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 Video

Updated: Jun 23, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Feature selection for predicting tumor metastases in microarray experiments using paired design.

Qihua Tan1, Mads Thomassen, Torben A Kruse

  • 1Department of Biochemistry, Pharmacology and Genetics, Odense University Hospital, Odense, Denmark. qihua.tan@ouh.fyns-amt.dk

Cancer Informatics
|May 21, 2009
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

Differential DNA Methylation of the Serotonin Receptor Signaling and Glutamatergic Synapse Pathways in Adult Twins Born Preterm.

Genes·2026
Same author

Homologous recombination deficiency-driven genomic instability in ovarian cancer as an indicator of BRCA1 and BRCA2 variant pathogenicity.

American journal of human genetics·2026
Same author

Circulating tumor DNA-guided response evaluation in patients with previously treated gastroesophageal adenocarcinoma.

Gastric cancer : official journal of the International Gastric Cancer Association and the Japanese Gastric Cancer Association·2026
Same author

Updated ENIGMA recommendations for reporting germline variants in cancer susceptibility genes and their translation into twenty languages.

Journal of medical genetics·2026
Same author

Epigenetic heterogeneity in women with polycystic ovary syndrome.

Molecular and cellular endocrinology·2026
Same author

Somatic mutational landscape in von Hippel-Lindau familial hemangioblastoma.

Molecular oncology·2026

This study introduces a novel feature selection method for paired microarray data, crucial for classifying gene expression profiles. The new approach enhances accuracy in identifying genes that predict tumor metastasis in breast cancer patients.

Area of Science:

  • Bioinformatics
  • Genomics
  • Cancer Research

Background:

  • High-dimensional microarray data presents challenges in gene expression profile classification.
  • Feature selection is critical for developing effective classification rules.
  • Existing methods lack specific approaches for paired microarray experiments.

Purpose of the Study:

  • To introduce a novel feature selection procedure tailored for paired microarray experiments.
  • To apply this method to identify predictive genes for tumor metastasis in breast cancer.
  • To improve the efficiency and accuracy of gene selection in matched case-control studies.

Main Methods:

  • A modified t-statistic-based procedure for feature selection.
  • Application to a matched case-control study design.
Keywords:
feature selectiongene expression microarraymetastasisprediction

More Related Videos

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

Related Experiment Videos

Last Updated: Jun 23, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

  • Optimization via thresholding with leave-one-pair-out cross-validation.

    • Main Results:

    • The proposed method demonstrates improved efficiency in gene selection.
    • Achieved high sensitivity and specificity in identifying predictive genes.
    • Successfully applied to identify genes associated with tumor metastasis in breast cancer.

    Conclusions:

    • The novel feature selection method is effective for paired microarray data.
    • This approach enhances the ability to identify genes predicting disease outcomes.
    • The method offers a valuable tool for cancer research and gene expression analysis.