As a starting point, we characterized lymphocyte populations in human atherosclerotic plaques obtained by endarterectomy, a surgical procedure to remove the atheromatous plaque from carotids (31). Donor's characteristics are presented in Table 1 (section Materials and Methods). As shown in Figure 1A, in order to better characterize Tregs diversity, each carotid artery has been divided into an adjacent atherosclerotic plaque region (APR) and atherosclerotic plaque (AP), using peripheral blood mononuclear cells (PBMC) as a control of circulating immune cells. We performed a multiparameter flow cytometry analysis as described in Supplementary Table 1.

We estimated the frequency (%) of leukocyte populations (CD45+), CD4+ T cells (CD4+CD8–), CD8+ T cells (CD8+CD4–), conventional T (Tconv) cells (CD127+/–FOXP3–/CD4+ T cells), and Tregs (CD127^lowFOXP3+/CD4+ T cells) by flow cytometry using the gating strategy shown in Supplementary Figure 1. We observed a significant decrease of CD45+ cells in APR compared to PBMC and a significant decrease of CD8+ T cells in AP compared to APR, while CD4+ cells were comparable among the experimental groups. Interestingly, the frequency of Tregs was significantly increased in APR and in AP, when compared to PBMC, suggesting a higher frequency of Tregs in the atherosclerotic plaque microenvironment (Figure 1B). We did not observe any differences in Tregs frequency between AP and APR, indicating that infiltration of Tregs takes place also in the adjoining plaque region.

Recent observation highlighted the pivotal role of the expression of OX40, a member of the TNFR/TNF superfamily, on activated CD4+ and CD8+ T cells (32), in supporting Tregs fitness in mouse models of homeostatic proliferation and colitis and in promoting the expansion of stable and suppressive Tregs in human cancers (33–35). Based on these findings, we investigated whether Tregs and Tconv in AP were characterized by higher levels of OX40 expression (Figure 1C). The geometric mean fluorescence intensity (gMFI) of Tconv-OX40+ was significantly increased in AP if compared to PBMC. Furthermore, we found a significant increment of the frequency and the gMFI of Tregs-OX40+ in AP and APR when compared to PBMC (Figure 1C). These results suggest that Tregs in the atherosclerotic plaque microenvironment expressed higher levels of OX40, possibly contributing to Tregs expansion.

It has been recently demonstrated that, besides inducing a huge frequency of Tregs, OX40 expression was associated with fatty acid accumulation and with the promotion of selective proliferation of lipid-laden Tregs (36). Based on this evidence, we stained the cells with BODIPY, a cell-membrane-permeable fluorophore specific for neutral lipid stores; however, we did not find any significant difference in the intracellular lipid content of CD8+ T cells, Tconv, and Tregs derived from both APR and AP when compared to PBMC (Figure 1D).

Overall, these results show that a significant fraction of Tregs are found in APR and even more in the AP site when compared to PBMC, suggesting Tregs-mediated modulation of inflammation at the atherosclerotic plaque and its associated region.

To confirm our results in vivo, we took advantage of the ApoE-KO mouse, one of the most widely used models to study atherosclerosis (37). ApoE is a glycosylated protein, mainly bound to plasma lipoproteins but also expressed in hematopoietic stem and progenitor cells (HSPC) (37–39). In order to better resemble the human cardiovascular disease and to speed up plaque progression, we treated ApoE-KO mice with aldosterone at a dose of 6 μg/kg/day. Such concentration is able to raise serum aldosterone levels to a range which promotes atherosclerosis, without inducing hypertension (27, 30, 40). Aldosterone promotes rapid lipid accumulation in the aortic arch section of ApoE-KO mice, as shown in Figure 2A. In order to estimate the frequency of leukocytes (CD45+), CD4 T cells (CD4+CD3+CD45+), Th1 (CXCR3+CCR6–CD4+), Th17 (CCR6+CXCR3–CD4+), and Tregs (FOXP3+CD4+), we performed multiparameter flow cytometry (Supplementary Table 2) on splenocytes and aortic arches obtained from 8-week-old ApoE-KO mice treated with aldosterone or vehicle for 4 weeks (the gating strategy is shown in Supplementary Figure 2A).

