Plasma membrane contributes to the formation of pre-autophagosomal structures

Abstract

Autophagy is a catabolic process in which lysosomes degrade intracytoplasmic contents transported in double-membraned autophagosomes. Autophagosomes are formed by the elongation and fusion of phagophores, which derive from pre-autophagosomal structures. The membrane origins of autophagosomes are unclear and may involve multiple sources, including the endoplasmic reticulum and mitochondria. Here we show in mammalian cells that the heavy chain of clathrin interacts with Atg16L1 and is involved in the formation of Atg16L1-positive early autophagosome precursors. Atg16L1 associated with clathrin-coated structures, and inhibition of clathrin-mediated internalization decreased the formation of both Atg16L1-positive precursors and mature autophagosomes. We tested and demonstrated that the plasma membrane contributes directly to the formation of early Atg16L1-positive autophagosome precursors. This may be particularly important during periods of increased autophagosome formation, because the plasma membrane may serve as a large membrane reservoir that allows cells periods of autophagosome synthesis at levels many-fold higher than under basal conditions, without compromising other processes.

Figure 1. Atg16L1 interacts with clathrin-heavy chain

A. HeLa cell lysates were immunoprecipitated with Atg16L1 antibody (Atg16L1) or no antibody (No Ab) in control, subjected to SDS-PAGE, and proteins were stained with SimplyBlue safe stain (Invitrogen) according to manufacturer's protocol. Bands indicated in the box were cut out and digested with trypsin, and identified by MALDIToF. B. HeLa cells transfected with control vector, or wild-type or different deletion mutants (2-77, 2-275, 232-607) of Flag-Atg16L1 for 24h were immunoprecipitated with anti-Flag antibody (Atg16L1) and immunoblotted with anti-clathrin, anti-Flag and anti-Atg5 antibodies. Clathrin interacts with the N-terminus of Atg16L1, similar to Atg12-Atg5. Total lysates were run alongside as controls for protein input. C. HeLa cell lysates were immunoprecipitated (IP) with Atg16L1 antibody (+Ab) or no antibody (No Ab) and immunoblotted with anti-clathrin, anti-AP2 and anti-Atg16L1 antibodies. Total cell lysates (TL) were also blotted for input controls. Endogenous Atg16L1 interacts with clathrin-heavy chain and AP2. D. HeLa cells transfected with Flag-Atg16L1 and increasing concentrations of Atg5 for 24h were immunoprecipitated (IP) with anti-Flag antibody (Atg16L1) and immunoblotted with anti-clathrin, anti-Flag and anti-Atg5 antibodies. Atg5 overexpression neither interferes with, nor increases, clathrin-Atg16L1 binding. TL – total cell lysate.

Figure 2. Inhibition of clathrin-mediated endocytosis decreases autophagosome formation

A. HeLa cells transfected with two rounds of control, epsin 1, clathrin-heavy chain, AP2 or AP1 siRNA for 5 d were either left untreated or treated with Bafilomycin A1 (+/− BafA1) for 4 h, after which they were lysed for western blot analysis with anti-LC3 and anti-tubulin antibodies. Note that LC3-I is often very faint compared to LC3-II in HeLa cells under the protein extraction conditions we use. But this is not a problem as it is advisable to relate LC3-II to tubulin/actin, . B. Ratio of LC3-II to tubulin upon control, epsin, clathrin-heavy chain, AP2 or AP1 knockdown, with, or without Bafilomycin A1, is quantitated from three independent experiments (two for epsin) and represented in the graph. * - p<0.01, ** - p<0.001, *** - p<0.0001. C. HeLa cells stably expressing GFP-mRFP-LC3 were transfected with two rounds of control or clathrin-heavy chain siRNA for 5 d during which they were either left untreated (UT) or treated with Bafilomycin A1 (BafA1) for the last 15 h. Cells were then fixed and analysed on cellomics arrayscan system. Quantification of autophagic vacuoles (AV) or autolysosomes (AL) per cell in the different conditions is shown in the graph. * - p<0.01, NS - not significant. n = 2000 cells. D. HeLa cells transfected with control, clathrin-heavy chain, AP1 or AP2 siRNA for 4 d were grown in Hanks balanced salt solution (HBSS) for 6 h after which the cells were fixed and immunostained for endogenous LC3. The percentage of HeLa cells with more than 50 LC3-vesicles (marked with arrows) were counted as shown in the graph. *** - p<0.0001. n = 500 cells. All error bars in the graphs represent SEM.

