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

Inferring biological networks with output kernel trees.

Pierre Geurts1, Nizar Touleimat, Marie Dutreix

  • 1IBISC FRE CNRS 2873 & Epigenomics project, GENOPOLE, Evry, France. p.geurts@ulg.ac.be

BMC Bioinformatics
|May 12, 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

From prototype to deployment: An EU-centric lifecycle framework for law enforcement AI.

Open research Europe·2026
Same author

Sparing effects of FLASH irradiation in patient-derived lung tissue.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology·2025
Same author

A multidisciplinary view of flash irradiation.

Cancer radiotherapie : journal de la Societe francaise de radiotherapie oncologique·2024
Same author

The AsiDNA™ decoy mimicking DSBs protects the normal tissue from radiation toxicity through a DNA-PK/p53/p21-dependent G1/S arrest.

NAR cancer·2024
Same author

Differential Remodeling of the Oxylipin Pool After FLASH Versus Conventional Dose-Rate Irradiation In Vitro and In Vivo.

International journal of radiation oncology, biology, physics·2024
Same author

Recent Advances in Bioimage Analysis Methods for Detecting Skeletal Deformities in Biomedical and Aquaculture Fish Species.

Biomolecules·2023

This study introduces a novel machine learning method for inferring biological networks, specifically protein-protein interaction and enzyme networks in yeast. The approach offers competitive results and valuable biological insights, aiding experimental design in systems biology.

Area of Science:

  • Systems Biology
  • Computational Biology
  • Machine Learning

Background:

  • Elucidating biological networks is a key challenge in systems biology.
  • Computational methods complement high-throughput technologies for network inference.
  • This work focuses on completing biological networks using diverse experimental data.

Purpose of the Study:

  • To propose a novel machine learning approach for supervised inference of biological networks.
  • To apply and evaluate the method for protein-protein interaction and enzyme network inference in yeast.
  • To demonstrate the method's ability to provide biological insights and validate predictions.

Main Methods:

  • Developed a supervised machine learning approach based on kernelization of regression trees' output space.

Related Experiment Videos

  • Applied the method to infer protein-protein interaction and enzyme networks in yeast (S. cerevisiae).
  • Validated predictions using gene expression data analysis.

    • Main Results:

    • Achieved competitive results for both protein-protein interaction and enzyme network inference compared to existing methods.
    • The method demonstrated interpretability, robustness to irrelevant variables, and input scalability.
    • Provided relevant insights into input data relationships with interaction existence and confirmed biological validity.

    Conclusions:

    • Output kernel tree-based methods are efficient tools for biological network inference from experimental data.
    • The simplicity and interpretability of these methods offer significant value to biologists.
    • This approach aids in designing new experiments and understanding biological systems.