A spatiotemporally coordinated cascade of protein kinase C activation controls isoform-selective translocation

Abstract

In pituitary GH3B6 cells, signaling involving the protein kinase C (PKC) multigene family can self-organize into a spatiotemporally coordinated cascade of isoform activation. Indeed, thyrotropin-releasing hormone (TRH) receptor activation sequentially activated green fluorescent protein (GFP)-tagged or endogenous PKCbeta1, PKCalpha, PKCepsilon, and PKCdelta, resulting in their accumulation at the entire plasma membrane (PKCbeta and -delta) or selectively at the cell-cell contacts (PKCalpha and -epsilon). The duration of activation ranged from 20 s for PKCalpha to 20 min for PKCepsilon. PKCalpha and -epsilon selective localization was lost in the presence of Gö6976, suggesting that accumulation at cell-cell contacts is dependent on the activity of a conventional PKC. Constitutively active, dominant-negative PKCs and small interfering RNAs showed that PKCalpha localization is controlled by PKCbeta1 activity and is calcium independent, while PKCepsilon localization is dependent on PKCalpha activity. PKCdelta was independent of the cascade linking PKCbeta1, -alpha, and -epsilon. Furthermore, PKCalpha, but not PKCepsilon, is involved in the TRH-induced beta-catenin relocation at cell-cell contacts, suggesting that PKCepsilon is not the unique functional effector of the cascade. Thus, TRH receptor activation results in PKCbeta1 activation, which in turn initiates a calcium-independent but PKCbeta1 activity-dependent sequential translocation of PKCalpha and -epsilon. These results challenge the current understanding of PKC signaling and raise the question of a functional dependence between isoforms.

FIG. 1.

Analysis of PKCα, -β1, -ɛ, and -δ targeting in the GH3B6 cell line. (A) Micrographs depicting what we define as a targeting to the entire plasma membrane or to cell-cell contacts. PKCα, -β1, -ɛ, and -δ were subcloned in frame with GFP at the C-terminal end of their sequence in the pEGFP-N1 vector (Clontech). PKCβ1 and -δ accumulated at the entire plasma membrane in the presence (+) of 100 nM TRH, whereas PKCα and -ɛ accumulated selectively at the cell-cell contact. In isolated cells, PKCβ1 and -δ behaved as in cells in contact, whereas PKCα and -ɛ remained in the cytoplasm. Observations were performed with a confocal microscope. In Fig. 1 to 10, the empty arrowheads show translocation at the entire plasma membrane, whereas the filled arrowheads show selective translocation to cell-cell contacts. Bar, 5 μm. (B) Analysis with Image J 1.32j software (National Institutes of Health, Bethesda, Md.) was used to quantify PKC translocation and demonstrated that the pixel values increased only at the cell-cell contacts for PKCα and -ɛ, which was not the case for PKCβ1 and -δ. G. V., gray values. (C) Summary of the results as the percentages of cells where TRH-induced translocation was observed either selectively at cell-cell contacts or at the entire plasma membrane. The percentage of cells where no translocation was observed is also indicated.

FIG. 2.

Existence of a calcium-independent targeting of PKCα. (A) PKCα and -β1 behaved differently when GH3B6 cells were incubated with 2 μM ionomycin. PKCβ1 is activated and accumulated at the entire plasma membrane similar to what is seen in the presence of 100 nM TRH. PKCα was not activated and remained in the cytoplasm. (B) PKCα and -β bearing the triple point mutations D187/246/248N do not translocate in the presence of ionomycin. mut, mutant. (C) D187/246/248N PKCα, unable to bind calcium, was still targeted to the cell-cell contacts upon stimulation, indicating that its translocation can be calcium independent. The same mutations in the PKCβ1 sequence show that PKCβ1 behaved like PKCα when unable to bind calcium: it accumulated at cell-cell contacts. Bar, 5 μm. (D) An example of intracellular calcium modification upon TRH stimulation. Image acquisition was performed on a confocal microscope, with 0.533-s intervals between frames. Calcium monitoring was described previously (48). F/Fmin, fluorescence/minimum fluorescence. (E) Summary of the results as described in the legend to Fig. 1C.

