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

Protein ranking by semi-supervised network propagation.

Jason Weston1, Rui Kuang, Christina Leslie

  • 1NEC LABS AMERICA, 4 Independence Way, Princeton, NJ, USA. jasonw@nec-labs.com

BMC Bioinformatics
|May 26, 2006
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

Long-term Survival Rates in U.S. Veterans Shunted for iNPH: A Focused Analysis of Radiological Predictors.

World neurosurgery·2026
Same author

Author Correction: Ontogeny and transcriptional regulation of Thetis cells.

Nature·2026
Same author

drGT: Interpretable Drug Response Prediction with Attention-Guided Gene Attribution on a Drug-Cell-Gene Heterogeneous Graph.

BMC bioinformatics·2026
Same author

Prioritizing peptides for targeted mass spectrometry experiments using deep learning.

bioRxiv : the preprint server for biology·2026
Same author

Embryo-scale Visual Cell Sorting reveals a conserved transcriptomic signature of nucleolar size linked to proteostasis.

bioRxiv : the preprint server for biology·2026
Same author

Prediction and functional interpretation of inter-chromosomal genome architecture from DNA sequence with TwinC.

Nature communications·2026
Same journal

Research on multi-trait genome association study method based on Shannon information entropy.

BMC bioinformatics·2026
Same journal

A multi-view feature fusion framework with interpretable graph convolution for predicting microbe-drug associations.

BMC bioinformatics·2026
Same journal

Covariance decomposition for distance based species tree estimation.

BMC bioinformatics·2026
Same journal

SNPio: a Python interface for population genomic data processing.

BMC bioinformatics·2026
Same journal

SpaHNR: a spatial domain identification method via sparse attention-based hierarchical node representation and multi-view contrastive learning.

BMC bioinformatics·2026
Same journal

OpenIMC: an open-source platform for analyzing single-cell and spatial proteomics by imaging mass cytometry.

BMC bioinformatics·2026
See all related articles

RankProp, a network-based algorithm, improves protein similarity searches over traditional methods like PSI-BLAST. A semi-supervised version using labeled data further enhances remote relationship detection in biological sequence databases.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning

Background:

  • Biologists search DNA/protein databases for evolutionary or functional relationships.
  • Traditional methods (e.g., BLAST, PSI-BLAST) focus on local sequence alignments, potentially missing subtle similarities.
  • Machine learning leverages global network structure for detecting remote relationships.

Purpose of the Study:

  • Review and enhance the RankProp algorithm for protein similarity searching.
  • Introduce and evaluate a semi-supervised version of RankProp using labeled data.
  • Improve detection of remote evolutionary and functional relationships in biological sequences.

Main Methods:

  • RankProp utilizes a diffusion operation on a weighted protein similarity network.

Related Experiment Videos

  • A semi-supervised approach incorporates labeled examples for network learning and edge weight estimation.
  • Three methods for integrating label information are explored: model selection, network learning, and edge weight estimation.

    • Main Results:

    • RankProp demonstrates significant improvement over PSI-BLAST on a curated protein structure database.
    • Labeled data enables learning a network without parameter estimation, outperforming the original RankProp.
    • The semi-supervised RankProp effectively identifies remote protein similarities.

    Conclusions:

    • Combining labeled and unlabeled data maximizes information extraction from biological networks.
    • Exploiting both local and global network structures is crucial for comprehensive sequence analysis.
    • Semi-supervised RankProp offers a powerful approach for enhanced biological sequence similarity searches.