WIPI2 links LC3 conjugation with PI3P, autophagosome formation, and pathogen clearance by recruiting Atg12-5-16L1

Abstract

Mammalian cell homeostasis during starvation depends on initiation of autophagy by endoplasmic reticulum-localized phosphatidylinositol 3-phosphate (PtdIns(3)P) synthesis. Formation of double-membrane autophagosomes that engulf cytosolic components requires the LC3-conjugating Atg12-5-16L1 complex. The molecular mechanisms of Atg12-5-16L1 recruitment and significance of PtdIns(3)P synthesis at autophagosome formation sites are unknown. By identifying interacting partners of WIPIs, WD-repeat PtdIns(3)P effector proteins, we found that Atg16L1 directly binds WIPI2b. Mutation experiments and ectopic localization of WIPI2b to plasma membrane show that WIPI2b is a PtdIns(3)P effector upstream of Atg16L1 and is required for LC3 conjugation and starvation-induced autophagy through recruitment of the Atg12-5-16L1 complex. Atg16L1 mutants, which do not bind WIPI2b but bind FIP200, cannot rescue starvation-induced autophagy in Atg16L1-deficient MEFs. WIPI2b is also required for autophagic clearance of pathogenic bacteria. WIPI2b binds the membrane surrounding Salmonella and recruits the Atg12-5-16L1 complex, initiating LC3 conjugation, autophagosomal membrane formation, and engulfment of Salmonella.

Graphical abstract

Figure 1

WIPI2 Binds and Colocalizes with the Atg12–5-16L1 Complex (A) HEK293A cell lines stably expressing GFP, GFP-WIPI1a, and GFP-WIPI2b were incubated in full medium (F) or starvation medium (EBSS) (S) for 2 hr before being used for GFP-TRAP pull-down. (B) WIPI2 was immunoprecipitated from HEK293A cells treated with DSP, at the indicated concentrations, before immunoblotting. (C) WT or Atg16L1^Δ/Δ MEFs in fed medium or starved for 2 hr in EBSS were fixed and labeled with an anti-WIPI2 antibody. Scale bars, 10 μm. (D) WIPI2 puncta in (C) were counted, and a statistical analysis of WIPI2 puncta was performed using an unpaired Student’s t test. ^∗p < 0.05. SEM for n = 3. (E–H) CLEM (correlative light and electron microscopy) of endogenous WIPI2 in Atg16L1^Δ/Δ MEFs. (E) Merged phase and confocal section of Atg16L1^Δ/Δ cells labeled with anti-WIPI2 antibody. Scale bar, 10 μm. (F) Low-magnification TEM of cell in (E). Scale bar 10μm. (G and H) High magnification of boxed regions in (E) and (F). Top box and bottom box indicate panels (G) and (H), respectively. Arrows indicate open phagophores. M, mitochondria; ER, endoplasmic reticulum. Scale bars, 1 μm (G) and 0.5 μm (H). (I and J) 2GL9 cells (GFP-LC3 HEK293 cells; Chan et al., 2007) were starved for 2 hr before visualization using indicated antibodies. Scale bars, 10 μm. (K) Live-cell imaging demonstrates that Atg16L1 translocates to WIPI2b-positive puncta in starvation. HEK293 cells expressing GFP-WIPI2b and mCherry-Atg16L1 were starved in EBSS and imaged every 2 s using a spinning disk microscope. See also Figure S1 and Movie S1.

Figure 2

Interaction of Atg16L1 with WIPI2 Requires 207–242, a Domain Not Functionally Conserved in Atg16L2 (A) Scheme of mouse Atg16L1 and deletion mutants showing the N-terminal Atg5 interacting domain (white box), a coiled-coil domain (black box), and a WD propeller-repeat domain (striped box). (B) Untransfected (UN) or FLAG-Atg16L1 full-length (FL), 79–623, or 1–265 constructs were expressed in HEK293A cells stably expressing GFP-WIPI2b and immunoprecipitated using GFP-TRAP. Tags were visualized by immunoblotting. I, input; UB, unbound. (C) GFP, CFP-Atg5, GFP-WIPI1a, and GFP-WIPI2b were transiently expressed in HEK293A cells. GFP-tagged proteins were isolated using GFP-TRAP and incubated with in vitro translated ³⁵S-labeled FLAG-Atg16L1 constructs 1–265, 1–242, 1–230, and 1–207 before washing and analysis by autoradiography. Protein expression was validated by immunoblot (bottom panel). (D) Lysates from HEK293A cells transiently expressing GFP, GFP-WIPI1a, or GFP-WIPI2b were mixed with lysates from HEK293A cells transiently expressing FLAG-Atg16L1 or Atg16L2. Protein complexes were immunoprecipitated using GFP-TRAP, followed by immunoblot. See also Figure S2 and Table S1.