FIG. 3.

Analysis of the translocation kinetics of PKCα, -β1, -ɛ, and -δ. (A) Examples of real-time recordings of spatiotemporal activation of PKCβ1, -α, -ɛ, and -δ fused to GFP in GH3B6 cells stimulated with 100 nM TRH. Recordings were performed with a Noran confocal microscope. Images were acquired continuously, with intervals of 0.533 s between frames. Time zero is defined as the time of TRH application. Videos can be seen in the supplemental material. Bar, 5 μm. (B) Schematic representation of the data showing the different onsets and durations of PKCβ1, -α, -ɛ, and -δ translocations. (C) Statistical analysis of the data, with the number of cells analyzed. The P values were calculated with the Student t test.

FIG. 4.

Cell-cell contact targeting of PKCα and -ɛ is dependent on PKC activity, unlike the PKCβ1 and -δ targeting to the entire plasma membrane. (A to D) GH3B6 cells were preincubated (A and B) or not (C and D) with the cPKC activity inhibitor Gö6976 and then stimulated (+) with 100 nM TRH. Real-time recordings were performed as described in the legend to Fig. 2. (C) When preincubated with 100 nM Gö6976 for 15 min, PKCα and -ɛ behaved like PKCβ1 and -δ: they accumulated at the entire plasma membrane. Gö6976 had no effect on PKCβ1 and -δ targeting (D). Bar, 5 μm. (E) Summary of the number of cells analyzed.

FIG. 5.

PKCα and -ɛ translocation depends on PKCβ1 activity. CA PKCβ1-RFP was first cotransfected with PKCα-GFP in GH3B6 cells, and observations were performed 48 h later. (A) PKCα-GFP still accumulated at cell-cell contacts in the presence of CA PKCβ1, which bypasses receptor activation and therefore does not induce any increase in intracellular Ca²⁺ and DAG concentrations. Observations were performed with a conventional microscope. A video in the supplemental material shows that CA PKCβ1-GFP oscillates spontaneously, without TRH, between the cytoplasm and plasma membrane. In the presence of DN PKCβ1-RFP (B) and in the presence of 100 nM TRH, PKCα-GFP remained in the cytoplasm of most cells or accumulated at the entire plasma membrane in 9/26 cells, as did PKCɛ (C). PKCδ translocation was not affected by the cotransfection of DN PKCβ1-RFP (D). All the data presented in panels A to D were obtained 48 h after the cotransfection by real-time recordings. (E) Summary of the total number of cells analyzed in each situation and the subcellular localizations of the different GFP fusion proteins. As previously shown by others for DN PKCγ and -δ (49), we found that in the presence of 100 nM TRH, DN PKCβ1 accumulated at the same site as the native enzyme, namely, at the entire plasma membrane (B, C, and D), while the CA PKCβ1 keeps oscillating between the cytoplasm and plasma membrane (see the video in the supplemental material). In each experiment, it was checked (n = 5 cells for each PKC) that PKCα, PKCɛ, and PKCδ-GFP transfected alone were localized exclusively at cell-cell contacts.

FIG. 6.

PKCɛ translocation depends on PKCα activities. When cotransfected with DN PKCα-RFP, PKCɛ-GFP remained in the cytoplasm of all the TRH-stimulated cells analyzed (B). Under the same conditions, PKCβ1 and -δ translocation were not affected (A and C). (D) Summary of the total number of cells analyzed in each situation and the subcellular localizations of the different GFP fusion proteins. All the data presented in panels A, B, and C were obtained 48 h after the cotransfection by real-time recordings. In each experiment, it was checked (n = 5 cells for each PKC) that PKCβ1, PKCɛ, and PKCδ-GFP, transfected alone, were localized at cell-cell contacts for PKCɛ and at the entire membrane for PKCβ1 and -δ. Bar, 5 μm.

