The retromer coat complex coordinates endosomal sorting and dynein-mediated transport, with carrier recognition by the trans-Golgi network

Abstract

Early endosome-to-trans-Golgi network (TGN) transport is organized by the retromer complex. Consisting of cargo-selective and membrane-bound subcomplexes, retromer coordinates sorting with membrane deformation and carrier formation. Here, we describe four mammalian retromers whose membrane-bound subcomplexes contain specific combinations of the sorting nexins (SNX), SNX1, SNX2, SNX5, and SNX6. We establish that retromer requires a dynamic spatial organization of the endosomal network, which is regulated through association of SNX5/SNX6 with the p150(glued) component of dynactin, an activator of the minus-end directed microtubule motor dynein; an association further defined through genetic studies in C. elegans. Finally, we also establish that the spatial organization of the retromer pathway is mediated through the association of SNX1 with the proposed TGN-localized tether Rab6-interacting protein-1. These interactions describe fundamental steps in retromer-mediated transport and establish that the spatial organization of the retromer network is a critical element required for efficient retromer-mediated sorting.

Figure 1

SNX1, SNX2, SNX5, and SNX6 Form a Network of Interactions (A) Results of four genome-wide yeast two-hybrid screens using SNX1, SNX2, SNX5, and SNX6 as baits. Arrows indicate interactions identified in a given screen; numbers indicate the number of hits/clones isolated. (B) Immunoprecipitation of endogenous protein by antibodies directed against either a nonrelated control (anti-sulfotransferase), SNX6, SNX1, SNX2, or omission of antibody (−) and probing for the coprecipitation of either endogenous SNX1 or SNX2. Under conditions in which SNX1 and SNX2 bind the positive control SNX6, they do not show any association with one another. (C) GST pull-downs from HeLa cells expressing either GST or GST-tagged SNX3, SNX4, SNX5, or SNX6. Endogenous SNX1 and SNX2 coprecipitate with GST-SNX5 or GST-SNX6 but not with any of the controls. The anti-GST blot shows expression levels of the GST-fusions. (D) Immunoprecipitation of Flag-SNX6 from HeLa cells coexpressing either GFP-SNX1 or GFP-SNX5 demonstrates that while the positive control GFP-SNX1 strongly coprecipitates with Flag-SNX6, GFP-SNX5 does not. (E) Association of SNX1, SNX2, SNX5, or SNX6 with the retromer cargo-selective subcomplex formed by VPS26, VPS29, and VPS35 was analyzed by immunoprecipitation. Flag-VPS26, VPS29, and VPS35 were coexpressed with GFP-SNX1, GFP-SNX2, GFP-SNX5 or GFP-SNX6, in HEK293T cells prior to immunoprecipitation using immobilized Flag antibody. Control cells expressed the GFP-fusion alone.

Figure 2

SNX5 and SNX6 Associate with p150^glued (A) Coimmunoprecipitation of endogenous p150^glued from HeLa cell lysates with SNX5 and SNX6 antibodies demonstrates the association of p150^glued with SNX5/SNX6 in vivo. To maximize the efficiency of the IP, a combination of two different antibodies was used. (B) GST pull-down of endogenous p150^glued, DYNC1I2, p50^dynamitin, SNX1 and SNX2 from HEK293T cells expressing either GST-SNX5, GST-SNX6, GST-SNX3, or GST (expression level of GST-fusions shown by the anti-GST blot). While both GST-SNX5 and GST-SNX6 coprecipitate p150^glued, DYNC1I2, p50^dynamitin, SNX1 and SNX2, GST-SNX3, and GST do not. (C) Stills of Movie S1 at various time points, displaying a HeLa cell expressing lentivirally transduced Cherry-SNX6 and GFP-p150^glued. Colocalization and comovement of retromer-positive vesicles and tubules decorated with p150^glued are indicated by the arrow and the arrowhead in the insets. Bar, 20 μm.

