Degradation of engulfed mitochondria is rate-limiting in Optineurin-mediated mitophagy in neurons

Abstract

Mitophagy, the selective removal of damaged mitochondria, is thought to be critical to maintain neuronal homeostasis. Mutations of proteins in the pathway cause neurodegenerative diseases, suggesting defective mitochondrial turnover contributes to neurodegeneration. In primary rat hippocampal neurons, we developed a mitophagy induction paradigm where mild oxidative stress induced low levels of mitochondrial damage. Mitophagy-associated proteins were sequentially recruited to depolarized mitochondria followed by sequestration into autophagosomes. The localization of these mitophagy events had a robust somal bias. In basal and induced conditions, engulfed mitochondria remained in non-acidified organelles for hours to days, illustrating efficient autophagosome sequestration but delayed lysosomal fusion or acidification. Furthermore, expression of an ALS-linked mutation in the pathway disrupted mitochondrial network integrity and this effect was exacerbated by oxidative stress. Thus, age-related decline in neuronal health or expression of disease-associated mutations in the pathway may exacerbate the slow kinetics of neuronal mitophagy, leading to neurodegeneration.

Keywords: autophagy; cell biology; lysosome acidification; mitochondrial quality control; mitophagy; mouse; neurodegeneration; neuroscience; parkin; rat.

Figure 1.. Antioxidant removal induces low levels of mitochondrial damage and sequestration without compromising the entire neuronal network.

(A) Schematic of experimental paradigm to initiate mitophagy. (B) Fluorescence intensity quantification of intracellular ROS by the CellROX reagent in control and treated conditions. Mean ± SEM; n = 8 wells/condition per replicate, from 4 biological replicates; 7 DIV. *, p < 0.05; **, p < 0.01 by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test. (C–D) Representative images (C) and quantification (D) of TMRE fluorescence intensity. Mean ± SEM; n = 31-38 neurons from 3-4 biological replicates; 7 DIV. Not significant (n.s.) by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test. Scale bar, 5 μm. (E) Volume renderings of the somal mitochondrial network; original and enlarged images are shown for each neuron. Scale bar, 0.7 μm; inset, 4 μm. (F) Quantification of the somal mitochondrial content. Mean ± SEM; n = 16-24 neurons from 3-4 biological replicates; 6-7 DIV. Not significant (n.s.) by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test. (G–H) Representative Western blot (G) and quantification (H) of mitophagy-associated proteins from cultured hippocampal neurons. Data shown as the fold change over control of the protein of interest divided by total protein stain. Normalization factors are shown under representative images. Mean ± SEM; n = 5 biological replicates; 7-8 DIV. Not significant (n.s.); *, p < 0.05 by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test. (I) Representative single plane images from a somal z-stack showing OPTN sequestration of damaged spherical mitochondria; examples of these mitophagy events are shown in insets. Scale bar, 3 μm.

Figure 1—figure supplement 1.. OPTN puncta localize to rounded and fragmented mitochondria.

(A) Relative frequency of the somal mitochondrial aspect ratio. n = 21-28 neurons from 3 biological replicates; 7 DIV. (B–C) Representative Western blot (B) and quantification (C) of ATG16L1 and ATG5. Data shown as the fold change over control of the protein of interest divided by total protein stain. Normalization factors are shown under representative images. Mean ± SEM; n = 4 biological replicates; 7 DIV. Not significant (n.s.) by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test. (D) Quantification of the percent of OPTN puncta on linear and rounded mitochondria. Mean ± SEM; n = 21-28 neurons from 3 biological replicates; 7 DIV. Not significant (n.s.); ***, p < 0.001 by unpaired t test.

Figure 2.. OPTN colocalizes with upstream mitophagy-associated proteins within an hour of antioxidant removal.

(A) Schematic of the translocation of mitophagy-associated proteins to a damaged organelle. (B) Volume rendering of an OPTN-positive mitochondrion. Scale bar, 0.5 μm. (C) Representative image of an OPTN-positive mitochondrion that is TMRE-negative, confirming specific recruitment to damaged organelles. Scale bar, 1 μm. (D–F) Representative somal images of neurons expressing markers for mitochondria, OPTN, and ubiquitin (Ub; D), Parkin (E), and TBK1 (F). After 1 h in AO-free media, translocated proteins form rings around damaged mitochondria (1; red arrows and inset) and form puncta that colocalize with damaged mitochondria (2; green arrows and inset). Scale bar, 5 μm.

Figure 2—figure supplement 1.. OPTN is expressed in various brain regions and localized throughout the neuron.

