The Metabolomic Signature of Opa1 Deficiency in Rat Primary Cortical Neurons Shows Aspartate/Glutamate Depletion and Phospholipids Remodeling

Abstract

Pathogenic variants of OPA1, which encodes a dynamin GTPase involved in mitochondrial fusion, are responsible for a spectrum of neurological disorders sharing optic nerve atrophy and visual impairment. To gain insight on OPA1 neuronal specificity, we performed targeted metabolomics on rat cortical neurons with OPA1 expression inhibited by RNA interference. Of the 103 metabolites accurately measured, univariate analysis including the Benjamini-Hochberg correction revealed 6 significantly different metabolites in OPA1 down-regulated neurons, with aspartate being the most significant (p < 0.001). Supervised multivariate analysis by OPLS-DA yielded a model with good predictive capability (Q²_cum = 0.65) and a low risk of over-fitting (permQ2 = -0.16, CV-ANOVA p-value 0.036). Amongst the 46 metabolites contributing the most to the metabolic signature were aspartate, glutamate and threonine, which all decreased in OPA1 down-regulated neurons, and lysine, 4 sphingomyelins, 4 lysophosphatidylcholines and 32 phosphatidylcholines which were increased. The phospholipid signature may reflect intracellular membrane remodeling due to loss of mitochondrial fusion and/or lipid droplet accumulation. Aspartate and glutamate deficiency, also found in the plasma of OPA1 patients, is likely the consequence of respiratory chain deficiency, whereas the glutamate decrease could contribute to the synaptic dysfunction that we previously identified in this model.

Figure 1

Box plot showing the OPA1 protein content relative to GAPDH protein in neurons transfected with siLUC or siOPA1, and cultured 9 days in vitro. Data represent the mean ± SEM of 10 independent experiments, and were statistically treated with Mann–Whitney **p < 0.01. AU = Arbitrary Units. One representative immunoblot is shown on the right panel.

Figure 2

Box plot showing the 6 metabolites significantly different in siOPA1 (n = 10) compared to siLUC controls (n = 10) neurons using the univariate Wilcoxon test after Benjamini-Hochberg correction. Values in the y-axis have no dimension as they represent relative concentrations. ***p < 0.001; **p < 0.01. PC ae: Alkyl-acyl phosphatidylcholine; lysoPC: lysophosphatidylcholine; SM: sphingomyelin; SM(OH): hydroxy-sphingomyelin.

Figure 3

PCA (A) and OPLS-DA (B) scatter plots obtained from the matrix of metabolites for the 10 samples from siLUC (blue circles) and the 10 samples from siOPA1 (green circles). (A) PCA shows neither clear grouping nor outlier in the first principal plan, the green point appearing outside the ellipse being not a strong outlier according to Hotelling’s T2 range. (B) There is a clear between-group discrimination in the OPLS-DA plot along the predictive latent variable (p LV). Legend: PC1,2: Principal Components 1 and 2; o LV: first orthogonal latent variable; p LV: predictive latent variable.

Figure 4

Volcano plot (p_corr vs. VIP) from the OPLS-DA model. Only the most discriminating metabolites having high VIP values ≥ 1 (indicated by the horizontal red line) have been labelled. Negative p_corr values (left) indicate diminished metabolite concentrations in siOPA1 neurons versus siLuc neurons, whereas positive p_corr values (right) indicate increased metabolite concentrations in siOPA1 neurons compared to the control group. The metabolomic signature accompanying the loss of OPA1 expression is associated to decreased levels of the amino acids (green bubbles) aspartate (Asp), glutamate (Glu) and threonine (Thr) and to increased levels of 34 phosphatidylcholines (PC, orange bubbles), 4 lysophosphatidylcholines (lysoPC, blue bubbles), 4 sphingomyelins (SM and SM(OH)), yellow bubbles) and the amino acid lysine (Lys, green bubble). Red-rimmed bubbles indicate metabolites significantly different between siOPA1 and siLUC neurons in univariate analysis (Wilcoxon test) after Benjamini-Hochberg correction.