Figure 3

WIPI2b and FIP200 Bind in Adjacent, but Distinct, Regions of Atg16L1 (A) Alignment of Atg16L1 and Atg16L2 in the WIPI2b binding region. The acidic residues in Atg16L1 (highlighted in red) that are not conserved in Atg16L2 were individually mutated to arginine (basic residues in blue, noncharged in green). (B) Lysates from HEK293A cells transfected with GFP-WIPI2b were mixed with lysates from HEK293A cells transfected with FLAG-Atg16L2, FLAG-Atg16L1, or Flag-Atg16L1 mutants, immunoprecipitated, and analyzed by immunoblotting. (C) Statistical analysis of FLAG-Atg16L1 binding in (B) was performed by Student’s t test. SEM for n = 4. ^∗p < 0.05. (D) Cell lysates from HEK293A cells transiently expressing FLAG-Atg16L2, FLAG-Atg16L1, or FLAG-Atg16L1 mutants were subjected to immunoprecipitation using FLAG M2 agarose beads. Protein complexes were analyzed using immunoblotting. (E) Statistical analysis of FIP200 binding in (D) was performed by Student’s t test. SEM for n = 3. ^∗p < 0.05. (F) WIPI2 was immunoprecipitated from lysates from WT or FIP200^−/− MEFS after treatment with 0.5 mM DSP. Bound Atg16 and Atg12–5 were detected by immunoblotting. (G) HEK293 cells stably expressing GFP-WIPI2b were and transiently transfected either FLAG-Ag16L1 WT, E226R E230R (ERER), or D237R D239R (DRDR). Bound and input (bottom) were analyzed by immunoblotting. (H) Structural model of the region of Atg16L1 207–246 that interacts with WIPI2b and FIP200. See also Figure S3 and Table S1.

Figure 4

WIPI2 Binds Atg16L1 though R108E and R125E in a Solute-Exposed Cleft in WIPI2 (A) Lysates from HEK293A cells transiently expressing GFP, GFP-WIPI1a, GFP-WIPI2a, GFP-WIPI2b, or GFP-WIPI2b FTTG mutant were used for GFP-Trap. Endogenous Atg16L1 binding was analyzed by immunoblot. (B) Statistical analysis of (A) was performed by one-way ANOVA with Tukey’s posttest. SEM for n = 3. ^∗p < 0.05. (C) Model of WIPI2b based on crystal structure of Kluyveromyces marxianus Atg18 (Protein Data Bank ID 3VU4) (Watanabe et al., 2012). The β1-β2 loop colored yellow is the site of an18 aa insertion in WIPI2a. (D) GFP-Trap from HEK293A cells transiently expressing GFP, GFP-WIPI1a, GFP-WIPI2b, GFP-WIPI2b R108E, GFP-WIPI2b R125E, or GFP-WIPI2b R108E R125E was mixed with in vitro translated ³⁵S-labeled FLAG-Atg16L1 and analyzed by autoradiography. (E) Lysates from HEK293A cells transiently expressing GFP, GFP-WIPI2b, GFP-WIPI2b ΔCT, GFP-WIPI2a, GFP-WIPI1a, or GFP-WIPI1a ΔCT were used for GFP-Trap. Endogenous Atg16L1 binding was analyzed by immunoblot. (F) Statistical analysis of (E) was performed by one-way ANOVA with Tukey’s posttest. SEM for n = 2. ^∗p < 0.05. (G) Lysates from HEK293A cells transiently expressing GFP-WIPI2b WT, GFP-WIPI2b R108E, R125E, or R108E R125E were mixed with lysates from HEK293A cells transiently expressing FLAG-Atg16L1 WT, E226R, E230R, or E226R E230R in all possible permutations. Protein complexes from mixed lysates were immunoprecipitated using GFP-Trap, followed by immunoblot analysis. (H) Statistical analysis of (G) was performed by one-way ANOVA with Tukey’s posttest. SEM from n = 3. ^∗p < 0.05. (I) CLEM analysis of HEK293 cells treated with siRNA to WIPI2 were transfected with GFP-WIPI2b RERE and starved in EBSS. Bright-field image (top), GFP-WIPI2 RERE signal (middle), TEM of selected cell (bottom). Boxed area shown in (J). Scale bars represent 10 μM for bright-field and confocal and 5 μM for TEM. (J) High-magnification TEM of boxed area in (I). Arrows indicate open phagophores in the vicinity of ER and mitochondria (M), which contain GFP-WIPI2b RERE. See also Figures S4 and S5 and Table S1.

