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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Cross-species transcriptomic analysis of rodent model fidelity to human mesial temporal lobe epilepsy.

Nature communications·2026
Same author

Somatic mutation analysis of mucin genes and pathways in idiopathic pulmonary fibrosis.

American journal of respiratory and critical care medicine·2026
Same author

Proteomic Profiling of Human Extracellular Vesicles Reveals Diagnostic Biomarkers for Colon Adenocarcinoma.

Journal of extracellular vesicles·2026
Same author

Correction: Role of the suppressor of cytokine signaling-3 in the pathogenesis of Graves' orbitopathy.

Frontiers in endocrinology·2025
Same author

Erratum: Machine Learning Predicts Oxaliplatin Benefit in Early Colon Cancer.

Journal of clinical oncology : official journal of the American Society of Clinical Oncology·2025
Same author

Human Retinal Organoid Modeling Defines Developmental Window and Therapeutic Vulnerabilities in MYCN-Amplified Retinoblastoma.

International journal of molecular sciences·2025

Related Experiment Video

Updated: Nov 28, 2025

Optimization of a Multiplex RNA-based Expression Assay Using Breast Cancer Archival Material
11:12

Optimization of a Multiplex RNA-based Expression Assay Using Breast Cancer Archival Material

Published on: August 1, 2018

8.2K

An Improved, Assay Platform Agnostic, Absolute Single Sample Breast Cancer Subtype Classifier.

Mi-Kyoung Seo1, Soonmyung Paik2, Sangwoo Kim1

  • 1Department of Biomedical Systems Informatics, Brain Korea 21 PLUS Project for Medical Science, Yonsei University College of Medicine, Seoul 03722, Korea.

Cancers
|December 1, 2020
PubMed
Summary

A new breast cancer (BC) classifier, MiniABS, uses only 11 genes for accurate, platform-independent subtype classification. This method improves upon existing techniques, enabling precise subtyping across diverse datasets.

Keywords:
breast cancerclassifiermachine learningoptimizationsubtyping

More Related Videos

Integration of Wet and Dry Bench Processes Optimizes Targeted Next-generation Sequencing of Low-quality and Low-quantity Tumor Biopsies
13:24

Integration of Wet and Dry Bench Processes Optimizes Targeted Next-generation Sequencing of Low-quality and Low-quantity Tumor Biopsies

Published on: April 11, 2016

12.1K
Isolation and Functional Assessment of Human Breast Cancer Stem Cells from Cell and Tissue Samples
07:03

Isolation and Functional Assessment of Human Breast Cancer Stem Cells from Cell and Tissue Samples

Published on: October 2, 2020

4.8K

Related Experiment Videos

Last Updated: Nov 28, 2025

Optimization of a Multiplex RNA-based Expression Assay Using Breast Cancer Archival Material
11:12

Optimization of a Multiplex RNA-based Expression Assay Using Breast Cancer Archival Material

Published on: August 1, 2018

8.2K
Integration of Wet and Dry Bench Processes Optimizes Targeted Next-generation Sequencing of Low-quality and Low-quantity Tumor Biopsies
13:24

Integration of Wet and Dry Bench Processes Optimizes Targeted Next-generation Sequencing of Low-quality and Low-quantity Tumor Biopsies

Published on: April 11, 2016

12.1K
Isolation and Functional Assessment of Human Breast Cancer Stem Cells from Cell and Tissue Samples
07:03

Isolation and Functional Assessment of Human Breast Cancer Stem Cells from Cell and Tissue Samples

Published on: October 2, 2020

4.8K

Area of Science:

  • Genomics
  • Bioinformatics
  • Cancer Research

Background:

  • Intrinsic molecular subtypes are crucial for breast cancer (BC) classification.
  • Current subtype assignment is affected by assay technology and cohort composition, limiting consistency.
  • A need exists for a robust, platform-independent method for single-sample BC subtyping.

Purpose of the Study:

  • To develop a platform-independent, absolute single-sample breast cancer subtype classifier.
  • To identify a minimal set of genes sufficient for accurate subtype classification.
  • To validate the classifier's performance across diverse datasets and platforms.

Main Methods:

  • Utilized pairwise ratios of subtype-specific differentially expressed genes from The Cancer Genome Atlas (TCGA) breast cancer samples.
  • Employed machine learning, specifically a random forest classifier, to develop the subtype classifier.
  • Selected the optimal classifier based on gene count and classification power during cross-validation, evaluating on independent datasets.

Main Results:

  • A random forest classifier (MiniABS) using 11 genes achieved 88.2% accuracy within the TCGA cohort.
  • MiniABS demonstrated an average accuracy of 85.15% on validation sets (RNA-seq and microarray), outperforming AIMS (77.72%).
  • MiniABS successfully subtyped low-throughput datasets with an average accuracy of 87.93%.

Conclusions:

  • MiniABS provides accurate, absolute breast cancer subtyping using only 11 genes and raw expression levels.
  • The classifier is independent of assay platform and study cohort, offering broader applicability.
  • MiniABS surpasses existing methods in accuracy and versatility for breast cancer molecular subtyping.