Posterior marginalization accelerates Bayesian inference for dynamical models of biological processes.
Biological sciences
Mathematical biosciences
Systems biology
Journal
iScience
ISSN: 2589-0042
Titre abrégé: iScience
Pays: United States
ID NLM: 101724038
Informations de publication
Date de publication:
17 Nov 2023
17 Nov 2023
Historique:
received:
05
04
2023
revised:
16
07
2023
accepted:
25
09
2023
medline:
23
10
2023
pubmed:
23
10
2023
entrez:
23
10
2023
Statut:
epublish
Résumé
Bayesian inference is an important method in the life and natural sciences for learning from data. It provides information about parameter and prediction uncertainties. Yet, generating representative samples from the posterior distribution is often computationally challenging. Here, we present an approach that lowers the computational complexity of sample generation for dynamical models with scaling, offset, and noise parameters. The proposed method is based on the marginalization of the posterior distribution. We provide analytical results for a broad class of problems with conjugate priors and show that the method is suitable for a large number of applications. Subsequently, we demonstrate the benefit of the approach for applications from the field of systems biology. We report an improvement up to 50 times in the effective sample size per unit of time. As the scheme is broadly applicable, it will facilitate Bayesian inference in different research fields.
Identifiants
pubmed: 37867942
doi: 10.1016/j.isci.2023.108083
pii: S2589-0042(23)02160-0
pmc: PMC10589897
doi:
Types de publication
Journal Article
Langues
eng
Pagination
108083Informations de copyright
© 2023 The Authors.
Déclaration de conflit d'intérêts
The authors declare no competing interests.
Références
Science. 2002 Mar 1;295(5560):1662-4
pubmed: 11872829
Bioinformatics. 2018 Dec 15;34(24):4266-4273
pubmed: 30010716
Cold Spring Harb Protoc. 2014 Oct 01;2014(10):pdb.top071795
pubmed: 25275114
Nanomedicine. 2014 May;10(4):679-88
pubmed: 24333584
PLoS Comput Biol. 2014 Jul 03;10(7):e1003686
pubmed: 24992156
NPJ Syst Biol Appl. 2017 Sep 20;3:27
pubmed: 28944080
Sci Signal. 2009 Jun 30;2(77):ra31
pubmed: 19567914
PLoS One. 2013 Sep 30;8(9):e74335
pubmed: 24098642
BMC Syst Biol. 2017 Jun 24;11(1):63
pubmed: 28646868
Bioinformatics. 2019 Mar 1;35(5):830-838
pubmed: 30816929
Bioinformatics. 2007 Oct 15;23(20):2747-53
pubmed: 17768165
Sci Signal. 2015 Dec 22;8(408):ra130
pubmed: 26696630
Quant Biol. 2020;8(1):11-19
pubmed: 32219006
Sci Signal. 2010;3(134):ra20
pubmed: 20731071
Philos Trans A Math Phys Eng Sci. 2012 Dec 31;371(1984):20110544
pubmed: 23277602
Bioinformatics. 2017 Mar 1;33(5):718-725
pubmed: 28062444
PLoS Comput Biol. 2021 Jan 26;17(1):e1008646
pubmed: 33497393
Sci Signal. 2010 Jul 27;3(132):ra56
pubmed: 20664065
Proc Natl Acad Sci U S A. 1979 Jul;76(7):3116-20
pubmed: 91164
NPJ Syst Biol Appl. 2017 Aug 8;3:20
pubmed: 28804640
Cell Syst. 2016 Jan 27;2(1):49-58
pubmed: 27136689
Bioinformatics. 2020 Jan 15;36(2):594-602
pubmed: 31347657
Nat Med. 2020 Jun;26(6):855-860
pubmed: 32322102
Math Biosci. 2013 Dec;246(2):293-304
pubmed: 23602931
PLoS Comput Biol. 2020 Mar 2;16(3):e1007147
pubmed: 32119655
J Proteome Res. 2014 Dec 5;13(12):5685-94
pubmed: 25333863
Bioinformatics. 2019 Sep 1;35(17):3073-3082
pubmed: 30624608
PLoS Comput Biol. 2022 Jul 13;18(7):e1010322
pubmed: 35830470
Mol Syst Biol. 2011 Jul 19;7:516
pubmed: 21772264