Designing Potent HIV-1 Protease Inhibitors Using Machine Learning and QSAR Approaches
Bibliographic record
Abstract
High Resolution Image Download MS PowerPoint Slide Acquired Immune Deficiency Syndrome (AIDS), caused by Human Immunodeficiency Virus type-1 (HIV-1), remains a global health crisis. Despite advances in antiretroviral therapy, drug resistance, particularly to protease inhibitors, persists as a significant challenge. Darunavir, a second-generation protease inhibitor, has reduced efficacy against resistant HIV-1 variants, underscoring the development of new inhibitors. This study combines machine learning (ML) and quantitative structure–activity relationship (QSAR) models to design potent HIV-1 protease inhibitors using phenol-based and polyphenol-based P2 ligands. QSAR models, including genetic function approximation (GFA), multiple linear regression (MLR), random forest (RF), gradient boosting regressor (GBR), and Extreme Gradient Boosting (XGBoost), were developed to analyze molecular descriptors. GBR exhibited the highest accuracy ( R 2 = 0.911 and 0.994) with GFA and PI-selected descriptors, respectively. SHAP analysis highlighted key contributions to pIC 50 predictions, including electronic charge at C53, low dipole moments, and shortened bond length (C53-O54). Five potent inhibitors (B01-B05) were predicted, outperforming HIV-1 protease inhibitors. Furthermore, molecular docking suggested that B03 and B05 exhibit strong binding interactions with wild-type and variants, particularly through hydrophobic and hydrogen bonding interactions, with key residues including D25, G27, D29, D30, D25′, and D30′. This integrated QSAR-ML and structure-based analysis offers promising candidates for addressing drug resistance.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".