Figure 5

WIPI2 Function in Amino Acid Starvation Requires Atg16L1 and PI3P Binding (A) GFP, siRNA-resistant GFP-WIPI2b, or GFP-WIPI2b RERE was expressed in HEK293A cells treated for 72 hr with either RISC-free (RF) or WIPI2 siRNA. Cells were left in full medium (F) or starved for 2 hr with EBSS (S) or EBSS with BafA (B) before immunoblot analysis. (B) Statistical analysis of (A). SEM for n = 3. Statistical analysis was performed by one-way ANOVA with Tukey’s posttest. ^∗p < 0.05. (C) GFP, siRNA-resistant GFP-WIPI2b, GFP-WIPI2b RERE, GFP-WIPI2b FTTG, or GFP-WIPI2b FTTG RERE was expressed in HEK293A cells treated for 72 hr with WIPI2 siRNA. Cells were left in full medium (F) or starved for 2 hr with EBSS (S) or EBSS with BafA (B) before immunoblot analysis. (D) Statistical analysis of (C) was performed by one-way ANOVA with Tukey’s posttest. The SEM for LC3 (n = 2) and p62 (n = 4) are shown. ^∗p < 0.05. (E) siRNA-resistant GFP-WIPI2b, GFP-WIPI2b RERE, GFP-WIPI2b FTTG, or GFP-WIPI2b FTTG RERE was expressed in HEK293A cells treated for 72 hr with WIPI2 siRNA. Cells were starved in EBSS for 2 hr without or with BafA, fixed, and labeled, and LC3 was visualized by confocal microscopy. Scale bars, 10 μm. (F) Quantification of WIPI2 puncta per cell from (E). SEM from 10 cells per condition; ^∗∗∗p < 0.001 using one-way ANOVA. (G) Statistical analysis of LC3 puncta from (E) with GFP control (not shown in E). SEM for n = 3. Statistical analysis was performed by one-way ANOVA with Dunn’s posttest t test. ^∗p < 0.05. See also Table S1.

Figure 6

Plasma Membrane Localized WIPI2b Promotes LC3 Lipidation through Binding Atg16L1 Independently of FIP200 (A) HEK293A cells transiently expressing the indicated mCherry constructs were treated in either full medium (F), starvation medium (S), or starvation medium with wortmannin (W) for 2 hr before immunoblot analysis. (B) Statistical analysis of (A) was performed by one-way ANOVA with Tukey’s post hoc test. SEM for n = 3. ^∗p < 0.05. (C) Complexes from HEK293A cells transiently expressing the indicated mCherry constructs were immunoprecipitated using RFP-Trap before analysis by immunoblotting. (D) 2GL9 cells transiently expressing the indicated mCherry constructs treated as in (A) were fixed and visualized by confocal microscopy. (E) CLEM of MCF7 cells expressing GFP-LC3 and mCherry-WIPI2b CAAX. Bright-field and confocal image merged (left), confocal of expressing cell (middle), low-magnification TEM of cell of interest (right). Boxed area indicates plasma membrane region showing colocalization of GFP-LC3 and mCherry-WIPI2b. Scale bar, 10 μm (n = 3). (F) High-magnification TEM showing plasma membrane region boxed in (E). Magnified insets, in top right, show small vesicular clusters under the plasma membrane detected in mCherry-WIPI2b CAAX, GFP-LC3 expressing cells but not in untransfected cells from a control experiment. (G) HEK293A cells treated with either RISC-free (RF), Atg16L1 siRNA, or FIP200 siRNA for 72 hr before transfection with HA-WIPI2b-CAAX were incubated in full medium (F), EBSS (S), or EBSS with wortmannin (W) for 2 hr before immunoblot analysis. Please note that all WIPI2 constructs are FTTG mutants. See also Figure S6 and Table S1.

Figure 7

Atg16L1 Mutants Unable to Bind WIPI2 Cannot Rescue LC3 Lipidation or LC3 Recruitment to Salmonella in Atg16L1^Δ/Δ MEFs (A) Atg16L1^Δ/Δ MEFs were transiently transfected with either mock, FLAG-tagged Atg16L1 WT, ERER, or DRDR. After 2 hr in EBSS, cells were fixed and labeled with anti-LC3 and anti-FLAG antibodies and visualized by confocal microscopy. Scale bars, 20 μm. (B) Statistical analysis of (A) was performed using one-way ANOVA with Dunn’s posttest. ^∗p < 0.05. SEM for n = 3. (C) Atg16L1^Δ/Δ MEFs were transiently transfected with either mock, FLAG-tagged Atg16L1 WT, E226R E230R (ERER), or D237R D239R (DRDR) before analysis by immunoblotting. (D) Statistical analysis of (C) was performed by one-way ANOVA with Tukey’s post hoc test. SEM for n = 3. ^∗p < 0.05. (E) HEK293A cells were treated with either RISC-free control or WIPI2 siRNA before infection with Salmonella (moi = 100) for 1 hr, labeled with anti-LC3, WIPI2, and p62 antibodies, and followed by confocal analysis. Scale bars, 5 μm. (F) Statistical analysis for (E) was performed using an unpaired Student’s t test. ^∗p < 0.05. SEM for n = 3. (G) Atg16L1^Δ/Δ MEFs were transiently transfected with FLAG-Atg16L1 WT, FLAG-Atg16L1 ERER, or FLAG-Atg16L2 DRDR 24 hr before being infected with Salmonella (moi = 25) for 1 hr, labeled with anti-LC3, anti-p62, and anti-FLAG antibodies, and followed by analysis by confocal microscopy. Scale bars, 5 μm. (H) Statistical analysis of (G) was performed by one-way ANOVA with Dunn’s post hoc test. SEM for n = 4. ^∗p < 0.05. See also Figure S7.