View in EDS

Quantifying the nuclear localization of fluorescently tagged proteins.

Saved in:
Bibliographic Details
Title: Quantifying the nuclear localization of fluorescently tagged proteins.
Authors: Hurbain J; AMOLF, Amsterdam, 1098 XG, The Netherlands.; School of Biological Sciences, The University of Edinburgh, Edinburgh, EH9 3BF, United Kingdom., Ten Wolde PR; AMOLF, Amsterdam, 1098 XG, The Netherlands., Swain PS; School of Biological Sciences, The University of Edinburgh, Edinburgh, EH9 3BF, United Kingdom.
Source: Bioinformatics advances [Bioinform Adv] 2025 May 12; Vol. 5 (1), pp. vbaf114. Date of Electronic Publication: 2025 May 12 (Print Publication: 2025).
Publication Type: Journal Article
Language: English
Journal Info: Publisher: Oxford University Press Country of Publication: England NLM ID: 9918282081306676 Publication Model: eCollection Cited Medium: Internet ISSN: 2635-0041 (Electronic) Linking ISSN: 26350041 NLM ISO Abbreviation: Bioinform Adv Subsets: PubMed not MEDLINE
Imprint Name(s): Original Publication: [Oxford] : Oxford University Press : International Society for Computational Biology, [2021]-
Abstract: Motivation: Cells are dynamic, continually responding to intra- and extracellular signals. Measuring the response to these signals in individual cells is challenging. Signal transduction is fast, but reporters for downstream gene expression are slow: fluorescent proteins must be expressed and mature. An alternative is to fluorescently tag and monitor the intracellular locations of transcription factors and other effectors. These proteins enter or exit the nucleus in minutes, after upstream signalling modifies their phosphorylation state. Although such approaches are increasingly popular, there is no consensus on how to quantify nuclear localization.
Results: Using budding yeast, we developed a convolutional neural network that determines nuclear localization from fluorescence and, optionally, bright-field images. Focusing on changing extracellular glucose, we generated ground-truth data using strains with a transcription factor and a nuclear protein tagged with fluorescent markers. We showed that the neural network-based approach outperformed seven published methods, particularly when predicting single-cell time series, which are key to determining how cells respond. Collectively, our results are conclusive-using machine learning to automatically determine the appropriate image processing consistently outperforms ad hoc approaches. Adopting such methods promises to both improve the accuracy and, with transfer learning, the consistency of single-cell analyses.
Availability and Implementation: We performed our analysis in Python; code is available at https://git.ecdf.ed.ac.uk/v1jhurba/neunet-nucloc.git.
(© The Author(s) 2025. Published by Oxford University Press.)
Competing Interests: No competing interest is declared.
References: Phys Rev E Stat Nonlin Soft Matter Phys. 2004 Jun;69(6 Pt 2):066138. (PMID: 15244698)
Mol Biol Cell. 2013 Jun;24(12):2045-57. (PMID: 23615444)
FEMS Microbiol Rev. 2014 Mar;38(2):254-99. (PMID: 24483210)
Biochim Biophys Acta. 2011 Feb;1813(2):358-66. (PMID: 21167216)
PLoS Biol. 2017 Dec 14;15(12):e2004050. (PMID: 29240790)
PLoS Genet. 2025 Jan 13;21(1):e1011552. (PMID: 39804939)
PLoS One. 2014 Jun 20;9(6):e100042. (PMID: 24950344)
Curr Biol. 2014 Sep 22;24(18):2189-2194. (PMID: 25220054)
Phys Biol. 2021 May 17;18(4):. (PMID: 33477124)
Phys Rev Lett. 2009 May 29;102(21):218101. (PMID: 19519137)
Nucleic Acids Res. 2023 Jun 9;51(10):4831-4844. (PMID: 36938874)
