# Forecasting drug resistant HIV protease evolution

## TL;DR

This paper presents a computational framework to predict how HIV protease evolves to become drug-resistant, helping design better treatment strategies.

## Contribution

The novel contribution is a framework combining coevolutionary and drug resistance data to simulate and forecast HIV protease evolution under treatment.

## Key findings

- Dual therapy with Atazanavir and Ritonavir is least likely to induce drug resistance.
- Seven point-mutations are predicted as critical for drug resistance.
- The L63P polymorphism is critical for resistance to Nelfinavir.

## Abstract

Protease inhibitors (PIs) target the protease (PR) enzyme to suppress viral replication. Their efficacy in human immunodeficiency virus treatment is compromised by the emergence of drug-resistant strains. Therefore, forecasting drug-resistance during viral evolution would help in the design of effective treatment strategies. To this end, we develop a framework that bridges two distinct data sets. First, we train probabilistic models to learn coevolutionary information in observed PR genotypes in different PI treatment regimens. We use these models to infer transition probabilities of point-mutations conditioned on the genotype and the treatment regimen. Second, we train another set of models to infer drug resistance of PR genotypes to different PIs using data of clinically measured drug resistance. We use these models together to simulate evolutionary trajectories and predict drug resistance. Importantly, we use these simulations to forecast the emergence of persistent drug resistant genotypes. Our analysis shows that the dual therapy of Atazanavir (ATV) and Ritonavir (RTV) is the multi-PI treatment regimen least likely to induce drug resistance. We also conduct an exhaustive ablation study of all possible mutations and predict seven point-mutations as critical for drug resistance. Interestingly, our results highlight the necessity of the amino-acid polymorphism of L63P by predicting that it is critical in developing resistance to Nelfinavir (NFV). The results validate that our framework effectively extracts and combines biological information from the distinct data sets of observed genotypes and drug resistance, while also tackling the challenge of sparsity of available sequence data compared to the large combinatorial complexity of protein evolution and changing functionality in dynamic environments.

The human immunodeficiency virus (HIV) rapidly evolves to evade medication, leading to drug resistance—a major global health challenge. Predicting the evolutionary paths the virus might take under different drug treatments could help us stay one step ahead. In our study, we developed a computational framework to forecast the emergence of drug resistance during evolution of HIV protease, a key protein targeted by many drugs. We used machine learning to learn the ‘rules of evolution’ from the virus’s genetic sequences under different drug environments and combined this with a model that predicts drug resistance. By simulating thousands of evolutionary pathways, our framework identifies the most critical mutations for causing resistance. Our findings confirmed the importance of mutations already known to be problematic in the clinic and also highlighted more subtle interactions, such as a key supporting mutation required for resistance to the drug Nelfinavir. Our work offers a new way to computationally explore viral evolution, providing insights that could help design more durable treatment strategies and next-generation drugs to combat HIV.