FIG. 7.

The different subcellular compartment localizations of PKCα, -β1, and -ɛ occur within the same cells. Cotransfection experiments of PKCβ1 and PKCα subcloned in the pcDNA-RFP vector with either PKCβ- or PKCɛ-GFP indicated that PKCβ1 accumulated at the entire plasma membrane in cells where PKCα and -ɛ were translocated to cell-cell contacts. Cotransfection with PKCα-RFP and PKCɛ-GFP indicated that these two isoforms accumulated at the same subcellular location, the cell-cell contacts, within the same cells. Recordings were performed with a Noran confocal laser-scanning microscope equipped with an Ar/Kr laser (Odyssey XL with InterVision 1.4.1 software; Noran Instruments, Inc., Middleton, WI). Images were acquired with intervals of 17 s between the two frames. Bar, 5 μm.

FIG. 8.

Endogenous PKCs are also sequentially activated by TRH. GH3B6 cells were stimulated with TRH for the indicated times and then immediately fixed with paraformaldehyde. Immunocytochemistry performed with selective PKC antibodies showed that endogenous PKCs behave like the GFP-tagged ones. After 15 s of TRH stimulation, all PKCs were translocated. After 60 s, only PKCβ1 and -ɛ were still activated, whereas at 5 min of stimulation, only PKCɛ was activated. Bar, 5 μm.

FIG. 9.

The sequential endogenous PKC activation is coordinated. By using siRNAs targeted to PKCβ1, -α, or -ɛ, we show that the sequential activation of endogenous PKCs is coordinated in the same way as it is for the GFP-tagged enzymes. (A) The efficacy of the siRNAs is dose dependent, and it is maximal for 200 nM. At this concentration, the siRNA targeted to PKCβ1 abolished translocation of PKCα and -ɛ but not that of PKCδ (B). The siRNA targeted to PKCα abolished translocation only of PKCɛ, and the siRNA targeted to PKCɛ did not affect the translocation of PKCβ1, -α, or -δ (B). wb, Western blot. Bar, 5 μm.

FIG. 10.

PKCα, but not PKCɛ, is responsible for the TRH-induced relocalization of β-catenin at cell-cell contacts. In order to clarify whether PKCα and -ɛ had distinct functions at the cell-cell contact, we analyzed the previously described TRH-induced β-catenin relocation to cell-cell contact (48) in the presence or absence of siRNAs targeted either to PKCα or to PKCɛ. (A) Relocation of β-catenin started as soon as 10 min after TRH stimulation, and the effect was maximal after 1 h of stimulation. The TRH-induced redistribution of β-catenin was abolished when cells were transfected with the siRNA targeted to PKCα, which was not the case in cells transfected with the siRNA targeted to PKCɛ (B). Bar, 5 μm.

FIG. 11.

Schematic representation of the coordinated cascade of PKCβ1, -α, and -ɛ activation. Upon stimulation of the Gq-coupled TRH receptor, intracellular Ca²⁺ and DAG concentrations increase and PKCβ1 would be activated according to the currently accepted paradigm of PKC translocation/activation. It accumulates at the plasma membrane where it would phosphorylate a substrate that would relocalize to the cytoplasm, as already shown for example in the case of MARCKS (31). The unknown PKCβ1 substrate would elicit directly or indirectly the selective translocation of PKCα to the cell-cell contact. PKCα would in turn phosphorylate a substrate that would mediate directly or indirectly PKCɛ translocation to the cell-cell contact. PKCδ would not enter in this scheme, as its translocation to the plasma membrane is not dependent on PKC activity. sβ, PKCβ1 substrate; sα, PKCα substrate; sɛ, PKCɛ substrate.