Chronic cyclodextrin treatment of murine Niemann-Pick C disease ameliorates neuronal cholesterol and glycosphingolipid storage and disease progression

Abstract

Background: Niemann-Pick type C (NPC) disease is a fatal neurodegenerative disorder caused most commonly by a defect in the NPC1 protein and characterized by widespread intracellular accumulation of unesterified cholesterol and glycosphingolipids (GSLs). While current treatment therapies are limited, a few drugs tested in Npc1(-/-) mice have shown partial benefit. During a combination treatment trial using two such compounds, N-butyldeoxynojirimycin (NB-DNJ) and allopregnanolone, we noted increased lifespan for Npc1(-/-) mice receiving only 2-hydroxypropyl-beta-cyclodextrin (CD), the vehicle for allopregnanolone. This finding suggested that administration of CD alone, but with greater frequency, might provide additional benefit.

Methodology/principal findings: Administration of CD to Npc1(-/-) mice beginning at either P7 or P21 and continuing every other day delayed clinical onset, reduced intraneuronal cholesterol and GSL storage as well as free sphingosine accumulation, reduced markers of neurodegeneration, and led to longer survival than any previous treatment regime. We reasoned that other lysosomal diseases characterized by cholesterol and GSL accumulation, including NPC disease due to NPC2 deficiency, GM1 gangliosidosis and mucopolysaccharidosis (MPS) type IIIA, might likewise benefit from CD treatment. Treated Npc2(-/-) mice showed benefits similar to NPC1 disease, however, mice with GM1 gangliosidosis or MPS IIIA failed to show reduction in storage.

Conclusions/significance: Treatment with CD delayed clinical disease onset, reduced intraneuronal storage and secondary markers of neurodegeneration, and significantly increased lifespan of both Npc1(-/-) and Npc2(-/-) mice. In contrast, CD failed to ameliorate cholesterol or glycosphingolipid storage in GM1 gangliosidosis and MPS IIIA disease. Understanding the mechanism(s) by which CD leads to reduced neuronal storage may provide important new opportunities for treatment of NPC and related neurodegenerative diseases characterized by cholesterol dyshomeostasis.

Figure 1. Combination treatment using NB-DNJ and allopregnanolone/CD in Npc1^−/− mice.

(A) Average weight over time for each treatment group shown for males and females separately. (B) Survival of each treatment group. Median survival of Npc1^−/− mice: no treatment, 79 days; CD (weekly), 118 days; Miglustat (daily), 123 days; Allopregnanolone/CD (weekly), 146 days; Combination therapy (Miglustat + Allopregnanolone/CD), 152 days.

Figure 2. Cholesterol and ganglioside immunohistochemistry (IHC) of Npc1^−/− and WT mice in the combination treatment study.

(A) Filipin labeling of unesterified cholesterol (seen as white areas in image) in the neocortex of age-matched untreated and treated Npc1^−/− and WT mice (all mice between 75 and 81 days of age) revealed less cholesterol accumulation of treated Npc1^−/− mice (second, third, and fourth panels) when compared to control Npc1^−/− mice (fifth panel). WT mice do not exhibit cholesterol accumulation (first panel). Each panel here and in (B) and (C) shows layers II (top) through VI (bottom) of the cerebral cortex. (B) IHC of GM2 ganglioside (visualized as brown punctae within cells) was also characterized by reduced GM2 storage in all treated Npc1^−/− mice. (C) IHC of GM3 ganglioside (again seen as brown punctae within cells) showed results similar to GM2. (D) Treated Npc1^−/− mice had more remaining Purkinje cells (brown areas in cerebellar images) than did untreated Npc1^−/− mice; however, treated mice still had Purkinje cell loss when compared to WT mice. Anti-calbindin antibody labels Purkinje cell bodies and dendritic arbors, while the Nissl counterstain (purple) labels all neuronal cell bodies. Images taken at 20X (A), 10X (B, C), and 2X (D); scale bars 20 µm (A), 50 µm (B, C), and 400 µm (D).

Figure 3. Short term (2 week) CD study in Npc1^−/− mice.

(A) Filipin labeling of unesterified cholesterol in the neocortex of untreated and CD-treated Npc1^−/− mice revealed dramatically less cholesterol accumulation in CD-treated mice at 22 days of age. Mice were administered SC injections of CD every other day for 2 weeks starting at P7. (B) IHC of untreated and CD-treated Npc1^−/− mice also revealed less GM2 storage present in CD-treated mice (similar finding for GM3, not shown). (C) Biochemical analysis of ganglioside levels further corroborated the reduction in GM2 and GM3 seen with IHC analysis. (D) Ultrastructural analysis of neocortical neurons in Npc1^−/− untreated and CD-treated mice showed remarkably normal neuronal morphology in CD-treated mice. (E) Filipin labeling of unesterified cholesterol in the cerebellum of untreated and CD-treated Npc1^−/− mice indicated little to no cholesterol accumulation present within Purkinje cells of CD-treated mice; cerebellar layers: molecular cell layer (MCL), Purkinje cell layer (PCL), and granular cell layer (GCL). (F) Western blot analysis of LC3-II, an autophagosome marker, revealed less LC3-II present in CD-treated Npc1^−/− as compared to untreated Npc1^−/− mice. Images taken at 20X (A, E) and 10X (B); scale bars 20 µm (A, E), 50 µm (B), 1 µm (D).

Figure 4. Chronic allopregnanolone and chronic CD treatment studies in Npc1^−/− mice.

