Prediction of HIV-associated neurocognitive disorder (HAND) from three genetic features of envelope gp120 glycoprotein

Abstract

BackgroundHIV-associated neurocognitive disorder (HAND) remains an important and yet potentially underdiagnosed manifestation despite the fact that the modern combination antiretroviral therapy (cART) has achieved effective viral suppression and greatly reduced the incidence of life-threatening events. Although HIV neurotoxicity is thought to play a central role, the potential of viral genetic signature as diagnostic and/or prognostic biomarker has yet to be fully explored.ResultsUsing a manually curated sequence metadataset (80 specimens, 2349 sequences), we demonstrated that only three genetic features are sufficient to predict HAND status regardless of sampling tissues; the accuracy reached 100 and 94% in the hold-out testing subdataset and the entire dataset, respectively. The three genetic features stratified HAND into four distinct clusters. Extrapolating the classification to the 1619 specimens registered in the Los Alamos HIV Sequence Database, the global HAND prevalence was estimated to be 46%, with significant regional variations (30–71%). The R package HANDPrediction was implemented to ensure public availability of key codes.ConclusionsOur analysis revealed three amino acid positions in gp120 glycoprotein, providing the basis of the development of novel cART regimens specifically optimized for HAND-associated quasispecies. Moreover, the classifier can readily be translated into a diagnostic biomarker, warranting prospective validation.Electronic supplementary materialThe online version of this article (10.1186/s12977-018-0401-x) contains supplementary material, which is available to authorized users.

Predicting neurodevelopmental outcomes in children with perinatal HIV using a novel machine learning algorithm

“…Previous machine learning studies of brain integrity in people living with HIV have exclusively targeted adult samples [19][20][21]. Our study is the first to establish a machine learning classifier of neurocognitive performance in children with pHIV.…”

“…Our GBM approach differentiated individuals designated as neurocognitively resilient vs. at risk. Unlike studies in adult samples [21], we focused on children without evidence of severe neurocognitive impairment and without a history of brain trauma. Differentiation of individuals with less severe neurocognitive impairment from normative performance requires analytic methods capable of integrating more input variables than what can be achieved with traditional statistics.…”

“…Advanced data science methods such as machine learning offer a promising alternative to detect latent variables that underlie complex clinical phenotypes such as HIV [14][15][16][17][18][19][20][21]. In studies of structural neuroimaging, Wade et al [19] achieved 72% accuracy classifying adults as either HIV-infected or HIV-uninfected, and Zhang et al [20] achieved 85% accuracy discriminating older adults with HIV from age-matched adults with early Alzheimer's disease.…”

“…In studies of structural neuroimaging, Wade et al [19] achieved 72% accuracy classifying adults as either HIV-infected or HIV-uninfected, and Zhang et al [20] achieved 85% accuracy discriminating older adults with HIV from age-matched adults with early Alzheimer's disease. Most recently, Ogishi et al [21] trained a classifier using viral signatures to identify adults with clinicallydefined severe neurocognitive impairment (HAD) versus individuals with no neurocognitive impairment. In this study, supervised machine learning achieved 90% predictive accuracy.…”

“…The studies above utilize cross-sectional data to develop a data-driven algorithm for group classification. Only one study [21] examined utilized advanced methods to explore the underlying mechanisms, but the study solely focused on viral signatures. No studies have integrated demographic, HIV disease variables, routine laboratory indices, and psychosocial variables to establish a robust predictive algorithm for neurocognitive sequelae of HIV.…”