» Articles » PMID: 33138911

DeepFRET, a Software for Rapid and Automated Single-molecule FRET Data Classification Using Deep Learning

Overview
Journal Elife
Specialty Biology
Date 2020 Nov 3
PMID 33138911
Citations 32
Authors
Affiliations
Soon will be listed here.
Abstract

Single-molecule Förster 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 ~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.

Citing Articles

Ligand response of guanidine-IV riboswitch at single-molecule level.

Gao L, Chen D, Liu Y Elife. 2024; 13.

PMID: 39620905 PMC: 11611296. DOI: 10.7554/eLife.94706.


Deep learning based local feature classification to automatically identify single molecule fluorescence events.

Zhou S, Miao Y, Qiu H, Yao Y, Wang W, Chen C Commun Biol. 2024; 7(1):1404.

PMID: 39468368 PMC: 11519536. DOI: 10.1038/s42003-024-07122-4.


Divergent molecular assembly and catalytic mechanisms between bacterial and archaeal RNase P in pre-tRNA cleavage.

Liang X, Chen D, Su A, Liu Y Proc Natl Acad Sci U S A. 2024; 121(43):e2407579121.

PMID: 39413135 PMC: 11513950. DOI: 10.1073/pnas.2407579121.


Foundation model for efficient biological discovery in single-molecule data.

Li J, Zhang L, Johnson-Buck A, Walter N bioRxiv. 2024; .

PMID: 39253410 PMC: 11383305. DOI: 10.1101/2024.08.26.609721.


An optofluidic antenna for enhancing the sensitivity of single-emitter measurements.

Morales-Inostroza L, Folz J, Kuhnemuth R, Felekyan S, Wieser F, Seidel C Nat Commun. 2024; 15(1):2545.

PMID: 38514627 PMC: 10957926. DOI: 10.1038/s41467-024-46730-w.


References
1.
Durisic N, Laparra-Cuervo L, Sandoval-Alvarez A, Borbely J, Lakadamyali M . Single-molecule evaluation of fluorescent protein photoactivation efficiency using an in vivo nanotemplate. Nat Methods. 2014; 11(2):156-62. DOI: 10.1038/nmeth.2784. View

2.
Zhang P, Liu S, Chaurasia A, Ma D, Mlodzianoski M, Culurciello E . Analyzing complex single-molecule emission patterns with deep learning. Nat Methods. 2018; 15(11):913-916. PMC: 6624853. DOI: 10.1038/s41592-018-0153-5. View

3.
Lu H, Xun L, Xie X . Single-molecule enzymatic dynamics. Science. 1998; 282(5395):1877-82. DOI: 10.1126/science.282.5395.1877. View

4.
Lerner E, Cordes T, Ingargiola A, Alhadid Y, Chung S, Michalet X . Toward dynamic structural biology: Two decades of single-molecule Förster resonance energy transfer. Science. 2018; 359(6373). PMC: 6200918. DOI: 10.1126/science.aan1133. View

5.
Hellenkamp B, Schmid S, Doroshenko O, Opanasyuk O, Kuhnemuth R, Rezaei Adariani S . Precision and accuracy of single-molecule FRET measurements-a multi-laboratory benchmark study. Nat Methods. 2018; 15(9):669-676. PMC: 6121742. DOI: 10.1038/s41592-018-0085-0. View