UBQLN2 Mediates Autophagy-Independent Protein Aggregate Clearance by the Proteasome

Abstract

Clearance of misfolded and aggregated proteins is central to cell survival. Here, we describe a new pathway for maintaining protein homeostasis mediated by the proteasome shuttle factor UBQLN2. The 26S proteasome degrades polyubiquitylated substrates by recognizing them through stoichiometrically bound ubiquitin receptors, but substrates are also delivered by reversibly bound shuttles. We aimed to determine why these parallel delivery mechanisms exist and found that UBQLN2 acts with the HSP70-HSP110 disaggregase machinery to clear protein aggregates via the 26S proteasome. UBQLN2 recognizes client-bound HSP70 and links it to the proteasome to allow for the degradation of aggregated and misfolded proteins. We further show that this process is active in the cell nucleus, where another system for aggregate clearance, autophagy, does not act. Finally, we found that mutations in UBQLN2, which lead to neurodegeneration in humans, are defective in chaperone binding, impair aggregate clearance, and cause cognitive deficits in mice.

Graphical abstract

Figure 1

UBQLN2 Is Required for Cell Survival after Heat Shock (A) Schematic of the known domains of UBQLN2, their binding partners, and reported familial disease mutations shown in italics. (B) Binding partners of UBQLN2 that were identified by immunoprecipitation (IP) of UBQLN2 from mouse brain lysate followed by mass spectrometry. (C) Depletion of UBQLN2 by two independent siRNAs (72 hr) leads to cell death on heat stress. (D–F) UBQLN2, HSP70, and proteasome, but not UBQLN1 or UBQLN4, co-purify with insoluble ubiquitin-rich aggregates upon heat stress. (G–I) UBQLN2 inducibly interacts with proteasomes, ubiquitylated proteins, and HSP70 after heat shock and loses binding to UBQLN1 and UBQLN4. See also Figures S1 and S7.

Figure 2

Heat Stress Activates UBQLN2 to Clear Aggregated Proteins (A) UBQLN2 depletion by siRNA leads to defective clearance of heat-shock-induced insoluble ubiquitin conjugates (left), and quantification of insoluble ubiquitin in the pellet (right) (n = 2). Error bars represent SEM. (B) Insoluble heat-shock-generated ubiquitin conjugates are cleared efficiently in ATG5 knockout (autophagy-deficient) MEFs in a proteasome-dependent manner. (C) UBQLN2 depletion in autophagy-deficient cells leads to attenuated clearance of heat-shock-induced insoluble ubiquitin conjugates. Quantification (n = 3) is shown (right). Error bars represent SD; statistical tests were two-tailed t tests. (D) HSP70 siRNA leads to a defective clearance of ubiquitylated aggregated proteins. Over time, the transcriptional heat shock response leads to increased levels of HSP70. (E) Increased interaction of UBQLN2 with HSP70 and ubiquitin was observed in HSP105 knockout (KO) MEF cells. (F) UBQLN2 and ubiquitin are more abundant in the pellet fraction after heat shock in HSP105 KO MEF cells. (G) HSP105 KO MEFs are deficient in clearing heat-shock-induced aggregates. In addition, increased binding of HSP70 and ubiquitin to UBQLN2 was detected. (H) Depletion of UBQLN2 by siRNA leads to defective clearance of puromycin-labeled truncated proteins. (I and J) UBQLN2 translocates to the nucleus after heat stress (see Figure S2A for fractionation protocol). Quantification of the normalized nuclear fluorescence intensity is shown (J, bottom) (n = 99 and 122 for 37°C and 43°C, respectively). Error bars represent SD. (K) UBQLN2 co-localizes with cellular HTT aggregates in HEK293 cells inducibly expressing pathological GFP-Huntingtin (HTTQ103). (L) UBQLN2 co-aggregates with pathological, but not non-pathological, GFP-Huntingtin, as shown by filter trap assay. (M) UBQLN2 depletion leads to increased HTT-Q103 aggregates, running in the stacking gel. Quadruplicate transfections are shown. See also Figures S2, S3, S4, and S7.

