RT Journal Article
SR Electronic
T1 Deep-Learning Assisted, Single-molecule Imaging analysis (Deep-LASI) of multi-color DNA Origami structures
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2023.01.31.526220
DO 10.1101/2023.01.31.526220
A1 Simon Wanninger
A1 Pooyeh Asadiatouei
A1 Johann Bohlen
A1 Clemens-Bässem Salem
A1 Philip Tinnefeld
A1 Evelyn Ploetz
A1 Don C. Lamb
YR 2023
UL http://biorxiv.org/content/early/2023/02/03/2023.01.31.526220.abstract
AB Single-molecule experiments have changed the way we investigate the physical world but data analysis is typically time-consuming and prone to human bias. Here, we present Deep-LASI (Deep-Learning Assisted Single-molecule Imaging analysis), a software package consisting of an ensemble of deep neural networks to rapidly analyze single-, two- and three-color single-molecule data, in particular from single-molecule Förster Resonance Energy Transfer (FRET) experiments. Deep-LASI automatically sorts single molecule traces, determines FRET correction factors and classifies the state transitions of dynamic traces, all in ~20-100 ms per trajectory. We thoroughly 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.Competing Interest StatementThe authors have declared no competing interest.