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

Fragment generation and support vector machines for inducing SARs.

S Kramer1, E Frank, C Helma

  • 1Institute for Computer Science, Machine Learning Lab, Albert-Ludwigs-University Freiburg, Germany. skramer@informatik.uni-freiburg.de

SAR and QSAR in Environmental Research
|November 22, 2002
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

Prediction of adverse drug reactions using decision tree modeling.

Clinical pharmacology and therapeutics·2010
Same author

Predictive models for carcinogenicity and mutagenicity: frameworks, state-of-the-art, and perspectives.

Journal of environmental science and health. Part C, Environmental carcinogenesis & ecotoxicology reviews·2009
Same author

Prediction of chemical toxicity with local support vector regression and activity-specific kernels.

SAR and QSAR in environmental research·2008
Same author

Validation of counter propagation neural network models for predictive toxicology according to the OECD principles: a case study.

SAR and QSAR in environmental research·2006
Same author

Data mining and knowledge discovery in predictive toxicology.

SAR and QSAR in environmental research·2005
Same author

Comorbidity in depression.

Acta psychiatrica Scandinavica. Supplementum·2003

This study introduces a novel method for predicting Structure-Activity Relationships (SARs) using structural fragments and Support Vector Machines (SVMs). The approach efficiently identifies relevant chemical fragments for improved SAR prediction in biochemical databases.

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Machine learning

Background:

  • Structure-Activity Relationships (SARs) are crucial for drug discovery and chemical safety assessment.
  • Existing methods for SAR induction can be computationally intensive or limited in scope.
  • Bio-chemical databases contain vast amounts of information on chemical compounds.

Purpose of the Study:

  • To develop and evaluate a new computational approach for SAR induction.
  • To leverage structural fragments and Support Vector Machines (SVMs) for enhanced SAR prediction.
  • To assess the efficiency and accuracy of the proposed method in predicting carcinogenicity and mutagenicity.

Main Methods:

  • Generation of structural fragments from chemical compounds based on frequency and generality constraints.

Related Experiment Videos

  • Application of Support Vector Machines (SVMs) for SAR induction using the generated fragments.
  • Querying for fragments within specified minimum and maximum frequency ranges in bio-chemical datasets.

    • Main Results:

    • The fragment generation and SVM approach successfully identified relevant fragments for SAR induction.
    • Experiments demonstrated satisfactory predictive accuracy for carcinogenicity and mutagenicity.
    • Frequency-based fragment queries were processed within a reasonable timeframe.

    Conclusions:

    • The proposed method offers a viable and efficient approach to SAR induction.
    • SVMs are well-suited for handling the high dimensionality of fragment-based SAR analysis.
    • Further validation is recommended to confirm the broad applicability of this SAR induction technique.