Exocyst requirement for endocytic traffic directed toward the apical and basolateral poles of polarized MDCK cells

Abstract

The octameric exocyst complex is associated with the junctional complex and recycling endosomes and is proposed to selectively tether cargo vesicles directed toward the basolateral surface of polarized Madin-Darby canine kidney (MDCK) cells. We observed that the exocyst subunits Sec6, Sec8, and Exo70 were localized to early endosomes, transferrin-positive common recycling endosomes, and Rab11a-positive apical recycling endosomes of polarized MDCK cells. Consistent with its localization to multiple populations of endosomes, addition of function-blocking Sec8 antibodies to streptolysin-O-permeabilized cells revealed exocyst requirements for several endocytic pathways including basolateral recycling, apical recycling, and basolateral-to-apical transcytosis. The latter was selectively dependent on interactions between the small GTPase Rab11a and Sec15A and was inhibited by expression of the C-terminus of Sec15A or down-regulation of Sec15A expression using shRNA. These results indicate that the exocyst complex may be a multipurpose regulator of endocytic traffic directed toward both poles of polarized epithelial cells and that transcytotic traffic is likely to require Rab11a-dependent recruitment and modulation of exocyst function, likely through interactions with Sec15A.

Figure 1.

Localization of exocyst subunits in polarized MDCK cells. (A and B) Cells were treated with saponin and then fixed using a pH-shift protocol. (A) Distribution of Sec8 (green), furin (red), and ZO-1 (blue). (B) Distribution of Sec8 (green), EEA1 (red), and ZO-1 (blue). (C and D) Cells were fixed using the pH-shift protocol. (C) Distribution of Exo70 (green), furin (red), and ZO-1 (blue). (D) Distribution of Exo70 (green), EEA1 (red), and ZO-1 (blue). (A and D) An XZ section is shown in the top of each column, and single optical sections at the designated position of the cell are shown below. The bottom-most panels show the distribution pattern of exocyst subunits (green), and cellular markers (red) within the regions are marked with the white boxes. Scale bar, 10 μm.

Figure 2.

Association of exocyst subunits with Tf-positive endosomes. (A) Distribution of Sec8 (green), Tf (red), and ZO-1 (blue). (B) Distribution of Exo70 (green), Tf (red), and ZO-1 (blue). Top, an XZ section; middle, a 3D reconstruction of optical sections taken from the apical to supranuclear level of the cells; and bottom, a 3D reconstruction of optical sections taken along the lateral surfaces of the cells. Examples of colocalization between exocyst subunits and Tf-positive endosomes are marked by arrows. In XZ sections, the scale bar is equal to 10 μm. In 3-D reconstructions each length of the grid is equivalent to 3.8 μm. (C) Endosomal-enriched fractions were incubated with a pool of Sec8-specific antibodies (10C2, 5C3, 2E12) or IgG and recovered using Dynabeads coated with goat anti-mouse secondary antibodies. The lane at the left is a loading control showing that Sec8 and the Tf receptor were present in the starting PNS. The other lanes show the immunoisolated fraction bound to Sec8-specific antibodies or nonspecific rabbit IgG antibodies that were resolved by SDS-PAGE and then sequentially probed with antibodies to Sec8 or the Tf receptor. The immunoisolation protocol was performed three times, and results from one experiment are shown.

Figure 3.

