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

Multivariate QSAR analysis of a skin sensitization database

M T Cronin1, D A Basketter

  • 1School of Pharmacy, Liverpool John Moores University, UK.

SAR and QSAR in Environmental Research
|January 1, 1994
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

Interspecies assessment factors and skin sensitization risk assessment.

Regulatory toxicology and pharmacology : RTP·2018
Same author

Advice for patients with hair dye allergy remains 'stop using permanent hair dyes'.

The British journal of dermatology·2016
Same author

Skin sensitization: Implications for integration of clinical data into hazard identification and risk assessment.

Human & experimental toxicology·2015
Same author

Structure-permeability Relationships for Transcorneal Penetration.

Alternatives to laboratory animals : ATLA·2014
Same author

T helper cell 2 immune skewing in pregnancy/early life: chemical exposure and the development of atopic disease and allergy.

The British journal of dermatology·2014
Same author

The hapten-atopy hypothesis III: the potential role of airborne chemicals.

The British journal of dermatology·2013

Regulatory assessment of chemical skin sensitization currently relies on animal testing. This study explored quantitative structure-activity relationship (QSAR) models, finding statistical limitations for predicting sensitization potential.

Area of Science:

  • Toxicology
  • Computational Chemistry
  • Dermatology

Background:

  • Regulatory bodies require assessment of new chemical skin sensitization potential.
  • Current methods predominantly utilize animal testing, raising ethical and efficiency concerns.
  • Developing in silico alternatives is crucial for modern chemical safety evaluation.

Purpose of the Study:

  • To investigate the utility of multivariate quantitative structure-activity relationship (QSAR) analysis for predicting chemical skin sensitization.
  • To evaluate the predictive performance of principal component analysis (PCA) and stepwise discriminant analysis (SDA) models.
  • To explore the limitations of statistical models in capturing complex structure-activity relationships for sensitization.

Main Methods:

  • A database of organic compounds from guinea pig maximization tests was compiled.

Related Experiment Videos

  • Compounds were characterized by whole molecule parameters and reactivity-associated structural features.
  • Multivariate statistical analyses, including PCA and SDA, were applied to the dataset.

    • Main Results:

    • PCA demonstrated moderate utility in reducing data dimensionality but limited predictive power.
    • SDA yielded a fourteen-parameter model (twelve structural features) with 82.6% cross-validated prediction accuracy.
    • A trend towards predicting non-sensitization was observed, indicating model limitations in discriminating classes.

    Conclusions:

    • Statistical QSAR models, including SDA, show limitations in accurately predicting skin sensitization potential.
    • The identified structural features may be better suited for expert systems to identify potential hazards.
    • Future research should focus on alternative approaches, like expert systems, to overcome statistical model constraints.