Figure 3

UBQLN2 Mutations Do Not Cause Protein Aggregation (A) Inducible HEK293 cells stably overexpressing the indicated FLAG-UBQLN2 exhibit cytosolic foci for both the wild-type (WT) and P506T mutant. The L619A ubiquitin non-binding point mutation abrogates foci formation for WT and P506T mutant. (B) UBQLN2 point mutants (F594V and L619A) are defective in polyubiquitin binding. (C) Circular dichroism performed on pure wild-type and mutant protein. PONDR prediction (inset) results in a small decrease of disorder for PXXP mutant proteins (WT, P506T, and P497H shown). Experimentally, no difference is seen in the amount of disorder and secondary structure for the mutants. (D) Purified UBQLN2 was analyzed by analytical ultracentrifugation at different concentrations, showing dimer and trimer peaks for both WT and mutant protein. See also Figures S3 and S4.

Figure 4

Disease Mutant UBQLN2 Loses Binding to HSP70 and Sensitizes to Protein Misfolding Stress (A) SILAC proteomics was performed on FLAG IP from cells stably expressing inducible FLAG-UBQLN2 WT or P506T. Interaction with proteasomal subunits (PSMA6 shown) is unaffected by the mutation, UBQLN2 P506T binding to HSP70 family members (HSPA1A, HSPA8) is significantly lower (p < 0.0001), and binding to ubiquitin is significantly higher (p = 0.011). Asterisks indicate a statistically significant difference from a SILAC ratio of 1 (two-tailed single-value t test). (B–D) Decreased binding to HSP70 and increased binding to ubiquitin was confirmed by UBQLN2 IP from wild-type and mP520T (equivalent to human P506T) primary male mouse embryonic fibroblasts (MEFs), derived from littermate embryos. HSP70 (B) and ubiquitin (C) were detected by western blot. (C) Quantification of mutant/wild-type signal ratio for co-immunoprecipitated HSP70 and ubiquitin. Asterisk indicates a statistically significant difference from a mean ratio of 1 (two-tailed single-value t test). (E) Stress-induced binding to HSP70, ubiquitin and proteasomes is defective for mutant UBQLN2. Asterisk indicates Rpt6 (proteasome). (F) Mutant UBQLN2 is defective in association to heat shock induced aggregates. Asterisk indicates a non-specific band. (G) mP520T MEFs are hypersensitive to heat shock as compared to WT counterparts. (H) mP520T MEFs are hypersensitive to 20-hr puromycin treatment at the indicated concentrations. Error bars represent SD. Statistical test was a two-tailed t test. See also Figures S5, S6, and S7.

Figure 5

HSP70 Client Interaction Drives UBQLN2-HSP70 Binding (A) UBQLN2 association to heat-shock-induced pelleted proteins is independent of ubiquitin. Cells were treated with the ubiquitin E1 inhibitor MLN7243, heat shocked, and fractionated into supernatant and pellet. (B) Presence of HSP70-client induces UBQLN2-HSP70 interaction in vitro. Reaction components were mixed and incubated at the indicated temperature, followed by pull-down of GST-HSP70. (C) Purified human 26S proteasome. Lane 1, Coomassie staining of 2 μg purified human proteasome; lanes 2–4, in-gel LLVY-AMC (N-succinyl-leucine-leucine-valine-tyrosine-7-amino-4-methylcoumarin) chymotrypsin activity of 2 μg human proteasome, Coomassie staining, and immunoblot with anti-Rpt5 antibody in 4% native-PAGE, respectively. (D) Heat-denatured (95°C) or native recombinant luciferase was added to the other reaction components, followed by GST-HSP70 pull-down. (E) Pathological Huntingtin aggregates induce binding of GST-HSP70 to purified wild-type, but not mutant (P506T), UBQLN2 in vitro. Brain extract from wild-type or R6/2 mice was spiked into the reaction mix, followed by GST-HSP70 pull-down and analysis of UBQLN2 binding. (F) UBQLN2 binds to the C-terminal domain of HSP70. IP of HSPA8-SV5 mutants expressed in HEK293 cells and detection of endogenous UBQLN2. Cells were heat shocked as indicated. Schematic shows the HSP70 domains. (G) Mutant UBQLN2 shows reduced binding to HSP70 in knockin mouse brain. (H and I) The UBQLN2 mP520T knockin mutation leads to cognitive impairment in aged mice. Male mice (n = 11 of each genotype) were aged and tested in novel-object and novel-place recognition tests. Error bars represent SD. Statistical tests were two-tailed t tests. (J) Aged UBQLN2 mP520T knockin animals have UBQLN2- and p62-positive inclusion body pathology. Brains from aged (15- to 18-month-old) mice were subjected to immunohistochemistry (IHC) for UBQLN2 and p62 (n = 6 per genotype). Red shading in schematic shows areas of inclusion pathology. (K) Mutant UBQLN2 is specifically present in the pellet from hippocampal lysates in aged (15- to 18-month-old) knockin mice. Isolated neocortex (CTX), hippocampus (HC), and cerebellum (CB) were separated into NP40-soluble and insoluble fractions. Asterisk indicates an unspecific band. See also Figures S5, S6, and S7.

