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

Class prediction in toxicogenomics.

Nandini Raghavan1, Dhammika Amaratunga, Alex Y Nie

  • 1Department of Non-Clinical Biostatistics, Johnson and Johnson Pharmaceutical Research and Development, LLC, Raritan, New Jersey 08869, USA. nraghava@prdus.jnj.com

Journal of Biopharmaceutical Statistics
|March 31, 2005
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

Long-term safety and efficacy of ponesimod in participants with relapsing multiple sclerosis: results from the phase 3 OPTIMUM 5-year long term extension study.

Journal of neurology·2026
Same author

Development of multiple microbiome biomarkers using penalized regression methods.

Journal of applied microbiology·2025
Same author

Corrigendum to "Integrated genomic, proteomic and cognitive assessment in Duchenne Muscular Dystrophy suggest astrocyte centric pathology" [Heliyon Volume 9, Issue 8, August 2023, Article e18530].

Heliyon·2025
Same author

Quasi-Empirical Bayes methods for parameter estimation involving many small samples.

Journal of biopharmaceutical statistics·2025
Same author

Serum metabolomic signatures of patients with rare neurogenetic diseases: an insight into potential biomarkers and treatment targets.

Frontiers in molecular neuroscience·2025
Same author

Phytochemistry and nutraceutical potential of Ceylon Cinnamomum species native to Sri Lanka.

Natural product research·2024

This study introduces a novel method for classifying chemical toxicity using gene expression data. The approach improves accuracy in identifying toxic compounds and their specific effects, like liver toxicity.

Area of Science:

  • Toxicogenomics
  • Bioinformatics
  • Computational Biology

Background:

  • Toxicogenomics studies generate complex data requiring sophisticated statistical analysis.
  • Classifying compound toxicity, particularly hepatotoxicity, is crucial for drug development and risk assessment.

Purpose of the Study:

  • To address statistical complexities in toxicogenomics data analysis.
  • To present a new procedure for classifying compounds into hepatotoxicity classes using gene expression data.

Main Methods:

  • Developed a two-step classification process: first identifying toxic vs. nontoxic compounds, then classifying toxic compounds into specific hepatotoxicity categories.
  • Utilized binary classifiers built with carefully selected genes that best differentiate between toxicity classes.

Related Experiment Videos

  • Employed a voting system among binary classifiers for final class assignment.

    • Main Results:

    • The proposed gene selection strategy significantly reduces misclassification error rates.
    • The selected genes and pathways demonstrate clear biological relevance to toxicity.
    • Successfully classified compounds into distinct hepatotoxicity classes.

    Conclusions:

    • The described methodology offers an effective approach to analyzing toxicogenomics data.
    • Gene selection is a key factor in improving classification accuracy and biological interpretability.
    • This method aids in understanding compound-induced liver toxicity through gene expression patterns.