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

Feature selection for structure-activity correlation using binary particle swarms.

Dimitris K Agrafiotis1, Walter Cedeño

  • 13-Dimensional Pharmaceuticals, Inc., 665 Stockton Drive, Exton, Pennsylvania 19341, USA. dimitris@3dp.com

Journal of Medicinal Chemistry
|February 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

Epilogue to the Gerald Maggiora Festschrift: a tribute to an exemplary mentor, colleague, collaborator, and innovator.

Journal of computer-aided molecular design·2022
Same author

Accurate prediction of clinical stroke scales and improved biomarkers of motor impairment from robotic measurements.

PloS one·2021
Same author

Xcellerate Investigator Portal: A New Web-Based Tool for Online Delivery of Central Laboratory Data, Reports, and Communications to Clinical Sites.

SLAS technology·2020
Same author

A new risk and issue management system to improve productivity, quality, and compliance in clinical trials.

JAMIA open·2020
Same author

A dimensional warehouse for integrating operational data from clinical trials.

Database : the journal of biological databases and curation·2019
Same author

A late-binding, distributed, NoSQL warehouse for integrating patient data from clinical trials.

Database : the journal of biological databases and curation·2019
Same journal

Rational Development of Activatable Prodrugs of the GSTP1 Inhibitor NBDHEX: Turn-On NIR Fluorogenic Drug Delivery with Selective Anticancer Activity.

Journal of medicinal chemistry·2026
Same journal

Recent Highlights in the Discovery and Design of Antibody-Drug Conjugates.

Journal of medicinal chemistry·2026
Same journal

One Face, Three Solutions: Structural Convergence in PD-L1 Inhibition across Antibodies, Macrocycles, and Small Molecules.

Journal of medicinal chemistry·2026
Same journal

A Potent and Selective Quinolone-Based PTPN22 Inhibitor with Improved Immunotherapeutic Activity.

Journal of medicinal chemistry·2026
Same journal

Structure-Based Discovery of (<i>E</i>)- and (<i>Z</i>)-4-Oxobut-2-enoate Derivatives as Novel Covalent Pin1 Inhibitors with Antitumor Activity.

Journal of medicinal chemistry·2026
Same journal

Hybrids of Benzenesulfonamide Oxadiazole Derivatives with Dual CA II and COX-2 Inhibitory Activity Demonstrating Antiglaucoma and Anti-inflammatory Action: Synthesis, In Silico Insights, and In Vitro and In Vivo Bioevaluation.

Journal of medicinal chemistry·2026
See all related articles

A novel particle swarm optimization algorithm enhances feature selection for quantitative structure-activity relationship (QSAR) models. This method efficiently identifies optimal molecular descriptors, improving predictive model accuracy and diversity.

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Machine learning

Background:

  • Structure-activity relationship (SAR) and structure-property correlation (SPC) are crucial in drug discovery and materials science.
  • Effective feature selection is vital for building accurate and parsimonious predictive models.
  • Existing methods like simulated annealing have limitations in exploring diverse solution spaces.

Purpose of the Study:

  • To introduce a new feature selection algorithm for SAR and SPC.
  • To adapt particle swarm optimization (PSO) for discrete feature selection problems.
  • To construct parsimonious quantitative structure-activity relationship (QSAR) models using feed-forward neural networks.

Main Methods:

  • Utilized a particle swarm optimization (PSO) algorithm adapted for feature selection.

Related Experiment Videos

  • Viewed particle location vectors as probabilities and employed roulette wheel selection for subset construction.
  • Applied the algorithm to build QSAR models using feed-forward neural networks.

    • Main Results:

    • The PSO-based feature selection method was tested on three classical QSAR datasets.
    • The algorithm demonstrated favorable comparison against simulated annealing.
    • Identified a superior and more diverse set of solutions within the same simulation time.

    Conclusions:

    • The proposed particle swarm optimization algorithm is effective for feature selection in QSAR.
    • This approach offers an advantage over simulated annealing in terms of solution quality and diversity.
    • The method facilitates the development of more robust and interpretable predictive models.