Poly(ADP-Ribose) Prevents Pathological Phase Separation of TDP-43 by Promoting Liquid Demixing and Stress Granule Localization

Abstract

In amyotrophic lateral sclerosis (ALS) and frontotemporal degeneration (FTD), cytoplasmic aggregates of hyperphosphorylated TDP-43 accumulate and colocalize with some stress granule components, but how pathological TDP-43 aggregation is nucleated remains unknown. In Drosophila, we establish that downregulation of tankyrase, a poly(ADP-ribose) (PAR) polymerase, reduces TDP-43 accumulation in the cytoplasm and potently mitigates neurodegeneration. We establish that TDP-43 non-covalently binds to PAR via PAR-binding motifs embedded within its nuclear localization sequence. PAR binding promotes liquid-liquid phase separation of TDP-43 in vitro and is required for TDP-43 accumulation in stress granules in mammalian cells and neurons. Stress granule localization initially protects TDP-43 from disease-associated phosphorylation, but upon long-term stress, stress granules resolve, leaving behind aggregates of phosphorylated TDP-43. Finally, small-molecule inhibition of Tankyrase-1/2 in mammalian cells inhibits formation of cytoplasmic TDP-43 foci without affecting stress granule assembly. Thus, Tankyrase inhibition antagonizes TDP-43-associated pathology and neurodegeneration and could have therapeutic utility for ALS and FTD.

Keywords: ALS; PARP; PARylation; TDP-43; Tankyrase; amyotrophic lateral sclerosis; motor neuron disease; phosphorylation; poly(ADP-ribose); stress granule.

Figure 1:

PARylation modulates TDP-43 toxicity in the fly. (A) Compared to control (ctrl), human TDP-43 (TDP-43+ ctrl) disrupted the external eye (upper panel) and internal retina (lower panel, arrowheads:retinal width and asterisk: vacuolization). Reduction of Tnks (Tnks.IR) mitigates the degeneration of TDP-43 (TDP-43 + Tnks.IR) and has no effect on its own (Tnks.IR). (B) Reduction of Tnks improved the external eye of TDP-43 flies. Mean (±s.e.m.), n=3, and a two-way ANOVA (P < 0.0001). (C) Reduction of Tnks reduced vacuolization of the TDP-43 retina. Mean (±s.e.m.), n=3, a one-way ANOVA (P < 0.0001) and a Tukey’s test. Asterisk: significant, NS: not significant. (D) Reduction of Tnks increased the retinal width of TDP-43 flies. Mean (±s.e.m.), n=3, a one-way ANOVA (P < 0.0001) and a Tukey’s test. Asterisk: significant, NS: not significant. (E) Reduction of Tnks (Tnks.IR) mitigated the lifespan defect of flies expressing TDP-43 in the brain. More than 190 male flies were followed per genotype. Log-rank test for trend, P < 0.0001. (F) Reduction of Tnks (Tnks.IR) had no effect on total TDP-43 levels, but increased nuclear and decreased cytoplasmic TDP-43. (G) TDP-43 protein levels relative to control protein (F). Mean (±s.e.m), one-way ANOVA (P < 0.001) and a Tukey’s test. Asterisks: significant, NS: not significant.Genotypes: (A-D) ctrl (control) is UAS-mCD8-GFP/+; gmr-GAL4 (III)/+: Tnks.IR is: UAS-Tnks.IR/+; gmr (III)-GAL4 (III) /+: TDP-43 + ctrl is UAS-TDP-43(M)/UAS-mCD8-GFP; gmr-GAL4 (III)/+ and TDP-43+Tnks-IR is UAS-TDP-43 (M)/UAS-Tnks-IR^4179R−4; gmr-GAL4 (III)/+. (E-G) elav > ctrl (control): UAS-mCD8-GFP/+; elav3A-GAL4/+: elav > TDP-43 + ctrl is UASmCD8-GFP/+; elav3A-GAL4, UAS-TDP-43 (S)/ + and elav > TDP-43+Tnks.IR is UAS-TnksIR^4179R−4/+; elav3A-GAL4, UAS-TDP-43 (S)/+. See Figure S1.