We first observed a significant increase of CD45+ cells and a significant decrease of CD4+ T cells in splenocytes of ApoE-KO mice treated with aldosterone (Figure 2B). Gated on CD4+ T cells, we checked the frequency of Th1 cells (CD4+CXCR3+), Th17 cells (CD4+CCR6+), and Tregs (CD4+FOXP3+), and we found a significant decrease of Th17 and a significant increase of Tregs in ApoE-KO mouse spleens treated with aldosterone (Figure 2B). However, we did not observe significant differences of Th17 and Tregs percentages in aortic arches. The calculation of the absolute cell numbers (%Cells of interest × CD4 × 100) of different T-cell populations revealed a statistically significant decrease in Th1 cells and Th17 and a significant increase of Tregs in spleens of ApoE-KO mice treated with aldosterone (Figure 2C). In agreement with previous results, the absolute cell number in aortic arches does not show any significant difference. Overall, these data show that Tregs accumulate in the spleens of ApoE-KO mice under the atherosclerotic development condition (with aldosterone treatment), whereas no changes in the presence of Tregs were observed in ApoE-KO mouse atherosclerotic plaque.

In order to investigate the possible role played by autophagy in lymphocyte homeostasis and in T-cell polarization, we analyzed the levels of microtubule-associated proteins 1A/1B light chain 3B (LC3), as a marker of autophagy in splenocytes and aortic arches obtained from 8-week-old ApoE-KO mice in the presence or absence of aldosterone. In particular, we detected the phosphatidylethanolamine-conjugated form of LC3, named LC3-II, which is closely correlated with the number of autophagosomes and serves as a good indicator of autophagosome formation (41). We then calculated gMFI LC3-II by flow cytometric analysis, and we observed a significant decrease of LC3-II in Th1 and Tregs in ApoE-KO mouse spleens treated with aldosterone (Figure 2D); however, similar to what was observed before, we did not find any difference in aortic arches of ApoE-KO mice in the presence or absence of aldosterone. A decrease in LC3-II levels could be an indication of (i) impaired autophagy, (ii) enhanced autophagic flux, or (iii) decreased LC3 transcription. We performed additional experiments on isolated lymphocytes to investigate this aspect.

Based on our results and previous studies about Tregs differentiation during atherosclerotic plaque progression, we estimated the frequency of Tregs (FOXP3+CD4+ T cells) by flow cytometry in splenocytes derived from 8-week-old C57BL/6 wild-type (wt) and ApoE-KO mice treated or not with aldosterone. In line with previous literature (42), we observed a reduction of the percentage of Tregs in ApoE-KO mice compared with wt mice (Figure 3A). Surprisingly, we found that the frequency of Tregs (CD4+FOXP3+ gated on CD4+ T cells) in splenocytes was significantly increased in ApoE-KO mice when treated with aldosterone (Figure 3A). To clarify if the differences observed derive from aldosterone treatment itself or from the atherogenic-prone background, naïve CD4 T cells from wt mice were cultured in the presence of aldosterone for 96 h and with TGFβ to stimulate Tregs differentiation. However, as shown in Supplementary Figures 2B–D, no significant differences have been observed upon aldosterone treatment either in %CD4 T cells or in %Tregs, suggesting that the genetic background of ApoE-KO mice, rather than aldosterone treatment, is the determinant of the differential percentage of circulating Tregs. Although this is an interesting result, for subsequent in vitro experiments, we isolated cells from ApoE-KO mice that were not treated with aldosterone, in order to focus only on the genetic background. Our data, indeed, suggest that the aldosterone effect is presumably not directly interfering with immune cells but rather with the hormonal response in the animal that we exploited solely to speed up plaque formation (43). Hereby, we focused on the differences in Tregs frequencies between wt and ApoE-KO genetic background.

