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

Bayesian network learning with feature abstraction for gene-drug dependency analysis.

Jeong-Ho Chang1, Kyu-Baek Hwang, S June Oh

  • 1Biointelligence Laboratory, School of Computer Science and Engineering, Seoul National University, Seoul 151-742, Korea. jhchang@bi.snu.ac.kr

Journal of Bioinformatics and Computational Biology
|March 8, 2005
PubMed
Summary

This study uses Bayesian networks to analyze gene expression and drug activity data from cancer cell lines. The method effectively identifies key relationships, confirming its utility in cancer research.

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

PKGPT: Expert-Orchestrated Recursive LLM Agent for Automated NONMEM PopPK Modeling with Human Benchmarking.

Pharmaceutics·2026
Same author

Disease- and gene-specific deep learning for pathogenicity prediction of rare missense variants in cancer predisposition genes.

BioData mining·2026
Same author

PKPy: a Python-based framework for automated population pharmacokinetic analysis.

PeerJ·2025
Same author

Pre-Training and Ensembling of Deep Neural Networks for Target Gene Expression Prediction From Landmark Genes.

IEEE transactions on computational biology and bioinformatics·2025
Same author

Gene-specific machine learning for pathogenicity prediction of rare BRCA1 and BRCA2 missense variants.

Scientific reports·2023
Same author

Mothers' use of touch across infants' development and its implications for word learning: Evidence from Korean dyadic interactions.

Infancy : the official journal of the International Society on Infant Studies·2023

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Cancer Research

Background:

  • Analyzing gene expression and drug activity data is crucial for understanding cancer.
  • High-dimensional datasets pose significant challenges for identifying meaningful biological relationships.

Purpose of the Study:

  • To apply Bayesian networks for analyzing gene expression and drug activity data.
  • To address data dimensionality issues using a feature abstraction technique.
  • To uncover relationships between gene expression and drug activity in malignant cells.

Main Methods:

  • Utilized Bayesian networks for probabilistic modeling of joint distributions.
  • Employed a feature abstraction technique to condense large datasets.
  • Applied the method to the NCI60 dataset, comprising gene expression and drug activity profiles.

Related Experiment Videos

Main Results:

  • Learned Bayesian networks identified salient pairwise correlations and known relationships.
  • The feature abstraction method proved effective in managing data dimensionality.
  • Discovered biologically meaningful relationships through literature survey.

Conclusions:

  • Bayesian networks combined with feature abstraction offer a powerful approach for analyzing complex biological datasets.
  • The findings highlight the potential for discovering novel insights into cancer biology and drug responses.