Figure 2:

TDP-43 binds to PAR via a PAR-binding region in the N-terminus. (A) Human TDP-43 expressed in the fly brain co-immunoprecipitated with PAR (arrow). PAR antibody: clone 10H, BSA-free, Tulip Biolabs. Head lysate purified from the adult fly head at day 4. elav > TDP-43 is +/+; elav3A-GAL4, UAS-TDP-43 (S)/ +. (B) PAR from Cos-7 cells co-immunoprecipitated with endogenous TDP-43 (arrow). Antibodies: Ab1: anti-PAR, clone 10H, BSA-free, Tulip Biolabs, Ab2: anti-PAR, ENZO. (C) Endogenous TDP-43 from Cos-7 cells co-immunoprecipitated with PAR (arrows). PAR antibody: LP96, BD Pharmingen. (D) GST-TDP-43-WT binds to PAR. Replica membranes stained for PonceauS and immunoblotted for TDP-43. (E)TDP-43 domains. NLS: nuclear localization sequence, RRM: RNA recognition motif, NES: nuclear export sequence, PrLD: prion-like domain. The PAR-binding motifs (PBMs) in the NLS: PBM1 and PBM2. The basic amino acids in PBM1 and PBM2 (red) were mutated to alanine for this study. (F) Peptides spanned either PBM1 (NLS_71–90) or PBM2 (NLS_91–110). MARCKS/MARCKSRelated Protein (MMRP) amino acids 152–176 (MMRP_172–156) was the positive control and MMRP_{152–176-mut} (Pleschke et al., 2000). (G) PAR-binding was detected on MMRP_152–176 and on NLS_91–110. Replica membranes stained with PonceauS. (H) Mutation of PBM1, PBM2 or both (PBM) in GST-TDP-43 diminished PAR binding. Replica membranes stained with SYPRO Ruby. (I) PAR dot blots quantified for PAR immunoreactivity, relative to TDP-43. Mean (±s.e.m), n=6, one-way ANOVA (P < 0.0001) and a Tukey’s test is presented. Asterisks: significant, NS: not significant. See Figure S2.

Figure 3:

PAR promotes LLPS of TDP-43 in vitro. (A) Spontaneous LLPS of 10μM SUMO-TDP-43-WT in 150mM NaCl. Repeated more than five times on two preparations of protein. (B) Fusion of two TDP-43-WT droplets. (white arrows). (C) The presence (green) or absence (red) of TDP-43-WT droplets. The grey area indicates phase boundary. Confirmed in two independent protein preparations. Conditions either side of phase boundary were repeated three times. (D) PAR reduced the phase boundary of TDP-43 LLPS. The presence (green) or absence (red) of protein droplets is plotted, grey area indicates phase boundary. Confirmed in two independent protein preparations. Conditions at phase boundary (grey side) were repeated three times. (E) Addition of PAR (1–5 μM mono ADP-ribose equivalents) promoted TDP-43-WT LLPS in a dose-dependent manner. This was performed on one protein preparation. (F) The presence (green) or absence (red) of TDP-43 droplets. (G) PAR promoted 5 μM TDP-43-WT LLPS in 50mM NaCL. Heparin, yeast total RNA, and mono (ADP-ribose) (MAR), at the same concentration had no effect. Repeated twice from 1 protein preparation. All at room temperature. See Figure S2.

