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

Unsupervised feature selection via two-way ordering in gene expression analysis.

Chris H Q Ding¹

¹NERSC Division, Lawrence Berkeley National Laboratory, University of California, Berkeley, CA 94720, USA. chqding@lbl.gov

Bioinformatics (Oxford, England)

|July 2, 2003

Summary

This summary is machine-generated.

This study introduces a new unsupervised gene selection method using only gene similarity. It effectively identifies relevant genes for discovering unknown phenotypes, outperforming baseline methods in cancer expression data.

Related Experiment Videos

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

Dynamic adaptive multi-view contrastive learning for unsupervised person re-identification.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

A novel classification algorithm for customer churn prediction based on hybrid Ensemble-Fusion model.

Scientific reports·2024

Same author

Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive Learning.

IEEE transactions on medical imaging·2023

Same author

Bio-driven visual saliency detection with color factor.

Frontiers in bioengineering and biotechnology·2022

Same author

Model Compression Based on Differentiable Network Channel Pruning.

IEEE transactions on neural networks and learning systems·2022

Same author

Similarity Learning of Manifold Data.

IEEE transactions on cybernetics·2014

Same journal

Cross-Domain Transfer Learning from Peptides to Metabolites Using a Multi-Property Fine-Tuned LLM.

Bioinformatics (Oxford, England)·2026

Same journal

Biomedical Concept Recognition with Error-aware Negative-enhanced Ranking Framework.

Bioinformatics (Oxford, England)·2026

Same journal

TEDLH: Domain HMMs for sensitive detection of remote homologues.

Bioinformatics (Oxford, England)·2026

Same journal

PLNFGL: Joint Estimation of Multi-Condition Gene Networks from Single-cell RNA-seq Data.

Bioinformatics (Oxford, England)·2026

Same journal

MCFST: Spatial domain identification method based on multi-view graph convolutional network and graph fusion network.

Bioinformatics (Oxford, England)·2026

Same journal

SpaBiT: Enhancing Spatial Transcriptomics Resolution via Bidirectional Attention Transformers.

Bioinformatics (Oxford, England)·2026

See all related articles

Area of Science:

Bioinformatics
Computational Biology
Genomics

Background:

Gene expression analysis is crucial for understanding phenotypes.
Current methods often rely on known phenotype information for gene selection.
Discovering genes linked to unknown phenotypes requires novel, unsupervised approaches.

Purpose of the Study:

To develop an effective unsupervised method for selecting relevant genes without prior phenotype data.
To identify genes associated with potentially novel phenotypes.

Main Methods:

A novel gene selection method based solely on gene similarity information.
Utilizing a two-way ordering mechanism to discard irrelevant genes.
Exploring variance and principal component analysis for gene selection.

Main Results:

The proposed unsupervised method successfully selects relevant genes based on similarity.
A two-way ordering effectively isolates and discards irrelevant genes.
Applied to colon cancer and leukemia data, the method outperformed a baseline approach and identified genes comparable to supervised methods.

Conclusions:

Unsupervised gene selection based on similarity is a viable approach for discovering novel phenotypes.
The two-way ordering method offers an effective way to filter genes without phenotype information.
This technique holds promise for advancing gene expression analysis and phenotype discovery.