(A–B) Representative Western blot (A) and quantification (B) of OPTN, p62, TAX1BP1, and NDP52 in total brain, cortex, and hippocampus. Mean ± SEM; n = 3 biological replicates. (C–E) Representative image of endogenous OPTN in the soma (C), distal axon (D), and dendrite (E). (F–H) Representative image of endogenous p62 in the soma (F), distal axon (G), and dendrite (H). Red arrows in panels C and F depict the axon labeled by anti-Neurofilament H (NF-H) and anti-Tau, respectively; an enlarged image of the soma is shown in the inset. Corresponding line scans for the axon and dendrite are shown to the right of the representative images; red arrows indicate OPTN and p62 puncta. Scale bars: soma, 20 μm; axons and dendrites, 5 μm.

Figure 2—figure supplement 2.. OPTN fails to engulf damaged mitochondria when Parkin is depleted.

(A–B) Representative Western blot (A) and quantification (B) of neurons after treatment with mock or Parkin siRNA. Normalization factors are shown under lanes. Data shown as the fold change over control of Parkin divided by total protein stain. Mean ± SEM; n = 3 from 3 biological replicates; 8 DIV. ***, p < 0.001 by unpaired t test. (C) Representative Western blot of non-transfected, Parkin siRNA treated, and Parkin siRNA treated neurons overexpressing mCherry-Parkin^WT or mCherry-Parkin^T240R. Normalization factors are shown under lanes. (D) Quantification of the percent of neurons with OPTN-positive mitochondria after 1 h AO-free treatment in a Parkin KD and rescue background. The dashed line represents the percent of cells with mitophagic events in treated cells not overexpressing Parkin (see Figure 3D). Mean ± SEM; n = 32-33 neurons from 3 biological replicates; 8 DIV. *, p < 0.05; **, p < 0.01 by one-way ANOVA with Tukey’s multiple comparisons test.

Figure 3.. OPTN is specifically recruited to damaged mitochondria in the soma after mitophagy induction.

(A–C) Representative image of the soma (A), dendrite (B), and axon (C) of a hippocampal neuron treated for 1 h with AO-free media. Mitophagy events are shown with red arrows. Scale bars: soma, 5 μm; axon and dendrite, 1 μm. (D) Quantification of the percent of neurons that contain OPTN-positive mitochondria. Mean ± SEM; n = 21-28 neurons from 3 biological replicates; 7 DIV. *, p < 0.05 by unpaired t test. (E) Quantification of the percent of OPTN-positive mitochondria in each cellular compartment for neurons treated for 1 h with AO-free media. Mean ± SEM; n = 21-28 neurons from 3 biological replicates; 7 DIV. ****, p < 0.0001 by one-way ANOVA with Dunn’s multiple comparisons test. (F) Quantification of the percent of cells with OPTN-positive mitochondria rings for longer and harsher treatment conditions. Mean ± SEM; n = 36-48 neurons from 3-4 biological replicates; 7 DIV. **, p < 0.01 by one-way ANOVA with Dunn’s multiple comparisons test. (G–H) Quantification of CellROX fluorescence intensity in the soma (G) and dendrites and axons (H). Mean ± SEM; n = 38-44 images from 3 biological replicates; 7-9 DIV. ***, p < 0.001; ****, p < 0.0001 by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test. Dendrite, Dend.

Figure 3—figure supplement 1.. Antioxidant removal alters axonal mitochondrial length with no effect on the TMRE fluorescence intensity.

(A) Kymographs from live-cell imaging of EGFP-LC3 in hippocampal neurons. Scale bars: horizontal, 10 μm; vertical, 1 min. (B–D) Quantification of autophagosome motility (B), density (C), and area flux (D) in the mid-axon. Mean ± SEM; n = 16-19 neurons from 3 biological replicates; 6 DIV. Not significant (n.s.) by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test. (E) Straightened images and representative kymographs of Mito-DsRed in the mid-axon. Scale bars: horizontal, 10 μm; vertical, 1 min. (F–H) Quantification of mitochondrial motility (F), density (G), and area flux (H). Mean ± SEM; n = 18-20 neurons from 3 biological replicates; 7-8 DIV. Not significant (n.s.) by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test. (I) Quantification of axonal mitochondria length in the mid-axon of control and treated neurons. Mean ± SEM; n = 18-20 neurons from 3 biological replicates; 7-8 DIV. **, p < 0.01; ***, p < 0.001 by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test. (J) Quantification of the TMRE fluorescence intensity of mitochondria in the mid-axon. Mean ± SEM; n = 40-46 neurons from 3 biological replicates; 7-8 DIV. Not significant (n.s.) by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test. (K) Quantification of the average number of mitochondrial fusion and fission events in the mid-axon. Mean ± SEM; n = 18-20 neurons from 3 biological replicates; 7-8 DIV. Not significant (n.s.) by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test.

