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

Warmr: a data mining tool for chemical data.

R D King1, A Srinivasan, L Dehaspe

  • 1Department of Computer Science, University of Wales, Aberystwyth Penglais, Ceredigion, UK.

Journal of Computer-Aided Molecular Design
|March 29, 2001
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

Integrating multimodal prehabilitation into enhanced recovery after surgery programs (MPhERAS) for elderly patients: a systematic review and meta-analysis of randomized controlled trials and cohort studies.

Techniques in coloproctology·2025
Same author

<i>Meso</i>-Modified Porphyrinoids: Stimuli-Driven Conformational Plasticity, Modulation of π-Conjugation, and Bis-Rh(I) Complexation.

Inorganic chemistry·2025
Same author

Nonalternant Acenaphthylene-Fused Carbaporphyrins: Topological Modulation of π-Delocalization, (Anti)aromaticity, and B<sup>III</sup> Coordination.

Organic letters·2025
Same author

Siamese Twin Homocarbaporphyrin Dimer: Nonplanar Architecture, Localized Conjugation and Bis-B<sup>III</sup> Complex.

Chemistry, an Asian journal·2025
Same author

<i>E</i>-Stilbene-Imprinted Cyclic Diphyrin and Its B<sup>III</sup> Complex.

Organic letters·2025
Same author

Persistent Uninterpretable or Failed Prenatal Cell-Free DNA Screening Indicates a High-Risk Pregnancy and is Associated With Biological Factors Interfering With cfDNA-Analysis: A Prospective Cohort Study.

Prenatal diagnosis·2025

Warmr, an Inductive Logic Programming (ILP) data mining algorithm, successfully identified frequent chemical substructures for predicting carcinogenicity. This approach enhances chemical database analysis and improves predictive model accuracy.

Area of Science:

  • Chemoinformatics
  • Computational Chemistry
  • Machine Learning

Background:

  • Manual analysis of large chemical databases is infeasible.
  • Inductive Logic Programming (ILP) offers potential for structural chemical data mining.
  • Existing methods may not fully leverage complex structure-activity relationships.

Purpose of the Study:

  • Introduce Warmr, the first ILP data mining algorithm for chemoinformatics.
  • Demonstrate Warmr's utility on a rodent carcinogenicity dataset.
  • Evaluate the value of frequent substructures in chemical data analysis.

Main Methods:

  • Applied Warmr to a chemical compound carcinogenicity database.
  • Identified frequent substructures within the dataset.
  • Converted substructures into probabilistic prediction rules.

Related Experiment Videos

  • Assessed rule accuracy and predictive power.
  • Utilized substructures to establish complexity bounds for predictive rules.

    • Main Results:

    • Warmr successfully identified frequent substructures, adding value to the database.
    • Probabilistic rules derived from substructures accurately predicted carcinogenicity.
    • Proved no accurate prediction rule exists with fewer than seven conditions.
    • Frequent substructures improved the accuracy of statistical and machine learning models.

    Conclusions:

    • Warmr and ILP data mining are valuable tools for chemical database analysis.
    • Frequent substructures provide insights into structure-activity relationships in carcinogenesis.
    • This study establishes a lower bound on the complexity required for accurate carcinogenicity prediction based on substructures.