Tregs differentiation and expansion can occur extrathymically from naïve CD4+ T-cell precursors upon antigenic stimulation (44). Given the differences between wt and ApoE-KO mice in the frequency of Tregs, we first investigated the differences either in expanding Tregs starting from total CD4+ T cells or in the differentiating Tregs starting from naïve CD4+ T cells obtained from wt and ApoE-KO mice. Total CD4+ T cells (>5% FOXP3+), taken as a heterogeneous population derived from wt and ApoE-KO mouse spleens, were cultured for different times (24, 48, and 96 h) with interleukin-2 (IL2) in the presence or absence of TGFβ. Since CD4+ T cells include naïve CD4+ T cells, the precursors of Tregs, we could not determine the difference in proliferating Tregs or in induced Tregs. However, we observed a significant Tregs expansion in wt mice, already detected after 24 h of TGFβ treatment, reaching a higher extent after 96 h in culture (Figures 3B,C). In contrast, the treatment with TGFβ of ApoE-KO CD4+ T cells did not show any Tregs expansion. In line with this observation, the frequency of Tregs induced by TGFβ in wt was significantly much higher with respect to ApoE-KO cells. Calculation of Tregs absolute cell number (%Tregs × %CD4 × 100) shows how Tregs derived from wt animals were responsive to TGFβ stimulus differently from ApoE-KO cells (Supplementary Figure 3A). In order to quantify flow cytometry data, we also evaluated the geometric mean of FOXP3 which showed a significant reduction of intensity in ApoE-KO mice at 48 and 96 h, in agreement with the previous results (Supplementary Figure 4).

Considering that naïve CD4+ T cells are the precursors of both effector and memory T-cell subsets and that Tregs can be generated in the thymus or can differentiate from peripheral naïve CD4+ T cells (45), we stimulated Tregs polarization by culturing naïve CD4+ T cells obtained from wt and ApoE-KO mouse spleens (46). In particular, we cultured naïve CD4+ T cells in the presence of IL2 for 24 and 96 h, adding or not TGFβ and maintaining the same conditions used for CD4+ T cells. We found that TGFβ treatment did not induce ApoE-KO CD4+ Tregs differentiation, while wt cells respond to the treatment at both 24 and 96 h (Figures 3D,E). Thus, the frequency of Tregs induced by TGFβ in wt was significantly much higher with respect to ApoE-KO cells. To better appreciate the differences between wt and ApoE-KO, we calculated the Tregs absolute cell number. In accordance with the data previously shown, Tregs differentiation from wt mice cells was detectable after 24 h of TGFβ treatment, reaching the highest levels after 96 h. Although the absolute cell number of Tregs differentiation in ApoE-KO mice increased upon TGFβ treatment at both 24 and 96 h, the extent was much lower with respect to wt counterparts, thus suggesting a deficiency in TGFβ-induced maturation of ApoE-KO Tregs (Supplementary Figure 3B). In summary, our results show that Tregs differentiation in ApoE-KO is significantly impaired compared to wt counterparts.

