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

A likelihood approach to analysis of network data.

Carsten Wiuf1, Markus Brameier, Oskar Hagberg

  • 1Bioinformatics Research Center, University of Aarhus, Høegh-Guldbergsgade 10, Building 1090, 8000 Aarhus C, Denmark. wiuf@birc.au.dk

Proceedings of the National Academy of Sciences of the United States of America
|May 10, 2006
PubMed
Summary

This study introduces a novel full-likelihood approach for analyzing network growth models. This method accurately estimates parameters and aids in understanding complex biological networks like protein interactions.

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

Expected survival is decreased in hereditary hemorrhagic telangiectasia: Results from a population-based registry study.

Journal of internal medicine·2026
Same author

AI-supported mammography screening: measuring benefit - Authors' reply.

Lancet (London, England)·2026
Same author

Molecular noise modulates transitions in the cell-fate differentiation landscape.

NPJ systems biology and applications·2026
Same author

Fifty years since a simple equation described the chaos of biology.

Nature·2026
Same author

Lymph node surgery after centralization of penile cancer care in Sweden: Extent of use and complications.

BJUI compass·2026
Same author

Application of the International Bladder Cancer Group prediction model for recurrence-free survival on a national cohort of primary intermediate risk non-muscle invasive bladder cancer.

Scandinavian journal of urology·2026

Area of Science:

  • Network science
  • Computational biology
  • Statistical modeling

Background:

  • Network data analysis commonly uses summary statistics and bootstrap methods.
  • Existing methods may not fully capture the complexity of network growth dynamics.

Purpose of the Study:

  • To present a full-likelihood approach for estimating parameters in general network growth models.
  • To develop an importance sampling scheme for analyzing large networks.

Main Methods:

  • Developed a full-likelihood approach for network growth models.
  • Implemented an importance sampling scheme for likelihood approximation.
  • Applied the method to the Caenorhabditis elegans protein interaction network.

Main Results:

Related Experiment Videos

  • Successfully estimated growth parameters for a complex biological network.
  • Demonstrated the efficacy of the full-likelihood and importance sampling methods.
  • Provided a robust framework for network inference and model analysis.

Conclusions:

  • The full-likelihood approach offers a powerful tool for network data analysis.
  • Importance sampling enables scalable inference for large-scale network models.
  • This methodology advances the understanding of biological network formation and evolution.