Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Tumor Progression

Tumor Progression

Tumor progression is a phenomenon where the pre-formed tumor acquires successive mutations to become clinically more aggressive and malignant. In the 1950s, Foulds first described the stepwise progression of cancer cells through successive stages.
Colon cancer is one of the best-documented examples of tumor progression. Early mutation in the APC gene in colon cells causes a small growth on the colon wall called a polyp. With time, this polyp grows into a benign, pre-cancerous tumor. Further...

Tumor Progression

Tumor Progression

You might also read

Related Articles

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

Sort by

Same author

Ethnicity and Pathway Progression: A Retrospective Cohort Study of Male Offenders Managed Under London Offender Personality Disorder Pathway Services.

Criminal behaviour and mental health : CBMH·2026

Same author

Social vulnerability and the mental health consequences of the death of a close friend in older adulthood.

The journals of gerontology. Series B, Psychological sciences and social sciences·2026

Same author

Protocol for first-hit oncogenic organoid modeling and lentiviral functional screening.

STAR protocols·2026

Same author

The Offender Personality Disorder Pathway for Men: Staff Perceptions About Possible Impact on Re-offending in High-Risk Individuals with Personality Disorder.

International journal of offender therapy and comparative criminology·2026

Same author

Epigenetic fingerprints link early-onset colon and rectal cancer to pesticide exposure.

Nature medicine·2026

Same author

Inactivation of CDKN2AARF Promotes p53-Independent Remodeling of the PDAC Tumor Microenvironment.

Cancer research·2026

Search research articles

Related Experiment Video

Updated: May 6, 2026

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

A pathway-based data integration framework for prediction of disease progression.

José A Seoane¹, Ian N M Day, Tom R Gaunt

¹MRC Centre for Causal Analyses in Translational Epidemiology, MRC Integrative Epidemiology Unit, School of Social and Community Medicine, University of Bristol, Clifton BS8 2BN, UK and Intelligent Systems Laboratory, University of Bristol, Bristol BS8 1UB, UK.

Bioinformatics (Oxford, England)

|October 29, 2013

Summary

Integrating multiple data types using multiple kernel learning improves breast cancer survival prediction accuracy. This approach enhances prognostic models by leveraging all available patient data for better predictive performance.

More Related Videos

Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization

Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization

Published on: October 3, 2025

A Pathway Association Study Tool for GWAS Analyses of Metabolic Pathway Information

A Pathway Association Study Tool for GWAS Analyses of Metabolic Pathway Information

Published on: July 1, 2020

Related Experiment Videos

Last Updated: May 6, 2026

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization

Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization

Published on: October 3, 2025

A Pathway Association Study Tool for GWAS Analyses of Metabolic Pathway Information

A Pathway Association Study Tool for GWAS Analyses of Metabolic Pathway Information

Published on: July 1, 2020

Area of Science:

Bioinformatics
Computational Biology
Medical Informatics

Background:

Increasing trend of deriving multiple data types from single individuals in medical research.
Need for effective prognostic prediction methods that maximize information utilization.
Exploration of learning strategies to enhance prediction performance using comprehensive data.

Purpose of the Study:

To investigate the efficacy of multiple kernel learning for integrating diverse data types.
To improve prognostic prediction accuracy in breast cancer survival analysis.
To develop a robust classification scheme incorporating feature selection and confidence measures.

Main Methods:

Utilized multiple kernel learning (MKL) for supervised learning and data integration.
Implemented feature selection based on statistical scores, stratified by data type and pathway membership.
Introduced a confidence measure for class assignment to refine training data and implement a cautious classifier.

Main Results:

Achieved improved predictive accuracy for 2000-day survival in breast cancer using the METABRIC dataset.
Demonstrated enhanced performance by incorporating pathway-specific gene kernels and clinical covariates (e.g., Estrogen Receptor status).
Attained nearly 80% test accuracy on new instances, with predictions made for 69.2% of the cohort.

Conclusions:

Multiple kernel learning effectively integrates multi-omics and clinical data for improved prognostic prediction.
Pathway-based feature selection and confidence-based classification enhance predictive model robustness and accuracy.
The proposed methods offer a powerful framework for leveraging comprehensive individual data in medical research.