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 Experiment Videos

Joint learning of gene functions--a Bayesian network model approach.

Xutao Deng1, Huimin Geng, Hesham H Ali

  • 1College of Information Science and Technology, University of Nebraska at Omaha, Omaha, NE 68182, USA. xdeng@mail.unomaha.edu

Journal of Bioinformatics and Computational Biology
|July 5, 2006
PubMed
Summary

This study introduces a machine learning system using a Weighted Naive Bayesian network (WNB) to predict gene functions. Integrating diverse data sources significantly improves prediction accuracy for biological understanding.

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

A Multi-Stage Framework for Refining Infant Daytime Sleep-Wake Labels from Wearable Accelerometer Data.

Sensors (Basel, Switzerland)·2026
Same author

Selective sensitivity of Ph-like B-cell acute lymphoblastic leukemia to BRG1 inhibition identifies a therapeutic vulnerability.

Leukemia·2026
Same author

FATP2-mediated lipid metabolism enhances chimeric antigen receptor T-cell therapy resistance in B-cell acute lymphoblastic leukemia.

Leukemia·2026
Same author

Spermine oxidase-DOX conjugates reshape tumor microenvironment via carbonyl stress to potentiate bladder cancer chemotherapy.

Materials today. Bio·2026
Same author

GPX4 regulates lipid peroxidation and ferroptosis of stored red blood cells.

Blood. Red cells & iron·2026
Same author

Integrated Analysis of Circadian and Sleep Signatures in Depression and Schizophrenia Using Multi-Day Actigraphy.

Bioengineering (Basel, Switzerland)·2026

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning in Genomics

Background:

  • Accurate gene function knowledge is vital for understanding biological mechanisms like regulatory pathways, cell cycles, and diseases.
  • Inferring gene functions computationally is challenging due to complex biological interactions and data sparsity from single sources.

Purpose of the Study:

  • To develop and validate a machine learning system for predicting gene functions using heterogeneous data sources.
  • To demonstrate that integrating multiple complementary data sources enhances prediction accuracy compared to using limited data.

Main Methods:

  • Development of a Weighted Naive Bayesian network (WNB) model for gene function prediction.
  • Integration of diverse data types including gene annotations, expression data, clustering outputs, keyword annotations, and sequence homology.

Related Experiment Videos

  • Training and testing the WNB system on genes from Saccharomyces cerevisiae.

    • Main Results:

    • Experimental results confirm that integrating multiple data sources significantly improves gene function prediction accuracy.
    • The WNB model provides guidelines for data collection, training, and prediction strategies.
    • The system successfully analyzed the contribution of each data source to prediction performance.

    Conclusions:

    • Integrating heterogeneous data sources is a valid and effective strategy for improving computational gene function prediction.
    • The WNB system offers a robust framework for gene function inference and can aid in discovering complex biological relationships.