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

Kernel-imbedded Gaussian processes for disease classification using microarray gene expression data.

Xin Zhao1, Leo Wang-Kit Cheung

  • 1Department of Information and Computer Sciences, University of Hawaii, 1680 East-West Road, Honolulu, Hawaii 96822, USA. xinz@hawaii.edu <xinz@hawaii.edu>

BMC Bioinformatics
|March 3, 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

MRDviz: an integrated platform for interactive visualization and joint simulation of minimal residual disease trajectories and associated survival outcomes.

Bioinformatics advances·2026
Same author

Functional data for the diagnosis of patellofemoral laxity obtained by MRI during quadriceps isometric contraction.

Orthopedics·2013
Same author

Oriented arrays of polyaniline nanorods grown on graphite nanosheets for an electrochemical supercapacitor.

Langmuir : the ACS journal of surfaces and colloids·2012
Same author

Fast, long-scan-range pump-probe measurement based on asynchronous sampling using a dual-wavelength mode-locked fiber laser.

Optics express·2012
Same author

Outcome after transfer of intercostal nerves to the nerve of triceps long head in 25 adult patients with total brachial plexus root avulsion injury.

Journal of neurosurgery·2012
Same author

Identification of novel genes involved in DNA damage response by screening a genome-wide Schizosaccharomyces pombe deletion library.

BMC genomics·2012
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
Same journal

SimMapNet: a Bayesian framework for gene regulatory network inference using gene ontology similarities as external hint.

BMC bioinformatics·2026
Same journal

Dual channel drug-drug interactions extraction based on cross attention.

BMC bioinformatics·2026
Same journal

FeSseqdb: a curated sequence-level database and interpretable machine learning framework for identifying iron-sulfur proteins.

BMC bioinformatics·2026
See all related articles

This study introduces the kernel-imbedded Gaussian process (KIGP), a novel machine learning method for identifying disease-related genes from gene expression data. The KIGP method effectively handles both linear and non-linear relationships, outperforming existing approaches in disease classification tasks.

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • Machine learning for gene identification is crucial for understanding disease at the genomic level.
  • Linear models dominate but struggle with complex gene-disease relationships and numerical instability.
  • Existing non-linear methods often lack unified frameworks for parameter tuning and model selection.

Purpose of the Study:

  • To develop a unified machine learning framework for binary disease classification using gene expression data.
  • To address limitations of existing linear and non-linear models in handling complex biological data.
  • To create a robust method for identifying disease-discriminating genes and improving classification accuracy.

Main Methods:

  • Developed a hierarchical statistical model: kernel-imbedded Gaussian process (KIGP).

Related Experiment Videos

  • Utilized a unified Bayesian framework with a probit regression setting.
  • Employed an adaptive algorithm with a cascading structure and Gibbs sampler for Bayesian inference.

    • Main Results:

    • KIGP performed near the theoretical Bayesian bound in simulations, irrespective of the underlying model complexity.
    • Demonstrated broad usability for microarray data analysis, especially for non-linear problems.
    • Outperformed or matched state-of-the-art methods on four published microarray datasets.

    Conclusions:

    • KIGP offers a unified approach to explore linear and non-linear gene-disease relationships under a Bayesian framework.
    • Effectively integrates model parameter tuning and addresses model selection via kernel type selection.
    • Provides robust, numerically stable, and accurate Bayesian probabilistic predictions for disease classification.