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

Quantitative self-organizing maps for clustering electron tomograms.

A Pascual-Montano1, K A Taylor, H Winkler

  • 1Centro Nacional de Biotecnología-CSIC, Campus Universidad Autónoma, 28049 Madrid, Spain.

Journal of Structural Biology
|August 6, 2002
PubMed
Summary

This study introduces a new neural network method for clustering 3D reconstructions from tomography. The technique effectively identifies similar structural patterns in biological specimens, aiding scientific discovery.

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

Ureteric stent versus percutaneous nephrostomy for acute ureteral obstruction - clinical outcome and quality of life: a bi-center prospective study.

BMC urology·2019
Same author

An unusual radiologic appearance of Wilms tumor.

Urology case reports·2018
Same author

Major histocompatibility complex genes partly explain early survival in house sparrows.

Scientific reports·2017
Same author

[X‑ray of the thoracic and lumbar spine in injured children and adolescents : Incidence, fracture rates and therapeutic consequences].

Der Unfallchirurg·2016
Same author

The Use of Inflammatory Cytokine Levels as a Measure of Symptom Distress and Quality of Life in Patients With Overactive Bladder.

Journal of minimally invasive gynecology·2016
Same author

[Associated injuries with greater tuberosity fractures : Mechanism of injury, diagnostics, treatment].

Der Unfallchirurg·2016

Area of Science:

  • Structural biology
  • Computational biology
  • Biophysics

Background:

  • Tomography is crucial for determining complex biological specimen architectures.
  • Analyzing large datasets of 3D reconstructions can reveal emergent structural patterns.

Purpose of the Study:

  • To present a novel quantitative approach for clustering 3D reconstructions.
  • To develop an unsupervised classification method for analyzing large sets of tomographic data.

Main Methods:

  • A new variant of a self-organizing neural network was formulated.
  • The algorithm uses a rigorous mathematical approach for unsupervised classification of noisy 3D data.
  • The method identifies representative items to approximate the input data's probability density.

Related Experiment Videos

Main Results:

  • The proposed neural network approach was applied to identify similar 3D motifs in insect flight muscle tomograms.
  • Experimental results demonstrate the technique's suitability for pattern identification in complex tomographic datasets.
  • The method successfully clusters 3D reconstructions, revealing underlying structural similarities.

Conclusions:

  • The developed neural network provides a powerful new tool for the electron microscopy community.
  • This approach facilitates the exploration of large tomogram datasets to uncover complex biological patterns.
  • The method enables unsupervised classification and pattern discovery in structural biology research.