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

Identifying P-glycoprotein substrates using a support vector machine optimized by a particle swarm.

Jianping Huang1, Guangli Ma, Ishtiaq Muhammad

  • 1Pharmaceutical Informatics Institute, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310027, China.

Journal of Chemical Information and Modeling
|July 5, 2007
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

Critical slowing down of semiarid vegetation resilience is amplified by intensifying heatwaves.

Nature communications·2026
Same author

Ultra flash cold events under global warming.

Nature communications·2026
Same author

Application and Evaluation of a NOAA GFS-Driven Air Quality Model Using CMAQv5.4 and High-Resolution Emissions: FIREX-AQ 2019.

Journal of geophysical research. Atmospheres : JGR·2026
Same author

Population pharmacokinetics and exposure-response modelling of firsekibart (GenSci048) in patients with acute gout flare: Implications for fixed-dose optimization.

British journal of clinical pharmacology·2026
Same author

In tune with AI: Singing as a social surrogate to ease loneliness and foster social connection.

Applied psychology. Health and well-being·2026
Same author

Experimental Determination of Isothermal Sections in the Ni-Al-Cr-Ru Quaternary System: Implications for Ni-Based Superalloys and High-Entropy Alloys.

Materials (Basel, Switzerland)·2026

Computational models accurately predict P-glycoprotein (P-gp) substrates, aiding cancer treatment and drug discovery. These advanced methods, utilizing Particle Swarm (PS) and Support Vector Machine (SVM), achieve over 90% accuracy in identifying drug efflux pump substrates.

Area of Science:

  • Computational chemistry and bioinformatics
  • Pharmacology and drug discovery
  • Cancer therapeutics

Background:

  • P-glycoprotein (P-gp) is a key drug efflux pump involved in multidrug resistance in cancer and affecting drug pharmacokinetics.
  • Understanding P-gp substrate specificity is crucial for effective chemotherapy and drug development, but its molecular mechanisms remain unclear.
  • Computational methods offer a promising approach to predict P-gp substrates and guide drug design.

Purpose of the Study:

  • To develop highly accurate quantitative structure-activity relationship (QSAR) models for predicting P-glycoprotein (P-gp) substrates.
  • To present a modified Particle Swarm (PS) algorithm for efficient molecular descriptor selection in QSAR model construction.
  • To identify key molecular descriptors associated with P-gp substrate specificity using PS and Support Vector Machine (SVM) approaches.

Related Experiment Videos

Main Methods:

  • Development and application of a modified Particle Swarm (PS) algorithm as a wrapper for feature selection in QSAR modeling.
  • Construction of predictive QSAR models using Multiple Linear (ML) regression and Support Vector Machine (SVM) algorithms.
  • Utilizing PS and SVM to analyze a dataset for identifying molecular descriptors linked to P-gp substrate specificity.

Main Results:

  • Achieved prediction accuracy exceeding 90% for P-gp substrates using the developed PS-SVM models.
  • The applied models demonstrated higher accuracy and employed fewer variables compared to previous studies.
  • Identified significant molecular descriptors contributing to P-gp substrate specificity through data analysis.

Conclusions:

  • The developed computational models, particularly the PS-SVM approach, are effective for accurately predicting P-gp substrates.
  • This study provides valuable insights into P-gp substrate specificity, aiding in the design of novel therapeutics and overcoming drug resistance.
  • The modified PS algorithm enhances QSAR model construction by optimizing molecular descriptor selection for predictive accuracy.