Related Experiment Video
Updated: Jan 29, 2026

In Silico Modeling Method for Computational Aquatic Toxicology of Endocrine Disruptors: A Software-Based Approach Using QSAR Toolbox
Published on: August 28, 2019
QSAR classification model for diverse series of antifungal agents based on improved binary differential search
A M Al-Fakih1,2, Z Y Algamal3, M H Lee4
1a Department of Chemistry , Universiti Teknologi Malaysia , Johor , Malaysia.
An improved binary differential search algorithm enhances quantitative structure-activity relationship (QSAR) classification for antimicrobial compounds. The V4 transfer function achieved the best results, improving accuracy and reducing computational complexity.
Area of Science:
- Computational chemistry
- Medicinal chemistry
- Bioinformatics
Background:
- Quantitative structure-activity relationship (QSAR) models are crucial for drug discovery.
- The binary differential search (BDS) algorithm is a metaheuristic optimization technique used in QSAR.
- Improving the efficiency and accuracy of QSAR classification is essential for identifying novel antimicrobial agents.
Purpose of the Study:
- To propose an improved binary differential search (improved BDS) algorithm for QSAR classification.
- To investigate the impact of different transfer functions on the performance of the BDS algorithm.
- To identify the optimal transfer function for QSAR classification of Candida albicans inhibitors.
Main Methods:
- Eight types of transfer functions were evaluated within the improved BDS algorithm.
- Performance metrics included classification accuracy (CA), G-mean, and area under the curve.
- Statistical significance of differences between functions was assessed using the Kruskal-Wallis test.
Main Results:
- The V4 transfer function demonstrated superior performance compared to other functions, including S1.
- The V4 function achieved the highest classification accuracy (98.07%) and G-mean (0.977%).
- The V4 function required the fewest iterations and selected the minimum number of descriptors.
Conclusions:
- The V4 transfer function significantly enhances the performance of the original BDS algorithm for QSAR classification.
- The improved BDS algorithm with the V4 function is effective for identifying antimicrobial compounds against Candida albicans.
- This study provides a robust method for optimizing QSAR models in drug discovery.
Related Concept Videos
Spasmolytic Agents: Chemical Classification
A major class of centrally acting spasmolytics is the α2-agonist, such as tizanidine. These drugs bind to α2-adrenoceptors, inhibiting the release of the excitatory neurotransmitter glutamate. They also...
Binary Fission
Binary Fission
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Modeling with Differential Equations
Classification of Titrimetric Analysis Based on Reaction Types
Titrations between an acid and a base lead to neutralization reactions that form...

