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, T. C.; Hatzakis, Nikos S.

doi:10.7554/elife.60404

Cited by 58 publications

(57 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To extract growth rate kinetics for each individual aggregate, we identified points belonging to the growing aggregate with an approximate Euclidean Minimum Spanning tree segmentation 38 and estimated the area using a gaussian mixture model, based on hierarchical clustering in Fig. 3c and 3d (see Supplementary information for the details) [23][24][25][26] . For isotropic morphologies a single linear growth rate is observed (rx), while for anisotropic morphologies the growth curve consists of two rate components (r1 and r2), as shown in Fig.…”

Section: Resultsmentioning

confidence: 99%

Direct Observation of Heterogeneous Formation of Amyloid Spherulites in Real-time by Super-resolution Microscopy

Zhang

Pinholt

Zhou

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Proteins misfolding and aggregation in the form of fibrils or amyloid containing spherulite-like structures, are involved in a spectrum of degenerative diseases. Current understanding of protein aggregation mechanism primarily relies on conventional spectrometric methods reporting the average growth rates and microscopy readouts of final structures, consequently masking the morphological and growth heterogeneity of the aggregates. Here we developed REal-time kinetics via binding and Photobleaching LOcalization Microscopy (REPLOM) super resolution method to observe directly and quantify the existence and abundance of diverse aggregation morphologies as well as the heterogeneous growth kinetics of each of them. Our results surprisingly revealed insulin aggregation is not exclusively isotropic, but it may also occur anisotropically. Combined with Machine learning we associated growth rates to specific morphological transitions and provided energy barriers and the energy landscape for each aggregation morphology. Our unifying framework of detection and analysis of spherulite growth can be extended to other protein systems and reveal their aggregation processes at single molecule level.

show abstract

Section: Resultsmentioning

confidence: 99%

Direct Observation of Heterogeneous Formation of Amyloid Spherulites in Real-time by Super-resolution Microscopy

Zhang

Pinholt

Zhou

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Logistic regression is a rather simple classifier, and we therefore tested whether further improvement could be made to its prediction accuracy by applying a more complex model. To investigate this, we tested two neural network architectures: a CNN previously proposed for diffusion classification ( 32 ) and a long short-term memory (LSTM) bidirectional neural network (a method previously employed by our laboratory for classifying fluorescence resonance energy transfer [FRET] time series) ( 57 ). The LSTM was trained to classify the variants based on their raw step lengths and position data, and the CNN was trained on raw positions.…”

Section: Fingerprinting Allows For Precise Identification Of Enzymes With Identical Catalytic Efficiencymentioning

confidence: 99%

Single-particle diffusional fingerprinting: A machine-learning framework for quantitative analysis of heterogeneous diffusion

Pinholt

Bohr

Iversen

et al. 2021

Proc. Natl. Acad. Sci. U.S.A.

Self Cite

View full text Add to dashboard Cite

Single-particle tracking (SPT) is a key tool for quantitative analysis of dynamic biological processes and has provided unprecedented insights into a wide range of systems such as receptor localization, enzyme propulsion, bacteria motility, and drug nanocarrier delivery. The inherently complex diffusion in such biological systems can vary drastically both in time and across systems, consequently imposing considerable analytical challenges, and currently requires an a priori knowledge of the system. Here we introduce a method for SPT data analysis, processing, and classification, which we term “diffusional fingerprinting.” This method allows for dissecting the features that underlie diffusional behavior and establishing molecular identity, regardless of the underlying diffusion type. The method operates by isolating 17 descriptive features for each observed motion trajectory and generating a diffusional map of all features for each type of particle. Precise classification of the diffusing particle identity is then obtained by training a simple logistic regression model. A linear discriminant analysis generates a feature ranking that outputs the main differences among diffusional features, providing key mechanistic insights. Fingerprinting operates by both training on and predicting experimental data, without the need for pretraining on simulated data. We found this approach to work across a wide range of simulated and experimentally diverse systems, such as tracked lipases on fat substrates, transcription factors diffusing in cells, and nanoparticles diffusing in mucus. This flexibility ultimately supports diffusional fingerprinting’s utility as a universal paradigm for SPT diffusional analysis and prediction.

show abstract

“…The applications of FRET in biological systems are broad, thanks to advances in instrumentations, analysis software, and site-specific dye-labeling methods. For instance, newly developed scientific CMOS (sCMOS) cameras and the developed smFRET software or algorisms [ 48 , 49 , 50 , 51 ] facilitate high-throughput smFRET imaging and robust data analysis.…”

Section: Single-molecule Förster Resonance Energy Transfer (Smfretmentioning

confidence: 99%

Single-Molecule FRET Imaging of Virus Spike–Host Interactions

2021

Viruses

View full text Add to dashboard Cite

As a major surface glycoprotein of enveloped viruses, the virus spike protein is a primary target for vaccines and anti-viral treatments. Current vaccines aiming at controlling the COVID-19 pandemic are mostly directed against the SARS-CoV-2 spike protein. To promote virus entry and facilitate immune evasion, spikes must be dynamic. Interactions with host receptors and coreceptors trigger a cascade of conformational changes/structural rearrangements in spikes, which bring virus and host membranes in proximity for membrane fusion required for virus entry. Spike-mediated viral membrane fusion is a dynamic, multi-step process, and understanding the structure–function-dynamics paradigm of virus spikes is essential to elucidate viral membrane fusion, with the ultimate goal of interventions. However, our understanding of this process primarily relies on individual structural snapshots of endpoints. How these endpoints are connected in a time-resolved manner, and the order and frequency of conformational events underlying virus entry, remain largely elusive. Single-molecule Förster resonance energy transfer (smFRET) has provided a powerful platform to connect structure–function in motion, revealing dynamic aspects of spikes for several viruses: SARS-CoV-2, HIV-1, influenza, and Ebola. This review focuses on how smFRET imaging has advanced our understanding of virus spikes’ dynamic nature, receptor-binding events, and mechanism of antibody neutralization, thereby informing therapeutic interventions.

show abstract

DeepFRET, a software for rapid and automated single-molecule FRET data classification using deep learning

Cited by 58 publications

References 67 publications

Direct Observation of Heterogeneous Formation of Amyloid Spherulites in Real-time by Super-resolution Microscopy

Direct Observation of Heterogeneous Formation of Amyloid Spherulites in Real-time by Super-resolution Microscopy

Single-particle diffusional fingerprinting: A machine-learning framework for quantitative analysis of heterogeneous diffusion

Single-Molecule FRET Imaging of Virus Spike–Host Interactions

Contact Info

Product

Resources

About