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

Detecting particles in cryo-EM micrographs using learned features.

Satya P Mallick1, Yuanxin Zhu, David Kriegman

  • 1Department of Electrical and Computer Engineering, University of California at San Diego, La Jolla, CA 92093, USA. spmallick@graphics.ucsd.edu

Journal of Structural Biology
|April 7, 2004
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

Serpinh1 promotes fracture healing by enhancing osteogenesis via activation of the Wnt/β-catenin signaling pathway.

Biochemical and biophysical research communications·2026
Same author

Alfalfa Polysaccharide Improves Rabbit Growth by Modulating Gut Microbiota and Suppressing Inflammation Through PPARγ/NF-κB Pathway.

International journal of molecular sciences·2026
Same author

HP1 enhances radio- and chemotherapy resistance in osteosarcoma via PARP1-dependent transcriptional repression and HR repair.

Cancer letters·2025
Same author

GPX4: A Key Regulator of Mitochondrial Function and Glycolysis in Pulmonary Artery Smooth Muscle Cells.

Journal of cardiovascular pharmacology·2025
Same author

Cytogenetic risk stratification combined with minimal residual disease status influences the therapeutic outcome and prognosis of multiple myelomas.

Scientific reports·2025
Same author

Radiographic features and subtypes of congenital thumb duplication type C3 according to Wu et al. and their potential implications for surgical management: new classification and preliminary results.

BMC musculoskeletal disorders·2024
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
Same journal

The mantis shrimp eye imaged in 3D using 4th generation synchrotron multiscale phase contrast tomography.

Journal of structural biology·2026
See all related articles

A novel Adaboost learning algorithm offers fast and generic particle detection in cryo-electron microscopy (cryo-EM) images. This method achieves structural resolution comparable to manual selection, improving efficiency in biological structure determination.

Area of Science:

  • * Cryo-electron microscopy (cryo-EM) and structural biology.
  • * Machine learning applications in scientific imaging.

Background:

  • * Accurate particle detection is crucial for high-resolution 3D reconstruction in cryo-EM.
  • * Manual particle selection is labor-intensive and time-consuming.
  • * Existing automated methods may be limited by particle shape or size.

Purpose of the Study:

  • * To develop a new, automated learning-based approach for particle detection in cryo-electron micrographs.
  • * To adapt successful face detection algorithms for cryo-EM particle identification.
  • * To evaluate the performance and efficiency of the Adaboost algorithm for cryo-EM data.

Main Methods:

  • * Utilized the Adaboost learning algorithm, a discriminative approach, for particle detection.

Related Experiment Videos

  • * Trained the algorithm using examples of particles and non-particle images.
  • * Applied the method to a dataset of keyhole lympet hemocyanin (KLH) cryo-EM images.

    • Main Results:

    • * The Adaboost algorithm demonstrated fast detection (10 seconds on a 1.3 GHz processor).
    • * The method is generic, not restricted by particle shape or size.
    • * Reconstructed the 3D structure of KLH at 23.2 Å resolution using automatically detected particles, matching manual selection results.

    Conclusions:

    • * The Adaboost learning-based approach provides an efficient and effective automated solution for particle detection in cryo-EM.
    • * This method significantly reduces the manual effort required for particle selection.
    • * The achieved resolution is comparable to traditional manual methods, validating the approach for structural biology research.