Since autophagy is an important mechanism protecting Tregs lineage and survival integrity, we tested the hypothesis that autophagy might affect Tregs differentiation in ApoE-KO mice (18). In order to determine if autophagy was related to Tregs differentiation and to analyze its contribution in the defective Tregs differentiation observed in ApoE-KO mice, we first investigated the kinetics of autophagy in TGFβ-induced Tregs derived from naïve CD4+ T cells. Cells were cultured in Tregs-polarizing conditions (IL2 treatment with or without TGFβ) and analyzed at two time points: 24 and 96 h. The autophagy flux has been analyzed by flow cytometry comparing the LC3-II amount in the presence and absence of the lysosomal inhibitor bafilomycin (Baf), added 4 h before the end of the experiment (47). In order to evaluate the autophagic flux of CD4+ T cells, we calculated the LC3-II ratio between Baf-treated and untreated cells. On expanded Tregs gated on CD4, we did not observe any significant difference in the LC3-II ratio analyzed at two different time points: 24 and 96 h (data not shown). We therefore repeated the analysis during Tregs differentiation induced from naïve CD4+ T cells isolated from wt and ApoE-KO mice. We observed that the LC3-II ratio significantly increased in wt Tregs upon TGFβ treatment at 24 h, while no difference was observed in ApoE-KO Tregs (Figure 4A). These results indicate that TGFβ induces autophagy in wt but not in ApoE-KO Tregs. In particular, by blocking the autophagosome–lysosome fusion by Baf, 4 h before the end of the experiment, ApoE-KO mice did not show any significant increase in LC3-II ratio when challenged with TGFβ, suggesting a block of autophagic machinery during Tregs differentiation in ApoE-KO mice (Figure 4A).

We previously showed a reduction in LC3-II signal in ApoE-KO mouse spleen treated with aldosterone (Figure 2A). In order to exclude any commitment of aldosterone in LC3 lipidation in Tregs, we analyzed LC3-II-positive cells during Tregs differentiation by treating cells in the presence or absence of aldosterone at the same dose used for the in vivo experiment. After 96 h of Tregs differentiation, aldosterone did not interfere with LC3 lipidation (Supplementary Figure 5), suggesting that all the differences that we observed in the ApoE-KO mouse spleen, derived from the genetic background and not from the aldosterone treatment.

Due to the fact that Tregs derived from ApoE-KO mice seem to be autophagy impaired, we pharmacologically modulated autophagy in sorted wt naïve CD4+ T cells (CD4+CD62L+CD25–) under a TGFβ stimulus for the subsequent experiments. TGFβ has been reported to induce autophagy through the SMAD 2/3 pathway in different cell lines and by the increase in the mRNA levels of autophagic genes such as BECLIN1, ATG5, and ATG7 (48, 49). Based on this knowledge, we performed RTqPCR at either 24 or 96 h by culturing naïve CD4+ T cells in IL2 in the presence or absence of TGFβ, in order to evaluate the mRNA levels of Foxp3 and autophagic genes such as p62, LC3A, and LC3B. The obtained results showed an increase of mRNA levels of Foxp3 after TGFβ and IL2 treatment at both 24 and 96 h (Figure 4B). As expected, the inhibition of autophagy by Baf or chloroquine, a lysosome acidification inhibitor, does not interfere with the transcriptional activation of Foxp3 induced by TGFβ. We then investigated the mRNA levels of autophagic genes after 24 h of TGFβ and IL2 treatment; we did not observe any significant increase of p62, LC3A, and LC3B. Interestingly, at 24 h, the addition of Baf and chloroquine led to a significant increase of LC3A mRNA (Figure 4B, top), probably due to feedback mechanism of cells trying to overcome autophagy inhibition. The mRNA expression of Foxp3, already boosted by TGFβ at early time points, was remarkably increased at 96 h, as well as the mRNA expression of autophagy-related genes (p62 and LC3A), confirming the transcriptional activation of autophagy by TGFβ (Figure 4B, bottom).

Autophagy is a crucial process controlling the turnover of proteins and organelles. In our experiments, we noticed that the percentage of Tregs (CD4+FOXP3+) was significantly increased after Baf treatment when added during the last 4 h of differentiation (Figures 5A,B) even if the same treatment did not affect the transcription of Foxp3 gene. Therefore, we investigated whether FOXP3 levels were affected by autophagy. The main pathway through which FOXP3 is degraded relies on the ubiquitination on lysine-48 and its subsequent proteasome degradation. However, several evidence reported that the natural p300 inhibitor, garcinol, can induce FOXP3 degradation via a lysosome-dependent pathway (50, 51). In order to investigate more in depth the potential autophagy-mediated FOXP3 degradation, we cultured sorted wt naïve CD4+ T cells (CD4+CD62L+CD25–) obtained from mouse spleens in the presence or absence of TGFβ and IL2 for 96 h, and we treated them with Baf or chloroquine for the last 4 h, in order to block the last steps of the autophagic flux. By flow cytometry analysis, we observed that the treatment with autophagy inhibitors led to an increase of FOXP3 in unstimulated cells after 96 h in culture upon 4-h treatment with Baf or chloroquine (Figure 5C), while the differences were abolished after TGFβ treatment, presumably because, after 96 h of stimulation, the differentiation was complete, autophagy shut down, and Foxp3 gene upregulated hundred-folds by the effect of the cytokine (as shown in Figure 4B). Although further experiments are needed to confirm the autophagy-mediated FOXP3 turnover, these data suggest that this transcription factor can be an autophagy target.

