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

Gene function classification using Bayesian models with hierarchy-based priors.

Babak Shahbaba1, Radford M Neal

  • 1Dept. of Public Health Sciences, Biostatistics, University of Toronto, Toronto, Ontario, Canada. babak@stat.utoronto.ca

BMC Bioinformatics
|October 14, 2006
PubMed
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

Scaling Up Bayesian Neural Networks with Neural Networks.

Transactions on machine learning research·2026
Same author

A Bayesian Time-Varying Psychophysiological Interaction Model.

Data science in science·2026
Same author

Neurodatascience: Past, Present, and Future.

Data science in science·2026
Same author

A HORSESHOE MIXTURE MODEL FOR BAYESIAN SCREENING WITH AN APPLICATION TO LIGHT SHEET FLUORESCENCE MICROSCOPY IN BRAIN IMAGING.

The annals of applied statistics·2026
Same author

Optimal Transport based Cross-Domain Integration for Heterogeneous Data.

Journal of the American Statistical Association·2025
Same author

REINFORCEMENT LEARNING FOR INDIVIDUAL OPTIMAL POLICY FROM HETEROGENEOUS DATA.

Annals of statistics·2025
Same journal

OpenIMC: an open-source platform for analyzing single-cell and spatial proteomics by imaging mass cytometry.

BMC bioinformatics·2026
Same journal

NAP: an open source pipeline for cross-domain microbiome profiling using Nanopore sequencing-derived amplicon data.

BMC bioinformatics·2026
Same journal

SurvGME: an R package for survival analysis with graphical and measurement error models.

BMC bioinformatics·2026
Same journal

SimMapNet: a Bayesian framework for gene regulatory network inference using gene ontology similarities as external hint.

BMC bioinformatics·2026
Same journal

Dual channel drug-drug interactions extraction based on cross attention.

BMC bioinformatics·2026
Same journal

FeSseqdb: a curated sequence-level database and interpretable machine learning framework for identifying iron-sulfur proteins.

BMC bioinformatics·2026
See all related articles

Improved gene function prediction is achieved using hierarchical Bayesian models. These models leverage phylogenetic descriptors, sequence attributes, and secondary structure for higher accuracy in classifying Open Reading Frames (ORFs).

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Gene function annotation is crucial for understanding biological systems.
  • Current methods may not fully leverage the hierarchical nature of functional classes.
  • Predicting gene function aids in deciphering the roles of Open Reading Frames (ORFs).

Purpose of the Study:

  • To enhance gene function annotation accuracy by incorporating a hierarchical classification scheme.
  • To compare the performance of different Bayesian models for gene function prediction.
  • To develop an improved method for combining diverse data sources for classification.

Main Methods:

  • Utilized phylogenetic descriptors, sequence-based attributes, and predicted secondary structure.
  • Developed and compared three Bayesian models: ordinary multinomial logit (MNL), nested MNL, and hierarchical prior MNL.

Related Experiment Videos

  • Implemented a novel scheme for integrating multiple sources of information.

    • Main Results:

    • All Bayesian models demonstrated substantial improvement over the C5 decision tree algorithm.
    • The MNL model with a hierarchical prior achieved superior performance compared to non-hierarchical and nested MNL models.
    • The new data combination approach yielded higher accuracy than using individual data sources.

    Conclusions:

    • Bayesian models incorporating hierarchical prior information significantly improve gene function prediction accuracy.
    • The developed methods offer a more effective approach to classifying gene functions.
    • Accurate gene function prediction is achievable through advanced computational modeling.