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

DNA Microarrays

DNA Microarrays

Microarrays are high-throughput and relatively inexpensive assays that can be automated to analyze large quantities of data at a time. They are used in genome-wide studies to compare gene or protein expression under two varied conditions, such as healthy and diseased states. Microarrays consist of glass or silica slides on which probe molecules are covalently attached through surface functionalization. Most commonly, the slides are prepared through the chemisorption of silanes to silica...

You might also read

Related Articles

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

Sort by

Same author

A systematic review of machine learning on clinical MALDI-TOF MS.

Briefings in bioinformatics·2026

Same author

Automated web-based typing of Clostridioides difficile ribotypes via MALDI-TOF MS.

BMC bioinformatics·2025

Same author

Predictive model of ibuprofen treatment failure in very preterm infants with patent ductus arteriosus using machine learning techniques.

Journal of perinatology : official journal of the California Perinatal Association·2025

Same author

Bayesian learning of feature spaces for multitask regression.

Neural networks : the official journal of the International Neural Network Society·2024

Same author

Predicting the effectiveness of drugs used for treating cardiovascular conditions in newborn infants.

Pediatric research·2023

Same author

Adaptive Sparse Gaussian Process.

IEEE transactions on neural networks and learning systems·2023

Search research articles

Related Experiment Video

Updated: Sep 9, 2025

Microarray-based Identification of Individual HERV Loci Expression: Application to Biomarker Discovery in Prostate Cancer

Microarray-based Identification of Individual HERV Loci Expression: Application to Biomarker Discovery in Prostate Cancer

Published on: November 2, 2013

Addressing wide-data studies of gene expression microarrays with the Relevance Feature and Vector Machine.

Albert Belenguer-Llorens¹, Carlos Sevilla-Salcedo¹, Emilio Parrado-Hernández¹

¹Universidad Carlos III de Madrid, (1), Department of Signal Processing and Communications, Leganés, 28911, Spain.

Computers in Biology and Medicine

|September 3, 2025

Summary

This study introduces a new Bayesian model, the Relevance Feature and Vector Machine (RFVM), to tackle gene expression data challenges. RFVM enhances diagnostic accuracy and interpretability by selecting relevant genes and patients simultaneously.

Keywords:

Feature selection Gene expression microarrays Low-sample-to-feature ratio Probabilistic machine learning Sample selection

More Related Videos

Determining Genetic Expression Profiles in C. elegans Using Microarray and Real-time PCR

Determining Genetic Expression Profiles in C. elegans Using Microarray and Real-time PCR

Published on: July 30, 2011

Analyzing Multifactorial RNA-Seq Experiments with DiCoExpress

Analyzing Multifactorial RNA-Seq Experiments with DiCoExpress

Published on: July 29, 2022

Related Experiment Videos

Last Updated: Sep 9, 2025

Microarray-based Identification of Individual HERV Loci Expression: Application to Biomarker Discovery in Prostate Cancer

Microarray-based Identification of Individual HERV Loci Expression: Application to Biomarker Discovery in Prostate Cancer

Published on: November 2, 2013

Determining Genetic Expression Profiles in C. elegans Using Microarray and Real-time PCR

Determining Genetic Expression Profiles in C. elegans Using Microarray and Real-time PCR

Published on: July 30, 2011

Analyzing Multifactorial RNA-Seq Experiments with DiCoExpress

Analyzing Multifactorial RNA-Seq Experiments with DiCoExpress

Published on: July 29, 2022

Area of Science:

Bioinformatics
Computational Biology
Machine Learning in Genomics

Background:

Gene expression microarrays generate wide-data, where features outnumber observations, posing challenges for machine learning algorithms.
The "wide-data problem" is prevalent in genomic studies, complicating accurate analysis and model generalizability.
Existing models often struggle with interpretability and overfitting in high-dimensional genomic datasets.

Purpose of the Study:

To introduce a novel Bayesian model, the Relevance Feature and Vector Machine (RFVM), designed to address wide-data challenges in gene expression analysis.
To enhance model interpretability in both feature (gene) and sample (patient) spaces.
To improve the performance and compactness of models used in diagnostic tasks for genomic data.

Main Methods:

Developed the Relevance Feature and Vector Machine (RFVM), a Bayesian model operating in dual space.
Implemented a two-way sparsity approach incorporating priors over primal and dual variables for joint feature and sample selection.
Validated RFVM against existing models using multiple gene expression microarray datasets.

Main Results:

RFVM demonstrated superior performance in diagnostic tasks compared to other models.
The model produced significantly more compact solutions, enhancing interpretability.
Selected genes by RFVM aligned with known biomarkers, indicating clinical relevance.

Conclusions:

RFVM effectively addresses wide-data challenges in gene expression analysis, offering improved diagnostic performance.
The model's joint feature and sample selection enhances interpretability and leads to more compact, clinically relevant solutions.
RFVM shows potential as a valuable clinical tool for analyzing genomic data and identifying biomarkers.