We additionally investigated this aspect in ApoE-KO mice, particularly by culturing mechanically sorted naïve CD4+ T cells in the presence or absence of Baf and TGFβ. However, we did not observe any FOXP3 accumulation with only Baf treatment (data not shown) probably due to both lack of Tregs differentiation upon TGFβ treatment and, as previously shown in Figure 4A, autophagy being blocked in ApoE-KO mice at both 24 and 96 h.

Finally, we modulated autophagy on sorted wt naïve CD4+ T cells (CD4+CD62L+CD25–) under a TGFβ stimulus in order to ascertain the involvement of autophagy in Tregs differentiation. We used for 24 h Baf or 3-methyladenine (3MA) (a PI3 kinase inhibitor) to inhibit autophagy or, alternatively, rapamycin (RAPA) [the inhibitor of the main physiological autophagy suppressor mammalian target of RAPA (mTOR)] to boost autophagic flux (52, 53). As shown in Figures 6A,B, both Baf and 3MA were able to inhibit differentiation of Tregs induced by TGFβ, while autophagy activation by RAPA has no effects on Tregs differentiation, presumably because autophagy was already activated by TGFβ. We obtained the same results by quantifying the percentage of FOXP3+ cells (Figure 6A) or the absolute Tregs cell number (Figure 6B). Finally, to better appreciate the results, we normalized the percentage of FOXP3 in TGFβ-treated or untreated samples, and we observed that autophagy inhibition by 3MA led to a significant decrease of Tregs differentiation (Figure 6C). Altogether, these results suggest that the modulation of autophagy impacts Tregs differentiation.

Peripheral blood (PB), adjacent APR, and AP samples were obtained from nine patients undergoing carotid endarterectomy (CEA) (63) affected by different pathologies representing atherosclerosis risk factors. Patient's characteristics are shown in Table 1, displaying the percentage of occlusion (surgery-side) and associated pathologies.

PBMC were isolated from the PB of CEA patients by density gradient centrifugation with Lympholyte (Cedarlane Laboratories USA, cat. #CL5020) and collected in complete RPMI Dutch-modified medium containing 10% FBS (Gibco), 2 mM l-glutamine (Sigma-Aldrich), penicillin/streptomycin (Gibco), non-essential amino acids, sodium pyruvate (EuroClone), and 50 μM 2-mercaptoethanol (Sigma-Aldrich).

Mononuclear cells were extracted from APR and AP. Fragments of APR and AP were digested with Collagenase IV (C5138 Sigma) (2 mg/ml) + DNase I (0.1 mg/ml) in RPMI for 1–2 h at 37°C. Single-cell suspensions were obtained by disrupting the fragments with a syringe plunger over a cell strainer and pelleted through a 40% isotonic Percoll solution. Human studies were performed in accordance with the General Data Protection and Regulation (GDPR) and ethical guidelines of the 1975 Declaration of Helsinki and were approved by the Institutional Ethical Committee of the University of Rome “La Sapienza” (authorization: RIF. 3720_2015/23.07.2015 Prot. 2372/2015).

