Defective PITRM1 mitochondrial peptidase is associated with Aβ amyloidotic neurodegeneration

Abstract

Mitochondrial dysfunction and altered proteostasis are central features of neurodegenerative diseases. The pitrilysin metallopeptidase 1 (PITRM1) is a mitochondrial matrix enzyme, which digests oligopeptides, including the mitochondrial targeting sequences that are cleaved from proteins imported across the inner mitochondrial membrane and the mitochondrial fraction of amyloid beta (Aβ). We identified two siblings carrying a homozygous PITRM1 missense mutation (c.548G>A, p.Arg183Gln) associated with an autosomal recessive, slowly progressive syndrome characterised by mental retardation, spinocerebellar ataxia, cognitive decline and psychosis. The pathogenicity of the mutation was tested in vitro, in mutant fibroblasts and skeletal muscle, and in a yeast model. A Pitrm1(+/-) heterozygous mouse showed progressive ataxia associated with brain degenerative lesions, including accumulation of Aβ-positive amyloid deposits. Our results show that PITRM1 is responsible for significant Aβ degradation and that impairment of its activity results in Aβ accumulation, thus providing a mechanistic demonstration of the mitochondrial involvement in amyloidotic neurodegeneration.

Keywords: amyloid beta; mitochondrial disease; mitochondrial targeting sequence; neurodegeneration; pitrilysin 1.

Figure 1. Clinical and molecular studies on PITRM1 ^R183Q mutant patients

1. Family tree. Affected subjects are represented by filled shapes. The index case is II‐2 (arrow).

2. Brain MRI images of II‐1 (FLAIR). A: (a) sagittal interemispheric sequence showing profound cerebellar atrophy (arrow); (b) transverse sequence showing involvement of the dentate nuclei of cerebellum; (c) coronal sequence revealing cortical atrophy, a wide third ventricle, and high signal changes in the thalami, particularly on the left (arrow); (d) the thalamic lesion is indicated by an arrow.

3. Histochemical staining of skeletal muscle from II‐2. Combined COX/SDH staining shows scattered COX‐negative (blue) fibres (arrows). Scale bar corresponds to 100 μm.

4. Respiratory chain complex activities in skeletal muscle. Specific activities (nmol/min/mg) of complex I, II and IV are reduced in II‐2 (red) compared to the controls mean (blue); CS activity is also low (< 50% of controls), suggesting a reduction in mitochondrial mass (see main text for further details). Each activity was measured in triplicate.

5. Western blot analysis of PITRM1 in primary fibroblasts (left) and skeletal muscle (right) of controls (CTR) and subject II‐2. Densitometric quantification using the Genetools software is shown below the blots. In blue is PITRM1^WT and in red PITRM1^R183Q.

6. Proteolytic activity on two fluorescent oligopeptides (AnaSpec), reported at the bottom of each histogram, by 6‐His‐tagged PITRM1^WT and PITRM1^R183Q proteins expressed in E. coli and affinity‐purified by Ni‐agarose chromatography. Values are expressed as arbitrary units per sec per μg of protein (a.u./s/μg). Experiments were performed in duplicate.

7. Degradation rate of Aβ_1–42 by purified 6‐His‐tagged PITRM1^WT and PITRM1^R183Q proteins. Quantification of these experiments is displayed below the blots. Experiments were performed in duplicate.

Data information: Data are presented as mean ± SD.Source data are available online for this figure.

Figure 2. Characterisation of immortalised cells

1. Cell growth in glucose (GLU) and galactose (GAL). C29V, C47V and TpLV: immortalised fibroblast cell lines from control individuals; PITRM1V: immortalised fibroblasts from subject II‐2, carrying the PITRM1 ^R183Q mutation. pLKO.1: empty vector; sh38: shRNA38; sh41: shRNA41. Each cell line was measured six times. Statistical analysis was performed using two‐way ANOVA post hoc Bonferroni test, ***P < 0.001.

2. Western blot analysis of PITRM1 in C29V cells transduced with the empty vector plKO.1 and the two shRNAs, sh38 and sh41. SDHB and β‐actin are used as loading controls.

3. Co‐localisation of PITRM1 (red) with TOM20 (T20, green) in human fibroblast cells from a control (CTR) and subject II‐2. Note that the intensity of PITRM1 immunofluorescence is much lower in II‐2 cells than in CTR cells (see main text for further details). Nuclei are stained in blue by DAPI. Scale bar corresponds to 10 μm.

4. Mitochondrial membrane potential (ΔP). In healthy cells with high mitochondrial ΔP, JC‐1 forms complexes known as J‐aggregates that show an intense red fluorescence. On the contrary in unhealthy cells with low ΔP, JC‐1 remains in the monomeric form, showing only green fluorescence. Values are referred to as % of those of the control means, taken as 100%. The results are the mean of three independent experiments. Statistical analysis was performed using two‐way ANOVA, **P < 0.01; ****P < 0.0001.

Data information: Data are presented as mean ± SD. Exact P‐values are reported in Table EV1.Source data are available online for this figure.

Figure 3. Modelling the cym1 ^R163Q mutation in Saccharomyces cerevisiae

1. Oxidative growth. W303‐1B cym1Δ strains harbouring the wild‐type CYM1 allele (CYM1 ^wt), the cym1 ^R163Q mutant allele or the empty vector were serially diluted from 10⁷ to 10⁴ cells/ml. Five microlitres of each dilution was spotted on SC agar plates without uracil, supplemented with 2% glucose, 2% glycerol or 2% ethanol. Plates were incubated at 37°C for 3–7 days.

2. Oxygen consumption rate (OCR). Cells grown at 37°C SC medium without uracil were supplemented with 0.5% glucose. Values were normalised to the OCR of the CYM1 ^wt strain (49 nmol O₂/min/mg) and represented as the mean of at least three values ± SD.