Figure 4.. LC3 translocates to damaged mitochondria after OPTN ring formation.

(A–C) Representative image of the soma (A), dendrite (B), and axon (C) of a hippocampal neuron treated for 6 h with AO-free media. A mitophagosome is specified by red arrows and inset. Scale bars: soma, 5 μm; axon and dendrite, 2 μm. (D) Gallery of representative images demonstrating fully formed OPTN rings around damaged mitochondria with various stages of LC3 ring development, including EGFP-LC3 positive, negative, or incomplete (containing a punctum or partial ring). Red arrows highlight LC3 puncta. Scale bar, 1 μm. (E) Quantification of the number OPTN rings that are LC3-positive, LC3-negative, or partial-LC3. The total number of events are listed for each condition. n = 36–48 neurons from 3 to 4 biological replicates; 7 DIV.

Figure 5.. Mitochondria are sequestered in LAMP1-positive organelles that are non-acidified.

(A) Representative image of a hippocampal neuron 6 h after AO-free treatment; an OPTN-LAMP1-positive event is indicated by the red arrows and the inset. Scale bar, 5 μm. (B) Quantification of the ratio of OPTN-positive mitochondria that are LAMP1-positive or LAMP1-negative compared to the total number of events. Mean ± SEM; n = 32-35 neurons from 3 biological replicates; 6-8 DIV. *, p < 0.05 by unpaired t test. (C) Representative image of a hippocampal neuron; an OPTN-positive mitochondrion is negative for Lysotracker Green (LysoT) 6 h after mitophagy induction (red arrows and inset). Scale bar, 5 μm. (D) Quantification of the ratio of OPTN-positive events that are LysoT-positive or LysoT-negative compared to the total number of events. Mean ± SEM; n = 33-40 neurons from 3-4 biological replicates; 6-8 DIV. Not significant (n.s.) by one-way ANOVA with Tukey’s multiple comparisons test. (E–G) Representative Western blot (E) and quantification of TFEB (F) and pTFEB^S211 (G) from cultured hippocampal neurons. Data shown as the fold change over control of TFEB divided by total protein stain (F) or as pTFEB^S211 over total TFEB (G). Normalization factors are shown under representative images. Mean ± SEM; n = 3 biological replicates; 7-8 DIV. Not significant (n.s.) by one-way ANOVA with Dunn’s multiple comparisons test. (H–J) Representative Western blot (H) and quantification of ProCathepsin D (ProCatD; I) and mature Cathepsin D (CatD; J) from primary hippocampal neurons. Data shown as the fold change over control of the protein of interest divided by total protein stain. Mean ± SEM; n = 3 biological replicates; 7-8 DIV. Not significant (n.s.); *, p < 0.05 by one-way ANOVA with Dunn’s multiple comparisons test. (K) Schematic of lysosomal fusion (marked by LAMP1) and acidification (marked by LysoT) of damaged mitochondria in basal and induced conditions. The majority of mitophagosomes are LAMP1-positive in control conditions, but only half of mitophagosomes are LAMP1-positive in treated neurons. However, most fragmented mitochondria are LysoT-negative in either basal or induced neurons. (L) Table depicting the various vesicular compartments that sequester damaged mitochondria.

Figure 5—figure supplement 1.. Mitophagy induction does not alter the acidification of cellular autophagosomes or lysosomes.

(A–B) Quantification of the percent of autophagosomes per neuron that are non-acidified and acidified 1 h (A) or 6 h (B) after treatment. Mean ± SEM; n = 23-29 neurons from 3 biological replicates; 6 DIV. Not significant (n.s.) by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test. (C) Quantification of the percent of lysosomes per neuron that are non-acidified and acidified 1 h after treatment. Mean ± SEM; n = 37-38 neurons from 3 biological replicates; 6-7 DIV. Not significant (n.s.) by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test. (D–E) Representative images of hippocampal neurons expressing LAMP1-EGFP (D) or LAMP2-EGFP (E) and labeled with LysoT. The majority of LAMP organelles are LysoT-positive (red arrows and inset), denoting acidified organelles. A minor population are non-acidified (LAMP-positive LysoT-negative; white arrows). Scale bar, 5 μm. (F–G) Representative images of hippocampal neurons treated for 1 h with control (F) or AO-free (G) media. OPTN-LC3-positive mitochondria are negative for WIPI2B, indicating fully formed autophagosomes (red arrows and inset); immature autophagosomes, WIPI2B-LC3-positive, are also found in the soma (green arrows). Scale bar, 5 μm.

