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

Optimization models for cancer classification: extracting gene interaction information from microarray expression

Alexey V Antonov1, Igor V Tetko, Michael T Mader

  • 1GSF National Research Center for Environment and Health, Institute for Bioinformatics, Ingolstädter Landstrasse 1, D-85764 Neuherberg, Germany. antonov@gsf.de

Bioinformatics (Oxford, England)
|March 23, 2004
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

Unveiling tumor heterogeneity by single cell RNA-sequencing: from basic considerations to clinical applications.

Seminars in cancer biology·2026
Same author

[Artificial intelligence in molecular pathology : Introduction and overview].

Pathologie (Heidelberg, Germany)·2026
Same author

ATM Deficiency Induces TGF-β-Mediated Stromal Programming in Pancreatic Cancer.

Cancer research·2026
Same author

SangsterLogP - the largest publicly available dataset of logP values.

Scientific data·2026
Same author

Personalizing the treatment of head and neck cancer in vitro: The 3D-OTC model.

BMC medicine·2026
Same author

Spatial transcriptomics reveals a molecular tumor budding signature in head and neck cancer.

Genome medicine·2026
Same journal

OmicsTransformer: Self-Supervised Masked Consistency and Uncertainty-Aware Fusion for Robust Multi-Omics Prediction.

Bioinformatics (Oxford, England)·2026
Same journal

Computational Tool Choice Impacts CRISPR Spacer-Proto spacer Detection.

Bioinformatics (Oxford, England)·2026
Same journal

ARISE: RNA-Anchored Shared-Edge Topology and Hierarchical Fusion for Spatial Multi-Omics Integration.

Bioinformatics (Oxford, England)·2026
Same journal

Interactive exploration of biobank-scale ancestral recombination graphs with Lorax.

Bioinformatics (Oxford, England)·2026
Same journal

PepMCP: A Graph-Based Membrane Contact Probability Predictor for Membrane-Lytic Antimicrobial Peptides.

Bioinformatics (Oxford, England)·2026
Same journal

ARGscape: A modular, interactive tool for manipulation of spatiotemporal ancestral recombination graphs.

Bioinformatics (Oxford, England)·2026
See all related articles

A new method called Maximal Margin Linear Programming (MAMA) analyzes gene interactions in microarray data for improved cancer classification. This approach detects gene expression changes missed by other methods, enhancing diagnostic accuracy.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Cancer Genomics

Background:

  • Microarray data is crucial for understanding cancer biology and cell cycle control.
  • Current cancer classification methods using microarrays focus on gene expression levels.
  • These methods may miss crucial diagnostic information from altered gene interactions in tumors.

Purpose of the Study:

  • To develop a novel classification procedure that incorporates changes in gene interactions from microarray data.
  • To improve the accuracy of cancer diagnosis by considering a broader range of genetic alterations.

Main Methods:

  • Proposed a Maximal Margin Linear Programming (MAMA) method for classifying tumor samples using microarray data.
  • MAMA identifies groups of genes and builds models (features) correlating with specific tumor types.

Related Experiment Videos

  • The method focuses on detecting changes in functional gene relationships indicative of cancer.

    • Main Results:

    • Tested MAMA on two public microarray datasets.
    • Demonstrated superior prediction ability compared to existing classification schemes.
    • Successfully identified features reflecting altered gene interactions in specific cancer types.

    Conclusions:

    • MAMA offers a more comprehensive approach to cancer classification by analyzing gene interactions.
    • This method enhances the diagnostic power of microarray data.
    • The MAMA system, developed with LINDO, provides a valuable tool for cancer research.