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 new pairwise kernel for biological network inference with support vector machines.

Jean-Philippe Vert1, Jian Qiu, William S Noble

  • 1Centre for Computational Biology, Ecole des Mines de Paris, 35 rue Saint-Honoré, 77300 Fontainebleau, France. Jean-Philippe.Vert@ensmp.fr

BMC Bioinformatics
|February 27, 2008
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

Identifying Novel Estrogenic Mitochondrial Targets in Hypothalamic Proopiomelanocortin Neurons by Chemoproteomics.

bioRxiv : the preprint server for biology·2026
Same author

Blockade of FGFR1 Trafficking to the Cell Surface Results in the Partial Mistargeting of the Receptor to Peroxisomes.

FASEB journal : official publication of the Federation of American Societies for Experimental Biology·2026
Same author

Ionic Liquid-Laden Mesoporous Silica for Ultrafast Gold Recovery Via Nanoconfined Interfacial Anion Exchange.

The journal of physical chemistry letters·2026
Same author

The role of leptin in reproductive dysfunction in patients with varicocele: a systematic review and meta-analysis.

Frontiers in urology·2026
Same author

Regulation of Pore Evolution via Progressive Electroporation Enhanced Intracellular Molecule Transport.

Research (Washington, D.C.)·2026
Same author

GGAs: Regulation of Multiple Sorting Pathways and Potential Association With Human Diseases.

Journal of cellular and molecular medicine·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
Same journal

NAP: an open source pipeline for cross-domain microbiome profiling using Nanopore sequencing-derived amplicon data.

BMC bioinformatics·2026
Same journal

SurvGME: an R package for survival analysis with graphical and measurement error models.

BMC bioinformatics·2026
See all related articles

We developed a new method for inferring biological networks using a metric learning pairwise kernel within support vector machines (SVMs). This approach improves direct inference from heterogeneous genomic data.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Bioinformatics research increasingly focuses on inferring biological networks (gene regulation, protein interactions).
  • Supervised inference of network edges commonly uses heterogeneous data like gene expression and protein sequences.
  • Distinguishing between direct and indirect inference modes is crucial for network analysis.

Purpose of the Study:

  • To propose a novel supervised approach for direct inference of biological network edges.
  • To introduce the metric learning pairwise kernel for support vector machine (SVM) algorithms.
  • To enhance the accuracy of inferring pairwise relationships from diverse biological datasets.

Main Methods:

  • Formulated direct inference as a distance metric learning problem.

Related Experiment Videos

  • Developed a convex optimization approach, relaxed to a support vector machine (SVM) algorithm.
  • Introduced a novel 'metric learning pairwise kernel' for SVMs to handle heterogeneous data.

    • Main Results:

    • The metric learning pairwise kernel enables supervised classification and inference of pairwise relationships.
    • Demonstrated improved performance on real biological networks and genomic datasets compared to existing SVM methods.
    • Showed that combining the new kernel with existing ones consistently yields superior results.

    Conclusions:

    • The metric learning pairwise kernel offers a new formulation for inferring pairwise relationships using SVMs.
    • This method achieves state-of-the-art results for biological network inference from heterogeneous genomic data.