Figure 5—figure supplement 2.. Mitophagosomes are quickly acidified to clear damaged mitochondria in HeLa cells.

(A–B) Representative images of HeLa cells expressing untagged Parkin that were treated for 90 min with AA/Oligomycin A (OA) and allowed to recover in control media. Cells were imaged at various time points after the completion of treatments to monitor LAMP1 (A) and LysoT (B) recruitment to OPTN-positive mitochondria; events are highlighted in insets. Quantification of the percent of mitophagosomes per cell that are LAMP1- and LysoT-positive are shown below the representative images. Mean ± SEM; n = 47-55 cells from 3 biological replicates. ****, p < 0.0001 by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test.

Figure 6.. Lysosomal acidification is a rate-limiting step in the turnover of damaged mitochondria in neurons.

(A) Representative images of OPTN-positive mitochondria that are labeled with a tandem Mito-EGFP-mCherry marker. Line scans of the mitophagy events are shown under representative images for all conditions. Scale bar, 1 μm. (B) Representative image of the dual labeled somal mitochondria network labeled with Mito-EGFP-mCherry. A population have undergone lysosomal fusion and acidification (shown as magenta only puncta; red arrows). A subset of this population is also OPTN-positive demonstrating turnover (blue arrows). Scale bar, 5 μm. (C) Schematic of the tandem SEP-LAMP1-RFP marker. In acidified environments, SEP is quenched and lysosomes are labeled only by RFP. (D) Representative images of OPTN-positive mitochondria showing conditions where they were LAMP1-negative, dual labeled in ‘late’ mitophagosomes, or RFP-only labeled in mitophagolysosomes. Scale bar, 1 μm. (E) Quantification of the number OPTN-positive mitochondria that are LAMP1-negative, LAMP1 dual labeled, or only labeled by RFP. The total number of events are listed for each condition. n = 30–32 neurons from 3 biological replicates; 6–7 DIV.

Figure 6—figure supplement 1.. OPTN-positive mitochondria rings and puncta undergo lysosomal engulfment.

(A) Representative images of OPTN rings and puncta that colocalize with damaged mitochondria. Line scans of mitophagy events are shown under representative images. Scale bar, 1 μm. (B) Quantification of the total number of OPTN rings (data presented in Figure 6E) and puncta that are LAMP1-negative, LAMP1 dual labeled, or only labeled by RFP. The total number of events are listed for each condition. n = 30–32 neurons from three biological replicates; 6–7 DIV.

Figure 7.. ‘Aged’ mitochondria are sequestered in non-acidified compartments twenty-four hours after treatment.

(A–B) Time line (A) and schematic (B) of mitochondrial pulse-chase experiments. Following transient transfection, mitophagy was induced (6 h control or AO-free) and mitochondria were labeled with the first SNAP ligand (‘Old’ Mito; shown as magenta). SNAP block was added for 2 h to saturate the remaining binding sites and neurons were left overnight. Prior to imaging, mitochondria were labeled with a second spectrally distinct SNAP ligand (‘Young’ Mito; shown in green). Both ‘Old’ and ‘Young’ ligands were labeled for 30 min, followed by two quick washes, and a 30 min washout. (C) Representative image of ‘Old’ and ‘Young’ mitochondrial populations in the soma. Scale bar, 5 μm. (D–E) Representative images of neurons that are 24 h post-treatment illustrating OPTN sequestered ‘Old’ mitochondria that are negative for LAMP1 and the ‘Young’ mitochondria marker (red arrows and insets). Scale bar, 5 μm. Line scans of mitophagy events are shown on the right. (F–G) Representative somal images of neurons that are 24 h post-treatment. Red arrows highlight OPTN-positive ‘Old’ mitochondria that are negative for ‘Young’ mitochondria and LysoT. Scale bar, 5 μm. Line scans of mitophagic events are shown to the right of the image.

Figure 8.. A disease-associated OPTN mutant increases mitochondrial vulnerability to oxidative stress.

