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

Classification of heterogeneous microarray data by maximum entropy kernel.

Wataru Fujibuchi1, Tsuyoshi Kato

  • 1National Institute of Advanced Industrial Science and Technology (AIST), Computational Biology Research Center, 2-42 Aomi, Koto-ku, Tokyo 135-0064, Japan. w.fujibuchi@aist.go.jp

BMC Bioinformatics
|July 27, 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

OCT-Defined Foveal Restoration Is Associated with Visual Recovery after Vitrectomy for Lamellar Macular Hole: A Multicenter Study: LMH Report No. 1.

Ophthalmology. Retina·2026
Same author

AMPK-p38 axis converts human pluripotent stem cells to naive state.

iScience·2026
Same author

Cyclin-dependent kinase 10 controls bone formation and is linked to human skeletal health.

Journal of orthopaedic translation·2026
Same author

From pixels to pores: 3D-(im)printed hierarchically porous polymer monoliths.

iScience·2026
Same author

Inhalation of 1-bromopropane alters hippocampal expression of pathways related to immune system/inflammation and insulin signaling in experimental rats.

Scientific reports·2025
Same author

Mechanism of CD83 expression induction through dectin-1 and β-glucan interaction in innate immune responses.

Immunology and cell biology·2025
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

A new maximum entropy (ME) kernel improves support vector machine (SVM) classification for heterogeneous microarray data. This robust ME kernel enhances prediction accuracy, especially for datasets with missing values and noise.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Large-scale microarray data is available in public databases for joint analysis.
  • Support vector machines (SVMs) with standard kernels are widely used for microarray classification.
  • Standard kernels struggle with heterogeneous data from different platforms due to low gene consistency.

Purpose of the Study:

  • Introduce a novel maximum entropy (ME) kernel for SVM classification of microarray data.
  • Evaluate the performance of the ME kernel on heterogeneous and noisy datasets.

Main Methods:

  • Developed a maximum entropy (ME) kernel using kernel entropy maximization with sample distance matrices.
  • Applied the ME kernel to SVM classification tasks using heterogeneous kidney carcinoma, leukemia, and oral cavity carcinoma metastasis data.

Related Experiment Videos

Main Results:

  • The ME kernel demonstrated robustness against missing values and high noise in heterogeneous data.
  • Achieved higher prediction accuracies compared to standard linear, polynomial, and RBF kernels.
  • Successfully classified complex datasets, including those from rare specimens.

Conclusions:

  • The ME kernel is effective for analyzing diverse and challenging microarray datasets.
  • Offers a powerful tool for research involving rare diseases or species where homogeneous data is difficult to obtain.