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 Concept Videos

Structure-Activity Relationships and Drug Design01:28

Structure-Activity Relationships and Drug Design

Drug design is a dynamic field that involves discovering and developing new medications based on specific biological targets. This process heavily relies on structure-activity relationships (SAR) and quantitative structure-activity relationships (QSAR) to guide the design and optimization of efficient drugs.
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence its...
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Highly Efficient Isolation and Rapid Detection of Pancreatic Cancer-Derived Small Extracellular Vesicles by Specific Aggregation from Aptamer-Functionalized DNA Long Chains.

Analytical chemistry·2026
Same author

A Tyndall Effect-Based Visible Aptasensing Platform Enables Sensitive and Isolation-Free Profiling of Small Extracellular Vesicle Surface Proteins.

Nano letters·2025
Same author

CRISPR/Pepper-tDeg: A Live Imaging System Enables Non-Repetitive Genomic Locus Analysis with One Single-Guide RNA.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2024
Same author

Identifying Protein Phosphorylation Site-Disease Associations Based on Multi-Similarity Fusion and Negative Sample Selection by Convolutional Neural Network.

Interdisciplinary sciences, computational life sciences·2024
Same author

Dephosphorylation Switch DNAzyme-RCA Circuit: A Robust Strategy for the Homogeneous and Reliable Detection of FTO Demethylase.

Analytical chemistry·2023
Same author

On-Site-Activated Transmembrane Logic DNA Nanodevice Enables Highly Specific Imaging of Cancer Cells by Targeting Tumor-Related Nucleolin and Intracellular MicroRNA.

Analytical chemistry·2023

Related Experiment Video

Updated: Jun 11, 2026

Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions
08:31

Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions

Published on: December 1, 2020

QSAR modeling of peptide biological activity by coupling support vector machine with particle swarm optimization

Xuan Zhou1, Zhanchao Li, Zong Dai

  • 1School of Chemistry and Chemical Engineering, Sun Yat-Sen University, Guangzhou 510275, PR China.

Journal of Molecular Graphics & Modelling
|July 13, 2010
PubMed
Summary

A new hybrid algorithm combining particle swarm optimization (PSO) and genetic algorithm (GA) optimizes machine learning models and selects key features for peptide quantitative structure-activity relationship (QSAR) studies and protein prediction.

More Related Videos

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions
06:50

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions

Published on: January 26, 2024

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules
10:58

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Published on: July 25, 2013

Related Experiment Videos

Last Updated: Jun 11, 2026

Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions
08:31

Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions

Published on: December 1, 2020

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions
06:50

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions

Published on: January 26, 2024

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules
10:58

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Published on: July 25, 2013

Area of Science:

  • Computational Chemistry
  • Bioinformatics
  • Machine Learning

Background:

  • Quantitative Structure-Activity Relationship (QSAR) studies are crucial for drug discovery and development.
  • Accurate feature selection and model parameter optimization are essential for robust QSAR models.
  • Existing optimization methods may struggle with local optima and efficiency.

Purpose of the Study:

  • To develop a novel hybrid optimization algorithm coupling Particle Swarm Optimization (PSO) and Genetic Algorithm (GA).
  • To simultaneously optimize Support Vector Machine (SVM) kernel parameters and select optimal feature subsets for QSAR.
  • To evaluate the proposed method's efficacy in peptide QSAR and protein structure prediction.

Main Methods:

  • A hybrid PSO-GA algorithm was developed, incorporating GA's crossover and mutation into PSO.
  • The algorithm was applied to optimize SVM kernel parameters and identify feature subsets.
  • Four peptide datasets were used for quantitative structure-activity relationship (QSAR) analysis.
  • A protein dataset was utilized for predicting protein structural class.

Main Results:

  • High correlation coefficients (R) and low root-mean-square errors (RMSEs) were achieved on peptide QSAR datasets.
  • Achieved R values of 1.0000, 0.9508, 1.0000, 0.9995 (training) and 0.9922, 0.9687, 0.9022, 0.7404 (test).
  • Demonstrated good overall success rates in predicting protein structural class.

Conclusions:

  • The coupled PSO-GA method effectively optimizes SVM parameters and selects relevant features.
  • The proposed method shows high potential for applications in peptide QSAR and protein prediction.
  • This approach offers a robust and efficient tool for chemoinformatics and bioinformatics research.