Figure 6

UBQLN2 Mutation Impairs Aggregate Clearance In Vivo (A and B) UBQLN2 interacts with aggregated, but not SDS-soluble, HTT in vivo, as judged by reciprocal IP of HTT and UBQLN2 from the R6/2 transgenic (A) and HdhQ150 knockin (B) Huntington’s disease models. (C) UBQLN2, but not UBQLN1, translocates to the nucleus in the R6/2 and HdhQ150 models. (D) UBQLN2 is present in ubiquitylated Huntingtin aggregates from brains of the R6/2 and HdhQ150 mouse models. Aggregated HTT and UBQLN2 were captured with a ubiquitin binding resin (GST-TUBE). (E) The R6/2 and UBQLN2 mP520T mice were crossed to produce double-mutant animals, and 9-week-old male brains from these were assayed for aggregated HTT by western blot. Quantification of soluble HTT is shown (bottom) (n = 4 per genotype). (F) Immunofluorescence (IF) of nuclear HTT aggregates in R6/2 and R6/2;mP520T brains shows more inclusion bodies in the double mutant. Quantification is shown (right). Error bars represent SEM. Statistical test was a two-tailed t test. (G) The Seprion ligand assay independently confirms a significant increase in aggregated HTT in double mutants, compared to R6/2 littermates (n = 8 per genotype). Error bars represent SEM. See also Figure S7.

Figure 7

Model of How UBQLN2 Manages Proteotoxic Stress Under non-stressed conditions, UBQLN2 is held inactive in homo- or hetero-dimers (1). In the presence of HSP70 clients, UBQLN2 binds to HSP70 and associated misfolded/aggregated proteins, which are ubiquitylated (2). HSP70/HSP110-dependent disaggregase activity pulls aggregated proteins apart, allowing for UBQLN2 to act as a proteasome shuttle connecting ubiquitylated misfolded proteins to the proteasome, after forming a HSP70-client-UBQLN2-proteasome degradation complex (3) ending in client proteolysis (4). Disease mutant UBQLN2 (star) is defective in its association to HSP70 and no longer effectively forms a degradation complex, leading to accumulation of misfolded/aggregated proteins (5).

