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

Comparison of different computerized classification methods for predicting carcinogenicity from short-term test

R Benigni1, G Pellizzone, A Giuliani

  • 1Laboratory of Comparative Toxicology and Ecotoxicology, Istituto Superiore di Sanitá, Rome, Italy.

Journal of Toxicology and Environmental Health
|January 1, 1989
PubMed
Summary

Predicting chemical carcinogenicity from short-term tests is challenging. A new method, dynamic carcinogenicity assessment (DYCA), shows promise for identifying carcinogens, outperforming K-nearest neighbor (KNN) and linear discriminant analysis.

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

Prospective biomarkers of posttraumatic stress disorder in children and adolescents: a systematic review and meta-analysis.

Translational psychiatry·2026
Same author

Half-Life and Precision Shape Measurement of the 2νββ Decay of ^{130}Te.

Physical review letters·2025
Same author

Primary subtalar arthrodesis in displaced intra-articular calcaneal fracture: a systematic review.

Musculoskeletal surgery·2025
Same author

Occupational Rhinoconjunctivitis Induced by Flaxseed: Identification of Novel Allergenic Proteins From Cupin, Chaperonin, and Enzyme Families.

Journal of investigational allergology & clinical immunology·2025
Same author

First Observation of a Nuclear Recoil Peak at <math></math> (100eV) with Crab: A Potential New Calibration Standard for Cryogenic Detectors.

Journal of low temperature physics·2025
Same author

Search for Fractionally Charged Particles with CUORE.

Physical review letters·2025

Area of Science:

  • Toxicology
  • Computational Biology
  • Biostatistics

Background:

  • Accurate prediction of chemical carcinogenicity from short-term tests remains a significant challenge.
  • Existing mathematical classification methods may not fully capture biological nuances, leading to ambiguous results.
  • The development of robust predictive models is crucial for risk assessment and regulatory decision-making.

Purpose of the Study:

  • To compare the performance of different mathematical classification methods for predicting carcinogenicity.
  • To introduce and evaluate a novel classification method, dynamic carcinogenicity assessment (DYCA), designed to better reflect biological data.
  • To identify the strengths and limitations of linear discriminant analysis, K-nearest neighbor (KNN), and DYCA.

Main Methods:

Related Experiment Videos

  • Comparative analysis of three classification algorithms: linear discriminant analysis, K-nearest neighbor (KNN), and dynamic carcinogenicity assessment (DYCA).
  • Application of these methods to a real-world database of carcinogenicity test results.
  • Evaluation of algorithm performance based on sensitivity to carcinogens and accuracy in identifying noncarcinogens.

Main Results:

  • K-nearest neighbor (KNN) demonstrated inferior performance compared to the other two methods.
  • The novel dynamic carcinogenicity assessment (DYCA) approach exhibited higher sensitivity in identifying potential carcinogens.
  • Linear discriminant analysis proved more effective in accurately classifying noncarcinogens.

Conclusions:

  • Dynamic carcinogenicity assessment (DYCA) offers an improved approach for detecting carcinogens in short-term tests.
  • Linear discriminant analysis remains a valuable tool for identifying noncarcinogens.
  • The choice of classification method impacts the prediction accuracy of carcinogenicity, highlighting the need for tailored approaches.