scholarly journals CryoDiscoveryTM: A Machine Learning Platform for Automated Cryo-electron Microscopy Particle Classification

2020 ◽  
Vol 26 (S2) ◽  
pp. 2308-2310
Author(s):  
Narasimha Kumar ◽  
John Harkness ◽  
Craig Yoshioka ◽  
Shiva Aditham ◽  
Tuan Phamdo ◽  
...  
Keyword(s):  
Electron Microscopy ◽  
Machine Learning ◽  
Learning Platform ◽  
Cryo Electron Microscopy ◽  
Particle Classification

scholarly journals Real-time object locator for cryo-EM data collection --- You only navigate EM once ---

2021 ◽  
Author(s):  
Koji Yonekura ◽  
Saori Maki-Yonekura ◽  
Hisashi Naitow ◽  
Tasuku Hamaguchi ◽  
Kiyofumi Takaba
Keyword(s):  
Electron Microscopy ◽  
Machine Learning ◽  
Electron Diffraction ◽  
Data Collection ◽  
Real Time ◽  
Single Particle ◽  
Detection System ◽  
Target Object ◽  
Electron Crystallography ◽  
Cryo Electron Microscopy

In cryo-electron microscopy (cryo-EM) data collection, locating a target object is the most error-prone. Here, we present a machine learning-based approach with a real-time object locator named yoneoLocr using YOLO, a well-known object detection system. Implementation showed its effectiveness in rapidly and precisely locating carbon holes in single particle cryo-EM and for locating crystals and evaluating electron diffraction (ED) patterns in automated cryo-electron crystallography (cryo-EX) data collection.

scholarly journals Machine learning-based real-time object locator/evaluator for cryo-EM data collection

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Koji Yonekura ◽  
Saori Maki-Yonekura ◽  
Hisashi Naitow ◽  
Tasuku Hamaguchi ◽  
Kiyofumi Takaba
Keyword(s):  
Electron Microscopy ◽  
Machine Learning ◽  
Data Collection ◽  
Real Time ◽  
Detection System ◽  
Target Object ◽  
Accurate Data ◽  
Electron Crystallography ◽  
Cryo Electron Microscopy ◽  
Diffraction Patterns

AbstractIn cryo-electron microscopy (cryo-EM) data collection, locating a target object is error-prone. Here, we present a machine learning-based approach with a real-time object locator named yoneoLocr using YOLO, a well-known object detection system. Implementation shows its effectiveness in rapidly and precisely locating carbon holes in single particle cryo-EM and in locating crystals and evaluating electron diffraction (ED) patterns in automated cryo-electron crystallography (cryo-EX) data collection. The proposed approach will advance high-throughput and accurate data collection of images and diffraction patterns with minimal human operation.

New challenges to image processing posed by cryo-Electron microscopy of single particles

1991 ◽  
Vol 49 ◽  
pp. 422-423
Author(s):  
Joachim Frank
Keyword(s):  
Electron Microscopy ◽  
Phase Contrast ◽  
Particle Orientation ◽  
Single Particles ◽  
Contrast Transfer Function ◽  
Virtual Absence ◽  
Cryo Electron Microscopy ◽  
Spatial Frequencies ◽  
New Challenges ◽  
Particle Images

Compared with images of negatively stained single particle specimens, those obtained by cryo-electron microscopy have the following new features: (a) higher “signal” variability due to a higher variability of particle orientation; (b) reduced signal/noise ratio (S/N); (c) virtual absence of low-spatial-frequency information related to elastic scattering, due to the properties of the phase contrast transfer function (PCTF); and (d) reduced resolution due to the efforts of the microscopist to boost the PCTF at low spatial frequencies, in his attempt to obtain recognizable particle images.

Enhanced information from biological materials through technological improvements in cryo-electron microscopy

1992 ◽  
Vol 50 (1) ◽  
pp. 788-789
Author(s):  
Marc J.C. de Jong ◽  
Wim M. Busing ◽  
Max T. Otten
Keyword(s):  
Electron Microscopy ◽  
Electron Beam ◽  
Biological Materials ◽  
Electron Crystallography ◽  
Cryo Electron Microscopy ◽  
Transmission Electron ◽  
The Many ◽  
Technological Improvements ◽  
Beam Damage

Biological materials damage rapidly in the electron beam, limiting the amount of information that can be obtained in the transmission electron microscope. The discovery that observation at cryo temperatures strongly reduces beam damage (in addition to making it unnecessaiy to use chemical fixatives, dehydration agents and stains, which introduce artefacts) has given an important step forward to preserving the ‘live’ situation and makes it possible to study the relation between function, chemical composition and morphology.Among the many cryo-applications, the most challenging is perhaps the determination of the atomic structure. Henderson and co-workers were able to determine the structure of the purple membrane by electron crystallography, providing an understanding of the membrane's working as a proton pump. As far as understood at present, the main stumbling block in achieving high resolution appears to be a random movement of atoms or molecules in the specimen within a fraction of a second after exposure to the electron beam, which destroys the highest-resolution detail sought.

Study of eukaryotic flagellar components by cryo-electron microscopy

1986 ◽  
Vol 44 ◽  
pp. 98-101
Author(s):  
John M. Murray ◽  
Rob Ward
Keyword(s):  
Electron Microscopy ◽  
Primary Motion ◽  
Cryo Electron Microscopy ◽  
Cross Links ◽  
Cilia And Flagella

The eukaryotic flagellum is constructed from 11 parallel tubular elements arranged as 9 peripheral fibers (doublet microtubules) and 2 central fibers (singlet microtubules). The primary motion generating component has been found to be arranged as axially periodic “arms” bridging the adjacent doublets. The dynein, comprising the arms, has been isolated and characterized from several different cilia and flagella. Various radial and azimuthal cross-links stabilize the axially aligned microtubules, and probably play some role in controlling the form of the flagella beat cycle.

Sign in / Sign up

Export Citation Format

Share Document