PickYOLO: Fast deep learning particle detector for annotation of cryo electron tomograms
Standard
PickYOLO: Fast deep learning particle detector for annotation of cryo electron tomograms. / Genthe, Erik; Miletic, Sean; Tekkali, Indira; Hennell James, Rory; Marlovits, Thomas C; Heuser, Philipp.
in: J STRUCT BIOL, Jahrgang 215, Nr. 3, 09.2023, S. 107990.Publikationen: SCORING: Beitrag in Fachzeitschrift/Zeitung › SCORING: Zeitschriftenaufsatz › Forschung › Begutachtung
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - PickYOLO: Fast deep learning particle detector for annotation of cryo electron tomograms
AU - Genthe, Erik
AU - Miletic, Sean
AU - Tekkali, Indira
AU - Hennell James, Rory
AU - Marlovits, Thomas C
AU - Heuser, Philipp
N1 - Copyright © 2023. Published by Elsevier Inc.
PY - 2023/9
Y1 - 2023/9
N2 - Particle localization (picking) in digital tomograms is a laborious and time-intensive step in cryogenic electron tomography (cryoET) analysis often requiring considerable user involvement, thus becoming a bottleneck for automated cryoET subtomogram averaging (STA) pipelines. In this paper, we introduce a deep learning framework called PickYOLO to tackle this problem. PickYOLO is a super-fast, universal particle detector based on the deep-learning real-time object recognition system YOLO (You Only Look Once), and tested on single particles, filamentous structures, and membrane-embedded particles. After training with the centre coordinates of a few hundred representative particles, the network automatically detects additional particles with high yield and reliability at a rate of 0.24-3.75 s per tomogram. PickYOLO can automatically detect number of particles comparable to those manually selected by experienced microscopists. This makes PickYOLO a valuable tool to substantially reduce the time and manual effort needed to analyse cryoET data for STA, greatly aiding in high-resolution cryoET structure determination.
AB - Particle localization (picking) in digital tomograms is a laborious and time-intensive step in cryogenic electron tomography (cryoET) analysis often requiring considerable user involvement, thus becoming a bottleneck for automated cryoET subtomogram averaging (STA) pipelines. In this paper, we introduce a deep learning framework called PickYOLO to tackle this problem. PickYOLO is a super-fast, universal particle detector based on the deep-learning real-time object recognition system YOLO (You Only Look Once), and tested on single particles, filamentous structures, and membrane-embedded particles. After training with the centre coordinates of a few hundred representative particles, the network automatically detects additional particles with high yield and reliability at a rate of 0.24-3.75 s per tomogram. PickYOLO can automatically detect number of particles comparable to those manually selected by experienced microscopists. This makes PickYOLO a valuable tool to substantially reduce the time and manual effort needed to analyse cryoET data for STA, greatly aiding in high-resolution cryoET structure determination.
U2 - 10.1016/j.jsb.2023.107990
DO - 10.1016/j.jsb.2023.107990
M3 - SCORING: Journal article
C2 - 37364763
VL - 215
SP - 107990
JO - J STRUCT BIOL
JF - J STRUCT BIOL
SN - 1047-8477
IS - 3
ER -