Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

An automatic particle pickup method using a neural network applicable to low-contrast electron micrographs.

T Ogura1, C Sato

  • 1Neuroscience Research Institute, National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, 305-8568, Japan.

Journal of Structural Biology
|June 8, 2002
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Impact of deep learning on radiologists and radiology residents in detecting breast cancer on CT: a cross-vendor test study.

Clinical radiology·2023
Same author

Optimisation of Radiation Therapy in Bladder Preservation Therapy for Patients With Clinical Stage T2N0M0 Bladder Cancer.

Clinical oncology (Royal College of Radiologists (Great Britain))·2022
Same author

Hailey-Hailey disease with a novel variant, c.1978dupG, in the ATP2C1 gene.

Clinical and experimental dermatology·2020
Same author

CT findings in 11 patients with TAFRO syndrome: a variant of multicentric Castleman's disease.

Clinical radiology·2017
Same author

Releasing Mechanism of Neurotrophic Factors via Polysialic Acid.

Vitamins and hormones·2017
Same author

A laser-induced pulsed water jet for layer-selective submucosal dissection of the esophagus.

Laser therapy·2016
Same journal

MLAC: MicroED-assisted ligand structure analysis in complexes and its application to hERG-ligand complexes.

Journal of structural biology·2026
Same journal

Ultrastructural evidence of autophagy-related processes and mitochondrial remodeling in the myxozoan parasite Henneguya piaractus.

Journal of structural biology·2026
Same journal

Architecture and dynamics of a supramolecular oxygen transport system in human homogentisate 1,2-Dioxygenase.

Journal of structural biology·2026
Same journal

Connecting pathways between mineralized fibrocartilage and bone at the Achilles tendon insertion.

Journal of structural biology·2026
Same journal

Structural and functional characterization of thermostable EstS1 esterase for BHET degradation.

Journal of structural biology·2026
Same journal

Following the white rabbit: multiscale 2D3D correlative imaging of bone structure.

Journal of structural biology·2026
See all related articles

A new automated particle recognition method uses a three-layer neural network to improve 3D reconstruction from electron microscopy. This technique enhances the detection of faint, noisy images and small proteins, requiring fewer particles for accurate results.

Area of Science:

  • Structural biology
  • Biophysics
  • Computational biology

Background:

  • Three-dimensional (3D) reconstruction from electron micrographs is crucial for determining protein structures at high resolution.
  • Traditional methods require selecting over 10,000 single-particle projection images, which is labor-intensive and challenging for faint or noisy data.
  • Existing automated detection algorithms are effective for large, symmetric protein complexes but have limitations in broader applications.

Purpose of the Study:

  • To develop a novel automated particle recognition and pickup procedure for electron microscopy.
  • To enhance the efficiency and applicability of 3D reconstruction by reducing the number of required particles.
  • To demonstrate the method's effectiveness on challenging datasets, including faint and noisy electron micrographs.

Related Experiment Videos

Main Methods:

  • Implementation of a three-layer neural network for automated particle recognition and selection.
  • Training the neural network with a significantly reduced dataset (200 selected particles).
  • Validation of the method's performance on various electron micrograph qualities and protein sizes.

Main Results:

  • The developed method demonstrates a wider application range compared to existing automated procedures.
  • Successful detection of protein images from both faint and noisy electron micrographs.
  • The algorithm can accurately identify images of proteins as small as 200 kDa with minimal learning data.

Conclusions:

  • The three-layer neural network-based automated particle recognition offers a more versatile and efficient approach to 3D electron microscopy.
  • This method significantly lowers the data requirement for structural analysis, making high-resolution 3D reconstruction more accessible.
  • The procedure is particularly valuable for analyzing challenging samples, advancing structural biology research.