ApoE-KO mice were kindly provided by the Laboratory of Cardiovascular Endocrinology, IRCCS San Raffaele (Rome, Italy), maintained at Animal Facility Castel Romano (Rome) under protocols approved by the Italian Ministry of Health (493/2016-PR).

In 9-week-old male mice deficient for ApoE (ApoE-KO), osmotic minipump (Alzet model 1004) containing vehicle (ethanol/saline) or aldosterone (6 μg/mouse/day) was subcutaneously placed, and mice were fed with a proatherogenic HF diet (Harlan Teklad TD.88137) for 4 weeks (43). This dose of aldosterone was chosen on the basis of published studies demonstrating resultant serum aldosterone levels in physiologically relevant range, no change in blood pressure, and reproducible increases in atherosclerosis (30). At the time of sacrifice, animals were perfused with phosphate-buffered saline (PBS), and aortic valves were embedded in an optimal cutting compound (OCT) and collected at −80°C.

Cryosections of embedded aortic roots at the site where all three aortic valve leaflets could be visualized were taken at 10-μm intervals. Sequential sections were stained with Oil-Red O (ORO) in the aortic root at the level of the aortic valve.

To study the autophagy process, 8- to 12-weeks-old male C57BL/6J mice (Charles River Laboratories) housed at the animal facility of the Department of Anatomy, Histology, Forensic Medicine and Orthopaedics (DAHFMO), Unit of Histology and Medical Embryology (Sapienza University of Rome), were used. C57BL/6J mice were killed by CO₂ euthanasia.

Eight- to ten-weeks-old male C57BL/6N mice (Taconic), housed at the animal facility at the Danish Cancer Society Research Center (Copenhagen, Denmark), were used to study autophagy modulation (e.g., Baf, 3MA, and RAPA treatments) and FOXP3 accumulation (RTqPCR and cytofluorometry analyses).

Characterization of ApoE-KO mouse spleens was performed in collaboration with the Laboratory of Cardiovascular Endocrinology, IRCCS San Raffaele (Rome, Italy). Splenocytes were obtained by spleen mechanical rupture with a syringe plunger followed by incubation with ACK (Lonza, Alpharetta, GA, USA, cat. no. 10-548E) for 5 min at room temperature (RT), and after washing, cells were filtered on a 70-μm cell strainer. The aortic arches were separated from the apical portion of the heart and were digested with collagenase IV (C5138 Sigma) (2 mg/ml) + DNase I (0.1 mg/ml) in RPMI 1640 for 1 h at 37°C.

Splenocytes were obtained by spleen mechanical rupture with a syringe plunger followed by incubation with sterile ddH₂O for 10 s, blocking and washing with PBS 10×. CD4+ T cells were purified from splenocytes by using a CD4+ T-cell isolation kit (130-104-454 Miltenyi Biotec) and naïve CD4 T cells purified from splenocytes by using a naïve CD4+ T-cell isolation kit (130-104-453 Miltenyi Biotec) according to the manufacturer's instructions. Naïve CD4+ T cells and CD4+ T cells purified were cultured on 3 μg/ml of anti-CD3 (145-2C11) precoated wells (96-u bottom multiwell) at 37°C, at different time points (24, 48, and 96 h). Cells were plated in RPMI 1640 (R0883 Sigma) supplemented with 10% FBS, 2 mM l-glutamine, 100 U/ml penicillin, 100 μg/ml streptomycin, 10 mM HEPES, 50 μM 2-mercaptoethanol, 1 mM pyruvate, and 15 μg/ml gentamicin, in the presence of 2 μg/ml soluble anti-mouse CD28 (37.51 monoclonal antibody) and of human recombinant IL2 (354043 BD Bioscience) at 100 U/ml in the presence or absence of 2 ng/ml mouse recombinant TGFβ (14-8342 Affymetrix eBioscience). In some sets of experiments, cell cultures were treated with modulators of autophagy: Baf A1 (100 nM) (B1793 Sigma), chloroquine (40 μM) (C6626 Sigma), 3-methyladenine (5 mM) (M9281 Sigma), RAPA (100 nM) (R0395 Sigma). Aldosterone (10⁻⁸ M) treatment was used, maintaining the same conditions of the in vitro experiment (64).

