Related Experiment Video
Updated: Apr 21, 2026
10:29
Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors
Published on: May 9, 2025
2.7K
Harnessing machine learning models to repurpose drugs targeting HIV-1 integrase, protease, and reverse transcriptase
Ciprian-Bogdan Chirila1, Luminita Crisan2
1University Politehnica Timisoara, 2 V. Parvan Avenue, Timisoara, 300223, Romania.
Scientific Reports
|April 19, 2026
Summary
This study introduces a machine learning and molecular docking approach to identify new uses for existing drugs against HIV-1. Three drugs—enoxacin, larotrectinib, and pipamazine—show potential for HIV-1 treatment, warranting further investigation.
Area of Science:
- Computational chemistry and bioinformatics
- Drug discovery and repurposing
- Virology and infectious diseases
Background:
- The global human immunodeficiency virus type 1 (HIV-1) epidemic affects millions, necessitating novel therapeutic strategies.
- Traditional experimental drug screening is costly and time-consuming.
- Existing research often focuses on single or dual HIV-1 molecular targets.
Purpose of the Study:
- To develop and validate an ensemble approach combining machine learning and molecular docking for HIV-1 drug repurposing.
- To identify existing drugs with potential efficacy against multiple key HIV-1 enzymes: protease, integrase, and reverse transcriptase.
- To establish a predictive framework for accelerating drug discovery and development.
Main Methods:
- An integrative meta-learning strategy was employed to predict drug candidates targeting multiple HIV-1 enzymes.
- Machine learning models (mllh-18 and mllh-18-hp) were trained and evaluated using metrics like Matthews correlation coefficient (MCC) and precision-recall area under the curve (PR-AUC).
- The DrugCentral database was screened, and active compounds were subjected to molecular docking to prioritize candidates for repurposing.
Main Results:
- The meta-learning models demonstrated high predictive performance across all three HIV-1 targets, with MCC values exceeding 95% and PR-AUCs nearing 100%.
- Screening identified enoxacin, larotrectinib, and pipamazine as potential drug candidates for HIV-1 management.
- These drugs, originally developed for other conditions, showed promise through computational analysis.
Conclusions:
- The developed ensemble approach effectively identifies potential drug candidates for HIV-1 repurposing.
- Enoxacin, larotrectinib, and pipamazine are promising candidates for further experimental validation against HIV-1.
- This meta-learning based strategy offers a valuable tool for future drug discovery and development efforts.
Related Concept Videos
01:10Retrovirus Life Cycles
50.9K
Retroviruses have a single-stranded RNA genome that undergoes a special form of replication. Once the retrovirus has entered the host cell, an enzyme called reverse transcriptase synthesizes double-stranded DNA from the retroviral RNA genome. This DNA copy of the genome is then integrated into the host’s genome inside the nucleus via an enzyme called integrase. Consequently, the retroviral genome is transcribed into RNA whenever the host’s genome is transcribed, allowing the...
50.9K
01:26Size and Structure of Viral Genomes
1.2K
Viral genomes exhibit remarkable diversity in size, structure, and composition, influencing their replication strategies and interactions with host cells. These genomes consist of either DNA or RNA and may be linear or circular. Additionally, they can be single-stranded or double-stranded, with each configuration affecting how the virus propagates within a host. RNA viruses, for instance, generally have smaller genomes than DNA viruses, a factor that contributes to their high mutation rates and...
1.2K