Figure 3. Influence of clathrin-mediated endocytosis on Atg16L1-positive autophagosome precursors

A, B, C, D. HeLa cells transfected with control, epsin 1, clathrin-heavy chain, AP2 or AP1 siRNA for 72 h were treated with Hanks balanced salt solution (to induce autophagy) for 6 h, after which they were fixed and immunostained for endogenous Atg16L1. The percentages of HeLa cells with Atg16L1 vesicles were quantitated. *** - p<0.0001. Scale bar – 10 μm. (Note that we used single siRNAs for all experiments and the effects were confirmed with two independent sequences for clathrin-heavy chain). n = 600 cells. E. F. HeLa cells transfected with Flag-tagged wild-type Atg16L1 or the Atg16L1 deletion mutants - 2-275 or 232-607 Atg16L1 for 24 h were fixed and imunostained with anti-Flag antibody and the proportion of cells with Flag-Atg16L1 vesicles were quantitated and represented in the graph. Representative images of Atg16L1 vesicles with the different mutant constructs is shown in the top panel. NS – not significant, *** - p<0.0001. n = 100 cells. G, H, I. HeLa cells transfected with control, epsin 1, clathrin-heavy chain, AP2 or AP1 siRNA, as above, were transfected with GFP-Atg16L1 and tomato-LC3 for a further 24 h, after which the cells were fixed. Percentage of GFP-Atg16L1 (green) that co-localised (yellow, marked by arrows) with tomato-LC3 vesicles (red) was quantitated as shown in the graph. n = 21 cells. *** - p<0.0001. Scale bar – 10 μm. All error bars in the graphs represent SEM.

Figure 4. Atg16L1 vesicles are found close to the plasma membrane

A. HeLa cells transfected with GFP-Atg16L1 for 24 h were fixed to visualise the Atg16L1 vesicles (green). Scale bar – 10 μm. B. HeLa cells transiently transfected with GFP-Atg16L1 and mRFP-GPi for 20 h were cultured in starvation medium for a further 2 h. TIRF image with GFP-Atg16L1 (green) and mRFP-GPi (red) is shown. Arrows indicate co-localization between Atg16L1 and GPi. Percentage co-localisation of GFP-Atg16L1 with mRFP-GPi is shown in the graph. n = 2. Scale bar – 5 μm. C. HeLa cells transfected with GFP-Atg16L1 for 24 h, were either left untreated or treated with 50 μM dynasore (Sigma) for 4h and processed for immuno-gold EM with anti-GFP (15 nm gold particles) and anti-clathrin (10 nm gold particles) antibodies. Co-localisation can be seen in boxed areas. Quantification of clathrin-coated structures (CCS) that were associated with Atg16L1 per 1000 μM² is shown in the graph. *** - p<0.0001. Scale bar – 100 nm. All error bars in the graphs represent SEM.

Figure 5. Atg16L1 vesicles co-localise with cholera toxin-subunit B-labelled vesicles

A. HeLa cells transfected for 24 h with GFP-Atg16L1 (green) and CFP-LC3 (blue) were incubated with Alexa fluor-555-conjugated cholera toxin-subunit B (red) for 15 minutes at 4°C (allowing toxin binding to the plasma membrane). Then cells were incubated at 37°C (which allows cholera toxin internalization) for 10 minutes and fixed for confocal analysis. Vesicles positive for Atg16L1 and cholera toxin are yellow (also see high magnification images). Note that the small Atg16L1 vesicles co-localising with cholera toxin are negative for LC3 (as marked with yellow arrows) and the Atg16L1 vesicles co-localising both with cholera toxin and LC3 (marked with blue arrows) are shown in the magnified panels on the right. Scale bar – 10 μm. B. HeLa cells transfected for 24 h with GFP-Atg16L1 (green) were incubated with Alexa fluor-555-conjugated cholera toxin-subunit B (red) as in A after which they were fixed, immunostained for endogenous EEA1 (blue) and analysed by confocal microscopy. Vesicles positive for Atg16L1 and cholera toxin B are yellow (white arrows) and vesicles positive for both EEA1 and cholera toxin are purple (blue arrows) and is shown in the high magnification images. Graph shows percentage co-localisation. n = 20 cells. Scale bar – 10 μm. C. HeLa cells treated with HBSS for 6 h were incubated Alexa fluor-555-labelled cholera toxin-subunit B (red) as in A. Cells were then fixed, and immunostained for endogenous Atg16L1 (green) and endogenous EEA1 (blue). Cells were analysed as in B and graph shows quantitation. Scale bar – 10 μm. Arrows show Atg16L1-cholera toxin co-localisation. Triangles show EEA1-cholera toxin co-localisation. n = 20 cells. D. HeLa cells treated with HBSS for 6 h were incubated with Alexa fluor-555-labelled cholera toxin-subunit B (red) as in A. Cells were then fixed and immunostained for endogenous Atg5 (green) or endogenous Atg12 (green). Co-localisation of the Atg5 (n = 18 cells) or Atg12 vesicles (n = 39 cells) with cholera toxin is shown in yellow (arrows) and quantitated in graph. Scale bar – 10 μm. All error bars in the graphs represent SEM.

