Mutations in FBXL4 cause mitochondrial encephalopathy and a disorder of mitochondrial DNA maintenance

Abstract

Nuclear genetic disorders causing mitochondrial DNA (mtDNA) depletion are clinically and genetically heterogeneous, and the molecular etiology remains undiagnosed in the majority of cases. Through whole-exome sequencing, we identified recessive nonsense and splicing mutations in FBXL4 segregating in three unrelated consanguineous kindreds in which affected children present with a fatal encephalopathy, lactic acidosis, and severe mtDNA depletion in muscle. We show that FBXL4 is an F-box protein that colocalizes with mitochondria and that loss-of-function and splice mutations in this protein result in a severe respiratory chain deficiency, loss of mitochondrial membrane potential, and a disturbance of the dynamic mitochondrial network and nucleoid distribution in fibroblasts from affected individuals. Expression of the wild-type FBXL4 transcript in cell lines from two subjects fully rescued the levels of mtDNA copy number, leading to a correction of the mitochondrial biochemical deficit. Together our data demonstrate that mutations in FBXL4 are disease causing and establish FBXL4 as a mitochondrial protein with a possible role in maintaining mtDNA integrity and stability.

Figure 1

Genetic Investigation of the Families Confirms Segregation with Disease of Recessive FBXL4 Mutations The pedigrees of S1 (A), S2 (B), and S3 (C) are shown, highlighting the consanguineous nature of each family. The probands are indicated by black arrows, and all individuals presenting with similar clinical features are shown as filled black symbols (pedigrees are drawn to accepted standards³⁷). A sequencing chromatogram obtained by targeted resequencing is shown for each proband, confirming the presence of the c.1555C>T (p.Gln519^∗) (S1), c.1303C>T (p.Arg435^∗) (S2), and c.1703G>CGC (S3) mutations.

Figure 2

FBXL4 Protein Structure and Localization (A) Schematic of FBXL4 showing the location of the bioinformatically determined mitochondrial localization sequence (mt) and conserved domains (F-box CDD ID pfam12937, AMN1 CDD ID cd09293). The locations of each of the mutations are indicated. (B) Three-dimensional structural modeling of FBXL4 shows the canonical folds of the F-box and nine leucine-rich repeats. The protein schematic and 3D structure are both displayed in reverse rainbow from the N to C terminus. (C) Splicing of exon 9 was demonstrated to be significantly impaired in S3 compared to controls. Error bars indicate standard deviation; ^∗∗∗p < 0.0001. (D) FBXL4 was confirmed to be a mitochondrial protein through an immunolocalization study in human fibroblasts, showing HA-tagged FBXL4 (green) colocalizing with MitoTracker Red-labeled mitochondria. Nuclei were counterstained with DAPI (blue).

Figure 3

Individuals with FBXL4 Mutations Display Mitochondrial Biochemical Dysfunction (A) Cytochrome c oxidase (COX) histocytochemical activities in skeletal muscle from S1 and S2 are globally decreased in comparison to control muscle, although somewhat unusually there are occasional, COX-positive fibers in S1 showing discrete, punctate enzyme activity. (B and C) Respiratory chain complex biochemical activity was determined in both skeletal muscle (B) and fibroblasts (C) from all probands (dark gray columns, S1; light gray columns, S2; white columns, S3) and is shown relative to the mean activity measured in 25 controls. (D) Mitochondrial membrane potential was measured in fibroblasts from S1, S2, and S3 together with seven controls (C). Cells from each affected individual showed severely compromised membrane potential compared to controls. ^∗∗∗p < 0.0001. (E) Severe depletion of mtDNA was determined in skeletal muscle and fibroblasts from each of the three probands (dark gray columns, S1; light gray columns, S2; white columns, S3) when measured in comparison to age-matched control muscle (n = 20) and fibroblasts (n = 3) (black columns). For all data, error bars indicate standard deviation.

Figure 4

Characterization of the OXPHOS Defects in Fibroblasts (A) Microscale oxygraphy analysis of live fibroblasts demonstrated a profound respiratory deficiency in cells from both S1 (c.1555C>T [p.Gln519^∗], n = 22, white triangles) and S2 (c.1303C>T [p.Arg435^∗], n = 14, white circles), compared to the combined data of control cell lines (n = 5, black squares). Error bars indicate the standard deviation. (B) The total amount of ATP produced by fibroblasts from S1 and S2 is not dramatically different to controls, but the proportion contributed by OXPHOS (black columns) is significantly reduced, whereas that contributed by glycolysis (white columns) is significantly increased. (C) The ability of fibroblasts from S1 and S2 to respond to stress, as measured by the spare respiratory capacity (maximal OCR minus basal OCR), is significantly reduced in comparison to controls. ^∗∗∗p < 0.0001. (D) The efficiency of the coupling of respiration to ATP synthesis (oligomycin-sensitive OCR as a percent of basal OCR) was significantly impaired in fibroblasts from S2 but not S1 compared to controls. For all data, error bars indicate standard deviation. ^∗∗∗p < 0.0001; NS, not significant. (E) Immunoblotting for protein components of each of the mitochondrial respiratory chain complexes was completed in S1 and S2 to determine their abundance relative to control (labeled C). Three subunits of complex I (NDUFA13, NDUFB8, and NDUFA9), one of complex II (SDHA), one of complex III (UQCRC2), three of complex IV (COXI, COXII, and COXIV), and one of complex V (ATPB) were probed, with TOMM20 as a mitochondrial marker and β-actin as a loading control.

Figure 5

Mitochondrial Network and Nucleoid Morphology Is Disrupted in Individuals with FBXL4 Mutations The upper panels show representative images of MitoTracker Red staining of control (left), S1 (middle), and S2 (right) fibroblasts. Note fragmentation and shortening of mitochondria in both these cell lines compared to the control. The lower panels show nucleoid staining by PicoGreen, revealing larger nucleoids with perinuclear clustering in cells from both subjects.

Figure 6

FBXL4 Gene Rescue Studies in S1 and S2 Cells Fibroblasts were transduced with either GFP (black columns) or wild-type FBXL4 (gray columns) and compared to transduced control fibroblasts. (A–C) mtDNA copy number (A), complex IV activity (B), and membrane potential (C) were recovered to normal levels in S1 and S2 fibroblasts transfected with wild-type FBXL4 but not GFP. (D) FBXL4 mRNA levels were increased in control (C) and S1 and S2 fibroblasts infected with wild-type FBXL4 but not in those infected with GFP. Transcript levels are reported relative to GAPDH. For all graphs, error bars indicate standard deviation; ^∗∗∗p < 0.0001, ^∗∗p < 0.01.