DeepFRET, a software for rapid and automated single-molecule FRET data classification using deep learning
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
DeepFRET, a software for rapid and automated single-molecule FRET data classification using deep learning. / Thomsen, Johannes; Sletfjerding, Magnus Berg; Jensen, Simon Bo; Stella, Stefano; Paul, Bijoya; Malle, Mette Galsgaard; Montoya, Guillermo; Petersen, Troels Christian; Hatzakis, Nikos S.
I: eLife, Bind 9, e60404, 11.2020.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - DeepFRET, a software for rapid and automated single-molecule FRET data classification using deep learning
AU - Thomsen, Johannes
AU - Sletfjerding, Magnus Berg
AU - Jensen, Simon Bo
AU - Stella, Stefano
AU - Paul, Bijoya
AU - Malle, Mette Galsgaard
AU - Montoya, Guillermo
AU - Petersen, Troels Christian
AU - Hatzakis, Nikos S.
PY - 2020/11
Y1 - 2020/11
N2 - Single-molecule Forster Resonance energy transfer (smFRET) is an adaptable method for studying the structure and dynamics of biomolecules. The development of high throughput methodologies and the growth of commercial instrumentation have outpaced the development of rapid, standardized, and automated methodologies to objectively analyze the wealth of produced data. Here we present DeepFRET, an automated, open-source standalone solution based on deep learning, where the only crucial human intervention in transiting from raw microscope images to histograms of biomolecule behavior, is a user-adjustable quality threshold. Integrating standard features of smFRET analysis, DeepFRET consequently outputs the common kinetic information metrics. Its classification accuracy on ground truth data reached >95% outperforming human operators and commonly used threshold, only requiring similar to 1% of the time. Its precise and rapid operation on real data demonstrates DeepFRET's capacity to objectively quantify biomolecular dynamics and the potential to contribute to benchmarking smFRET for dynamic structural biology.
AB - Single-molecule Forster Resonance energy transfer (smFRET) is an adaptable method for studying the structure and dynamics of biomolecules. The development of high throughput methodologies and the growth of commercial instrumentation have outpaced the development of rapid, standardized, and automated methodologies to objectively analyze the wealth of produced data. Here we present DeepFRET, an automated, open-source standalone solution based on deep learning, where the only crucial human intervention in transiting from raw microscope images to histograms of biomolecule behavior, is a user-adjustable quality threshold. Integrating standard features of smFRET analysis, DeepFRET consequently outputs the common kinetic information metrics. Its classification accuracy on ground truth data reached >95% outperforming human operators and commonly used threshold, only requiring similar to 1% of the time. Its precise and rapid operation on real data demonstrates DeepFRET's capacity to objectively quantify biomolecular dynamics and the potential to contribute to benchmarking smFRET for dynamic structural biology.
U2 - 10.7554/eLife.60404
DO - 10.7554/eLife.60404
M3 - Journal article
C2 - 33138911
VL - 9
JO - eLife
JF - eLife
SN - 2050-084X
M1 - e60404
ER -
ID: 252105188