Integrative Machine Learning, Virtual Screening, and Molecular Modeling for BacA-Targeted Anti-Biofilm Drug Discovery Against Staphylococcal Infections DOI Creative Commons
Ahmad Almatroudi

Crystals, Год журнала: 2024, Номер 14(12), С. 1057 - 1057

Опубликована: Дек. 6, 2024

The rise in antibiotic-resistant Staphylococcal infections necessitates innovative approaches to identify new therapeutic agents. This study investigates the application of machine learning models potential phytochemical inhibitors against BacA, a target related infections. Active compounds were retrieved from BindingDB while decoy was generated DUDE. RDKit utilized for feature engineering. Machine such as k-nearest neighbors (KNN), support vector (SVM), random forest (RF), and naive Bayes (NB) trained on an initial dataset consisting 226 active chemicals 2550 inert compounds. Accompanied by MCC 0.93 accuracy 96%, RF performed better. Utilizing model, library 9000 phytochemicals screened, identifying 300 potentially compounds, which 192 exhibited drug-like properties further analyzed through molecular docking studies. Molecular results identified Ergotamine, Withanolide E, DOPPA top BacA protein, accompanied interaction affinities −8.8, −8.1, −7.9 kcal/mol, respectively. dynamics (MD) applied 100 ns these hits evaluate their stability dynamic behavior. RMSD, RMSF, SASA, Rg analyses showed that all complexes remained stable throughout simulation period. Binding energy calculations using MMGBSA analysis revealed BacA_Withanolide E complex most favorable binding profile with significant van der Waals interactions substantial reduction gas-phase energy. It also contributed significantly electrostatic played secondary role. integration MD simulations proved effective promising inhibitors, emerging potent candidate. These findings provide pathway developing antibacterial agents infections, pending experimental validation optimization.

Язык: Английский

Evolution of computational techniques against various KRAS mutants in search for therapeutic drugs: a review article DOI
Asif Mehmood, Mohammed Ageeli Hakami, Hanan A. Ogaly

и другие.

Cancer Chemotherapy and Pharmacology, Год журнала: 2025, Номер 95(1)

Опубликована: Апрель 7, 2025

Язык: Английский

Процитировано

0
Decoding KRAS Dynamics: Exploring the Impact of Mutations and Inhibitor Binding DOI
Divya Pandey, Kuldeep K. Roy

Archives of Biochemistry and Biophysics, Год журнала: 2024, Номер unknown, С. 110279 - 110279

Опубликована: Дек. 1, 2024

Язык: Английский

Процитировано

2
Elucidating the interactions of advanced glycation end products with RAGE, employing molecular docking and MD simulation approaches: Implications of potent therapeutic for diabetes and its related complications DOI Creative Commons

Chandni Hayat,

Muhammad Yaseen, Sajjad Ahmad

и другие.

Journal of Molecular Liquids, Год журнала: 2024, Номер 416, С. 126467 - 126467

Опубликована: Ноя. 13, 2024

Язык: Английский

Процитировано

1
Decoding Kras Dynamics: Exploring the Impact of Mutations and Inhibitor Binding DOI
Divya Pandey,

Kuldeep Kumar Roy

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

0
3D physiologically-informed deep learning for drug discovery of a novel vascular endothelial growth factor receptor-2 (VEGFR2) DOI Creative Commons
Meng‐Yang Xu, Xiaoyue Xiao, Yinglu Chen

и другие.

Heliyon, Год журнала: 2024, Номер 10(16), С. e35769 - e35769

Опубликована: Авг. 1, 2024

Angiogenesis is an essential process in tumorigenesis, tumor invasion, and metastasis, intriguing pathway for drug discovery. Targeting vascular endothelial growth factor receptor 2 (VEGFR2) to inhibit angiogenic pathways has been widely explored adopted clinical practice. However, most drugs, such as the Food Drug Administration -approved axitinib (ATC code: L01EK01), have considerable side effects limited tolerability. Therefore, there urgent need development of novel VEGFR2 inhibitors. In this study, we propose a strategy design potential candidates targeting using three-dimensional (3D) deep learning structural modeling methods. A geometric-enhanced molecular representation method (GEM) model employing graph neural network (GNN) its underlying predictive algorithm was used predict activity candidates. method, flexible docking performed screen data with high affinity explore mechanism Small -molecule compounds consistently improved properties were identified based on intersection scores obtained from both Candidates GEM-GNN selected silico dynamics simulations further validate their efficacy. The enabled identification candidate potentially more favorable than existing drug, axitinib, while achieving higher

Язык: Английский

Процитировано

0
Identification of potential natural product inhibitors against the Mpro enzyme of Covid-19: a computational study DOI
Amir Zeb, Bader S. Alotaibi, Muhammad Haroon

и другие.

Chemical Papers, Год журнала: 2024, Номер 79(1), С. 533 - 543

Опубликована: Ноя. 15, 2024

Язык: Английский

Процитировано

0
Integrative Machine Learning, Virtual Screening, and Molecular Modeling for BacA-Targeted Anti-Biofilm Drug Discovery Against Staphylococcal Infections DOI Creative Commons
Ahmad Almatroudi

Crystals, Год журнала: 2024, Номер 14(12), С. 1057 - 1057

Опубликована: Дек. 6, 2024

The rise in antibiotic-resistant Staphylococcal infections necessitates innovative approaches to identify new therapeutic agents. This study investigates the application of machine learning models potential phytochemical inhibitors against BacA, a target related infections. Active compounds were retrieved from BindingDB while decoy was generated DUDE. RDKit utilized for feature engineering. Machine such as k-nearest neighbors (KNN), support vector (SVM), random forest (RF), and naive Bayes (NB) trained on an initial dataset consisting 226 active chemicals 2550 inert compounds. Accompanied by MCC 0.93 accuracy 96%, RF performed better. Utilizing model, library 9000 phytochemicals screened, identifying 300 potentially compounds, which 192 exhibited drug-like properties further analyzed through molecular docking studies. Molecular results identified Ergotamine, Withanolide E, DOPPA top BacA protein, accompanied interaction affinities −8.8, −8.1, −7.9 kcal/mol, respectively. dynamics (MD) applied 100 ns these hits evaluate their stability dynamic behavior. RMSD, RMSF, SASA, Rg analyses showed that all complexes remained stable throughout simulation period. Binding energy calculations using MMGBSA analysis revealed BacA_Withanolide E complex most favorable binding profile with significant van der Waals interactions substantial reduction gas-phase energy. It also contributed significantly electrostatic played secondary role. integration MD simulations proved effective promising inhibitors, emerging potent candidate. These findings provide pathway developing antibacterial agents infections, pending experimental validation optimization.

Язык: Английский

Процитировано

0