Figure S1

Heat Shock Generates Insoluble Ubiquitin-Positive Aggregates and Does Not Inactive Proteasomes, Related to Figure 1 (A) UBQLN2 is not pelleted when cells are heat shocked post lysis. Cell lysates were incubated at 37 or 42°C and then fractionated into soluble (S) and pellet (P) fraction. This indicates that UBQLN2 itself does not aggregate as a result of high temperature. (B) UBQLN2 levels are not upregulated in response to heat shock. HSP70 and GAPDH were used as a positive and negative controls, respectively. (C) Heat shock aggregates are insoluble in up to and including 1% SDS but are solubilized in 2% SDS. Blotting of soluble and pellet fractions with anti-ubiquitin and UQBLN2 antibodies confirmed dissolution of the aggregates in 2% SDS. (D) Proteasomes are active after heat shock. To confirm that proteasome activity was not affected by heat shock, we incubated U2OS and MEFs at the indicted temperatures for 2h. Cells were then harvested and cell lysates were incubated with the proteasome inhibitor MG132 or DMSO, followed by incubation with a fluorescent proteasome-activity probe, as indicated. The presence of fluorescently labeled beta-subunits at the same intensity under both heat stress and normal temperature, indicate that proteasome activity is not significantly affected by heat shock. (E) U2OS cells were treated with control or UBQLN2 siRNA and subjected to heat shock for the indicated times. Analysis of the pellet fraction revealed that insoluble ubiquitylated aggregates are generated within 5 min of heat shock, but that depletion of UBQLN2 does not noticeably alter the accumulation of these aggregates at any of the indicated time points.

Figure S2

Puromycin Does Not Upregulate UBQLN2 Levels and UBQLN2 Clears Nuclear Aggregated GFP-u, Related to Figure 2 (A) Schematic representation on how the three fractions, total insoluble, nuclear soluble and total insoluble were generated. (B) Cells treated with puromycin were fractionated as indicated and treatment did not induce the nuclear localization of UBQLN2. (C) Puromycin treatment did not induce the upregulation of UBQLN2 protein. (D) Schematic showing the GFPu-NLS construct (Bennett et al., 2005). (E) HEK293 cells stably expressing GFPu-NLS were subject to heat shock for 2h at 42°C and fractionated into soluble and insoluble fractions. GFPu-NLS recruited to the insoluble fraction after heat shock indicating its heat-induced aggregation. (F) GFPu-NLS cells were subject to heat shock for 2h at 42°C and proteasome inhibition with 25 μM MG132 as indicated. UBQLN2 was immunoprecipitated and GFPu-NLS was found to co-immunoprecipitate only upon heat shock, consistent with UBQLN2 nuclear localization. Combined heat shock and proteasome inhibition increased the binding further. (G) GFPu-NLS cells were depleted of UBQLN2 or treated with a control non-targeting siRNA then treated with 50 μg/ml cycloheximide (CHX) for the indicated time to measure turnover. Turnover was quantified using data from three independent experiments. Error bars represent SE.

Figure S3

Proteasomes and HSP70 Co-localize with HTTQ103 Aggregates and Overexpressed UBQLN2 Form Cytosolic Foci, Related to Figures 2 and 3 (A and B) HEK293 cells expressing inducible HttQ103-GFP were stained with antibodies to (A) HSP70 and (B) proteasome subunit RPT3. Inclusion bodies were positive for booth HSP70 and the proteasome, the latter forming a ring around the perimeter of the inclusion. (C) Endogenous UBQLN2 co-aggregates with pathological Huntingtin (HTT-Q103) but not with non-pathological HTT-Q25. GFP-HTT Q25 or Q103 expression was induced in HEK293 cells, followed by cell harvesting and fractionation into soluble (S) and pellet (P) fractions. HTT-Q103 runs as high molecular weight aggregates present in the stacking gels for the pellet fraction, and endogenous UBQLN2 is observed to also be upshifted to the stacking gel. (D) The cytosolic foci visible on UBQLN2 overexpression do not co-localize with markers for p-bodies or stress-granules. (E) FLAG-UBQLN2 was transiently transfected into U2OS cells, with either GFP-DCP1A (p-body marker) or GFP-G3BP1 (stress granule marker). UBQLN2 was detected by indirect immunofluorescence to the FLAG-tag, using mouse monoclonal anti-FLAG antibody (SIGMA ALDRICH F3165), and an anti-mouse secondary Alexa Fluor 647 (Jackons 715-605-151). (F) Cytosolic UBQLN2 foci do not co-localize with the autophagosome marker LC3. U2OS cells stably expressing inducible EGFP-UBQLN2 were induced with 2 ng/ml doxycycline for 24 hr, then treated with 50 nM Bafilomycin A1 for 1 hr prior to fixation and staining. LC3 staining was performed using a mouse monoclonal anti-LC3 (MBL M152-3). Secondary antibody was anti-mouse Alexa Fluor 647 (Jackson 715-605-151). Vehicle control was DMSO.