(A) Schematic of OPTN and its various domains. LIR, LC3 interacting region. UBAN, ubiquitin binding in ABIN and NEMO. The ALS-associated OPTN mutant E478G fails to bind ubiquitin. (B) Representative image of AO-free treated neurons expressing WT OPTN (OPTN^WT; upper panel) or a disease-linked OPTN mutant (OPTN^E478G; lower panel). White arrows denote swollen mitochondria. Scale bar, 5 μm. (C) Volume renderings of the somal mitochondrial network; OPTN^E478G expression induces the appearance of enlarged organelles compared to the expression of OPTN^WT (white arrows). Scale bar, 1 μm. (D) Quantification of the somal mitochondrial content. Mean ± SEM; n = 24-40 neurons from 5 biological replicates; 8 DIV. Not significant (n.s.) by unpaired t test. (E) Quantification of the number of OPTN puncta per cell. Mean ± SEM; n = 24-40 neurons from 5 biological replicates; 8 DIV. ****, p < 0.0001 by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test. (F) Quantification of the TMRE fluorescence intensity. Mean ± SEM; n = 24-40 neurons from 5 biological replicates; 8 DIV. **, p < 0.01; ****, p < 0.0001 by Kruskal-Wallis ANOVA with Dunn’s multiple comparisons test.

Figure 8—figure supplement 1.. OPTN is efficiently knocked-down in neurons with siRNA.

(A–B) Representative Western blot (A) and quantification (B) of neurons after treatment with mock or OPTN siRNA. Data shown as the fold change over control of OPTN divided by total protein stain. Normalization factors are shown under lanes. Mean ± SEM; n = 4 from 3 biological replicates; 8 DIV. ****, p < 0.0001 by unpaired t test. (C) Representative Western blot of non-transfected, OPTN siRNA treated, and OPTN siRNA treated neurons overexpressing Halo-OPTN^WT or Halo-OPTN^E478G mutant. Normalization factors are shown under lanes.

Figure 9.. Model depicting the spatial and temporal regulation of OPTN-mediated neuronal mitophagy.

(A) Upon mitophagy induction, Parkin translocates to spherical mitochondria and increases the abundance of ubiquitin chains. OPTN and its kinase TBK1 are recruited followed by sequestration and elimination via autophagosome engulfment and lysosomal fusion, as monitored by LC3 and LAMP1/LysoT, respectively. This quality control mechanism is compartmentally restricted to the soma and rarely occurs in the axon. As a result, other quality control pathways may regulate axonal mitochondria. (B) Parkin, Ub, TBK1 and OPTN localize with damaged organelles within an hour of inducing mitophagy. LC3 translocation occurs after OPTN and ~75% of OPTN-positive mitochondria are LC3-positive, forming mitophagosomes an hour after initial damage. Under basal conditions, ‘late’ mitophagosomes (OPTN-LAMP-positive mitochondria) routinely form within an hour. However, mitophagy induction perturbs this pathway, increasing the number of LAMP1-negative OPTN-positive mitochondria. Interestingly, only a small fraction of OPTN-positive mitochondria are acidified in either basal or induced conditions, suggesting lysosomal acidification to eliminate damaged organelles is rate-limiting.

Author response image 1.. Representative images of hippocampal neurons (A) and HeLa cells (B) comparing OPTN expression levels in non-transfected and Halo-OPTN transfected cells.

aOPTN polyclonal antibody; Abcam ab23666. Scale bar, 100 μm.

Author response image 2.. Representative images of a hippocampal neuron showing Halo-OPTN puncta are found in LAMP1-EGFP containing organelles in the soma.

These puncta are negative for mitochondria. Examples of events are indicated by the red arrows. Scale bar, 5 μm.

Author response image 3.. Representative images of a hippocampal neuron following antioxidant removal for 6 hours.

An example of a LC3-positive mitochondrion in the absence of overexpressed OPTN is shown. Both the GFP and mCherry of the tandem LC3 marker are present, illustrating the damaged mitochondrion is sequestered in a nonacidified organelle. Scale bar, 1 μm.

Author response image 4.. Representative images of hippocampal neurons illustrating that the majority of LAMP1-positive (A) or LAMP2-positive (B) organelles are acidified, as indicated by the presence of LysoT.

LAMP-LysoT-positive lysosomes are indicated by red arrows and inset; LAMP-positive LysoT-negative organelles are indicated by open white arrows. Scale bar, 5 μm.

Author response image 5.. Representative images of neurons 1 h after control or AO-free treatment.

Mitophagosomes are indicated by red arrows and inset. OPTNLC3-positive mitochondria are negative for WIPI2B, indicating fully formed autophagosomes. Scale bar, 5 μm.