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

Boosting: an ensemble learning tool for compound classification and QSAR modeling.

Vladimir Svetnik1, Ting Wang, Christopher Tong

  • 1Biometrics Research and Molecular Systems, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065, USA. vladimir_svetnik@merck.com

Journal of Chemical Information and Modeling
|June 1, 2005
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

Imaginary Poynting momentum: polarization topology and versatile optical manipulation.

National science review·2026
Same author

Observation of Spin-Duality Breaking in Pancharatnam-Berry Metasurfaces.

Physical review letters·2026
Same author

Local-nonlocal assisted multifunctional photonic crystals.

Light, science & applications·2026
Same author

J-shaped association between serum bicarbonate and 28-day ICU mortality in adult patients with sepsis: A multicenter cohort analysis.

Medicine·2026
Same author

Robust chirality through merging BICs.

Light, science & applications·2026
Same author

Mechanical interplay between adipose tissues and disease progression.

Bioengineering & translational medicine·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
Same journal

DeepKbhb: Context-Aware Prediction of Human Lysine β-Hydroxybutyrylation Sites.

Journal of chemical information and modeling·2026
Same journal

HyperDC: A Non-Uniform Hypergraph Framework for Dual- and Higher-Order Drug Combination Recommendation Across Diverse Complex Diseases.

Journal of chemical information and modeling·2026
Same journal

Correction to "AstraMEV (AI-Guided Structural Assembly of Multi-Epitope Vaccines) Against Infectious Bronchitis Virus".

Journal of chemical information and modeling·2026
Same journal

MolPy: A Large Language Model-Friendly Toolkit for Reactive Topology Editing in Polymer Simulations.

Journal of chemical information and modeling·2026
Same journal

Molecular Mechanisms of KIT Receptor Dimerization and Oncogenic Activation Revealed by Multiscale Simulations.

Journal of chemical information and modeling·2026
See all related articles

Stochastic Gradient Boosting (SGB) predicts compound biological activity from molecular structure. This machine learning method shows performance competitive with Random Forest and other QSAR approaches.

Area of Science:

  • Computational chemistry
  • Machine learning
  • Cheminformatics

Background:

  • Predicting compound biological activity is crucial in drug discovery.
  • Quantitative Structure-Activity Relationship (QSAR) models are widely used.
  • Ensemble learning methods offer robust predictive capabilities.

Purpose of the Study:

  • To apply Stochastic Gradient Boosting (SGB), a machine learning algorithm, for predicting compound biological activity.
  • To evaluate SGB's performance against established QSAR and ensemble methods.
  • To demonstrate SGB's utility in analyzing cheminformatics data.

Main Methods:

  • Stochastic Gradient Boosting (SGB) was employed for classification and regression tasks.
  • SGB builds models stage-wise by fitting regression trees to the gradient of a loss function.

Related Experiment Videos

  • The method was applied to 10 publicly available cheminformatics datasets.

    • Main Results:

    • SGB demonstrated performance comparable to Random Forest.
    • The method's results were competitive with or superior to other QSAR techniques.
    • SGB's variable importance and partial dependence plots were utilized for model interpretation.

    Conclusions:

    • Stochastic Gradient Boosting is an effective tool for predicting compound biological activity.
    • SGB offers a competitive alternative to existing QSAR and ensemble learning methods.
    • The interpretability features of SGB enhance its practical application in cheminformatics.