Figure S4

UBQLN2 Does Not Form Aggregates, and the Antibody Used for UBQLN2 Immunofluorescence Is Specific for UBQLN2, Related to Figures 2 and 3 (A) Coomassie stain of bacterially expressed and purified, untagged UBQLN2 wild-type and mutant proteins. (B) Analytical ultracentrifugation was performed to investigate differences in oligomerization or aggregation for purified UBQLN2. Additional mutants shown here to support results in main Figure 3. No significant amount of aggregated protein was detected for any mutant, and no differences in dimerization or trimerisation were observed. (C) Analytical gel filtration of UBQLN2 WT, P506T and P497H show a single sharp peak migrating at an apparent molecular weight above 158 kDa, without any indication of additional UBQLN2 species or aggregated material. (D) UBQLN2 P506T and P497H mutants are more compact particles than WT – flexibility analysis based on small-angle X-ray scattering experiments. The radius of gyration based dimensionless Kratky plot (top panel) has a characteristic shape for partially disordered protein containing both ordered and disordered fragment(s) – the peak of the curve (dotted gray line) is shifted from a position characteristic for globular folded protein (solid gray line). At the same time the plot demonstrates that WT contains more disorder (the right wing on the WT curve is slightly lifted comparing with P506T and 497H). The protein concentrations were 4.67, 4.03, 4.91 mg/ml for WT, P506T and 497H respectively. The volume-of-correlation based dimensionless Kratky plot (bottom panel) gives a more in-depth analysis and reveals the increase in volume-to-surface ratio for the P506T and 497H mutants, indicating more compact particles compared to WT UBQLN2 (the maximal possible volume-to-surface ratio of 0.82 is for a sphere; see arrow). (E) Mutations in UBQLN2 do not cause the protein to become insoluble in cells. FLAG-tagged wild-type and mutant UBQLN2 were overexpressed, and cells were fractionated into 1% NP-40 soluble (S) and insoluble pellet (P) fractions, and detected with FLAG-HRP conjugated antibody (SIGMA ALDRICH A8592). No difference in distribution as compared to the wild-type was seen for any of the mutants. FUS was used as a marker for the pellet. (F and G) Validation of UBQLN2 antibody for staining of endogenous UBQLN2 in U2OS cells. U2OS cells were transfected with control siRNA or siRNA targeting UBQLN2. 72h post-transfection, cells were trypsinised, and seeded on glass slides for microscopy. Cells were either seeded as separate groups (i.e., control and UBQLN2 siRNA) or mixed 1:1 and seeded together (third panel from the left). As a separate control, cells were transfected with plasmid encoding for FLAG-tagged UBQLN2 (right-most panel only). These cells show large UBQLN2 foci not present at endogenous levels. Cells were stained using the mouse monoclonal anti-UBQLN2 6H9 (Novus NBP2-25164), at 1:250 in 2% BSA PBS for 1h. Secondary antibody was goat Anti-Mouse DyLight 488 (Abcam ab96871). Knockdown of UBQLN2 can be clearly seen to decrease the signal, indicating that the antibody is specific to UBQLN2. (G) displays zoom of the indicated areas in. For the mixed cells (third panel from the left) a white arrowhead indicates a cell transfected with control siRNA and a black arrowhead a cell transfected with UBQLN2 siRNA.

