Time-series metabolomic profiling of SARS-CoV-2 infection: Possible prognostic biomarkers in patients in the ICU by ¹H-NMR analysis

Abstract

The global impact of SARS-CoV-2, which causes COVID-19, remains significant, being intensified by the emergence of variants. Comprehensive metabolomic studies aimed to elucidate the distinctive metabolic footprint of the virus. For critically ill patients with COVID-19 in the intensive care unit (ICU), longitudinal monitoring based on their prognosis is crucial to optimize treatment outcomes. This study retrospectively investigated the temporal changes in the metabolomic profiles of patients admitted to the ICU with COVID-19, who were categorized into three prognostic groups: healthy discharged (HD), polyneuropathic syndrome (PS), and Exitus. In total, 32 serum samples collected in April 2020 at regular intervals (four samples per patient) and stored at -80°C, were analyzed using proton nuclear magnetic resonance (1H-NMR) spectroscopy. Significant (p < 0.05) prognostic changes in creatine and tyrosine levels were revealed by two-way analysis of variance (ANOVA) and ANOVA-simultaneous component analysis (ASCA). Furthermore, supervised random forest analysis demonstrated excellent group prediction with a 21.9% out-of-bag error rate based on prognosis. Specifically, creatine levels were highest in the PS group, whereas tyrosine levels were highest in the Exitus group. However, no metabolite displayed significant changes over time. In addition, metabolic pathway analysis using the Kyoto Encyclopedia of Genes and Genomes database indicated that the most significantly impacted pathway (p < 0.05) across different prognostic groups was "phenylalanine, tyrosine and tryptophan biosynthesis." This preliminary study emphasizes the need for time-series analysis of samples from unvaccinated patients with varying prognoses, providing valuable insights into the metabolic impact of COVID-19.

Fig 1. Multivariate analysis of prognostic groups in ICU COVID-19 patients over time.

(a) An iPCA 3D score plot is presented in the middle of the diagram (classified by prognostic group by color and sample collection time by shape), with PC1 explaining the highest variance, followed by PC2 and PC3 (total variance: 42.4%). (b, c, d) 2D OPLS-DA score plots providing better discrimination between different prognostic groups (HD, PS, and Exitus) according to the collection times of the samples in patients with COVID-19 treated in the ICU.

Fig 2. Temporal and prognostic variation of key metabolites in ICU COVID-19 patients.

(a) Venn diagram of two-way ANOVA consisting of prognosis, time, and their interaction indicating the number of significant metabolites. (b, c, d, e) Box–whisker plots of four metabolites (tyrosine, creatine, phenylalanine, and formic acid respectively) with their change in relative abundance classified for prognosis (HD, Exitus, and PS) and collection times (0, 1st, 2nd and 3rd time points).

Fig 3. Principal patterns of metabolite variance across time and prognosis in ICU COVID-19 patients.

Scree plots illustrating the major patterns of metabolite changes over time (0, 1st, 2nd, and 3rd time points) and across prognostic groups (HD, Exitus, and PS), along with their interaction. The scores in these plots represent the percentage of variance explained between the groups.

Fig 4. ASCA leverage/SPE analysis highlighting key metabolites associated with time, prognosis, and their interaction.

The metabolites in the red area exhibit high loadings and align closely with the expression patterns delineated by the sub-models. By contrast, metabolites in the blue area (outliers) display expression patterns that deviate from these major patterns. The well-modeled metabolites in the red areas were specifically identified.

Fig 5. Permutation-based validation of ASCA models.

Statistical significance was only observed for prognosis with p < 0.05.

Fig 6. Random forest analysis.

Variable importance plot highlighting prognostic metabolite predictors in ICU COVID-19 patients based on the mean decrease accuracy value. A higher value indicates the importance of that metabolite in predicting group with red color representing the higher importance, whereas blue color representing the lower importance in evaluation.