Journal
KNOWLEDGE-BASED SYSTEMS
Volume 231, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.knosys.2021.107433
Keywords
Protein-ligand docking; Differential evolution; Parameter adaptation; Optimization; Molecular docking
Categories
Funding
- Research Foundation for Talented Scholars of Changzhou University, China [ZMF20020459]
- JSPS, Japan KAKENHI [19K12136]
- Changzhou Municipal Science and Technology Bureau, China [CE20205048]
- Grants-in-Aid for Scientific Research [19K12136] Funding Source: KAKEN
Ask authors/readers for more resources
This study utilizes an adaptive differential evolution algorithm and the scoring function of AutoDock Vina to address the protein-ligand docking problem, with experimental results indicating its effectiveness compared to other evolutionary algorithms.
The protein-ligand docking problem plays a crucial role in the drug discovery process and remains challenging in bioinformatics. A successful protein-ligand docking approach depends on two key factors: an efficient search strategy and an effective scoring function. In this study, we attempt to use an adaptive differential evolution (DE) algorithm as the search strategy. The search ability of the proposed DE algorithm is improved by incorporating a parameter adaptation scheme and a modified mutation strategy. In addition, the scoring function of the classical AutoDock Vina suite is employed as the fitness function of the proposed approach. Finally, the performance of the adaptive DE method in solving the protein-ligand docking problem is evaluated on 40 test docking instances. The experimental results and statistical analysis demonstrate the effectiveness of the proposed adaptive DE algorithm compared with five other classical evolutionary algorithms. The results of this study reveal that employing powerful evolutionary algorithms, such as adaptive DE, contributes to solving the protein-ligand docking problem. (C) 2021 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available