Localization of exocyst subunits to Rab11a- and IgA-positive recycling endosomes. (A–D) Distribution of Sec8/Exo70 (green) and Rab11a (A and C) or IgA (B and D). The distribution of ZO-1 was also examined but is not apparent in all of the panels. (B and D) IgA was internalized from the basolateral pole of the cell for 10 min and chased 20 min at 37°C. (E and F) IgA was internalized from apical pole of the cell for 10 min. (E) The cells were fixed and stained with antibodies to Sec8 (green), Rab11a (red), and IgA (blue). (F) Cells were stained with antibodies to Exo70 (green), Rab11a (red), and IgA (blue). In B and E cells were treated with saponin before fixation, whereas in A, C, D, and F cells were fixed before permeabilization. Arrows indicate areas of colocalization between the three markers. Scale bar, 10 μm. (G) Association of Sec8 and pIgR with immunoisolated Rab11-positive endosomes. The lane at the left shows that Sec8, pIgR, and Rab11 were present in the starting PNS, and the other lanes show the immunoisolated fraction bound to Rab11-specific antibodies or nonspecific rabbit IgG antibodies that were resolved by SDS-PAGE and then sequentially probed with antibodies to Sec8, pIgR, or Rab11. The immunoisolation protocol was repeated three times, and results from one experiment are shown.

Figure 4.

Association of exocyst subunits with GFP/HA-Rab11aSV. (A) MDCK cells were infected with virus encoding GFP/HA-Rab11aSV and then fixed and processed for IF. The distribution of GFP/HA-Rab11aSV (green) and Exo70 (red) are shown. A merged image is shown at the right. Scale bar, 10 μm. (B) Cells were infected with virus encoding GFP/HA-Rab11aSV, lysed, and Sec8 and associated proteins were immunoprecipitated using Sec8-specific mAb 10C2 or protein G alone. The cell lysate (one-twentieth of the total) or the immunoprecipitated proteins were resolved by SDS-PAGE, and a Western blot was sequentially probed with antibodies to Sec6, Sec8, Sec15, Exo70, and Rab11a. The coimmunoprecipitation protocol was performed two times and results from one experiment are shown.

Figure 5.

Exocyst requirement for endocytic traffic in SLO-permeabilized MDCK cells. (A) Basolateral recycling of ¹²⁵I-Tf in SLO-permeabilized MDCK cells incubated in the presence of an ATP-regenerating system (ATP), cytosol, and either Myc antibodies (Myc) or a pool of Sec8 antibodies (10C2, 5C3, 2E12). The ATP-independent fraction was ∼12% and values for control reactions performed in the presence of an ATP-regenerating system and cytosol were ∼46%. Data are mean ± SEM (n = 3; performed in triplicate). (B) IgA was internalized basolaterally for 10 min at 37°C, and the cells were incubated in the absence of IgA for 20 min. The cells were fixed and stained with antibodies to IgA (blue), ZO-1 (blue), Tf receptor (green), and Rab11a (red). 3-D reconstructions are shown. Each length of the grid = 3.8 μm. (C) Ligand was internalized as described in B, and apical release of ¹²⁵I-IgA was quantified in SLO-permeabilized cells. The ATP independent fraction was ∼8%, and values for control reactions were ∼42%. Data are mean ± SEM (n = 2; performed in triplicate). (D) Apical ¹²⁵I-IgA recycling in SLO-permeabilized cells. The ATP independent fraction was ∼30%, and values for control reactions were ∼47%. Data are mean ± SEM (n = 2; performed in triplicate). (E) Release of ¹²⁵I-IgA-labeled cargo vesicles from mechanically perforated MDCK cells. The ATP-independent fraction was ∼8%, and values for control reactions were ∼30%. Data are mean ± SEM (n = 3; performed in duplicate). *Statistically significant difference between reactions performed in the presence of Myc or Sec8 antibodies (p < 0.05).

Figure 6.

Interaction between Rab11a and the C-terminus of Sec15A. (A) Sec15A constructs used to identify the Sec15A-Rab11a interaction domain. (B–E) Results of CPRG assay between the Sec15A constructs shown in panel A and either wild-type Rab11a (Rab11a), dominant active Rab11a-SV, dominant negative Rab11a-SN, lamin C (LamC), or empty vector (EV). These assays were repeated two times. Data from one determination are shown. Mean ± SD (n = 3). (F) Untransfected MDCK cells or stable MDCK cells lines expressing GFP-Sec15CT or GFP-Sec15CT(NA) were infected with adenovirus encoding GFP/HA-Rab11aSV. The cells were cross-linked and lysed, and GFP/HA-Rab11aSV was immunoprecipitated with anti-HA antibodies. The immunoprecipitates were resolved by SDS-PAGE and Western blots were sequentially probed with antibodies that recognize Rab11a or Sec15A.

