TY - JOUR

T1 - HIV-V3Augur

T2 - A Novel Machine Learning Model for Predicting HIV-1 Tropism in Sub-Subtype A6 and CRF63_02A6, Predominant Variants in Russia and Countries of the Former Soviet Union

AU - Elfimov, Kirill

AU - Gotfrid, Ludmila

AU - Nokhova, Alina

AU - Gashnikova, Mariya

AU - Ekushov, Vasiliy

AU - Halikov, Maksim

AU - Osipova, Irina

AU - Baboshko, Dmitriy

AU - Murzin, Andrey

AU - Kondeikin, Ivan

AU - Kiryakina, Arina

AU - Totmenin, Aleksey

AU - Agaphonov, Aleksandr

AU - Gashnikova, Natalya

N1 - Elfimov, K.; Gotfrid, L.; Nokhova, A.; Gashnikova, M.; Ekushov, V.; Halikov, M.; Osipova, I.; Baboshko, D.; Murzin, A.; Kondeikin, I.; et al. HIV-V3Augur: A Novel Machine Learning Model for Predicting HIV-1 Tropism in Sub-Subtype A6 and CRF63_02A6, Predominant Variants in Russia and Countries of the Former Soviet Union. Viruses 2026, 18, 703. https://doi.org/10.3390/v18070703 Funding: Federal Service for Surveillance on Consumer Rights Protection and Human Wellbeing: The study was supported by State Assignment no. 4/26 (FBRI SRC VB ‘Vector’ Rospotrebnadzor).

PY - 2026/6/25

Y1 - 2026/6/25

N2 - Determining HIV-1 tropism provides the prognosis of HIV infection and is required before prescribing maraviroc, an entry inhibitor that blocks the interaction between the viral gp120 and the CCR5 coreceptor. However, existing prediction algorithms have been developed primarily for the globally most prevalent subtypes (B, C, and CRF01_AE) and often show reduced performance for other HIV-1 genetic variants. Sub-subtype A6 and circulating recombinant form CRF63_02A6 dominate the HIV-1 epidemic in Russia and other Former Soviet Union (FSU) countries, yet the reliability of tropism prediction for these viruses remains virtually unexplored. We phenotypically determined the tropism of 25 clinical isolates (11 R5, 1 X4, and 7 dual-tropic R5/X4) using U87.CD4.CCR5 and U87.CD4.CXCR4 cell lines and performed a comparative analysis of eight existing genotypic tools (Geno2pheno, WebPSSM, T-CUP 2.0, the Delobel/Garrido rules, and others) or their modifications on a combined dataset that included Los Alamos National Laboratory (LANL) reference sequences (subtypes A, B, C, CRF01_AE, and CRF02_AG) and our laboratory-derived isolates. Most models achieved high accuracy for globally prevalent subtypes (≈95% for B, C, and CRF01_AE) but showed markedly reduced performance for sub-subtype A6 (best accuracy among existing models, 85%) and CRF63_02A6 (best accuracy, 72%), with a poor balance between sensitivity and specificity. To address this problem, we developed HIV-V3Augur, an ensemble stacking model based on the Random Forest and Support Vector Machine (SVM) machine learning algorithms, trained on Pseudo Amino Acid Composition (PseAAC) and Relative Synonymous Codon Usage (RSCU) features with 10-fold stratified cross-validation. HIV-V3Augur achieved an accuracy of 77%, sensitivity of 79%, and specificity of 79% on sub-subtype A6, and on CRF63_02A6 it reached an accuracy of 95%, sensitivity of 87%, and specificity of 100%. Cross-validation demonstrated that HIV-V3Augur represents a balanced genotypic tropism prediction tool for understudied HIV-1 variants circulating in the FSU region. HIV-V3Augur can be used locally through a graphical user interface.

AB - Determining HIV-1 tropism provides the prognosis of HIV infection and is required before prescribing maraviroc, an entry inhibitor that blocks the interaction between the viral gp120 and the CCR5 coreceptor. However, existing prediction algorithms have been developed primarily for the globally most prevalent subtypes (B, C, and CRF01_AE) and often show reduced performance for other HIV-1 genetic variants. Sub-subtype A6 and circulating recombinant form CRF63_02A6 dominate the HIV-1 epidemic in Russia and other Former Soviet Union (FSU) countries, yet the reliability of tropism prediction for these viruses remains virtually unexplored. We phenotypically determined the tropism of 25 clinical isolates (11 R5, 1 X4, and 7 dual-tropic R5/X4) using U87.CD4.CCR5 and U87.CD4.CXCR4 cell lines and performed a comparative analysis of eight existing genotypic tools (Geno2pheno, WebPSSM, T-CUP 2.0, the Delobel/Garrido rules, and others) or their modifications on a combined dataset that included Los Alamos National Laboratory (LANL) reference sequences (subtypes A, B, C, CRF01_AE, and CRF02_AG) and our laboratory-derived isolates. Most models achieved high accuracy for globally prevalent subtypes (≈95% for B, C, and CRF01_AE) but showed markedly reduced performance for sub-subtype A6 (best accuracy among existing models, 85%) and CRF63_02A6 (best accuracy, 72%), with a poor balance between sensitivity and specificity. To address this problem, we developed HIV-V3Augur, an ensemble stacking model based on the Random Forest and Support Vector Machine (SVM) machine learning algorithms, trained on Pseudo Amino Acid Composition (PseAAC) and Relative Synonymous Codon Usage (RSCU) features with 10-fold stratified cross-validation. HIV-V3Augur achieved an accuracy of 77%, sensitivity of 79%, and specificity of 79% on sub-subtype A6, and on CRF63_02A6 it reached an accuracy of 95%, sensitivity of 87%, and specificity of 100%. Cross-validation demonstrated that HIV-V3Augur represents a balanced genotypic tropism prediction tool for understudied HIV-1 variants circulating in the FSU region. HIV-V3Augur can be used locally through a graphical user interface.

KW - HIV-1/physiology

KW - Viral Tropism

KW - Humans

KW - Russia/epidemiology

KW - HIV Envelope Protein gp120/genetics

KW - HIV Infections/virology

KW - Genotype

KW - Machine Learning

KW - USSR/epidemiology

KW - Predictive Learning Models

KW - Genetic Variation

KW - Cell Line

KW - Prediction Algorithms

KW - ВИЧ-1

KW - тропизм

KW - суб-субтип A6

KW - CRF63_02A6

KW - V3-петля gp120;

KW - генотипическое прогнозирование тропизма

KW - бывший Советский Союз

KW - Россия

UR - https://www.scopus.com/pages/publications/105045895302

U2 - 10.3390/v18070703

DO - 10.3390/v18070703

M3 - Article

C2 - 42515555

VL - 18

JO - Viruses

JF - Viruses

SN - 1999-4915

IS - 7

ER -