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

Drug design by machine learning: support vector machines for pharmaceutical data analysis.

R Burbidge1, M Trotter, B Buxton

  • 1University College London, Gower Street, London WCIE 6BT, UK.

Computers & Chemistry
|January 5, 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

The ASSIST CLAD study: A phase 2 randomized controlled trial of mesenchymal stromal cells for new-onset chronic lung allograft dysfunction.

The Journal of heart and lung transplantation : the official publication of the International Society for Heart Transplantation·2026
Same author

Does the format matter? A cross-sectional analysis of suspected injuries and game events across the different versions of field hockey.

Frontiers in sports and active living·2025
Same author

Development and evaluation of a new semi-quantitative and morphometric scoring system for magnetic resonance imaging in adolescents with Osgood Schlatter Disease (The OSIS Score).

European journal of radiology·2025
Same author

Understanding the Interactions Between Loading, Pain Dynamics, and Imaging Characteristics for Osgood Schlatter: A Cross-Sectional Study.

Scandinavian journal of medicine & science in sports·2024
Same author

A comprehensive MRI investigation to identify potential biomarkers of Osgood Schlatter disease in adolescents: A cross sectional study comparing Osgood Schlatter disease with controls.

Scandinavian journal of medicine & science in sports·2024
Same author

Many physiotherapists lack preparedness to prescribe physical activity and exercise to people with musculoskeletal pain: A multi-national survey.

Physical therapy in sport : official journal of the Association of Chartered Physiotherapists in Sports Medicine·2021
Same journal

Constructing a useful tool for characterizing amino acid conformers by means of quantum chemical and graph theory indices.

Computers & chemistry·2002
Same journal

CLiBE: a database of computed ligand binding energy for ligand-receptor complexes.

Computers & chemistry·2002
Same journal

On the solution of mixed-integer nonlinear programming models for computer aided molecular design.

Computers & chemistry·2002
Same journal

Use of the Numerov method to improve the accuracy of the spatial discretisation in finite-difference electrochemical kinetic simulations.

Computers & chemistry·2002
Same journal

Automatic identification by 13C NMR of substituent groups bonded in natural product skeletons.

Computers & chemistry·2002
Same journal

A new redundant variable pruning approach--minor latent variable perturbation-PLS used for QSAR studies on anti-HIV drugs.

Computers & chemistry·2002
See all related articles

Support Vector Machine (SVM) classification excels in predicting drug-target interactions. SVM outperforms other machine learning methods for analyzing structure-activity relationships in drug discovery.

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Machine learning

Background:

  • Structure-activity relationship (SAR) analysis is crucial for drug discovery.
  • Machine learning techniques are increasingly applied to SAR studies.
  • Predicting biological activity, such as enzyme inhibition, aids in identifying potential drug candidates.

Purpose of the Study:

  • To evaluate the performance of Support Vector Machine (SVM) classification for SAR analysis.
  • To compare SVM against other prevalent machine learning algorithms in a benchmark study.
  • To assess the utility of SVM in predicting the inhibition of dihydrofolate reductase by pyrimidines.

Main Methods:

  • Utilized the Support Vector Machine (SVM) classification algorithm.
  • Compared SVM performance against three artificial neural networks, a radial basis function network, and a C5.0 decision tree.

Related Experiment Videos

  • Employed a dataset from the UCI machine learning repository for predicting dihydrofolate reductase inhibition by pyrimidines.

    • Main Results:

    • The SVM classification algorithm demonstrated superior performance in predicting dihydrofolate reductase inhibition compared to other tested methods.
    • SVM significantly outperformed artificial neural networks and a C5.0 decision tree.
    • While a manually capacity-controlled neural network showed comparable results, it required substantially longer training times.

    Conclusions:

    • Support Vector Machine (SVM) classification is a highly effective tool for structure-activity relationship analysis.
    • SVM offers a powerful and efficient alternative to existing machine learning techniques for cheminformatics and drug discovery.
    • The findings suggest SVM's strong potential for accelerating the identification of novel therapeutic agents.