Identification of potential biomarkers for predicting the early onset of diabetic cardiomyopathy in a mouse model

Abstract

Type 2 diabetes (T2D) is characterized by metabolic derangements that cause a shift in substrate preference, inducing cardiac interstitial fibrosis. Interstitial fibrosis plays a key role in aggravating left ventricular diastolic dysfunction (LVDD), which has previously been associated with the asymptomatic onset of heart failure. The latter is responsible for 80% of deaths among diabetic patients and has been termed diabetic cardiomyopathy (DCM). Through in silico prediction and subsequent detection in a leptin receptor-deficient db/db mice model (db/db), we confirmed the presence of previously identified potential biomarkers to detect the early onset of DCM. Differential expression of Lysyl Oxidase Like 2 (LOXL2) and Electron Transfer Flavoprotein Beta Subunit (ETFβ), in both serum and heart tissue of 6-16-week-old db/db mice, correlated with a reduced left-ventricular diastolic dysfunction as assessed by high-resolution Doppler echocardiography. Principal component analysis of the combined biomarkers, LOXL2 and ETFβ, further displayed a significant difference between wild type and db/db mice from as early as 9 weeks of age. Knockdown in H9c2 cells, utilising siRNA of either LOXL2 or ETFβ, revealed a decrease in the expression of Collagen Type I Alpha1 (COL1A1), a marker known to contribute to enhanced myocardial fibrosis. Additionally, receiver-operating curve (ROC) analysis of the proposed diagnostic profile showed that the combination of LOXL2 and ETFβ resulted in an area under the curve (AUC) of 0.813, with a cut-off point of 0.824, thus suggesting the favorable positive predictive power of the model and further supporting the use of LOXL2 and ETFβ as possible early predictive DCM biomarkers.

Figure 1

Venn diagram of differentially expressed genes (DEGs). Within the type 2 diabetes mellitus (T2DM) and cardiovascular disease (CVD) datasets, 812 and 296 candidate genes were identified respectively. Integration of the T2DM and CVD datasets, a diabetic cardiomyopathy (DCM) dataset was generated, in which 2 possible candidate genes were identified based on their Wilcoxon score (p value  < 6 × 10^–6).

Figure 2

mRNA expression of LOXL2 and ETFβ in hearts tissue of 6–16-week-old db/db mice. Differential mRNA expression of (A) Lysyl Oxidase Like 2 (LOXL2) and (B) Electron transfer flavoprotein subunit beta (ETFβ) in heart tissue of leptin receptor-deficient mice (db/db) compared to aged matched lean control (db/ +). Results are expressed as mean ± SEM of n = 4–8 animals per group. *p < 0.05 and ***p ≤ 0.001 compared to wild type control (db/ +).

Figure 3

Expression of serum LOXL2 and ETFβ in 6–16-week-old Leptin receptor-deficient db/db mice and aged matched controls. (A) Lysyl Oxidase Like 2 (LOXL2), (B) Electron transfer flavoprotein subunit beta (ETFβ) and (C) N-terminal pro b-type natriuretic peptide protein expression in serum of leptin receptor-deficient mice (db/db) compared to aged matched lean control (db/ +). Results are expressed as mean ± SEM of n = 8 animals per group. *p < 0.05, **p < 0.01 and ***p < 0.001 compared to wild type control (db/ +) at the same point.

Figure 4

High-resolution Doppler echocardiography analysis in 6–16-week-old Leptin receptor-deficient db/db mice and their age matched db/+ heterozygous non-diabetic control group. (A) Measurement of left ventricular ejection fraction (LVEF) as a marker of systolic function; (B) Measurement of mitral E:A ratio as a marker of left ventricular diastolic function. Results are expressed as mean ± SEM of 6–8 animals per group. Statistical significance was evaluated using Mann–Whitney test . *p < 0.05, **p < 0.01, and ***p < 0.001 compared to aged matched wild type control.

Figure 5

Correlation analysis of serum LOXL2, ETFβ and proBNP with mitral E:A ratio in Leptin receptor-deficient db/db mice at 16 weeks. Mitral E:A ratio is a marker of left ventricular diastolic dysfunction, (A) Lysyl Oxidase Like 2 (LOXL2), was negatively and (B) Electron transfer flavoprotein subunit beta (ETFβ) was positively correlated with mitral E:A ratio, while no correlation was observed with (C) N-terminal pro b-type natriuretic peptide (proBNP).

Figure 6

Effect of LOXL2 knockdown on Col1A and ETFβ expression. The degree of knockdown after H9c2 cardiomyocytes transfected with (A) siLOXL2 and (C) siETFβ was exposed to 100 µM Palmitate (PAL) and 33 mM glucose (HG). The relative mRNA expression of the fibrosis gene, COL1A in (B) LOXL2 and (D) ETFβ after transfection of cells with either small interfering RNA (siRNA) or scrambled RNA (scrRNA). The expression levels were normalized relative to the control. Statistical significance was evaluated using the one-way ANOVA with a Tukey Post-hoc t-test. This graph represents the SEM of triplicate samples. p < 0.05, p < 0.01 and p < 0.001 when compared to control or scrambled control.

Figure 7

Receiver operating characteristics (ROC) of LOXL2 and ETFβ between 9 and 14 weeks. ROC curve analysis of ETFβ with (A) groups not specified and (B) groups specified. (C) Linear combination of LOXL2 and ETFβ when groups are not specified and when (D) groups are specified a good predictive cut-off point of 0.824 was obtained. Logistic regression was used to perform ROC, p < 0.05.