All experimental procedures used in this work were approved by the Ethics Committee on Animal Use (CEUA) of the Federal University of São Paulo, protocol 1073090614.

Tissue culture-derived trypomastigotes (TCT) of the T. cruzi Y strain were collected from the culture supernatants after 5 days after infection of LLCMK₂ epithelial cells (monkey kidney epithelial cell line, ATCC© CCL-7™, VA, USA). Cells were maintained in low-glucose DMEM supplemented with 10% fetal bovine serum (FBS) (Invitrogen, CA, USA) at 37°C in a humidified 5% CO₂ atmosphere. THP-1 (human peripheral blood monocyte cell line, ATCC© TIB-202™, VA, USA) cells were cultured in RPMI-1640 medium supplemented with 10% FBS and maintained at 37°C in a humidified 5% CO₂ atmosphere. Cells were tested for Mycoplasma contamination by using the polymerase chain reaction (PCR) methodology (Uphoff and Drexler, 2002). The THP-1 monocytes were induced to differentiate into macrophages by the addition of phorbol myristate acetate (50 ng/mL) (Calbiochem, CA, USA) for 24 h in serum-free RPMI 1640. To determine the number of infected cells and the number of intracellular parasites, cells were cultured on circular glass coverslips and subsequently stained with Giemsa.

EVs from trypomastigotes (EV-TY) were obtained by incubation of parasites for 2 h in DMEM containing 2% glucose at 37°C and 5% CO₂ and purified by size-exclusion chromatography (SEC), as previously described (Ribeiro et al., 2018). To obtain EVs from THP-1 infected and non-infected macrophages (respectively EV-THP-1inf and EV-THP1) were incubated with T. cruzi trypomastigotes at a 1:10 ratio (1 mL) for 4 h at 37°C/5% CO₂ in RPMI 1640 containing 10% ultracentrifuged FBS to remove serum EVs. After infection, the THP-1 macrophages were washed three times with PBS, and then maintained in the same fresh medium for the production of EVs. Controls included THP-1 cells without T. cruzi infection. EVs were then recovered at the indicated times by differential ultracentrifugation of culture supernatants. Briefly, the supernatants were submitted to 10 min at 500 × g, followed by 10 min at 3,000 × g and 15 min at 8,000 × g to remove cells and cellular debris. EVs were then pelleted at 100,000 × g for 1 h using a T-890 fixed angle rotor (Thermo Fisher Scientific, MA, USA) as previously described in MISEV guideline (Théry et al., 2018).

The obtained EVs were characterized by NTA analysis to determine concentration and size using NanoSight NS300 (Malvern Instruments, Worcestershire, UK) equipped with a 405 nm laser and coupled to a CCD camera. Data were analyzed using NTA software (version 2.3). Each sample diluted (1:10) in PBS was analyzed in triplicate; and loaded into the instrument for 30 s at 20 frames per second with the camera level set to 14.

THP-1 cells infected or not with T. cruzi, and THP-1 cells treated with EV-TY were fixed in a 2.5% glutaraldehyde solution as reported elsewhere (Nogueira et al., 2015). The cells were post fixed with osmium tetroxide, treated with tannic acid, and dehydrated with ethanol. Samples were observed in a Field Emission FEI Quanta 250 FEG scanning electron microscope (FEI, OR, USA).

EVs samples containing 10 μg of protein, quantified by Micro BCA Assay kit (Thermo Fisher Scientific, MA, USA), were resolved by 12% SDS-PAGE and transferred to nitrocellulose membranes using standard procedures. The presence of exosome proteins and parasite surface proteins was evaluated by incubating membranes with primary antibodies against CD63, CD9, MHC II (Thermo Fisher Scientific, MA, USA) and the serum of a rabbit immunized with the extract of T.cruzi TCT membranes (Schenkman et al., 1991). Detection was achieved using horseradish peroxidase-conjugated anti-mouse or anti-rabbit (KPL Antibodies Seracare, MA, USA) secondary Abs and visualized with Pierce ECL Western Blotting Substrate (Thermo Fisher Scientific, MA, USA).

