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

IdeaDistiller-AI Support for Idea Synthesis in Concept Mapping: Algorithm Development and Validation Study.

JMIR medical informatics·2026
Same author

PP-GWAS: Privacy Preserving Multi-Site Genome-wide Association Studies.

Nature communications·2025
Same author

Privacy-preserving AUC computation in distributed machine learning with PHT-meDIC.

PLOS digital health·2025
Same author

Target leakage and the use of diagnostic variables in diabetes prediction models.

Nutrition & diabetes·2025
Same author

Privacy-preserving federated unsupervised domain adaptation with application to age prediction from DNA methylation data.

Bioinformatics (Oxford, England)·2025
Same author

Long-term impact of the SARS-CoV-2 pandemic on respiratory viruses in Germany.

BMC public health·2025

Related Experiment Video

Updated: Feb 21, 2026

A Streamlined Approach for Mass Spectrometry-Based Proteomics Using Selected Tissue Regions
09:00

A Streamlined Approach for Mass Spectrometry-Based Proteomics Using Selected Tissue Regions

Published on: April 18, 2025

1.4K

Towards Multiple Kernel Principal Component Analysis for Integrative Analysis of Tumor Samples.

Nora K Speicher1, Nico Pfeifer1

  • 1.

Journal of Integrative Bioinformatics
|July 9, 2017
PubMed
Summary

This study introduces a new method for integrating multiple cancer data sources to identify subtypes. This approach improves personalized cancer therapy by revealing hidden patterns in diverse patient data.

Keywords:
Cancer subtypingDimensionality reductionIntegrative kernel principal component analysisMultiple kernel learningPatient clustering

More Related Videos

On-Site Sampling and Extraction of Brain Tumors for Metabolomics and Lipidomics Analysis
06:48

On-Site Sampling and Extraction of Brain Tumors for Metabolomics and Lipidomics Analysis

Published on: May 31, 2020

6.4K
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

16.4K

Related Experiment Videos

Last Updated: Feb 21, 2026

A Streamlined Approach for Mass Spectrometry-Based Proteomics Using Selected Tissue Regions
09:00

A Streamlined Approach for Mass Spectrometry-Based Proteomics Using Selected Tissue Regions

Published on: April 18, 2025

1.4K
On-Site Sampling and Extraction of Brain Tumors for Metabolomics and Lipidomics Analysis
06:48

On-Site Sampling and Extraction of Brain Tumors for Metabolomics and Lipidomics Analysis

Published on: May 31, 2020

6.4K
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

16.4K

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Personalized cancer treatment relies on accurate identification of tissue-specific subtypes.
  • Current subtype diagnosis often uses single data sources, limiting comprehensive analysis.
  • Integrating diverse patient data is crucial for advancing precision oncology.

Purpose of the Study:

  • To develop an unsupervised method for integrating multiple cancer patient data sources.
  • To address limitations of existing methods in utilizing all available data.
  • To enable improved cancer subtype identification and visualization.

Main Methods:

  • Kernel principal component analysis (KPCA) adapted for multi-matrix integration.
  • A novel scoring function to weigh the contribution of each data matrix.
  • Unsupervised clustering on integrated data for subtype discovery.
  • Application to five distinct cancer datasets.

Main Results:

  • Successfully integrated multiple data sources, overcoming limitations of standard KPCA extensions.
  • Developed a method that visualizes integrated data and facilitates subtype clustering.
  • Demonstrated advantages in results and usability across five cancer datasets.
  • The method requires no hyperparameter tuning.

Conclusions:

  • The proposed unsupervised data integration method enhances cancer subtype identification.
  • This approach offers a powerful tool for precision medicine by leveraging multi-omics data.
  • The method provides a user-friendly and effective solution for complex cancer data analysis.