HIV OctaScanner: A Machine Learning Approach to Unveil Proteolytic Cleavage Dynamics in HIV-1 Protease Substrates.

Abstract

The rise of resistance to antiretroviral drugs due to mutations in human immunodeficiency virus-1 (HIV-1) protease is a major obstacle to effective treatment. These mutations alter the drug-binding pocket of the protease and reduce the drug efficacy by disrupting interactions with inhibitors. Traditional methods, such as biochemical assays and structural biology, are crucial for studying enzyme function but are time-consuming and labor-intensive. To address these challenges, we developed HIV OctaScanner, a machine learning algorithm that predicts the proteolytic cleavage activity of octameric substrates at the HIV-1 protease cleavage sites. The algorithm uses a Random Forest (RF) classifier and achieves a prediction accuracy of 89% in the identification of cleavable octamers. This innovative approach facilitates the rapid screening of potential substrates for HIV-1 protease, providing critical insights into enzyme function and guiding the development of more effective therapeutic strategies. By improving the accuracy of substrate identification, HIV OctaScanner has the potential to support the development of next generation antiretroviral treatments.