Figure S5

Nuclear Translocation of UBQLN2 Is Unaffected by Disease Mutation, and HSP70 Clients Induce HSP70-UBQLN2 Interaction, Related to Figures 4 and 5 (A) Wild-type of P520T knock-in MEFs were heat shocked and fractionated as indicated and no difference was observed in the nuclear localization as a result of the disease mutation. (B) HEK293 cells were treated with the broad spectrum kinase inhibitor Staurosporine (1 μM) or the p38 (BIRB-0796 and VX-745; 1 μM) and JNK (JNKIN8; 10 μM) kinase inhibitors for 1h prior to heat shock and showed that kinase signaling is not regulating the inducible interaction of HSP70 and UBQLN2. (C) HEK293 cells were treated with the ubiquitin E1 inhibitor MLN7243 (10 μM) for 1h prior to heat shock and demonstrated that ubiquitylation or ubiquitin signaling is not involved in regulating the inducible interaction between HSP70 and UBQLN2. (D) UBQLN2 does not bind non-specifically to GST in the presence or absence of denatured luciferase. GST or GST-HSP70 and purified UBQLN2 was incubated at 42°C in the presence or absence of Luciferase, as indicated. This was followed by GST pulldown, and Western blot for associated UBQLN2. (E) Luciferase was denatured at 95°C for 5 min and found to stimulate the binding of untagged recombinant UBQLN2 to GST-HSP70 upon GST-pulldown, unlike native luciferase. (F) R6/2 brain extracts but not WT brain extracts were found to be able to stimulate the interaction of recombinant untagged UBQLN2 with GST-HSP70 in GST pulldown experiments. (G) HEK293 cells stably expressing inducible UBQLN2 WT or PXXP deletion mutants were found to both equally interact with endogenous HSP70 after heat shock, indicating that the PXXP motif does not directly mediate the interaction.

Figure S6

Generation of a Constitutive Knock-in Mouse Model and Locomotor Tests of a Male Cohort, Related to Figures 4, 5, and 6 (A) Targeting strategy used to generate the UBQLN2 P520T knock-in mice. (B) Western blot of brain extracts showing that UBQLN2 levels are expressed at the same level in WT and UBQLN2 knock-in male mice (expressing one copy each of UBQLN2 due to being X-linked). (C) Gait analysis in the mP520T mouse model. Gait analysis was performed at 6, 9 and 12 months of age, showing a marginal, but significant decrease in stride length at 6 months of age for the mutant animals. At 9 and 12 months the trend persists. Habituation to handling/runway corridor was followed by assessment of gait by painting of front and hind paws. Gait parameters including stride length and width between paws was analyzed manually from the paw print records. (D) Accelerating rotarod tests showed no impairment in motor function for UBQLN2 mP520T animals at any age. The animals performed 8 trials (4 trials on day 1 and a further 4 trials on the following day). On each trial the mouse was placed on the RotaRod and the rod accelerates from a speed of 5 rpm up to 45 rpm, with a maximum trial time of 5 min. (E) Fixed speed rotarod tests showed no impairment in motor function for UBQLN2 mP520T animals at any age.

Figure S7

UBQLN2 Is Aggregated in Hippocampus and Associates to HSP70 and HTT Aggregates; Characterization of UBQLN Antibodies, Related to Figures 1, 2, 4, 5, and 6 (A and B) Hippocampal or cortical extracts were examined from WT or P520T knock-in mice. UBQLN2 expression levels were quantified and found to be indistinguishable between brain regions in either genotype. (C) UBQLN2 was found in the pellet fraction of the hippocampus in P520T knock-in, but not WT mice, in three additional independent pairs of animals. (D) UBQLN2 co-localizes with HTT inclusions in R6/2 brains. Sections of 14 week R6/2 brains were stained for HTT (MW8 antibody) and UBQLN2. (E) UBQLN2 was immunoprecipitated from 14-week-old R6/2 brains and blotted for the indicated proteins. HTT and HSP70 were detected in the stacking gel, indicated UBQLN2 interacts with SDS-insoluble HTT aggregates that are positive for HSP70. (F–I) Validation of specificity for UBQLN antibodies produced in-house. All antibodies were raised in sheep. UBQLN1, UBQLN2 or UBQLN4 were knocked down using siRNA and the indicated antibody used for detection. No cross-reactivity between ubiquilins was seen. (J) Purified untagged mouse UBQLN1, 2, 3 and 4 was further used to assess specificity of the raised antibodies, which confirm that there is no cross reactions.