NRBO-AGP: A novel feature selection approach for accurate protein solubility prediction
Yazarlar (2)
Dr. Öğr. Üyesi Zehra ELMI İstinye Üniversitesi, Türkiye
Soheil Elmı
Koç University, Türkiye
Koç University, Türkiye
| Makale Türü |
Özgün Makale
(SSCI, AHCI, SCI, SCI-Exp dergilerinde yayınlanan tam makale)
|
||
| Dergi Adı | Expert Systems with Applications (Q1) | ||
| Dergi ISSN | 0957-4174 Wos Dergi Scopus Dergi | ||
| Dergi Tarandığı Indeksler | SCI-Expanded | ||
| Makale Dili | İngilizce | Basım Tarihi | 01-2026 |
| Cilt / Sayı / Sayfa | 296 / 1 / 1–23 | DOI | 10.1016/j.eswa.2025.129194 |
| Makale Linki | https://www.sciencedirect.com/science/article/pii/S0957417425028106 | ||
| UAK Araştırma Alanları |
Yapay Zeka
Robotik
|
||
| Özet |
| Protein solubility determines how well a protein dissolves in an aqueous solution, and this property is a critical factor in the functional analysis of proteins and biotechnological applications. Accurately estimating solubility can provide significant advantages in areas such as protein engineering and drug discovery. This study proposes a new feature selection method, Newton-Raphson-based Optimization and Adaptive Gradient Perturbation (NRBO-AGP) for predicting protein solubility. The research combines the accuracy and speed of the Newton-Raphson method with the capacity of population-based optimization techniques to balance exploration and exploitation. Using 3144 protein sequences from the eSOL database, descriptor features were obtained for each protein, resulting in a dataset with 3104 features. The performance of NRBO-AGP was compared with eight different metaheuristic algorithms and … |
| Anahtar Kelimeler |
| Drug discovery | Feature selection | Metaheuristic approach | Protein solubility prediction |
Science Direct
NRBO-AGP: A novel feature selection approach for accurate protein solubility prediction
| Atıf Sayıları | |
| Scopus | 2 |
| Google Scholar | 3 |