3. Reduced versus oxidised cytochrome spectra. Peaks at 550, 560 and 602 nm correspond to cytochromes c, b and aa3, respectively. The height of each peak relative to the baseline is an index of cytochrome content.

4. Respiratory chain complex activities. Biochemical activities of succinate quinone DCPIP reductase, SQDR (CII), NADH‐cytochrome c oxidoreductase activity NCCR (CIII) and cytochrome c oxidase (CIV) were measured on a mitochondrial enriched fraction from cells grown at 37°C as in (B). Values were normalised to that of CYM1 ^wt strain and represented as the mean of three independent experiments ± SD.

5. Western blot on total protein extract using an anti‐HA monoclonal antibody visualising the CYM1^wt and cym1^R163Q recombinant proteins both fused in frame with the HA epitope on the C‐terminus. Total protein extracts were obtained by strains expressing HA‐tagged CYM1 ^wt and cym1 ^R163Q. PGK was used as a loading control, and signals were normalised to the wt. The quantification was performed on five independent blots.

6. Prolonged exposure of a Western blot containing the CYM1^wt and cym1^R163Q recombinant proteins reveals the presence of a band corresponding to a degradation product in the cym1^R163Q lanes (arrow).

7. Western blot of Aβ_1–42 ^myc monomer and dimer incubated with purified mitochondrial extracts from cells grown at 37°C in SC medium supplemented with 0.15% glucose and 2% galactose. VDAC was used as a loading control. Each experiment was performed in triplicate.

Data information: Statistical analysis was performed using unpaired, two‐tailed Student's t‐test. **P < 0.01; ***P < 0.001. Exact P‐values are reported in Table EV1. Source data are available online for this figure.

Figure 4. Behavioural studies of Pitrm1 ^+/− mouse

1. A

   Western blot analysis of Pitrm1 protein in brain, muscle and liver of two 4‐mo male Pitrm1 ^+/− mice and two Pitrm1 ^+/+ littermates. Densitometric analysis is reported in the histograms below the blots. Pitrm1 ^+/+ is in blue and Pitrm1 ^+/− in red.

2. B

   Representative hindlimb clasping phenomenon is shown in a 4‐mo Pitrm1 ^+/− male mouse, consisting in strong adduction of the hindlimbs when the animal is suspended by the tail; a littermate Pitrm1 ^+/+ control displays the normal reflex, consisting in wide abduction of the limbs. All examined Pitrm1 ^+/− animals displayed this abnormal reflex from 2 months of age.

3. C

   Rotarod test. Blue and red lines refer to Pitrm1 ^+/+ (n = 9) and Pitrm1 ^+/− (n = 7) 4‐mo animals, respectively.

4. D–F

   Negative geotaxis (D), cylinder (E) and pole (F) tests. The experiments were carried out on the same group of animals as in (B).

Data information: Data are presented as mean ± SD. Statistical analysis was performed using unpaired, two‐tailed Student's t‐test. *P < 0.05; **P < 0.01; ***P < 0.001. Exact P‐values are reported in Table EV1.Source data are available online for this figure.

Figure 5. Molecular and morphological analysis of Pitrm1 ^+/− mouse brain

1. Western blot analysis of amyloid precursor protein (APP) in 6‐mo male mice. GAPDH was used as a loading control. Densitometric analysis on a total of five independent samples is shown in the histogram on the right. ***P =  0.00058. Data are presented as mean ± SD. Statistical analysis was performed using unpaired, two‐tailed Student's t‐test.

2. Morphological analysis of an AD subject and of Pitrm1 ^+/− and Pitrm1 ^+/+ mouse brains. TF: thioflavin T (thalamus); CR: Congo red (brain cortex); PL: polarised light (same sections as those stained with CR); Aβ_1–42 immunostaining (pons); Ub: ubiquitin immunohistochemistry shown as brownish staining (brain cortex). Scale bar indicates 20 μm.

Source data are available online for this figure.

Figure EV1. Aβ_1–42 immunostaining in brains of 12‐mo mice

Brain sections from an AD patient are shown as positive controls. The brownish areas correspond to Aβ_1–42 deposits. A black bar indicates 100×. The same magnification was used for all images.

Figure 6. Aβ_1–42 mitochondrial import and degradation

1. Upper panel: import of Aβ_1–42 into mitochondria. Lower panel: relative quantification from two independent experiments. Values of Aβ_1–42 signal were normalised to HSP60 signal, and the resulting value at 5 min without trypsin was arbitrarily set as 1.

2. Upper panel: pulse and chase experiment to assess clearance of Aβ_1–42; lower panel: quantification from three independent experiments. Values of Aβ_1–42 signal were normalised to HSP60 signal, and the pulse value was arbitrarily chosen as 1.

Data information: Data are presented as mean ± SD. Statistical analysis was performed using unpaired, two‐tailed Student's t‐test. *P < 0.05, **P < 0.01. Exact P‐values are reported in Table EV1.

Figure 7. Degradation of Aβ_1–40 peptide in fibroblasts and MEFs

1. MEFs from Pitrm1 ^+/+, Pitrm1 ^+/−, Mfn1 ^−/− and Mfn2 ^−/−, as well as h‐PITRM1 ^R183Q and h‐ PITRM1 ^WT, were exposed to Aβ_1–40 peptide for 18 h. Note that Aβ_1–40 signal was still evident in Pitrm1 ^+/− and h‐PITRM1 ^R183Q cells.

2. Quantification of three independent experiments similar to those shown in (A). Data are presented as mean ± SD. Statistical analysis was by unpaired, two‐tailed Student's t‐test. **P < 0.01, ***P < 0.001. Exact P‐values are reported in Table EV1.