Purified TPC isoforms form NAADP receptors with distinct roles for Ca(2+) signaling and endolysosomal trafficking

Abstract

Intracellular Ca(2+) signals constitute key elements in signal transduction. Of the three major Ca(2+) mobilizing messengers described, the most potent, nicotinic acid adenine dinucleotide phosphate (NAADP) is the least well understood in terms of its molecular targets [1]. Recently, we showed that heterologous expression of two-pore channel (TPC) proteins enhances NAADP-induced Ca(2+) release, whereas the NAADP response was abolished in pancreatic beta cells from Tpcn2 gene knockout mice [2]. However, whether TPCs constitute native NAADP receptors is unclear. Here we show that immunopurified endogenous TPC complexes possess the hallmark properties ascribed to NAADP receptors, including nanomolar ligand affinity [3-5]. Our study also reveals important functional differences between the three TPC isoforms. Thus, TPC1 and TPC2 both mediate NAADP-induced Ca(2+) release, but the subsequent amplification of this trigger Ca(2+) by IP(3)Rs is more tightly coupled for TPC2. In contrast, TPC3 expression suppressed NAADP-induced Ca(2+) release. Finally, increased TPC expression has dramatic and contrasting effects on endolysosomal structures and dynamics, implicating a role for NAADP in the regulation of vesicular trafficking. We propose that NAADP regulates endolysosomal Ca(2+) storage and release via TPCs and coordinates endoplasmic reticulum Ca(2+) release in a role that impacts on Ca(2+) signaling in health and disease [6].

Figure 1

Endogenous SpTPC Protein Complexes Bind to [³²P]NAADP with Hallmark Properties of the NAADP Receptor (A) Schematic representation of protocol used for membrane preparations from Strongylocentrotus purpuratus egg homogenates via differential centrifugation. The following abbreviations are used: H, homogenate; S, supernatant; P, pellet. (B) Levels of specific [³²P]NAADP binding in membrane preparations (n = 3). Panels below graph correspond to immunoblots probed with affinity-purified SpTPC isoform-specific antibodies showing high molecular weight forms of SpTPCs. (C) Specific [³²P]NAADP binding for SpTPC1 and SpTPC3 immunoprecipitates (IPs) from S10P100 fractions with anti-SpTPC1 and anti-SpTPC3 sera. Values (n = 6) determined by Cerenkov counting were normalized against control IP with nonimmune serum. (D) Specific [³²P]NAADP binding for SpTPC2 IP from P100 fractions with anti-SpTPC2 serum. Values (n = 11) obtained by phosphorimaging were normalized against control IP with preimmune serum. (E) Inhibition of [³²P]NAADP binding to S10P100 membranes or SpTPC1 or SpTPC3 IPs by increasing concentrations of NAADP (n = 3). Values were normalized to amount of bound [³²P]NAADP in absence of competitor. (F) Same as in (E), but with NADP as competitor (n = 3). (G) Bound [³²P]NAADP to S10P100 membranes or SpTPC1 or SpTPC3 IPs after washes with buffer with K⁺ (GluIM) or without K⁺ (HEPES), in the absence or presence of 10 μM NAADP. Values (n = 3) of remaining radioactivity were normalized to values obtained for GluIM washes in the absence of NAADP. Data are represented as mean ± standard error of the mean (SEM); p > 0.05 (not significant, NS), ^∗p < 0.05, ^∗∗p < 0.01, ^∗∗∗p < 0.001. See also Figure S1.

