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

Tumor classification by tissue microarray profiling: random forest clustering applied to renal cell carcinoma.

Tao Shi1, David Seligson, Arie S Belldegrun

  • 1Department of Human Genetics, University of California, Los Angeles, CA 90095-7088, USA.

Modern Pathology : an Official Journal of the United States and Canadian Academy of Pathology, Inc
|November 6, 2004
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

PGS Browser: a public platform for personalized polygenic score analysis and interpretation.

Nature communications·2026
Same author

Genetic architecture of 67 oral diseases and their links to systemic diseases.

HGG advances·2026
Same author

GWAS Meta-analysis Identifies Novel Associated Loci and Points to Causal Tissues in Central Serous Chorioretinopathy.

medRxiv : the preprint server for health sciences·2026
Same author

Altered neurodevelopmental trajectories of brain structure in Tourette syndrome and Chronic Tic Disorders.

medRxiv : the preprint server for health sciences·2026
Same author

Scalable biological-cognitive profiling for Alzheimer's disease in the population.

Brain communications·2026
Same author

Discovering Age- and Sex-Specific Genetic Risk Factors in Sensorineural Hearing Loss: Genome-Wide Evidence from Large-Scale Biobanks.

Journal of the Association for Research in Otolaryngology : JARO·2026

We developed random forest clustering for novel tumor profiling using tissue microarray data. This method discovered new renal cell carcinoma subtypes with improved survival prediction compared to traditional classifications.

Area of Science:

  • Oncology
  • Bioinformatics
  • Computational Biology

Background:

  • Renal cell carcinoma (RCC) classification relies on traditional pathological groupings.
  • Protein expression profiles offer a potential avenue for more refined tumor subtyping.
  • Existing methods may not fully leverage complex, high-dimensional tissue microarray data.

Purpose of the Study:

  • To introduce and validate a novel random forest clustering strategy for tumor profiling using tissue microarray data.
  • To discover new molecular subtypes of renal cell carcinoma (RCC) patients.
  • To assess if molecular subtypes improve survival prediction over classical pathological classifications.

Main Methods:

  • Applied unsupervised random forest clustering to tissue microarray data from 366 RCC patients.

Related Experiment Videos

  • Utilized eight tumor markers assessing proliferation, cell cycle, mobility, and hypoxia.
  • Performed hierarchical clustering to identify finer subclasses within identified groups.

    • Main Results:

    • Random forest clustering successfully differentiated clear cell from non-clear cell RCC.
    • Molecular grouping significantly improved survival prediction (logrank P=0.000090) versus pathological grouping (logrank P=0.023).
    • Discovered novel subclasses within clear cell RCC, including grade-based and distinct molecular profiles, some unexplained by clinicopathological variables.

    Conclusions:

    • Random forest clustering is a robust method for tumor profiling with tissue microarray data.
    • This approach identified fundamental and finer subtypes of RCC with superior prognostic value.
    • The discovered molecular subclasses offer new insights into RCC heterogeneity and potential therapeutic targets.