Figure 3

Suppression of p150^glued Expression Perturbs the Efficiency of Retromer-Mediated Endosome-to-TGN Transport (A) Demonstration of knock down of p150^glued in HeLa cells using three different siRNAs and probing for endogenous p150^glued, using tubulin staining to indicate equal loading. (B) Quantification of knock down obtained in four different experiments for p150^glued suppression using three different siRNAs each. Error bars indicate standard deviation. (C) Suppression of p150^glued affects the steady-state distribution of CI-MPR in HeLa cells, leading to a peripheral dispersal of the label in comparison to control cells, phenocopying loss of retromer components. Note that under these conditions, knock down of p150^glued does not affect the general organization of the giantin-stained Golgi, the TGN, the microtubule array, or EEA1-positive early endosomes, while a minor alteration in the distribution of the CD63-positive late endosomal/lysosomal compartment is apparent (Figure S4). (D) Quantification of the number of Golgis with more than half-maximal intensity of CI-MPR staining expressed as percent of total Golgis analyzed, using three different siRNAs for p150^glued suppression and including SNX1 knock down as a positive control for defective retromer trafficking. Error bars indicate standard deviation. (E) Kinetics of the uptake of a CD8-tagged CI-MPR from the plasma membrane and trafficking to the TGN, quantified as percent of CD8 label in the TGN. Knock down of p150^glued or SNX1 induces a major reduction in the efficiency of transport to the TGN in comparison to control cells. Error bars indicate standard deviation.

Figure 4

Association with p150^glued Regulates the Long-Range Transport and Steady-State Distribution of SNX6-Labeled Endosomes (A) Live-cell confocal imaging of HeLa cells lentivirally transduced with GFP-SNX6 and mCherry-Rab6a′ and then treated with control or p150^glued siRNA. Selected single cells are shown corresponding to the initial frame of Movies S3 and S5. The tracks of selected GFP-SNX6-labeled endosomes are marked with arrows indicating the direction of movement over time. Yellow arrows indicate movement toward the TGN (defined by mCherry-Rab6a′), red arrows movement away from the TGN, and blue traces little net movement over the duration of the imaging. Note that the distribution of GFP-SNX6 structures is altered between the control and p150^glued-suppressed cell. Bar, 20 μm. (B) Imaging sequence of vesicles in a control cell illustrates what appears to be a fusion event between two GFP-SNX6-positive structures (arrow) and subsequently a fission event (arrowhead) from the same structure. Time in seconds from the beginning of Movie S4 is indicated. Reconstruction of movements of GFP-SNX6-positive structures over 5 min in a HeLa cell illustrates the complexity of the retromer sorting system. Starting points of vesicles are indicated by numbers, visible merging events that most likely represent fusion events by a red dot, splitting of structures by gray spots. Note the occurrence of several merging and splitting events on most traces that travel notable distances. Bar, 20 μm. (C) Knock down of p150^glued affects mobility of GFP-SNX6-positive carriers relative to the TGN. About 50 vesicles per condition were tracked over 5 min and the distance traveled toward the Golgi between the start and the end point measured. Percent of vesicles per distance class are plotted in the histogram, with positive values indicating net movement away from the Golgi and negative values indicating movement toward the Golgi. Knock down of p150^glued shifts the distribution toward greater distances from the Golgi at the endpoint of the movie and strongly reduces the group of about 38% of carriers that move far distances toward the Golgi in control cells. (D) Imaging and quantification of the redistribution of vesicles decorated with endogenous SNX1 from the Golgi area toward the cell periphery by suppression of p150^glued. Bar, 40 μm. (E) Suppression of p150^glued leads to the occurrence of long and relatively static SNX1-decorated tubules in a subset of cells (∼20%) from a clonal HeLa cell line expressing GFP-SNX1. Bar, 20 μm.

