Deep-LASI: deep-learning assisted, single-molecule imaging analysis of multi-color DNA origami structures.
Journal
Nature communications
ISSN: 2041-1723
Titre abrégé: Nat Commun
Pays: England
ID NLM: 101528555
Informations de publication
Date de publication:
17 10 2023
17 10 2023
Historique:
received:
09
02
2023
accepted:
05
10
2023
medline:
23
10
2023
pubmed:
18
10
2023
entrez:
17
10
2023
Statut:
epublish
Résumé
Single-molecule experiments have changed the way we explore the physical world, yet data analysis remains time-consuming and prone to human bias. Here, we introduce Deep-LASI (Deep-Learning Assisted Single-molecule Imaging analysis), a software suite powered by deep neural networks to rapidly analyze single-, two- and three-color single-molecule data, especially from single-molecule Förster Resonance Energy Transfer (smFRET) experiments. Deep-LASI automatically sorts recorded traces, determines FRET correction factors and classifies the state transitions of dynamic traces all in ~20-100 ms per trajectory. We benchmarked Deep-LASI using ground truth simulations as well as experimental data analyzed manually by an expert user and compared the results with a conventional Hidden Markov Model analysis. We illustrate the capabilities of the technique using a highly tunable L-shaped DNA origami structure and use Deep-LASI to perform titrations, analyze protein conformational dynamics and demonstrate its versatility for analyzing both total internal reflection fluorescence microscopy and confocal smFRET data.
Identifiants
pubmed: 37848439
doi: 10.1038/s41467-023-42272-9
pii: 10.1038/s41467-023-42272-9
pmc: PMC10582187
doi:
Substances chimiques
DNA
9007-49-2
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
6564Informations de copyright
© 2023. Springer Nature Limited.
Références
Biophys J. 2008 Mar 1;94(5):1826-35
pubmed: 17921203
Proc Natl Acad Sci U S A. 2023 Jan 24;120(4):e2211896120
pubmed: 36652471
Nat Methods. 2016 Apr;13(4):341-4
pubmed: 26878382
Biophys J. 2004 Aug;87(2):1328-37
pubmed: 15298935
Biophys J. 2005 Apr;88(4):2939-53
pubmed: 15653725
Science. 2018 Jan 19;359(6373):296-301
pubmed: 29348232
Nat Methods. 2023 Apr;20(4):523-535
pubmed: 36973549
Nat Commun. 2022 Sep 14;13(1):5402
pubmed: 36104339
J Mol Graph Model. 2022 Jul;114:108169
pubmed: 35378434
Adv Mater. 2021 Jun;33(24):e2101099
pubmed: 33938054
PLoS One. 2012;7(2):e30024
pubmed: 22363412
Biophys J. 2014 Mar 18;106(6):1327-37
pubmed: 24655508
Sci Rep. 2016 Sep 19;6:33257
pubmed: 27641327
Methods Appl Fluoresc. 2023 Oct 12;12(1):
pubmed: 37726007
J Am Chem Soc. 2019 May 1;141(17):6976-6985
pubmed: 30950273
Proc Natl Acad Sci U S A. 2021 Aug 17;118(33):
pubmed: 34389669
Biophys J. 2018 Dec 18;115(12):2310-2326
pubmed: 30527334
Chemphyschem. 2012 Mar;13(4):1060-78
pubmed: 22383292
Elife. 2021 Mar 29;10:
pubmed: 33779550
Physiol Chem Phys Med NMR. 1993;25(4):273-80
pubmed: 7512269
Nat Methods. 2015 Jul;12(7):593-4
pubmed: 26125588
Science. 2016 Oct 21;354(6310):305-307
pubmed: 27846560
Acc Chem Res. 2005 Jul;38(7):523-33
pubmed: 16028886
Anal Chem. 2021 Jun 29;93(25):8856-8863
pubmed: 34124890
Biophys J. 2006 Sep 1;91(5):1941-51
pubmed: 16766620
Nat Commun. 2023 Oct 17;14(1):6564
pubmed: 37848439
Biophys J. 2016 Oct 4;111(7):1375-1384
pubmed: 27705761
ACS Synth Biol. 2020 Oct 16;9(10):2665-2678
pubmed: 32910644
Elife. 2020 Nov 03;9:
pubmed: 33138911
J Am Chem Soc. 2009 Apr 15;131(14):5018-9
pubmed: 19301868
J Phys Chem B. 2019 Aug 15;123(32):6901-6916
pubmed: 31117611
Nat Methods. 2018 Sep;15(9):669-676
pubmed: 30171252
ACS Nano. 2021 Apr 27;15(4):6430-6438
pubmed: 33834769
Nat Commun. 2020 Nov 17;11(1):5833
pubmed: 33203879
Biophys Chem. 2007 Mar;126(1-3):176-85
pubmed: 16920250
EMBO J. 2013 May 29;32(11):1639-49
pubmed: 23624933
Biophys J. 2010 Nov 3;99(9):3102-11
pubmed: 21044609
J Phys Chem B. 2016 Jul 7;120(26):6401-10
pubmed: 27184889