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 co-complexed protein pairs using genomic and proteomic data integration.

Lan V Zhang1, Sharyl L Wong, Oliver D King

  • 1Department of Biological Chemistry and Molecular Pharmacology, Harvard Medical School, Boston, MA 02115, USA. lan_zhang@student.hms.harvard.edu

BMC Bioinformatics
|April 20, 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

Image-based, pooled phenotyping reveals multidimensional, disease-specific variant effects.

Cell·2026
Same author

Global genetic interaction network of a human cell maps conserved principles and informs functional interpretation of gene co-essentiality profiles.

Cell·2026
Same author

Experimental assessment of AI-based interactome mapping.

Nature communications·2026
Same author

Selective chr21 homolog silencing reveals polymorphisms influence the epigenetic silencing and functional dosage of RWDD2B.

American journal of human genetics·2026
Same author

A scalable approach to resolving variants of uncertain significance.

bioRxiv : the preprint server for biology·2026
Same author

Mapping the Functional Landscape of <i>KCNQ1</i> to Define Ion Channel Mechanisms and Arrhythmia Risk.

medRxiv : the preprint server for health sciences·2025

This study integrates multiple datasets using a probabilistic decision tree to accurately predict protein complexes. The enhanced method improves sensitivity and specificity over traditional techniques like yeast two-hybrid and APMS.

Area of Science:

  • Proteomics
  • Computational Biology
  • Systems Biology

Background:

  • Identifying protein-protein interactions and complexes is crucial in proteomics.
  • High-throughput methods like yeast two-hybrid (Y2H) and affinity purification coupled with mass spectrometry (APMS) have limitations, including high false-positive rates.
  • Integrating diverse datasets can improve the prediction of protein complex relationships.

Purpose of the Study:

  • To develop a more accurate method for predicting co-complexed protein pairs (CCPs).
  • To leverage a supervised machine learning approach to integrate various data sources for improved prediction.
  • To enhance the identification of functional protein partnerships within organisms.

Main Methods:

  • Utilized a supervised machine learning approach, specifically a probabilistic decision tree.

Related Experiment Videos

  • Integrated high-throughput protein interaction datasets (Y2H, APMS) with other gene- and protein-pair characteristics.
  • Employed a reference set from the MIPS complex catalogue for training and validation.

    • Main Results:

    • The probabilistic decision tree approach significantly improved prediction sensitivity and specificity compared to Y2H or APMS alone or combined.
    • Top predictions not initially annotated as CCPs showed validation in separate databases (e.g., YPD), suggesting potential novel complexes.
    • The method effectively identified likely co-complexed protein pairs, offering new hypotheses for experimental investigation.

    Conclusions:

    • The probabilistic decision tree is a successful approach for predicting co-complexed protein pairs.
    • This computational method enhances the accuracy of protein complex identification.
    • Top predictions serve as valuable, testable hypotheses for future experimental validation in proteomics.