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

Predicting zinc binding at the proteome level.

Andrea Passerini1, Claudia Andreini, Sauro Menchetti

  • 1Machine Learning and Neural Networks Group, Dipartimento di Sistemi e Informatica, Università degli Studi di Firenze, Italy. passerini@dsi.unifi.it

BMC Bioinformatics
|February 7, 2007
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

Author Correction: Mitochondrial fission links ECM mechanotransduction to metabolic redox homeostasis and metastatic chemotherapy resistance.

Nature cell biology·2026
Same author

Ill Fate of Rectal Mucinous Adenocarcinoma: A Defect in Immunosurveillance or a Mucin Coating Effect?-The IMMUNOREACT 20 Study.

Cancers·2026
Same author

Manufacturing 3D aortic root models for in vitro assessment of calcific aortic valve stenosis.

Annals of biomedical engineering·2026
Same author

Gut microbiota-associated predictors as biomarkers of neoadjuvant treatment response in rectal cancer-a systematic review.

British journal of cancer·2026
Same author

Towards a more reliable assessment of aortic diameters using a Bayesian Z-score.

Scientific reports·2026
Same author

Targeting peptidyl-arginine deiminase 4 suppresses SARS-CoV-2 replication and modulates the inflammatory response.

iScience·2026

A new machine learning method accurately predicts zinc-binding sites in proteins by analyzing amino acid pairs. This automated tool improves metalloprotein identification and discovers novel zinc-binding sites, aiding experimental research.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Structural Biology

Background:

  • Metalloproteins bind metal ions for biological function, regulation, or structure.
  • Predicting metal-binding properties and identifying metalloproteins at a proteome-wide scale remains challenging.
  • Current knowledge of metalloproteins is incomplete due to experimental and predictive limitations.

Purpose of the Study:

  • To develop a machine learning method for predicting zinc-binding sites in proteins.
  • To improve the identification of metalloproteins using computational approaches.
  • To identify novel, previously uncharacterized zinc-binding sites.

Main Methods:

  • Development of a machine learning predictor using support vector machines.
  • Training the predictor on known zinc-binding sites and non-metalloproteins.

Related Experiment Videos

  • Utilizing pairwise amino acid residue correlations to enhance prediction accuracy.

    • Main Results:

    • The developed predictor accurately identifies zinc-binding residues.
    • Modeling correlations between nearby residues significantly improves prediction performance.
    • Application to the human proteome shows good agreement with existing data and identifies novel zinc-binding sites validated by structural modeling.

    Conclusions:

    • The approach provides a highly automated and accurate tool for metalloprotein identification.
    • The method offers significant improvements over traditional 1D prediction approaches by incorporating residue correlations.
    • Identifies unprecedented metal sites, offering valuable insights for experimental researchers.