A baseline metabolomic signature is associated with immunological CD4+ T-cell recovery after 36 months of antiretroviral therapy in HIV-infected patients

Abstract

Objectives: Poor immunological recovery in treated HIV-infected patients is associated with greater morbidity and mortality. To date, predictive biomarkers of this incomplete immune reconstitution have not been established. We aimed to identify a baseline metabolomic signature associated with a poor immunological recovery after antiretroviral therapy (ART) to envisage the underlying mechanistic pathways that influence the treatment response.

Design: This was a multicentre, prospective cohort study in ART-naive and a pre-ART low nadir (<200 cells/μl) HIV-infected patients (n = 64).

Methods: We obtained clinical data and metabolomic profiles for each individual, in which low molecular weight metabolites, lipids and lipoproteins (including particle concentrations and sizes) were measured by NMR spectroscopy. Immunological recovery was defined as reaching CD4 T-cell count at least 250 cells/μl after 36 months of virologically successful ART. We used univariate comparisons, Random Forest test and receiver-operating characteristic curves to identify and evaluate the predictive factors of immunological recovery after treatment.

Results: HIV-infected patients with a baseline metabolic pattern characterized by high levels of large high density lipoprotein (HDL) particles, HDL cholesterol and larger sizes of low density lipoprotein particles had a better immunological recovery after treatment. Conversely, patients with high ratios of non-HDL lipoprotein particles did not experience this full recovery. Medium very-low-density lipoprotein particles and glucose increased the classification power of the multivariate model despite not showing any significant differences between the two groups.

Conclusion: In HIV-infected patients, a baseline healthier metabolomic profile is related to a better response to ART where the lipoprotein profile, mainly large HDL particles, may play a key role.

Fig. 1

Flowchart of the patients included in the study.

Fig. 2

Univariate analysis of measured metabolomic variables at baseline.

Fig. 3

Variable importance plot of the Random Forest analysis resulting from a large number of models built around immunological response to antiretroviral therapy.

Fig. 4

Using receiver-operating characteristic curves, we assessed multimetabolite biomarker models that could accurately predict a discordant response to HIV-infection treatment.