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

De novo pathway-based biomarker identification.

Nicolas Alcaraz1,2,3, Markus List4, Richa Batra5,6

  • 1Department of Mathematics and Computer Science, University of Southern Denmark, 5230 Odense, Denmark.

Nucleic Acids Research
|September 22, 2017
PubMed
Summary

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

Inferring and evaluating network medicine-based disease modules with nextflow.

Bioinformatics (Oxford, England)·2026
Same author

Aberrant splicing in human cancer shows possible functional impact on transcription factors.

Oncogene·2026
Same author

An Integrated Skin Cell Atlas Decodes the Pilosebaceous Unit.

The Journal of investigative dermatology·2026
Same author

Phenotypic similarity of adverse drug reactions and disease phenotypes is a bridge to mechanistic discovery.

npj drug discovery·2026
Same author

Origin of sexual dimorphism in osteoarthritis risk: the impact of pregnancy and parental care.

BMC public health·2026
Same author

Association between Geriatric 8 frailty and overall survival, treatment intensity, and treatment tolerance in older patients with cancer (PROGNOSIS-G8).

Journal of geriatric oncology·2026

This study introduces meta-gene (MG) features for predicting cancer subtypes, outperforming traditional single-gene (SG) models in stability and accuracy. The novel approach offers a more personalized therapy strategy for complex diseases like breast cancer.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Gene expression profiles aid cancer therapy prediction but single-gene (SG) models lack stability.
  • Network-based approaches using meta-gene (MG) features improve prediction but are limited to two-class outcomes.
  • Stratifying patients by molecular subtypes enables personalized cancer therapies.

Purpose of the Study:

  • To develop and evaluate a novel meta-gene (MG) approach using de novo pathways for multi-class cancer subtype prediction.
  • To enhance the stability and performance of gene expression-based prediction models for complex diseases.
  • To provide a tool for personalized cancer therapy by accurately classifying molecular subtypes.

Main Methods:

  • Developed a novel meta-gene (MG) feature extraction method based on de novo pathways.

Related Experiment Videos

  • Applied the MG approach to a multi-class classification problem for cancer subtype prediction.
  • Evaluated model performance and stability using The Cancer Genome Atlas (TCGA) breast cancer cohort and an independent dataset.

    • Main Results:

    • Meta-gene (MG) models demonstrated significantly higher stability compared to single-gene (SG) models.
    • MG features consistently outperformed SG models on both the TCGA and independent benchmark datasets.
    • The approach provided insights into cancer hallmarks driving different subtypes.

    Conclusions:

    • The novel MG approach offers a more robust and accurate method for predicting cancer subtypes than traditional SG models.
    • This method advances personalized medicine by enabling precise molecular subtype classification.
    • A web service is available for researchers to utilize this approach for breast cancer gene expression data analysis.