A Computational Approach for Classification of HIV Drug Resistance Based on the Self-Consisted Extreme Classifier

Abstract

The development of viral resistance can significantly reduce the effectiveness of therapy. Human immunodeficiency virus type 1 is the cause of chronic immune dysfunction, leading to the development of co-infections and serious complications. Despite worldwide progress and consolidated efforts to overcome HIV drug resistance, the development of novel approaches to rational drug therapy of HIV infection is still needed. Our study is dedicated to the development of a novel computational ML-driven approach for the ternary classification of HIV protease, reverse transcriptase, and integrase sequences. The approach is based on the Self-Consisted Extreme Classifier (SCEC). The average prediction accuracy (AUC ROC) for one versus other models is about 0.88, which is comparable when to classes are compared in binary classification. We tested our approach in a clinical task and performed prospective validation for eight sequences of HIV protease and reverse transcriptase obtained from treatment-naive HIV-positive male patients. We performed a prediction and compared the results with the therapeutic outcome, in particular, with the viral load decline at 24 weeks. The results of the prospective validation are generally consistent with the results of the therapeutic outcome and confirm the possibility of using the developed approach for the selection of the most appropriate therapeutic regimens.

Note:
Funding declaration: The study is supported by the Program for Basic Research in the Russian Federation for a longterm period (2021-2030) (№ 124050800018-9).

Conflict of Interests: The authors declare no conflicts of interest.

Ethical Approval: The study dedicated to the collection and an analysis of blood plasma samples from HIV-infected people was carried out in accordance with The Code of Ethics of the World Medical Association (Declaration of Helsinki) for experiments involving humans. The Ethical Approval was given by the Ethics Committee of the Federal Budget Institution of Science “Central Research Institute for Epidemiology” (protocol code 114; date of approval 22 April 2021).

Keywords: HIV, drug resistance, machine learning, self-consistent extreme classifier