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

Improving molecular cancer class discovery through sparse non-negative matrix factorization.

Yuan Gao1, George Church

  • 1Department of Genetics, Harvard Medical School Boston, MA 02115, USA. g1m1c1@receptor.med.harvard.edu

Bioinformatics (Oxford, England)
|October 26, 2005
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

Derivation of elephant induced pluripotent stem cells.

Nature methods·2026
Same author

Standardized metrics for assessment and reproducibility of imaging-based spatial transcriptomics datasets.

Nature biotechnology·2025
Same author

Integrated AAV optimization enables efficient gene delivery to kidney in murine and human tissue.

Research square·2025
Same author

Large language models for drug discovery and development.

Patterns (New York, N.Y.)·2025
Same author

Validation of human sensory neurons derived from inducible pluripotent stem cells as a model for latent infection and reactivation by herpes simplex virus 1.

mBio·2025
Same author

The Spatial Atlas of Human Anatomy (SAHA): A Multimodal Subcellular-Resolution Reference Across Human Organs.

bioRxiv : the preprint server for biology·2025
Same journal

3DICE: Interpretable 3D Cross-Modal Learning for Drug-Target Interaction Prediction and Large-Scale Drug Discovery.

Bioinformatics (Oxford, England)·2026
Same journal

KASSPer: Kinase Active Site Structure Prediction using Protein and Ligand Language Models and Its Application to Virtual Screening.

Bioinformatics (Oxford, England)·2026
Same journal

IDR searcher: a search engine solution for public image resources.

Bioinformatics (Oxford, England)·2026
Same journal

KCFtools: Rapid alignment-free method for introgression screening and GWAS using k-mer profiles.

Bioinformatics (Oxford, England)·2026
Same journal

Meta2DB: Curated shotgun metagenomic feature sets and metadata for health state prediction.

Bioinformatics (Oxford, England)·2026
Same journal

conMItion: an R package adjusting confounding factors for associations in multi-omics.

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

This study introduces sparse non-negative matrix factorization for improved cancer classification using gene-expression data. This method enhances tumor subclass discovery and identifies key genes involved in cancer.

Area of Science:

  • Computational Biology
  • Genomics
  • Bioinformatics

Background:

  • Cancer classification is complex, impacting diagnosis and treatment.
  • Gene-expression data clustering aids cancer class discovery.
  • Non-negative matrix factorization (NMF) is a powerful clustering technique.

Purpose of the Study:

  • To investigate the benefits of enforcing sparseness in NMF for cancer classification.
  • To improve unsupervised cancer classification using gene-expression profiles.
  • To identify potential cancer-driving genes through co-expression analysis.

Main Methods:

  • Sparse Non-negative Matrix Factorization (sNMF) applied to gene-expression data.
  • Comparison of sNMF with classic NMF.
  • Analysis of three established cancer datasets.

Related Experiment Videos

Main Results:

  • Sparse NMF demonstrates improved cancer classification accuracy over classic NMF.
  • The method successfully identified distinct cancer subclasses.
  • A small subset of co-expressed genes potentially involved in cancer was identified.

Conclusions:

  • Sparse NMF offers an enhanced approach for unsupervised cancer classification.
  • This technique aids in discovering biologically relevant gene signatures.
  • The findings have implications for cancer diagnosis and targeted therapies.