A Multi-Model Machine Learning Framework for Identifying Raloxifene as a Novel RNA Polymerase Inhibitor from FDA-Approved Drugs
RNA-dependent RNA polymerase (RdRP) represents a critical target for antiviral drug development. We developed a multi-model machine learning framework combining five traditional algorithms (ExtraTreesClassifier, RandomForestClassifier, LGBMClassifier, BernoulliNB, and BaggingClassifier) with a CNN d...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Current Issues in Molecular Biology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1467-3045/47/5/315 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849710853578817536 |
|---|---|
| author | Nhung Thi Hong Van Minh Tuan Nguyen |
| author_facet | Nhung Thi Hong Van Minh Tuan Nguyen |
| author_sort | Nhung Thi Hong Van |
| collection | DOAJ |
| description | RNA-dependent RNA polymerase (RdRP) represents a critical target for antiviral drug development. We developed a multi-model machine learning framework combining five traditional algorithms (ExtraTreesClassifier, RandomForestClassifier, LGBMClassifier, BernoulliNB, and BaggingClassifier) with a CNN deep learning model to identify potential RdRP inhibitors among FDA-approved drugs. Using the PubChem dataset AID 588519, our ensemble models achieved the highest performance with accuracy, ROC-AUC, and F1 scores higher than 0.70, while the CNN model demonstrated complementary predictive value with a specificity of 0.77 on external validation. Molecular docking studies with the norovirus RdRP (PDB: 4NRT) identified raloxifene as a promising candidate, with a binding affinity (−8.8 kcal/mol) comparable to the positive control (−9.2 kcal/mol). The molecular dynamics simulation confirmed stable binding with RMSD values of 0.12–0.15 nm for the protein–ligand complex and consistent hydrogen bonding patterns. Our findings suggest that raloxifene may possess RdRP inhibitory activity, providing a foundation for its experimental validation as a potential broad-spectrum antiviral agent. |
| format | Article |
| id | doaj-art-b7d6ff1d84ca4874bcee8e67382c2e94 |
| institution | DOAJ |
| issn | 1467-3037 1467-3045 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Current Issues in Molecular Biology |
| spelling | doaj-art-b7d6ff1d84ca4874bcee8e67382c2e942025-08-20T03:14:46ZengMDPI AGCurrent Issues in Molecular Biology1467-30371467-30452025-04-0147531510.3390/cimb47050315A Multi-Model Machine Learning Framework for Identifying Raloxifene as a Novel RNA Polymerase Inhibitor from FDA-Approved DrugsNhung Thi Hong Van0Minh Tuan Nguyen1Department of Physiology, Dongguk University College of Medicine, Gyeongju 38066, Republic of KoreaCollege of Pharmacy, Dongguk University, Seoul 04620, Republic of KoreaRNA-dependent RNA polymerase (RdRP) represents a critical target for antiviral drug development. We developed a multi-model machine learning framework combining five traditional algorithms (ExtraTreesClassifier, RandomForestClassifier, LGBMClassifier, BernoulliNB, and BaggingClassifier) with a CNN deep learning model to identify potential RdRP inhibitors among FDA-approved drugs. Using the PubChem dataset AID 588519, our ensemble models achieved the highest performance with accuracy, ROC-AUC, and F1 scores higher than 0.70, while the CNN model demonstrated complementary predictive value with a specificity of 0.77 on external validation. Molecular docking studies with the norovirus RdRP (PDB: 4NRT) identified raloxifene as a promising candidate, with a binding affinity (−8.8 kcal/mol) comparable to the positive control (−9.2 kcal/mol). The molecular dynamics simulation confirmed stable binding with RMSD values of 0.12–0.15 nm for the protein–ligand complex and consistent hydrogen bonding patterns. Our findings suggest that raloxifene may possess RdRP inhibitory activity, providing a foundation for its experimental validation as a potential broad-spectrum antiviral agent.https://www.mdpi.com/1467-3045/47/5/315RNA-dependent RNA polymerasemachine learningdeep learningraloxifeneantiviral |
| spellingShingle | Nhung Thi Hong Van Minh Tuan Nguyen A Multi-Model Machine Learning Framework for Identifying Raloxifene as a Novel RNA Polymerase Inhibitor from FDA-Approved Drugs Current Issues in Molecular Biology RNA-dependent RNA polymerase machine learning deep learning raloxifene antiviral |
| title | A Multi-Model Machine Learning Framework for Identifying Raloxifene as a Novel RNA Polymerase Inhibitor from FDA-Approved Drugs |
| title_full | A Multi-Model Machine Learning Framework for Identifying Raloxifene as a Novel RNA Polymerase Inhibitor from FDA-Approved Drugs |
| title_fullStr | A Multi-Model Machine Learning Framework for Identifying Raloxifene as a Novel RNA Polymerase Inhibitor from FDA-Approved Drugs |
| title_full_unstemmed | A Multi-Model Machine Learning Framework for Identifying Raloxifene as a Novel RNA Polymerase Inhibitor from FDA-Approved Drugs |
| title_short | A Multi-Model Machine Learning Framework for Identifying Raloxifene as a Novel RNA Polymerase Inhibitor from FDA-Approved Drugs |
| title_sort | multi model machine learning framework for identifying raloxifene as a novel rna polymerase inhibitor from fda approved drugs |
| topic | RNA-dependent RNA polymerase machine learning deep learning raloxifene antiviral |
| url | https://www.mdpi.com/1467-3045/47/5/315 |
| work_keys_str_mv | AT nhungthihongvan amultimodelmachinelearningframeworkforidentifyingraloxifeneasanovelrnapolymeraseinhibitorfromfdaapproveddrugs AT minhtuannguyen amultimodelmachinelearningframeworkforidentifyingraloxifeneasanovelrnapolymeraseinhibitorfromfdaapproveddrugs AT nhungthihongvan multimodelmachinelearningframeworkforidentifyingraloxifeneasanovelrnapolymeraseinhibitorfromfdaapproveddrugs AT minhtuannguyen multimodelmachinelearningframeworkforidentifyingraloxifeneasanovelrnapolymeraseinhibitorfromfdaapproveddrugs |