Regulation of monocarboxylic acid transporter-1 by cAMP dependent vesicular trafficking in brain microvascular endothelial cells

Abstract

In this study, a detailed characterization of Monocarboxylic Acid Transporter-1 (Mct1) in cytoplasmic vesicles of cultured rat brain microvascular endothelial cells shows them to be a diverse population of endosomes intrinsic to the regulation of the transporter by a brief 25 to 30 minute exposure to the membrane permeant cAMP analog, 8Br-cAMP. The vesicles are heterogeneous in size, mobility, internal pH, and co-localize with discreet markers of particular types of endosomes including early endosomes, clathrin coated vesicles, caveolar vesicles, trans-golgi, and lysosomes. The vesicular localization of Mct1 was not dependent on its N or C termini, however, the size and pH of Mct1 vesicles was increased by deletion of either terminus demonstrating a role for the termini in vesicular trafficking of Mct1. Using a novel BCECF-AM based assay developed in this study, 8Br-cAMP was shown to decrease the pH of Mct1 vesicles after 25 minutes. This result and method were confirmed in experiments with a ratiometric pH-sensitive EGFP-mCherry dual tagged Mct1 construct. Overall, the results indicate that cAMP signaling reduces the functionality of Mct1 in cerebrovascular endothelial cells by facilitating its entry into a highly dynamic vesicular trafficking pathway that appears to lead to the transporter's trafficking to autophagosomes and lysosomes.

Figure 1. Mct1 is apparent in cytoplasmic vesicles.

RBE4 cells expressing mCherry-Mct1 were imaged live using confocal microscopy (A). In the last three micrographs, RBE4 cells were immunostained with an anti-Mct1 antibody, fixed in 3.7% formaldehyde, and permeabilized with either methanol and acetone (B), or 0.5% TritonX-100 (C), or 5% glacial acetic acid (D). Scale = 5 µM.

Figure 2. Colocalization of mCherry-Mct1 with endosomal markers.

Each three part panel shows a large merged image and smaller images of the corresponding color channels, where Mct1 is pseudocolored red, the counter stain appears green, and colocalization appears yellow. Examples of colocalization are indicated by white arrows throughout. A single confocal plane near the basal region of the cells is shown in each case. mCherry-Mct1 co-localized with: YFP-caveolin-1 in puncta that were present near the plasma membrane and in the cytoplasm (upper left); GFP-clathrin in puncta near the plasma membrane and in cytoplasmic puncta (upper right); an anti-Rab5 antibody in numerous puncta (middle left); an anti-syntaxin-6 antibody in a cluster consistent with the trans-golgi and in cytoplasmic puncta (middle right); and GFP-Lamp1 in cytoplasmic puncta (lower left). Mct1 was also present in puncta that did not co-localize with Lamp1 (lower left, red arrow). Scale bars = 5 µM.

Figure 3. Characterization of Mct1 expression patterns in cells transfected with full length and deletion mCherry-Mct1 expression constructs.

A. Protein motifs in the C and N termini of Mct1 that could be involved in controlling its localization to vesicles include (in red); type 1 and 4 WW ligands, an AP2 clathrin interaction site, a PDZ ligand, a hydrophobic N terminus, a charged C terminus (+ and −), lysine residues (shown in green), and numerous phosphorylation sites (PO₄ ⁻). B. Confocal micrographs showed a similar appearance of Mct1 vesicles among cells expressing FL, XC, and XN mCherry-Mct1. C. An epi-fluorescence micrograph of an RBE4 cell expressing the C-terminus of Mct1 with mCherry fused to its amino terminus.

Figure 4. Histograms of the areas of Mct1 vesicles in RBE4 cells expressing FL, XC, and XN mCherry-Mct1.

Deletion of the termini caused a rightward shift in the size distribution for the XC and XN groups with disappearance of the smallest vesicles. Average vesicular sizes for each group were FL = 0.47+/−0.1, XC = 0.53+/−0.06, XN = 0.57+/−0.06 µm² (means and standard errors are given with n = 880 FL, 924 XC, and 759 XN vesicles).

Figure 5. Mct1 vesicles spanned a pH range that was acid shifted relative to the overall pH of the cell.

A. A single confocal plane from a RBE4 cell showing FL mCherry-Mct1 fluorescence (upper left) and the same plane showing BCECF fluorescence (lower left). As illustrated in the merged image (right), voids in BCECF staining often, but not always, colocalized with Mct1 vesicles. B. Histograms showing the distributions of the relative pH of Mct1 vesicles from 10 cells in each group expressing FL mCherry-Mct1 (880 vesicles), XC mCherry-Mct1 (924 vesicles), and XN mCherry-Mct1 (759 vesicles). Each distribution was fit with the Gaussian equation described in the text and is shown here as curves. Dashed lines show the average pH of the cells with relatively alkaline vesicles to their right and relatively acidic vesicles to the left. The mean relative pH's and standard errors were FL = 0.83+/−0.01, XC = 0.85+/−0.01, and XN = 0.91+/−0.01. Scale bars = 5 µM.

Figure 6. cAMP dependent changes in the localization and relative pH of mCherry-Mct1 vesicles in RBE4 cells.

A. Excerpts from a video experiment with DIC images of RBE4 cells superimposed upon single confocal planes showing mCherry-Mct1 vesicles (red). The cells were exposed to 500 µM 8Br-cAMP at the start of a video imaging experiment, t = 0 min, and changed their morphology and distribution of Mct1 vesicles by the end of the experiment. Arrows show the location of three clusters of Mct1 vesicles that formed and became stationary during the cell's response. B. Histograms showing the distribution of the relative pH of Mct1 vesicles in RBE4 cells expressing FL mCherry-Mct1 (418 vesicles), XC mCherry-Mct1 (454 vesicles), and XN mCherry-Mct1 (589 vesicles). The histograms were fit by the Gaussian equation described in the text (black curves). As a reference, curves generated from the untreated control cells in figure 5 were scaled and superimposed on the graph (red curves). Arrows show the approximate positions of acidic peaks which appeared with cAMP treatment.

Figure 7. cAMP dependent acidification of dual tagged Mct1 vesicles.

A. A confocal micrograph of EGFP-mCherry-Mct1, showing individual EGFP (green) and mCherry (red) color channels from a single plane on the left and the merged image on the right. The inset on the right diagrams the protein product of the expression construct. The arrow indicates a cluster of Mct1 vesicles that appear red because of selective quenching of the EGFP signal in more acidic endosomes. B. Histograms showing the distributions of the EGFP/mCherry intensity ratios in vesicles from control (n = 7 cells, 828 vesicles, upper left) and 500 µM 8Br-cAMP treated cells (7 cells, 748 vesicles, lower left) and curves fit with the Gaussian equation described in the text. The curves are shown superimposed in the right panel for comparison of results between control (black) and 8Br-cAMP treated cells (red). C. Dose response showing the effect of 8Br-cAMP on control-normalized EGFP/mCherry intensity ratios measured 30 minutes after treatment. In the H89 groups, 20 µM H89 was present for 10 minutes with or without 500 µM 8Br-cAMP (n = 6 cells with >200 vesicles per group). The experiment was repeated with similar results.