Sex differences in global metabolomic profiles of COVID-19 patients

Abstract

Coronavirus disease (COVID-19), caused by SARS-CoV-2, leads to symptoms ranging from asymptomatic disease to death. Although males are more susceptible to severe symptoms and higher mortality due to COVID-19, patient sex has rarely been examined. Sex-associated metabolic changes may implicate novel biomarkers and therapeutic targets to treat COVID-19. Here, using serum samples, we performed global metabolomic analyses of uninfected and SARS-CoV-2-positive male and female patients with severe COVID-19. Key metabolic pathways that demonstrated robust sex differences in COVID-19 groups, but not in controls, involved lipid metabolism, pentose pathway, bile acid metabolism, and microbiome-related metabolism of aromatic amino acids, including tryptophan and tyrosine. Unsupervised statistical analysis showed a profound sexual dimorphism in correlations between patient-specific clinical parameters and their global metabolic profiles. Identification of sex-specific metabolic changes in severe COVID-19 patients is an important knowledge source for researchers striving for development of potential sex-associated biomarkers and druggable targets for COVID-19 patients.

Fig. 1. Global metabolomic profiling of male and female COVID-19 patients and control individuals.

Principal component analysis (PCA) is used to define metabolomic profiles. a PCA of metabolomic data for 20 male and female COVID-19 patients and control subjects. Each dot represents an individual subject. PCA demonstrates segregation of serum samples based on a group. The percentage values refer to the percentage of total variance associated with each component. Note how disease status (control versus severe COVID-19) and sex contribute in Note how disease status (control versus COVID-19) and sex contribute in different ways to sample clustering (depicted with dashed lines). Purple: control female subjects, magenta: control male subjects, aquamarine: female COVID-19 patients, orange: male COVID-19 patients. b PCA demonstrates segregation of serum samples, based on disease status (control versus severe COVID-19). Blue: control male and female subjects, green: male and female COVID-19 patients. c PCA shows segregation of serum samples based on sex. Salmon: female control subjects and COVID-19 patients, red: male control subjects and COVID-19 patients.

Fig. 2. Metabolite summary and significantly altered biochemicals.

a The dataset comprises 1516 biochemicals, 1214 compounds of known identity (named biochemicals), and 302 compounds of unknown structural identity (unnamed biochemicals). ANOVA contrasts were used to identify biochemicals that differed significantly between experimental groups. A summary of the numbers of biochemicals that achieved statistical significance (p ≤ 0.05), as well as those approaching significance (0.05 < p < 0.10) is shown. b Analysis by two-way ANOVA identified biochemicals exhibiting significant interaction and main effects for experimental parameters of COVID-19 and sex. c A summary of biochemical families that achieved statistical significance (p ≤ 0.05). Ten families of metabolic biochemicals were identified: amino acids, peptides, carbohydrates, energy, lipids including primary and secondary bile acid metabolites, nucleotides, co-factors and vitamins, xenobiotics, partially characterized and unnamed biochemicals.

Fig. 3. Random forest analysis of metabolic serum datasets.

Random forest analysis bins individual samples into groups, based on their metabolite similarities and variances. Colored dots represent metabolite super pathway families. Salmon: amino acids, green: lipids, dark purple: partially characterized molecules, blue: unnamed biochemicals, magenta: xenobiotics, brown: carbohydrates, turquoise: nucleotides, olive: co-factors and vitamins, yellow: peptides. a The biochemical profiles predict the control sample group with a predictive accuracy of 93% (control male and female individuals) (top). Random forest analysis shows the 30 most important metabolites in the control group (male and female subjects) (bottom). b The biochemical profiles predict the COVID-19 sample group with a predictive accuracy of 65% (male and female COVID-19 patients) (top). Random forest analysis demonstrates top 30 ranking biochemicals of importance, based on male COVID-19 and female COVID-19 group separation in serum samples (bottom). c The biochemical profiles are highly successful in predicting the male groups correctly with 100% accuracy (control and COVID-19 samples) (top). Random forest analysis demonstrates the top 30 ranking biochemicals of importance, based on control male and COVID-19 male group separation in serum samples (bottom). d The biochemical profiles are highly successful in predicting the female groups correctly with 98% accuracy (control and COVID-19 samples) (top). Random forest analysis demonstrates the 30 most important metabolites in the female group (control and COVID-19 subjects) (bottom).

Fig. 4. Differences in phospholipid metabolism between control subjects and COVID-19 patients.

Red and green cells indicate p ≤ 0.05 (red indicates the fold-change values are significantly higher for that comparison; green values significantly lower). Light red and light green shaded cells indicate 0.05 < p < 0.10 (light red indicates the fold-change values trend higher for that comparison; light green values trend lower). Note that phosphatidylcholine metabolites are in general lower in male and female COVID-19 samples than controls, and phosphatidylethanolamine metabolites are higher in male and female COVID-19 samples than controls.

Fig. 5. Differences in metabolism of lysophospholipids, plasmalogens, and lysoplasmalogens between control subjects and COVID-19 patients.

Red and green cells indicate p ≤ 0.05 (red indicates the fold-change values are significantly higher for that comparison; green values significantly lower). Light red and light green shaded cells indicate 0.05 < p < 0.10 (light red indicates the fold-change values trend higher for that comparison; light green values trend lower). Note that most metabolites considerably reduced in COVID-19 patients with a sex association. These metabolites are lower in male patients than in female patients.

Fig. 6. Differences in metabolism of primary and secondary bile acids between control subjects and COVID-19 patients.

Red and green cells indicate p ≤ 0.05 (red indicates the fold-change values are significantly higher for that comparison; green values significantly lower). Light red and light green shaded cells indicate 0.05 < p < 0.10 (light red indicates the fold-change values trend higher for that comparison; light green values trend lower). Note that there is a sex association for many metabolites.

Fig. 7. Sex differences in primary and secondary bile acids metabolism pathways and in valine, isoleucine, leucine (BCAA) metabolism in COVID-19 groups, not present in control groups.

a Primary bile acid metabolism and b, c secondary bile acid metabolism pathways. d Branched-chain amino acids, valine, isoleucine, leucine metabolism, *p ≤ 0.05 (two-way ANOVA).

Fig. 8. Sex differences in pentose metabolites and microbiome related metabolites in COVID-19 groups, not present in control groups.

a Pentose, b phenylalanine, c tyrosine and, d tryptophan metabolism pathways. *p ≤ 0.05 (two-way ANOVA).