Cells obtained from human atherosclerotic plaques and ApoE-KO mice were analyzed following the complete panel of antibodies (Tables S1, S2). Surface staining was performed by incubating the cells with selected antibodies at 4°C for 30 min in PBS. Intracellular staining of cytokines and transcription factors was performed with Foxp3 Transcription Factor Staining Buffer (eBioscience) in accordance with the manufacturer's instructions. Dead cells were excluded using Fixable Viability Dye eFluor® 780 (eBioscience). Human samples were acquired on the BD LSRFortessa cell analyzer (BD Biosciences), while mouse samples were run on the BD LSRFortessa X20 (BD Bioscience).

Regarding in vitro experiments, intracellular FOXP3 and LC3-II staining was performed using PFA 4% and 90–100% Met-OH for fixation and permeabilization, according to Cell Signaling protocol. Dead cells were excluded by staining with NIR (Live Dead Fixable Near-IR Dead Cell stain kit; Invitrogen) according to the manufacturer's instructions. Samples were run on a Cyan cytometer (Beckman Coulter).

Autophagic flux was measured by FACS analysis using antibody against LC3-II-PE (Cell Signaling clone D-11), in the presence or absence of the modulators of autophagy as described above.

Samples were analyzed with FlowJo software, version 10.5.3.

Naïve CD4+ T cells were stained with the antibodies CD4 eFluor-450, CD25 APC, and CD62L PECy7 and were sorted by using FACS Melody (BD).

Total RNA was extracted using the NucleoSpin RNA kit (740955.250 Macherey-Nagel). RNA concentration and purity were measured by NanoDrop (NanoDrop™ 2000/2000c spectrophotometers). Quantitative PCR was performed with 2 μl of cDNA, 0.4 μl of each primer (10 μmol/μl), and 10 μl of PowerUp SYBR Green qPCR Master Mix (Thermo Fisher Scientific) and analyzed with the QuantStudio software (Applied Biosystems).

The cycle threshold values were used to calculate the normalized expression of FOXP3, LC3A, LC3B, and p62 against β-actin.

The sequences of primer pairs are listed below:

mFOXP3f: AAT AGT TCC TTC CCA GAG TTC

mFOXP3r: GGT AGA TTT CAT TGA GTG TCC

mLC3Af: TTG GTC AAG ATC ATC CGG C

mLC3Ar: GCT CAC CAT GCT GTG CTG G

mLC3Bf: CCC ACC AAG ATC CCA GTG AT

mLC3Br: CCA GGA ACT TGG TCT TGT CCA

mSqstm1f: AAT GTG ATC TGT GAT GGT TG

mSqstm1r: GAG AGA AGC TAT CAG AGA GG

mActinf: CAC ACC CGC CAC CAG TTC GC

mActinr: TTG CAC ATG CCG GAG CCG TT.

Statistical analysis was performed using the version 7.0 Prism software (GraphPad). A two-tailed paired Student's t-test was used to analyze human data to compare PBMC, APR, and AP in the same sample. The two-tailed unpaired Student's t-test was applied to compare data from Th1, Th17, and Tregs in ApoE-KO vs. aldosterone. Two-way analysis of variance (ANOVA) was performed for in vitro analysis in which we compared wt vs. ApoE-KO mice upon TGFβ treatment. The two-tailed unpaired Student's t-test was applied to compare treatment with autophagy modulators when only one group was analyzed (wt). One-way ANOVA was performed for the in vitro experiment to analyze autophagic flux upon aldosterone treatment during Tregs differentiation. Every in vitro assay was performed in duplicate or triplicate, when possible. The number of repetitions is indicated in the figure legend for all experiments. In all graphs, bars show means ± SEM. In all tests, P < 0.05 was considered statistically significant.

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.