Alterations of Plasma Lipids in Adult Women With Major Depressive Disorder and Bipolar Depression

Abstract

Lipidomics has been established as a potential tool for the investigation of mental diseases. However, the composition analysis and the comparison of the peripheral lipids regarding adult women with major depressive depression (MDD) or bipolar depression (BPD) has been poorly addressed. In the present study, age-matched female individuals with MDD (n = 28), BPD (n = 22) and healthy controls (HC, n = 25) were enrolled. Clinical symptoms were assessed and the plasma samples were analyzed by comprehensive lipid profiling based on liquid chromatography-mass spectrometry (LC/MS). We found that the composition of lipids was remarkably changed in the patients with MDD and BPD when compared to HC or compared to each other. Moreover, we identified diagnostic potential biomarkers comprising 20 lipids that can distinguish MDD from HC (area under the curve, AUC = 0.897) and 8 lipids that can distinguish BPD from HC (AUC = 0.784), as well as 13 lipids were identified to distinguish MDD from BPD with moderate reliability (AUC = 0.860). This study provides further understanding of abnormal lipid metabolism in adult women with MDD and BPD and may develop lipid classifiers able to effectively discriminate MDD from BPD and HC.

Keywords: bipolar depression; depression; lipidomics; plasma lipid; women.

FIGURE 1

Differential concentration of lipid class among major depressive disorder (MDD), bipolar depression (BPD), and healthy controls (HC). (A) Fatty acyls, (B) ChE, Co, DGDG, and MGDG, (C) sphingolipids, (D) glycerolipids, (E) glycerophospholipids. HC, healthy controls; MDD, major depressive disorder; BPD, bipolar depression; OAHFA, (O-acyl)-1-hydroxy fatty acid; WE, wax esters; AcCa, acylcarnitine; ChE, cholesterol ester; Co, coenzyme; DGDG, digalactosyldiacylglycerol; MGDG, monogalactosyldiacylglycerol; SM, sphingomyelin; ST, sulfatide; Cer, ceramides; CerP, ceramides phosphate; phSM, phytosphingomyelin; DG, diglyceride; TG, triglyceride; MG, monoglyceride; PC, phosphatidylcholine; PI, phosphatidylinositol; PS, phosphatidylserine; PE, phosphatidylethanolamine; PG, phosphatidylglycerol; CL, cardiolipin; LPC, lysophosphatidylcholine; LPE, lysophosphatidylethanolamine; LPI, lysophosphatidylinositol; PA, phosphatidic acid; PIP, phosphatidylinositol; PIP2, phosphatidylinositol 4,5-bisphosphate. *P < 0.05 vs. HC; **P < 0.01 vs. HC, ^##P < 0.01 vs. BPD.

FIGURE 2

Groupwise alterations in fatty acid composition in the plasma. Results of analysis of fatty acyl composition by (A) chain length (number of carbons) and (B) degree of unsaturation. Lipids showing low levels results have been enlarged in insets. HC, health control; MDD, major depressive disorder; BPD, bipolar depression; *P < 0.05 vs. HC; **P < 0.01 vs. HC; ^#P < 0.05 vs. BD; ^##P < 0.01 vs. BPD.

FIGURE 3

Characteristic lipid species in MDD. (A) Scatter plot of OPLS-DA model and (B) validation model of permutation test, (C) volcano map reveals the increased (red dots) and decreased (blue dots) lipid species between the MDD and HC, (D) random forest model and 10-fold cross-validation showed that the lipids with the top 20 importance had the lowest model error rate, (E) ROC analysis for the combinational lipids, (F) correlation between clinical parameters and levels of 20 lipid species. *P < 0.05; **P < 0.01, ***P < 0.001.

FIGURE 4

Characteristic lipid species in BPD. (A) Scatter plot of OPLS-DA model and (B) validation model of permutation test, (C) volcano map reveals the increased (red dots) and decreased (blue dots) lipid species between the BPD and HC, (D) random forest model and 10-fold cross-validation showed that the lipids with the top 8 importance had the lowest model error rate, (E) ROC analysis for the combinational lipids, (F) correlation between clinical parameters and levels of 8 lipid species. *P < 0.05; **P < 0.01, ***P < 0.001.

FIGURE 5

Characteristic lipid species between MDD and BPD. (A) Scatter plot of OPLS-DA model and (B) validation model of permutation test, (C) volcano map reveals the increased (red dots) and decreased (blue dots) lipid species between the MDD and BPD, (D) random forest model and 10-fold cross-validation showed that the lipids with the top 13 importance had the lowest model error rate, (E) ROC analysis for the combinational lipids, (F) correlation between clinical parameters and levels of 13 lipid species. *P < 0.05; **P < 0.01, ***P < 0.001.