinelearningmeetsmontecarlomethodsformodelsofmusclesmolecularmachinerytoclassifymutations