Figure 2

NAADP-Mediated Ca²⁺ Release in Mammalian Cells Expressing SpTPCs (A) Ca²⁺ traces of mCherry.SpTPC-expressing cells stimulated by 1 μM NAADP-AM. ATP (100 μM) was added at the end of each experiment to assess cell viability. The number of cells not responding to ATP was negligible. Traces of cells responding to NAADP-AM (F/F₀ > 1.5) are shown in color. (B) Summary of results from experiments performed over 4 days with 12–22 coverslips per cell line, as outlined in (A). Only cells responding to ATP were included in the data analysis. (C) Effect of mCherry.SpTPC3 transient expression on cells stably expressing HA.SpTPC2. Transfection of mCherry alone is included as control. Summary of results is from experiments performed over 2 days with 4–6 coverslips per transfection. There were no significant differences between untransfected cells and cells transfected with mCherry alone (data not shown). (D) Effect of pretreatment with NAADP-AM (1 nM, 30 min), bafilomycin A1 (3 μM, 60 min), or trans Ned-19 (10 μM, 15 min) upon 1 μM NAADP-AM-induced Ca²⁺ release in cells expressing mCherry.SpTPC1 or mCherry.SpTPC2. Spontaneous activity was determined by addition of dimethyl sulfoxide (DMSO). Results from 2–3 days of experiments with 6–17 coverslips for each treatment and cell line are shown. (E) Representative Ca²⁺ traces of cells dialyzed with NAADP (100 nM) via patch pipettes in whole-cell configuration, in the absence or presence of bafilomycin A1 (1 μM) or heparin (200 μg/ml). Arrows indicate break-in. In total, 5–7 cells per condition and cell line were analyzed, and all of the cells apart from SpTPC3 were responsive to NAADP dialysis, with SpTPC1 and SpTPC2 giving a biphasic response. (F) Summary of results from (E), quantifying total Ca²⁺ release as area under curve. (G) Summary of results from (E), quantifying the time required to trigger the secondary Ca²⁺ response after break-in. Data are represented as mean ± SEM; p > 0.05 (NS), ^∗p < 0.05, ^∗∗p < 0.01, ^∗∗∗p < 0.001. See also Figure S2.

Figure 3

Intracellular Localization of SpTPCs (A) Colocalization of mCherry.SpTPC with acidic organelles (LysoTracker Green) in live HEK293 cells expressing mCherry.SpTPCs. Scale bar corresponds to 10 μm. (B) Anti-SpTPC3 immunofluorescence of S. purpuratus eggs with or without peptide block for assessment of immunostaining specificity. Scale bar corresponds to 10 μm, or 2 μm for higher magnification panel. (C) Localization of SpTPCs.mCherry expressed in oocytes of starfish Asterina miniata and detected by mCherry fluorescence or by immunofluorescence with corresponding anti-SpTPC antibodies. Scale bar corresponds to 20 μm. Noninjected controls were not labeled with anti-SpTPC antibodies (data not shown). In oocytes expressing SpTPC3.mCherry, the germinal vesicle is out of the plane of focus. mCherry.SpTPCs showed similar cortical localization (data not shown). Oocytes expressing mCherry alone showed a signal across the entire cell (data not shown). Of note is the presence of an SpTPC1 signal in the nucleus. Indeed, SpTPC1 has a putative nuclear localization signal (amino acids 327–334). Its physiological significance may represent an important avenue for further analysis of TPC function, especially in light of reports describing NAADP signaling in nucleus [33, 34]. See also Figure S3.

Figure 4

Two-Pore Channel Overexpression Causes Changes in Endolysosomal Trafficking and Morphology (A) Lipid endocytosis and recycling in HA.SpTPC-overexpressing HEK293 cells assessed by Alexa Fluor 568-cholera toxin B subunit (CtxB; green). Nuclei are labeled with Hoechst 33342 (Hoechst, blue). Scale bar corresponds to 5 μm. Endolysosomal localization was confirmed by colocalization with endocytosed high molecular weight rhodamine dextran (data not shown); Golgi localization by a single perinuclear distribution is not overlapping with the dextran. (B) Summary of results from experiments in (A) corresponding to three separate experiments with a minimum of 50 cells analyzed per experiment. (C) Pattern of lysosomal staining by LysoTracker Green (LysoTracker, green) in HA.SpTPC-overexpressing HEK293 cells, in the absence or presence of NAADP receptor antagonist Ned-19 (10 μM, 12 hr). Nuclei were labeled with Hoechst 33342 (Hoechst, blue). Scale bars correspond to 5 μm. (D) Summary of results from experiments in (C) corresponding to three separate experiments, with a minimum of 50 cells analyzed per experiment. To allow meaningful comparison between images, we standardized LysoTracker loading conditions and imaging protocols for all cell types. pH differences between cell types were negligible, as assessed by fluorescein-dextran fluorescence (data not shown). (E) Lysosomal storage disease phenotype in HA.HsTPC2-overexpressing HEK293 cells visualized by electron microscopy. Inset is a magnification of one region of a HA.HsTPC2-overexpressing cell. Scale bars correspond to 200 nm. The following abbreviations are used: Nuc, nucleus; MLB, multiple lamellar inclusion body; L, lysosome. Data are represented as mean ± SEM. See also Figure S4.