PLoS One. 2014 Feb 19;9(2):e87357. (PMID: 24586270)
Elife. 2017 May 17;6:. (PMID: 28513433)
J Cell Biol. 2003 May 12;161(3):497-505. (PMID: 12732613)
Nat Genet. 2004 Feb;36(2):147-50. (PMID: 14730303)
Science. 2013 Jan 25;339(6118):460-4. (PMID: 23349292)
Proc Natl Acad Sci U S A. 2018 Jun 5;115(23):6088-6093. (PMID: 29784812)
Science. 2002 Nov 8;298(5596):1241-5. (PMID: 12424381)
Sci Signal. 2013 May 28;6(277):ra41. (PMID: 23716718)
J Biol Chem. 2003 Nov 14;278(46):45288-95. (PMID: 12952948)
J Biol Chem. 2014 May 2;289(18):12863-75. (PMID: 24627493)
Proc Natl Acad Sci U S A. 2009 Nov 24;106(47):19928-33. (PMID: 19901341)
Nature. 2015 Nov 5;527(7576):54-8. (PMID: 26466562)
Trends Biochem Sci. 1996 Feb;21(2):59-64. (PMID: 8851662)
PLoS Genet. 2018 Nov 2;14(11):e1007744. (PMID: 30388117)
IEEE Trans Neural Netw Learn Syst. 2024 Jun;35(6):7478-7498. (PMID: 37015131)
Nat Struct Mol Biol. 2011 Dec 18;19(1):31-9. (PMID: 22179789)
FEMS Yeast Res. 2009 Sep;9(6):875-84. (PMID: 19566686)
Proc Natl Acad Sci U S A. 2008 May 20;105(20):7165-70. (PMID: 18480263)
Nature. 2008 Sep 25;455(7212):485-90. (PMID: 18818649)
Elife. 2023 Jul 07;12:. (PMID: 37417869)
Elife. 2022 Nov 09;11:. (PMID: 36350693)
Mol Biol Cell. 2000 Dec;11(12):4241-57. (PMID: 11102521)
Elife. 2017 Apr 18;6:. (PMID: 28418333)
Lab Chip. 2024 Jul 23;24(15):3658-3667. (PMID: 38915274)
Nature. 2010 Jul 8;466(7303):267-71. (PMID: 20581820)
Science. 2008 Jan 25;319(5862):482-4. (PMID: 18218902)
Elife. 2024 Apr 03;12:. (PMID: 38568203)
Mol Biol Cell. 2001 Feb;12(2):323-37. (PMID: 11179418)
Nat Protoc. 2015 Aug;10(8):1181-97. (PMID: 26158443)
Mol Syst Biol. 2013 Nov 05;9:704. (PMID: 24189399)
Entry Date(s): Date Created: 20250604 Latest Revision: 20250621
Update Code: 20250621
PubMed Central ID: PMC12133273
DOI: 10.1093/bioadv/vbaf114
PMID: 40463405
Database: MEDLINE
Description
Abstract:Motivation: Cells are dynamic, continually responding to intra- and extracellular signals. Measuring the response to these signals in individual cells is challenging. Signal transduction is fast, but reporters for downstream gene expression are slow: fluorescent proteins must be expressed and mature. An alternative is to fluorescently tag and monitor the intracellular locations of transcription factors and other effectors. These proteins enter or exit the nucleus in minutes, after upstream signalling modifies their phosphorylation state. Although such approaches are increasingly popular, there is no consensus on how to quantify nuclear localization.<br />Results: Using budding yeast, we developed a convolutional neural network that determines nuclear localization from fluorescence and, optionally, bright-field images. Focusing on changing extracellular glucose, we generated ground-truth data using strains with a transcription factor and a nuclear protein tagged with fluorescent markers. We showed that the neural network-based approach outperformed seven published methods, particularly when predicting single-cell time series, which are key to determining how cells respond. Collectively, our results are conclusive-using machine learning to automatically determine the appropriate image processing consistently outperforms ad hoc approaches. Adopting such methods promises to both improve the accuracy and, with transfer learning, the consistency of single-cell analyses.<br />Availability and Implementation: We performed our analysis in Python; code is available at https://git.ecdf.ed.ac.uk/v1jhurba/neunet-nucloc.git.<br /> (© The Author(s) 2025. Published by Oxford University Press.)
ISSN:2635-0041
DOI:10.1093/bioadv/vbaf114