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

Radial basis function network-based transform for a nonlinear support vector machine as optimized by a particle swarm

Li-Juan Tang1, Yan-Ping Zhou, Jian-Hui Jiang

  • 1State Key Laboratory of Chemo/Biosensing and Chemometrics, College of Chemistry and Chemical Engineering, Hunan University, Changsha 410082, P. R. China.

Journal of Chemical Information and Modeling
|June 9, 2007
PubMed
Summary

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

Laser Light Scattering-Enhanced Deep Computer Vision Method for the Detection of Trace Mineral Oil in Vegetable Oils.

Analytical chemistry·2026
Same author

An image-based food quality analysis framework driven by large language models.

Analytical methods : advancing methods and applications·2026
Same author

[Cause Analysis of <i>HLA-B</i> Allele Missed Detection Based on Alltype<sup>TM</sup> Fastplex<sup>TM</sup> Next Generation Sequencing].

Zhongguo shi yan xue ye xue za zhi·2026
Same author

Analysis of HLA genotype in the recipients' different tissues after haploidentical hematopoietic stem cell transplantation.

Frontiers in immunology·2026
Same author

Multiple carbon quantum dots-enhanced excitation-emission matrix fluorescence strategy for accurate vintage discrimination of Anhua dark tea.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026
Same author

Description of the Novel HLA-DQB1*03:03:31 Allele, Identified in a Chinese Individual.

HLA·2026
Same journal

tmGNN-XAI: An Explainable Graph Neural Network Tool for Predicting Electronic Properties of Transition Metal Complexes from SMILES.

Journal of chemical information and modeling·2026
Same journal

QSAR in the Browser: An Interactive Cheminformatics Web Application.

Journal of chemical information and modeling·2026
Same journal

FoldDoF: Utilizing the Primary Degrees of Freedom of Protein Backbone for Geometric Modeling and Generation.

Journal of chemical information and modeling·2026
Same journal

Derisking Affinity Optimization for Macrocycles and Cyclic Peptides: High-Precision Free Energy Simulations across Five Diverse Targets.

Journal of chemical information and modeling·2026
Same journal

An End-User Audit of Reproducibility, Data Leakage, and Overfitting of the Top-Ranked ADMET Prediction Models in TDC Leaderboards.

Journal of chemical information and modeling·2026
Same journal

PFASGroups: An Open-Source Framework for Automated Identification, Structural Classification, and Prioritization of Per- and Polyfluoroalkyl Substances.

Journal of chemical information and modeling·2026
See all related articles
This summary is machine-generated.

This study introduces a novel nonlinear Support Vector Machine (SVM) algorithm using adaptive kernel transform and particle swarm optimization (PSO). This approach enhances quantitative structure-activity relationship (QSAR) predictions by avoiding local optima and improving generalization.

Area of Science:

  • Computational chemistry
  • Machine learning in drug discovery
  • Quantitative Structure-Activity Relationship (QSAR) studies

Background:

  • Support Vector Machines (SVMs) are valuable for QSAR but face challenges with local optima in nonlinear kernel optimization.
  • Overfitting and underfitting are common issues in conventional nonlinear SVMs due to support vector selection and kernel width optimization.

Purpose of the Study:

  • To propose a new nonlinear SVM algorithm that overcomes the limitations of traditional methods.
  • To enhance the performance of SVMs in QSAR studies through adaptive kernel transformation and synergetic parameter optimization.

Main Methods:

  • A novel nonlinear SVM algorithm is developed, incorporating an adaptive kernel transform via a radial basis function network (RBFN).
  • Particle Swarm Optimization (PSO) is employed for synergetic optimization of RBFN parameters (kernel centers, widths) and SVM model coefficients.

Related Experiment Videos

  • The algorithm transforms original variables into a feature space, intrinsically creating a flexible kernel transform.

    • Main Results:

    • The proposed algorithm demonstrated superior performance compared to backpropagation neural networks and conventional nonlinear SVMs in QSAR applications.
    • Applications to HIV-1 reverse transcriptase inhibitor binding affinity and 1-phenylbenzimidazole activity showed significant improvements.
    • Particle Swarm Optimization (PSO) proved efficient in converging to optimal solutions for the complex parameter space.

    Conclusions:

    • The developed adaptive kernel transform SVM algorithm effectively addresses local optima and generalization issues in nonlinear SVM learning.
    • This approach offers a promising and robust method for complex QSAR modeling and drug discovery.
    • The synergetic optimization using PSO allows for a flexible and high-performing kernel transform tailored to the specific QSAR problem.