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

Exploring bias in the Protein Data Bank using contrast classifiers.

K Peng1, Z Obradovic, S Vucetic

  • 1Center for Information Science and Technology, Temple University, 1805 N Broad St, Philadelphia, PA 19122, USA.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
|March 3, 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

[Familial florid cemento-osseous dysplasia with ANO5 mutation: a case report].

Zhonghua kou qiang yi xue za zhi = Zhonghua kouqiang yixue zazhi = Chinese journal of stomatology·2026
Same author

[A multicenter study on the classification and repair effects of stage 4 pressure injury in ischial tuberosity in elderly patients].

Zhonghua shao shang yu chuang mian xiu fu za zhi·2025
Same author

A thorough experimental assessment of THz-TDS plasma diagnostic techniques for nuclear fusion applications.

The Review of scientific instruments·2024
Same author

Determinants of depressive symptoms at individual, school and province levels: a national survey of 398,520 Chinese children and adolescents.

Public health·2024
Same author

[Reference values for carotid artery intima-media thickness among community adult dwellers in Shenzhen City].

Zhonghua yu fang yi xue za zhi [Chinese journal of preventive medicine]·2023
Same author

Development of a novel combined nomogram integrating deep-learning-assisted CT texture and clinical-radiological features to predict the invasiveness of clinical stage IA part-solid lung adenocarcinoma: a multicentre study.

Clinical radiology·2023

This study reveals biases in the Protein Data Bank (PDB). A novel contrast classifier shows transmembrane and disordered regions are underrepresented, while enzyme sites are overrepresented, guiding future protein selection.

Area of Science:

  • Structural biology
  • Bioinformatics
  • Computational biology

Background:

  • The Protein Data Bank (PDB) is a primary resource for protein structures.
  • Understanding biases in PDB is crucial for accurate biological interpretation and experimental design.
  • SWISS-PROT is considered a representative of natural protein sequence diversity.

Purpose of the Study:

  • To quantify biases in the Protein Data Bank (PDB) using a novel contrast classifier approach.
  • To identify protein features and regions that are underrepresented or overrepresented in the PDB.
  • To assess the utility of contrast classifiers for selecting proteins for structural characterization.

Main Methods:

  • Trained an ensemble of neural network classifiers (contrast classifier) to distinguish between PDB and SWISS-PROT sequence subsets.

Related Experiment Videos

  • Analyzed distributional differences to identify underrepresented and overrepresented protein properties in PDB.
  • Applied the contrast classifier to SWISS-PROT sequences to measure PDB representation bias.

    • Main Results:

    • Transmembrane, signal, disordered, and low complexity regions are significantly underrepresented in the PDB.
    • Disulfide bonds, metal binding sites, and enzyme activity sites are overrepresented in the PDB.
    • Hydroxylation and phosphorylation sites are underrepresented, while acetylation sites are overrepresented.

    Conclusions:

    • Contrast classifiers effectively measure PDB representation bias for various protein properties.
    • Identified biases highlight areas for improvement in structural data collection.
    • Findings can guide the selection of target proteins for structural characterization to enhance PDB diversity.