(A) Survival of untreated and allopregnanolone-treated Npc1^−/− mice using different vehicles for allopregnanolone. Median survival of Npc1^−/− mice: DMSO, 84 days; Allo/DMSO, 83 days; Corn Oil, 81 days; Allo/Corn Oil, 88 days; 5% CD, 114 days; Allo/5% CD, 121 days. (B) Average weight over time for untreated and chronically CD-treated Npc1^−/− and WT mice. Weights of untreated and CD-treated WTs were averaged for each gender as there was no significant difference between treatments (p<0.8125). (C) Survival of untreated and CD-treated Npc1^−/− and WT mice showing effects of different start times. Median survival of Npc1^−/− mice: no treatment, 83 days; CD (every other day, start at P7), 185 days; CD (every other day, start at P21), 149 days. Treatment initiated at P7 appeared more efficacious, although lifespan was not significantly longer when compared to treatment initiated at P21 (p<0.1870).

Figure 5. Chronic CD treatment study in Npc1^−/− mice.

(A) Filipin labeling of unesterified cholesterol in the neocortex of untreated (end-stage, 78 days old) and CD-treated (start at P21; end-stage, 197 days old) Npc1^−/− mice showed reduced cholesterol accumulation in a CD-treated mouse. (B) Higher magnification of neocortex in same CD-treated Npc1^−/− animal as previous panel, showed presence of neurons with cholesterol accumulation while neighboring cells lacked this storage. (C) Confocal microscopy further revealed that gangliosides and cholesterol appeared to always co-sequester within neurons in an untreated Npc1^−/− mouse (end-stage, 78 days old; upper panel). However, some neocortical neurons in a CD-treated Npc1^−/− mouse (start at P7; end-stage, 182 days old; lower panel) had little to no detectable cholesterol accumulation, yet still exhibited ganglioside storage. Cholesterol (red, visualized with BC Theta), GM2 (blue), and GM3 (green); n denotes nucleus of single neuron shown in each image. (D) IHC of untreated and CD-treated Npc1^−/− mice (same mice as A), revealed less GM2 storage (also GM3, not shown) in the neocortex of a CD-treated mouse. (E) Biochemical analysis of ganglioside levels further corroborated the reduction in GM2 and GM3 seen with IHC. Data from WT and untreated mutant mice represent mean ± SD. (F) Ultrastructural analysis of neocortical neurons in untreated and CD-treated Npc1^−/− mice (same mice as C) revealed presence of PCBs in both groups, but CD-treated mice appeared to have fewer of these storage bodies. (G) Western blot analysis of LC3-II in 85 day old untreated and CD-treated (start at P21) Npc1^−/− and WT mice revealed a reduction in LC3-II levels in the CD-treated Npc1^−/− mouse. Images taken at 20X (A), 40X (B), 63X (C), and 10X (D); scale bars 20 µm (A, B), 2 µm (C), 50 µm (D), 1 µm (F).

Figure 6. Chronic CD treatment study in Npc2^−/− mice.

(A) Average weight over time for untreated and CD-treated Npc2^−/− and WT mice. Weights of untreated and CD-treated WTs were averaged for each gender as there was no significant difference between treatments (p<0.8125). (B) Survival of untreated and CD-treated Npc2^−/− and WT mice. Median survival of Npc2^−/− mice: no treatment, 144 days; CD (every other day), 248 days. CD-treated Npc2^−/− mice lived significantly longer than untreated Npc2^−/− mice (p<0.0108). (C) Filipin labeling of unesterified cholesterol in neocortex of untreated (end-stage, 145 days old) and CD-treated (start at P9; 150 days old) Npc2^−/− mice revealed less cholesterol accumulation in the CD-treated mouse. (D) IHC of the same untreated and CD-treated Npc2^−/− mice showed reduced GM2 labeling in the neocortex of the CD-treated mouse (also for GM3, not shown). (E) Biochemical analysis of ganglioside levels confirmed the reduction in GM2 and GM3 storage seen with IHC. Data from WT and mutant mice represent mean ± SD. Images taken at 20X (C) and 10X (D); scale bars 20 µm (C) and 50 µm (D).

Figure 7. Free sphingosine concentrations in NPC disease following CD treatment.

(A) Biochemical analysis of sphingosine in brain of untreated and CD-treated Npc1^−/− and WT mice revealed that chronic CD treatment reduced sphingosine concentrations in affected mice, even when treatment was initiated post-weaning. Npc2^−/− mice exhibited a similar trend, although the effect was less pronounced. (B) Biochemical analysis of liver from untreated and CD-treated Npc1^−/− and Npc2^−/− mice showed that with chronic CD treatment, sphingosine accumulation was reduced to levels near those found in WT.

Figure 8. Chronic CD treatment study in GM1 and MPS IIIA mice.

(A, B) Filipin labeling of unesterified cholesterol (A) and IHC of GM1 ganglioside (B) in neocortex of untreated (138 days old) and CD-treated (start at P21; 138 days old) mice with GM1 gangliosidosis. Brown punctae indicate GM1 accumulation within cortical neurons. No differences were observed in either filipin or GM1 labeling between CD-treated and untreated GM1 mice. (C, D) Filipin labeling of unesterified cholesterol (C) and IHC of GM2 ganglioside (D) in neocortex of untreated (140 days old) and CD-treated (start at P30; 140 days old) MPS IIIA mice. As with GM1 mice, no differences were observed between CD-treated and untreated MPS IIIA mice. (E) No reductions in GM1, Asialo-GM1, GM2, or GM3 ganglioside levels were seen in cerebral homogenates of CD-treated GM1 and MPS IIIA mice compared to untreated mice as evidenced by the thin-layer chromatography plate. Images taken at 20X (A, C) and 10X (B, D); scale bars 20 µm (C, also applicable to A) and 50 µm (D, also applicable to B).