Lipidomic profiling of the cerebrospinal fluid in moyamoya angiopathy patients

Abstract

Background: Moyamoya angiopathy (MA) is a rare cerebrovascular disorder which can occur in both children and young adults, characterized by progressive occlusion of the intracranial carotid arteries, leading patients to ischemic and haemorrhagic strokes. Despite decades of research, the mechanisms underlying MA remain poorly clarified and current gaps in the understanding of pathogenesis have hampered the development of suitable preventive strategies and therapeutic options. Moreover, clinically approved biomarkers for MA patients' stratification are missing. The unknown pathophysiology and the lack of reliable biomarkers prompted us to investigate cerebrospinal fluid (CSF) lipidome through state-of-the-art lipidomics.

Methods: Intraoperative CSF from a subgroup of MA patients in comparison to age/sex matched controls (CTRL) was analysed through LC-MS/MS, by an untargeted lipidomic approach. Receiver operating characteristic (ROC) curve and simple linear regression analyses were performed for diagnostic use. We searched for simultaneously altered lipids in plasma and CSF of MA patients.

Results: Overall, we observed a significant increase of sphingolipids (p < 0.05) and phospholipids (p < 0.05) in MA CSF. A partial least squares discriminant analysis clearly separated MA and CTRL by 64% on Principal Component 1. We identified lipid classes (n = 12) with a Variance Importance in Projection score ≥ 1.5, within those lipids highly correlated with MA (n = 70). A significant increase in acylcarnitines, sphingolipids (sphingomyelins and ceramides), phospholipids (lysophosphatidylcholines; phosphatidylcholines; phosphatidylethanolamines; ether-phosphatidylethanolamines; ether-phosphatidylcholines) and cholesterol esters was found by multivariate and univariate analyses. Monoacylglycerols were the only lipid class displaying a markedly significant (p < 0.001) decrease in CSF of MA patients as compared to CTRL subjects. The ROC curve and simple linear regression analysis identified 10 out of 12 lipid classes as reliable MA biomarkers, mainly dealing with phospholipids. We then compared current and previous data on plasma lipidomic profile. The discriminant analysis returned n = 175 (in plasma) and n = 70 (in CSF) simultaneously altered lipids respectively, and phosphatidylcholines (n = 10) resulted as commonly decreased in plasma and increased in CSF.

Conclusions: Our findings highlighted a strong pro-inflammatory environment in MA CSF. These preliminary hallmarks could be helpful to decipher the complex MA pathogenesis, by supplying candidate biomarkers for patient stratification.

Keywords: CSF; Inflammation; Lipidomics; Moyamoya; Phosphatidylcholines; Phospholipids; Plasma; Sphingolipids.

Fig. 1

Overall CSF lipid content. A Total CSF lipid content in MA patients and in CTRL subjects with unrelated cerebrovascular diseases B Lipid classes significantly increased in CSF of MA patients. Statistical significance is evaluated by comparing ranks with Mann–Whitney U test. P values are schematized as follows: * < 0.05; *** < 0.001

Fig. 2

CSF untargeted lipidomics. CSF lipid alteration in MA patients (n = 5) in comparison to age and sex matched controls with unrelated cerebrovascular diseases (CTRL, n = 5). A Discriminant analysis (score plot) of the lipidome in MA and CTRL subjects. The axes are ranked according to their importance in the group discrimination. In the x-axis, component 1 (PC1, 64%) represents the maximum of the separation that can be reached within these clusters and variables, whereas, in the y-axis, component 2 (PC2, 12.8%) represents the direction that contains the most remaining variance. B Heatmap of the top 70 significantly altered lipid species highly correlated with the disease, chosen within those with a Variance Importance in Projection (VIP) score > 1.5, and ordered by lipid classes, coded by different colors. Each horizontal row represents a molecular lipid; each vertical column represents a sample. The concentrations were autoscaled and log- transformed for visualization. The color code bar indicates the log of the fold change of the mean concentration for a given lipid. The color-scale differentiates values as high (red), average (white) and low (blue). C VIP lipid classes concentrations in MA and CTRL subjects. Boxplots represent the trends in lipid class concentrations in MA and CTRL patients, except for Cer 18:0 and CE 22:4 which are the only VIP lipids found in their classes and therefore the boxes represent the trend of these single species. The boxes represent data obtained in the range 25th-75th percentile; the line across the boxes indicates the median value; the lines above and below the boxes indicate extreme values (10th or 90th percentile). Outliers are displayed as separate points. Statistical significance is evaluated by comparing ranks with Mann–Whitney U test. P values are schematized as follows: ** < 0.01; *** < 0.001

Fig. 3

ROC analysis of phospholipid biomarker candidates. The performance of five lipid classes belonging to the phospholipid category (A–E), showing significant alterations in CSF (i.e., with VIP ≥ 1.5), for discriminating MA patients from CTRL subjects was evaluated by the area under the ROC curve (AUC) and by the determination of specificity (percentage of true negatives) and sensitivity (percentage of true positive). The nomenclature of lipid classes was reported above (see Table 2)

Fig. 4

Simple linear regression model. Statistically significant simple linear regression analyses of selected lipid classes that showed VIP ≥ 1.5 in CSF of MA patients as compared to CTRL subjects; A PC/LPC; B LPC/ether PC; C PC/ether PC; D PE/ether PE; E PC/MAG. The nomenclature of lipid classes was reported above (see Table 2)

Fig. 5

Common lipid features between plasma and CSF of MA. A Intersection size graph showing the number of lipids altered in both plasma [33] and CSF of the same MA population. B Heatmap of lipids (n = 10) altered in both plasma and CSF. The concentrations were auto-scaled and log-transformed for visualization. The color-scale for plasma samples differentiates values as high (yellow) and low (blue), whereas for CSF as high (pink) and low (green). HD, healthy donors; CTRL, controls subjects with unrelated cerebrovascular diseases. Statistical significance is evaluated by comparing ranks with Mann–Whitney U test. P values are schematized as follows: ** < 0.01; *** < 0.001

Fig. 6

MA CSF lipidome profile analysis. The main deregulated lipid classes/species, associated with distinct pathological traits, are showed. Red arrows indicate the detection of increasing levels while the blue one stands for decreasing levels as compared to CSF of control subjects. CSF, cerebrospinal fluid; MA, moyamoya angiopathy (Figure created with BioRender)