A SAR and QSAR study on 3CLpro inhibitors of SARS-CoV-2 using machine learning methods DOI
Yonghao Zhang, Yujia Tian, Aixia Yan

et al.

SAR and QSAR in environmental research, Journal Year: 2024, Volume and Issue: 35(7), P. 531 - 563

Published: July 2, 2024

The 3C-like Proteinase (3CLpro) of novel coronaviruses is intricately linked to viral replication, making it a crucial target for antiviral agents. In this study, we employed two fingerprint descriptors (ECFP_4 and MACCS) comprehensively characterize 889 compounds in our dataset. We constructed 24 classification models using machine learning algorithms, including Support Vector Machine (SVM), Random Forest (RF), extreme Gradient Boosting (XGBoost), Deep Neural Networks (DNN). Among these models, the DNN- ECFP_4-based Model 1D_2 achieved most promising results, with remarkable Matthews correlation coefficient (MCC) value 0.796 5-fold cross-validation 0.722 on test set. application domains were analysed d

Language: Английский

Docking and Post-Processing of 1 Million Molecules from the CNCL Database in Search of SARS-CoV-2 Mpro Inhibitors DOI
А.В. Сулимов, Danil Kutov, Ivan Ilin

et al.

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 47 - 58

Published: Jan. 1, 2025

Language: Английский

Citations

0
Computer‐assisted Methods and Tools for Structure‐ and Ligand‐based Drug Design DOI
Saurav Kumar Mishra, Sneha Roy,

Tabsum Chhetri

et al.

Published: Nov. 29, 2024

Due to the increasing pandemic with current emerging and ongoing pathogenesis, situation overcome is getting difficult for humans. The research community keenly interested in computational approach therapeutics development, as we have seen pandemic, i.e., COVID-19. Although silico -based experiment not new community, advancement this going day by betterment of humankind. available earlier conventional strategies been successful developing novel drugs therapeutics; however, they a major drawback time cost. Interestingly, computer-assisted approaches are considerable interest due their efficacy accelerating drug development terms cost-effectiveness. Different potential molecules designed through approaches. Computer-assisted discovery significantly impacts overall process advanced high accuracy levels. Innovative techniques allow researchers integrate screen bulk high-throughput biological data generated globally repurposing or finding indications existing drugs. Therefore, study aims briefly introduce how structure- ligand-based were employed discovery. tools databases used perform these also described. Additionally, chapter discusses that using

Language: Английский

Citations

3
A SAR and QSAR study on 3CLpro inhibitors of SARS-CoV-2 using machine learning methods DOI
Yonghao Zhang, Yujia Tian, Aixia Yan

et al.

SAR and QSAR in environmental research, Journal Year: 2024, Volume and Issue: 35(7), P. 531 - 563

Published: July 2, 2024

The 3C-like Proteinase (3CLpro) of novel coronaviruses is intricately linked to viral replication, making it a crucial target for antiviral agents. In this study, we employed two fingerprint descriptors (ECFP_4 and MACCS) comprehensively characterize 889 compounds in our dataset. We constructed 24 classification models using machine learning algorithms, including Support Vector Machine (SVM), Random Forest (RF), extreme Gradient Boosting (XGBoost), Deep Neural Networks (DNN). Among these models, the DNN- ECFP_4-based Model 1D_2 achieved most promising results, with remarkable Matthews correlation coefficient (MCC) value 0.796 5-fold cross-validation 0.722 on test set. application domains were analysed d

Language: Английский

Citations

1