Figure 5

p150^glued/DNC-1 Is Required for EGL-20/Wnt Signaling in C. elegans (A) Schematic representation of the migration of the left and right Q neuroblast descendants (dorsal view). On the left side (“L”), the Q descendants express the homeobox gene mab-5 (green) and migrate toward the posterior. On the right side (“R”), the Q descendants do not express mab-5 (red) and migrate in the default anterior direction. Mutations that disrupt EGL-20 production, secretion, or signaling lead to a loss of mab-5 expression in the left Q neuroblast and to the anterior migration of its descendants. (B) EGL-20/Wnt triggers a canonical Wnt/β-catenin signaling pathway. (C) Visualization of the Q descendants using a mec-7::gfp reporter that is expressed in the left Q descendant PVM (arrow head), the right Q descendant AVM (asterisk)m and four other neurons. In wild-type animals, AVM is in an anterior position and PVM in a posterior position. In mutants that disrupt EGL-20 signaling, both AVM and PVM are in the anterior. (D) Synchronized embryos were shifted to the restrictive temperature of 25°C and grown for 2 days; the final positions of the left Q descendants (QL.d) were scored using the mec-7::gfp-expressing transgene muIs32 (Ch'ng et al., 2003). n > 400 out of two independent experiments. Data are represented as mean ± SD.

Figure 6

Association of SNX1 with Rab6IP1 Is Required for Retromer-Mediated Sorting (A) GST pull-down of bacterially expressed SNX1 demonstrates that GST-SNX1 can associate with FLAG-tagged Rab6IP1. Comparative levels of GST-SNX1 and GST expression are shown. (B) Knock down of Rab6IP1 using three different siRNAs and probing for Flag-Rab6IP1 lentivirally transduced into HeLa cells. (C) Quantification of Rab6IP1 knock down obtained in three different experiments using three different siRNAs. Error bars indicate standard deviation. (D) Knock down of Rab6IP1 influences the steady-state distribution of CI-MPR, leading to a peripheral dispersal of staining in comparison to control cells, phenocopying loss of retromer components. Knock down of Rab6IP1 does not appear to affect the organization of the TGN (Figure S4). (E) Quantification of the number of Golgis with more than half-maximal intensity of CI-MPR staining shows that knock down of Rab6IP1 induces a defect in CI-MPR recycling to the TGN. Error bars indicate standard deviation. (F) Kinetics of the trafficking of CD8-CI-MPR from the cell surface to the TGN shows that loss of Rab6IP1 reduces the efficiency of retromer-mediated transport in comparison to control cells. Error bars indicate standard deviation.

Figure 7

A Population of SNX1-Labeled Endosomes Resides in Close Proximity to the Rab6IP1-labeled TGN (A) Live-cell imaging shows an incoming carrier containing CD8-CI-MPR labeled with a CD8-FITC antibody colocalizing with a moving, mCherry-Rab6IP1-decorated fiber emanating from the TGN (arrowheads) (Movie S7). Time in seconds. Bar, 12 μm. (B) Triple labeling of GFP-Rab6IP1, TGN46, and SNX1 shows Rab6IP1 colocalization with the TGN, with numerous SNX1-labeled endosomes being concentrated in close proximity to TGN cisternae. Bar, 28 μm. (C) Imaging and quantification of the redistribution of vesicles decorated with endogenous SNX1 from the Golgi area towards the cell periphery by suppression of Rab6IP1. Bar, 28 μm. Error bars indicate standard deviation. (D) Electron micrograph of a Golgi/TGN complex of GFP-Rab6IP1 expressing HeLa cells immunolabeled for GFP (10 nm gold) and endogenous SNX1 (5 nm gold). SNX1 labeling is found in clusters on presumptive TGN tubulo-vesicular profiles (arrowheads). Rab6IP-1 labeling is mainly found on the same TGN profiles (arrows) and occasionally colocalizes with SNX1. Scale bar represents 100 nm.