Figure 4:

The PAR-binding region and the N-terminus are required for TDP-43 LLPS in vitro. (A) The NLS of human TDP-43 and the Drosophila homologue TAR DNA-binding protein-43 homolog (TBPH), share 42.9% identity. The protein domains of TDP-43-WT, -Q331K, ΔPBM, -C35 (amino acids 85–414) and -C25 (amino acids 176–414) are shown. NLS: nuclear localization sequence, PBM: PAR-binding motif, RRM: RNA recognition motif, NES: nuclear export sequence and PrLD: prion-like domain. (B) LLPS of 10 μM protein in 150mM NaCl. SUMO-TDP-43-WT underwent LLPS but SUMOTDP-43-ΔPBM and SUMO-TDP-43-C35 formed irregular-solid structures that did not fuse. SUMO-TDP-43-C25 formed fibrillar aggregates. TDP-43-Q331K formed liquid droplets and the occasional irregular-solid structure. Performed three independent times with two protein preparations of TDP-43-WT, C35 and C25 and twice from one protein preparation of TDP-43-Q331K. (C) The presence of liquid droplets, no liquid droplet, irregular solid structures, both liquid droplets and irregular solid structures and fibrillar aggregates is plotted. (D) LLPS at 5 μM protein and 50mM NaCl. PAR at 5 μM equivalents to ADP-ribose promoted LLPS of TDP-43-WT and did not promote LLPS of TDP-43-ΔPBM, TDP-43-C35, and TDP-43-C25. PAR promoted the formation of irregular-solid structures of TDP-43Q331K. Performed three independent times with two independent protein preparations. (E) The presence of liquid droplets, no liquid droplet, irregular-solid structures and fibrillar aggregates is plotted for each TDP-43 variant in the absence and presence of PAR.All at room temperature. See Figure S2

Figure 5:

The PAR-binding region is required for the recruitment of TDP-43 to stress granules. (A) Domain architecture of TDP-43-WT, -ΔPBM, -ΔPBM_PBM-A2/B1, -C35 and -C25. The peptide sequence added to the C-terminus of TDP-43-ΔPBM_PBM-A2/B1 is indicated. Red amino acids show the PBM of hnRNPA2/B1, with flanking amino acids of hnRNAPA2/B1 in black. NLS: nuclear localization sequence, PBM: PAR-binding motif, RRM: RNA recognition motif, NES: nuclear export sequence and PrLD: prion-like domain. (B) Normally, TDP-43-WT was nuclear and TDP-43-ΔPBM and TDP-43-ΔPBM_PBM-A2/B1 were cytoplasmic. Upon arsenite-treatment TDP-43-WT localized to stress granules, TDP-43ΔPBM was excluded from stress granules and TDP-43-ΔPBM_PBM-A2/B1 localized to stress granules. Cells exposed to 0.5mM sodium arsenite 1 hr, labelled for G3BP1 and stained with Hoescht. (C) The percentage of cells with cytoplasmic TDP-43-GFP foci. Mean (± s.e.m.), n=3, twoway ANOVA (P < 0.0001) and a Holm-Sidak’s test is presented Asterisks: significant. (D) The percentage of cells with one or more G3BP1-labelled stress granule (SG) colabelled with TDP-43-GFP. Mean (±s.e.m.), n=3, one-way ANOVA (P < 0.0001) and a Tukey’s test is presented. Asterisks: significant. (E) The percentage of G3BP1-labelled stress granules (SGs) co-labelled with TDP-43-GFP. Mean (±s.e.m.), n=3, one-way ANOVA (P < 0.0001) and a Tukey’s test is presented. Asterisks: significant. (F) The percentage of TDP-43-GFP foci co-labelled with G3BP1. Mean (±s.e.m.), n=3, oneway ANOVA (P < 0.0001) and a Tukey’s test is presented. Asterisks: significant. (G-H) Foci of TDP-43-C35 and TDP-43-C25-GFP are largely excluded from stress granules. Cells exposed to 0.5mM sodium arsenite 1 hr, labelled for TIAR and stained with Hoescht (DNA). (I) The percentage of cells with cytoplasmic TFP-43-GFP foci. Mean (±s.e.m.), n=3. two-way ANOVA (P = 0.0042) and a Holm-Sidak’s test is presented. Asterisks: significant. (J) The percentage of TIAR-labelled stress granules (SGs) co-labelled with TDP-43-GFP. Mean (±s.e.m.), n=3, two-way ANOVA (P < 0.0001) and a Tukey’s test is presented. Asterisks: significant, NS: not significant. (K) The percentage of TDP-43-GFP foci co-labelled with TIAR. Mean (±s.e.m.), n=3, one-way ANOVA (P < 0.0001) and a Tukey’s test is presented. Asterisks: significant. See Figure S3 and S4.