Figure 6. Analysis of wild-type and deletion mutants of Atg16L1

A. HeLa cells transfected for 24 h with Flag-tagged wild-type Atg16L1 or the Atg16L1 deletion mutants - 2-275 or 232-607 Atg16L1 together with GFP-Atg5 and CFP-LC3, were fixed and imunostained with anti-Flag antibody before confocal analysis. Co-localisation of wild-type or 2-275 Atg16L1 (red) with GFP-Atg5 (green) is marked by arrows in the inset. Scale bar – 10 μm. B. HeLa cells transfected for 24 h with GFP-Atg16L1 were incubated with HRP-conjugated cholera toxin-subunit B for 15 minutes at 4°C. The cells were then incubated at 37°C for 10 minutes, after which they were processed for double immuno-gold labelling with anti-HRP (15 nm gold particles) and anti-GFP (10 nm gold particles) antibodies for EM. PM – plasma membrane. Scale bar – 100 nm. Co-localisation can be seen in boxed areas. n = 49 fields. All error bars in the graphs represent SEM.

Figure 7. Plasma membrane contributes to Atg16L1-positive autophagosome precursors

A. HeLa cells transfected for 24 h with GFP-Atg16L1 (green) were incubated with CellMask orange plasma membrane stain for 5 minutes at 37°C, after which they were then imaged immediately (in an incubated chamber at 37°C). A time series following fusion of a CellMask orange vesicle (red) with GFP-Atg16L1 vesicle (green) is shown. Scale bar – 5 μm. A higher magnification image showing co-localisation (yellow) of GFP-Atg16L1 vesicle (green) with CellMask orange-positive vesicle (red), that are marked by arrows is also shown in the top and bottom panels. B, C. HeLa cells transfected with control, clathrin-heavy chain, AP1 or AP2 siRNA for 72 h were subsequently transfected with GFP-Atg16L1 (green) together with the siRNA for the next 24 h. The cells were then incubated with Alexa fluor-555-conjugated cholera toxin-subunit B (red) for 15 minutes at 4°C, followed by further incubation at 37°C for 10 minutes, after which the cells were fixed for confocal analysis. The co-localisation (yellow) of GFP-Atg16L1 (green) with cholera toxin (red) in control or clathrin-heavy chain knockdown is shown, which is quantitated in the graph in C. n = 25 cells. *** - p=0.0002 for clathrin-heavy chain KD and <0.0001 for AP2 KD. All error bars in the graphs represent SEM. Scale bar – 5 μm.

Figure 8. Effect of endocytic vesicle scission on phagophore formation

A. Hela cells transfected with two rounds of control, clathrin-heavy chain or AP2 siRNA for 4 d were collected for immunoprecipitation with anti-Atg16L1 antibody (IP). Western blot for total lysate (bottom) and IP (top) were performed using anti-Atg16L1 and anti-clathrin antibodies. Note the decrease in Atg16L1-Clathrin interaction with AP2 knockdown. Graph shows quantitation of the Atg16L1-clathrin or Atg16L1-AP2 with control, clathrin-heavy chain or AP2 knockdown from two independent experiments. B. HeLa cells transfected for 24 h with Flag-tagged wild-type Atg16L1, GFP-PLC(PH) together with empty vector (Control) or dominant-negative dynamin-II mutant (K44A Dynamin; DN-Dyn) were fixed and analysed by confocal microscopy. Note co-localisation of Atg16L1 with PLC(PH) at the plasma membrane which is quantified in the graph. * - p<0.01. Scale bar – 5 μm. n = 20 cells. C. Hela cells treated with HBSS alone or HBSS with 80 μM dynasore for 5 h were collected for immunoprecipitation with anti-Atg16L1 antibody (IP). Western blot analyses for total lysate (TL) and IP were performed using anti-Atg16L1 and anti clathrin antibodies. Note the strong Atg16L1-Clathrin interaction with dynasore treatment. Graph shows quantitation from two independent experiments. All error bars in the graphs represent SEM. D. Representation of plasma membrane contribution to autophagosome precursor formation. Cholera toxin is internalized by clathrin-dependent and clathrin-independent endocytosis. Clathrin knockdown significantly decreases cholera toxin uptake , . Clathrin-coated vesicles (CCV) budding immediately from the plasma membrane (EEA1-negative) are precursors to early endosomes (EE) (EEA1-positive). Previous studies showed that delivery of fully formed autophagosomes to lysosomes requires fusion of such autophagosomes with early or late endosomes/multi vesicular bodies (LE/MVB) to form amphisomes, which are Atg16L1-negative, LC3-positive and positive for endosomal markers , (red arrows). We show here that inhibition of clathrin-dependent internalization inhibits formation of early Atg16L1-positive precursors that mature to form phagophores and later autophagosomes (blue arrows). These Atg16L1-vesicles were positive for other early autophagosomal markers (Atg5 and Atg12), but not early endosomal markers (EEA1). AP2 is a clathrin adaptor at the plasma membrane while AP1 localises to TGN and endosomes.