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

Search research articles

Related Experiment Videos

Multi-platform, multi-site, microarray-based human tumor classification.

Greg Bloom¹, Ivana V Yang, David Boulware

¹H. Lee Moffitt Cancer Center, University of South Florida, Tampa, Florida 33612-9497, USA.

The American Journal of Pathology

|December 26, 2003

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

Clinical outcomes following transcatheter aortic valve replacement in patients with concordant versus discordant aortic stenosis.

American heart journal plus : cardiology research and practice·2026

Same author

New 2030 Global Targets for Histoplasmosis from International Society for Human and Animal Mycology (ISHAM) 2025 Histoplasmosis Working Group.

Emerging infectious diseases·2026

Same author

Flow Gradients in Severe Aortic Stenosis and Preserved Ejection Fraction: A 10-Year Transcatheter Aortic Valve Replacement Study.

Journal of the Society for Cardiovascular Angiography & Interventions·2026

Same author

Retraction Note: Farnesyl dimethyl chromanol targets colon cancer stem cells and prevents colorectal cancer metastasis.

Scientific reports·2025

Same author

Colorectal Tumors in Diverse Patient Populations Feature a Spectrum of Somatic Mutational Profiles.

Cancer research·2025

Same author

Building research infrastructure to advance precision medicine in colorectal cancer.

JNCI cancer spectrum·2025

Same journal

Krüppel-like factor 5 inhibition rescues cavernous nerve-injured erectile dysfunction by preventing phenotypic switch and mitochondrial dysfunction-dependent apoptosis in corpus cavernosum smooth muscle cells.

The American journal of pathology·2026

Same journal

APOE4 as a Modifier of Chemotherapy Response.

The American journal of pathology·2026

Same journal

Spatial Pathobiology in the Omics Era: Transforming Modern Pathology.

The American journal of pathology·2026

Same journal

Unbiased Spatial Proteomics Uncovers Hepatic in Situ Regulation in Alcohol-Associated Hepatitis.

The American journal of pathology·2026

Same journal

Zinc Finger Protein 143 Promotes Endometriotic Lesion Growth and Fibrosis through the Plasminogen Activator Inhibitor-1 Pathway.

The American journal of pathology·2026

Same journal

Dual Mechanisms Underlie the Repression of Repressor Element 1-Silencing Transcription Factor Expression in Lung Neuroendocrine Carcinoma Cells.

The American journal of pathology·2026

See all related articles

Artificial neural networks (ANNs) effectively classify human cancers using gene expression data from different microarray platforms. This approach achieves high accuracy in identifying tumor types and origins, even for metastatic lesions.

Area of Science:

Bioinformatics
Computational Biology
Oncology

Background:

Gene expression profiling generates extensive human data crucial for cancer diagnosis, prognosis, and treatment.
Artificial neural networks (ANNs) offer a powerful computational tool for analyzing complex biological datasets.

Purpose of the Study:

To develop and validate artificial neural network (ANN)-based tumor classifiers using gene expression data from multiple microarray platforms.
To assess the accuracy of these classifiers in identifying diverse human cancer types and origins.

Main Methods:

Utilized cDNA and oligonucleotide microarray data from numerous tumors across various cancer types.
Developed ANNs trained on independent datasets for classification tasks.
Evaluated classifier performance using independent test sets and metastatic lesion data.

Related Experiment Videos

Main Results:

A cDNA-based ANN achieved 83% accuracy in classifying adenocarcinoma subtypes.
An oligonucleotide-based ANN demonstrated 88% accuracy in predicting tumor origin.
A mixed-platform ANN achieved 85% accuracy, and classifiers correctly identified 84% of metastatic lesion origins.

Conclusions:

ANNs can effectively integrate gene expression data from diverse microarray platforms and sites to build robust multi-tissue tumor classifiers.
This approach shows promise for improving the classification of challenging cases, such as cancers of unknown primary origin.