Framework Predicts HIV Protease Drug-Resistant Evolution
Aggarwal and Periwal (published January 27, 2026) develop a computational framework that learns coevolutionary transition probabilities from protease genotypes and predicts drug resistance using clinical resistance measurements. They simulate thousands of evolutionary trajectories to forecast persistent drug-resistant HIV protease genotypes, finding the Atazanavir+Ritonavir regimen least likely to induce resistance and identifying seven critical point mutations including L63P for Nelfinavir.
Key Points
- 1Trains probabilistic coevolutionary models and resistance predictors to simulate HIV protease evolutionary trajectories.
- 2Identifies ATV+RTV dual therapy as least likely to induce protease inhibitor resistance across simulated regimens.
- 3Predicts seven critical point mutations, highlighting L63P's necessity for Nelfinavir resistance, guiding surveillance.
Scoring Rationale
Novel, peer-reviewed forecasting framework with actionable mutation predictions, limited by focus on protease-only evolution and dataset sparsity.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