Figure 6:

Initial recruitment to stress granules protects TDP-43 from phosphorylation. (A) Stress induced the formation of phosphorylated (pS409/10) foci of TDP-43-ΔPBM, TDP-43-C35 and TDP-43-C25 but not TDP-43-WT. Cells were stressed with 0.5 mM arsenite 1 hr, labelled for pS409/10 and Hoescht (DNA). (B) The percentage of cells with cytoplasmic TDP-43-GFP foci. Mean (± s.e.m.), n=3, twoway ANOVA (P < 0.0001) and Tukey’s test is presented Asterisks: significant and NS: not significant. (C) The percentage of cells with cytoplasmic TDP-43 foci co-labelled with pS409/10. Mean (±s.e.m.), n=3, one-way ANOVA (P <0.0001) and a Tukey’s test is presented. Asterisks: significant and NS: not significant. (D) The percentage of cells with cytoplasmic TDP43-GFP (WT, ΔPBM or ΔPBM_PBM-A2/B1) foci. Mean (± s.e.m.) n=3, one-way ANOVA and Dunnet’s test (P < 0.001) is presented. Asterisks: significant. (E) The percentage of cells with cytoplasmic TDP-43-GFP (WT, ΔPBM or ΔPBM_PBM-A2/B1) foci co-labelled with pS409/10. Mean (± s.e.m.), n=3, one-way ANOVA and Dunnet’s test is presented (normal P < 0.0001 and arsenite P = 0.0024). (F) Stress-induced the phosphorylation of cytoplasmic foci of TDP-43-ΔPBM-GFP foci and not TDP-43-WT-GFP or TDP-43-ΔPBM_PBM-A2/B1-GFP. Cells exposed to 0.5 mM arsenite (1 hr), were labelled for pS409/10 and Hoescht. See Figure S5 and S6.

Figure 7:

Prolonged stress leads to the phosphorylation of TDP-43 foci and TDP-43 foci formation can be mitigated with small molecule inhibitors of Tankyrase. (A) G3BP1-labelled stress granules resolved after 4 hr exposure to 0.5 mM arsenite. Mean (± s.e.m), n=3, one-way ANOVA (P = 0.005) and a Tukey’s test is presented. Asterisks: significant, NS: not significant. (B) Stress-induced foci of TDP-43-WT-YFP persisted after 4 hr exposure to 0.5 mM arsenite. Mean (± s.e.m.), n=3, one-way ANOVA (P < 0.0001) and a Tukey’s test is presented. Asterisks: significant and NS: not significant. (C) ytoplasmic TDP-43-WT-YFP foci formed in 0.5 mM arsenite (4 hr) were co-labelled for pS409/10 and not G3BP1. Cells were labelled for G3BP1, pS409/10 and Hoescht, and imaged by confocal microscopy. (D) Confocal images of cells with cytoplasmic TDP-43-WT-YFP foci were quantified. Mean (± s.e.m.), n=5 and one-way ANOVA (P < 0.0001) is presented. (E) Cells untreated or treated with 0.5 mM arsenite (30 mins) in the absence or presence of XAV-939 or G007-LK. A 30 min pretreatment was required and lack of a dose-response is likely due to being above the IC₅₀. (Figure S7H-I). Arrows: cells with cytoplasmic TDP-43WT-GFP foci. Cells were labelled for G3BP1 and Hoescht. (F) Cells were quantified for the presence of G3BP1-labelled stress granules (SGs). Mean (± s.e.m.), n=3, one-way ANOVA (P < 0.0001) and a Tukey’s is presented. NS: not significant. (H) Cells were quantified for the presence of cytoplasmic TDP-43-GFP foci. Mean (± s.e.m.), n=3, one-way ANOVA (P < 0.0001) and a Tukey’s test is presented. Asterisks: significant. See Figure S7.