Mitochondrial hsp60 chaperonopathy causes an autosomal-recessive neurodegenerative disorder linked to brain hypomyelination and leukodystrophy

Abstract

Hypomyelinating leukodystrophies (HMLs) are disorders involving aberrant myelin formation. The prototype of primary HMLs is the X-linked Pelizaeus-Merzbacher disease (PMD) caused by mutations in PLP1. Recently, homozygous mutations in GJA12 encoding connexin 47 were found in patients with autosomal-recessive Pelizaeus-Merzbacher-like disease (PMLD). However, many patients of both genders with PMLD carry neither PLP1 nor GJA12 mutations. We report a consanguineous Israeli Bedouin kindred with clinical and radiological findings compatible with PMLD, in which linkage to PLP1 and GJA12 was excluded. Using homozygosity mapping and mutation analysis, we have identified a homozygous missense mutation (D29G) not previously described in HSPD1, encoding the mitochondrial heat-shock protein 60 (Hsp60) in all affected individuals. The D29G mutation completely segregates with the disease-associated phenotype. The pathogenic effect of D29G on Hsp60-chaperonin activity was verified by an in vivo E. coli complementation assay, which demonstrated compromised ability of the D29G-Hsp60 mutant protein to support E. coli survival, especially at high temperatures. The disorder, which we have termed MitCHAP-60 disease, can be distinguished from spastic paraplegia 13 (SPG13), another Hsp60-associated autosomal-dominant neurodegenerative disorder, by its autosomal-recessive inheritance pattern, as well as by its early-onset, profound cerebral involvement and lethality. Our findings suggest that Hsp60 defects can cause neurodegenerative pathologies of varying severity, not previously suspected on the basis of the SPG13 phenotype. These findings should help to clarify the important role of Hsp60 in myelinogenesis and neurodegeneration.

Figure 1

Pedigree of the Analyzed Subjects The inheritance of the disease is compatible with an autosomal-recessive trait. Roman capitals indicate generations. Arabic numerals indicate serial numbers of study participants. Blackened symbols indicate affected individuals. Diagonal lines across symbols indicate deceased individuals. Asterisks indicate affected individuals who underwent DNA analysis.

Figure 2

MRI/MRS Brain Imaging (A–C) Axial T2WI in a 17-month-old patient showing high intensity of the white matter consistent with the complete absence of myelin. (D) Sagital T1WI of a 16-month-old patient demonstrating a small brain stem and atrophy of the cerebellum and vermis. (E) Proton MR spectroscopy MRS (TE = 35) of a 16-month-old patient disclosing a reduced NAA/Cr ratio and increased mI/Cr ratio in the white matter, a normal Cho/Creatine ratio consistent with hypomyelination rather than with myelin destruction, and peaks for lactate and lipids, consistent with defective oxidative phosphorylation.

Figure 3

Haplotype Analysis Confirmation of linkage was performed by genotyping of eight polymorphic microsatellite markers within the SNP-based candidate region on 2q32.3-q33.1 in ten affected children and their close relatives. Blackened symbols and diagonal lines across symbols indicate affected and deceased individuals, respectively. Numbers below symbols correspond to the position of individuals within the pedigree (see Figure 1 for details). Hyphens indicate nongenotyped markers. The shared disease-associated haplotype is shown in boxes.

Figure 4

HSPD1 Mutation Analysis (A) Genomic DNA sequence analysis of HSPD1 reveals a homozygous A→G transition at position g.1512 (indicated by an arrow) in exon 2, resulting in an aspartic-acid-to-glycine substitution at position 29 of the Hsp60 protein (D29G). The mutation is carried in a homozygous state by an affected child (left panel) and in a heterozygous state by his mother (middle panel). A healthy control shows the wild-type (WT) sequence (right panel). (B) Confirmation of the D29G mutation in an affected individual and his close relatives by mismatch PCR-RFLP. Numbers adjacent to symbols correspond to the position of individuals within the pedigree (see Figure 1 for details). PCR amplification was performed as described in the text. Amplicons containing both the mismatching forward primer and the D29G mutation in exon 2 of HSPD1 introduce a recognition site for BslI, which digests the 124 bp PCR product into 94 bp and 30 bp fragments. Homozygous carriers of the mutation display a 94 bp fragment (the additional 30 bp fragment is not shown), healthy individuals carrying the wild-type sequence show a 124-bp fragment, and heterozygous carriers of the mutation display two fragments of 124 bp and 94 bp. (C) ClustalW analysis of the Hsp60 N-terminal region encompassing the mutation site demonstrates that the D29 residue (highlighted in red) is highly conserved across Hsp60 homologs from various species. The D29 residue in human Hsp60 corresponds to D5 in the E. coli homolog protein because of the lack of a mitochondrial-targeting sequence in bacteria.

Figure 5

E. coli Complementation Assay (A) Impaired growth of GroEL-GroES-deleted E. coli cells complemented with the D29G-Hsp60 variant under various conditions. Single, fresh transductant colonies (12 expressing the wild-type Hsp60 and 12 expressing the mutant D29G-Hsp60) were resuspended in 10 mM MgSO₄; 20-fold serial dilutions were made, alternately spotted on LB agar plates containing varying amounts of IPTG inducer and 12.5 μg/ml of chloramphenicol, and incubated at various temperatures. Growth impairment of serial dilutions of mutant as compared to wild-type transductans alternating from left to right at 30°C in 25 μM IPTG (left panel), at 37°C in 25 μM IPTG (middle panel) and at 38.5°C in 500 μM IPTG (right panel) is shown. (B) Measurement of Hsp60 expression in GroEL-GroES-deleted E. coli transductants by immunoassay. The mean expression levels of Hsp60 in eight individual bacterial transductants, four expressing the wild-type Hsp60 (WT) and four expressing the mutant D29G-Hsp60 (mutant), were found to be comparable (p value for two-sample Student's t test = 0.47). Error bars indicate the standard error of the mean.