Figure 7.

Expression of GFP-Sec15CT and GFP-Sec15CT(NA) in polarized MDCK cells. (A) Filter transfection protocol. (B) Distribution of GFP-Sec15 (green), Rab11a (red), and the nucleus (blue). (C) Distribution of GFP-Sec15(NA) (green), Rab11a (red), and the nucleus (blue). Individual optical sections from the apical or medial regions of the cell are shown. A merged image (overlay) is shown in the right-hand panels. Examples of colocalization between exocyst subunits and Rab11a are marked by arrows.

Figure 8.

IgA transcytosis in polarized MDCK cells expressing GFP-Sec15CT or GFP-Sec15CT(NA). (A) Protocol for detecting basolaterally internalized IgA at the apical cell surface. (B) Distribution of GFP-Sec15CT or GFP-Sec15CT(NA) (green), the pIgR (red), and IgA (blue) endocytosed from the basolateral pole of the cell for 20 min at 18°C. An optical section from the apical pole of the cell and a projection of sections along the lateral region of the cell are shown. (C) IgA was internalized from the basolateral pole of the cell for 20 min at 18°C, and the cells were washed and then chased in for 20 min at 37°C. CY3-labeled anti-IgA antibodies were included in the apical medium during the incubation at 37°C. The distribution of GFP-Sec15CT or GFP-Sec15CT(NA) (green), pIgR (red), and anti-IgA (blue) is shown in projected optical sections taken from the apical pole of the cell.

Figure 9.

Effect of expressing GFP-Sec15CT and GFP-Sec15CT(NA) on the postendocytic fate of IgA and Tf in polarized MDCK cells infected with adenovirus encoding the pIgR. (A) Lysates of cells expressing GFP-Sec15CT or GFP-Sec15CT(NA) were resolved by SDS-PAGE, and Western blots were probed with an antibody against Sec15A. (B and C) Fate of basolaterally internalized ¹²⁵I-IgA in control MDCK cells or those expressing GFP-Sec15CT or GFP-Sec15CT(NA) (B and C, respectively). (D–E) Fate of apically internalized ¹²⁵I-IgA in control MDCK cells or those expressing GFP-Sec15CT or GFP-Sec15CT(NA) (D and E, respectively). (F and G) Fate of basolaterally internalized ¹²⁵I-Tf in control MDCK cells or those expressing GFP-Sec15CT or GFP-Sec15CT(NA) (F and G, respectively). In each panel, the fraction of ligand released from the apical or basal pole of the cell is shown. Data are mean ± SEM (n ≥ 2; performed in triplicate). *Values are significantly different (p < 0.05) from those observed in control MDCK cells.

Figure 10.

Dependence of basolateral-to-apical transcytosis on expression of Sec15A. (A) The upper panel shows Sec15A or Sec15B mRNA expression in three cell samples expressing pSuper-Sec15A (lanes 1–3) or pSuper-control (lanes 4–6). The lower panel shows a Western blot of lysates prepared from three cell samples expressing pSuper-Sec15A (lanes 1–3) or pSuper-control (lanes 4–6). The Western blot was sequentially probed with antibodies to Sec15A and then Sec8. (B) Basolateral-to-apical transcytosis of ¹²⁵I-IgA in cells expressing pSuper-Sec15A or pSuper-control. Shown is the amount of ligand released in the apical or basal chamber of the Transwell. (C) Apical recycling of ¹²⁵I-IgA in cells expressing pSuper-Sec15A or pSuper-control. (D) Basolateral recycling of ¹²⁵I-Tf in cells expressing pSuper-Sec15A or pSuper-control. Data are mean ± SEM (n ≥ 3; performed in triplicate). *Values are significantly different (p < 0.05) from those observed in cells expressing pSuper-control.