The CHO reporter cell lines (CHO/CD14, CHO/CD14/TLR-2, and CHO/CD14/TLR-4) were generated as described (Lien et al., 1999). These reporter cell lines contain a human CD25 gene reporter under the control of the E-selectin promoter, which contains an NF-κB-binding site (Delude et al., 1998; Lien et al., 1999 and Campos et al., 2001). All CHO reporter cell lines were grown in Ham's F-12 medium containing 10% FBS, 10 μg/ml ciprofloxacin, and 400 units/ml hygromycin B. Cells were plated at a concentration of 10⁵/well in 24-well tissue-culture dishes. Cells were incubated with EV-THP-1, EV-THP-1 infected (EV-THP-1 inf) and EV-TY. Medium alone, 100 ng/ml LPS (from Escherichia coli serotype 055: B5; Sigma-Aldrich, MI, USA), and UV-killed Staphylococcus aureus at a ratio of S. aureus/cell of 500:1 (American Type Culture Collection 12.692), were used as controls. After 24 h of stimulation, cells were stained with PE-labeled anti-CD25 (mouse MAb to human CD25, PE conjugate; Caltag Laboratories, CA, USA). The cells were examined by flow cytometry (BD Biosciences, NJ, USA), and analyses were performed using Cell Quest software (BD Biosciences, NJ, USA) (Campos et al., 2001).

TLR2- or TLR4-transfected CHO/CD14 cells were grown on 13 mm diameter glass coverslips in a 24-well dish and washed twice with DMEM/F12 medium (with antibiotics). Cells were incubated with culture supernatant or EV-TY (10⁵ and 10⁶particles/well) for 30 min, at 37°C, in RPMI-10% FBS. These cells were infected with TCTs (1:10, host cell: parasite ratio), for 1 h at 37°C, and then washed twice with RPMI without FBS. Non-adherent parasites were removed by addition of Lymphoprep (Axis-Shield, Norton, MA) to the cell layers, followed by two washes with PBS. The cells were incubated with RPMI-10% FBS for 18 h, at 37°C, or immediately fixed with methanol and stained with Hoechst fluorescent dye (Molecular Probes, Invitrogen Co., Carlsbad, CA). All experiments were performed in triplicate, and 24 photos of each replicate were made using a digital video-imaging fluorescent inverted microscope (Nikon), enabling the counting of infected and non-infected cells.

To evaluate the gene expression, quantitative reverse transcriptase polymerase chain reaction (qRT-PCR) was used in THP-1 cells untreated as control, or THP-1 incubated with EV-THP-1 inf, EV-TY (10⁸ particles/mL), or infected with trypomastigotes (TY). Total RNA was obtained from macrophages by using TRIzol reagent (Life Technologies, CA, USA). RNA samples were subjected to DNase treatment and cDNA synthesis with the RevertAid First Strand cDNA Synthesis kit (Thermo Fisher Scientific, MA, USA). RNA samples were quantified by UV absorption in a spectrophotometer (Nanodrop 2000c, Thermo Fisher) followed by electrophoresis in 1.5% agarose gels to assess RNA integrity. RNA samples with high quality and integrity were subjected to DNase treatment (RQ1 RNase-free DNase; Promega, Madison, WI, United States) and cDNA synthesis with the RevertAid First Strand cDNA Synthesis kit (Thermo Fisher Scientific, MA, USA). Specific primers for TLR2, TLR4, IL1β, IL6, TNF-α, STAT1, and STAT3 genes were used to analyze gene expression using RT-qPCR; all sequences were from PrimerBank (https://pga.mgh.harvard.edu/primerbank/) (Supplementary Table 1). The expression levels were normalized to those of the GAPDH and Actin-Beta (ACTB) reference genes using the 2^−ΔΔCt cycle threshold method (Schmittgen and Livak, 2008). Differences in the relative expression levels of target genes were determined by com comparison between noninfected cells (as reference samples) and the cells infected or treated with EVs. The gene expression from the reference sample was adjusted to be equal to 1·00. All qRT-PCR procedures were developed following the MIQE guidelines (Bustin et al., 2009).

EVs (~200 μg of protein) from uninfected and infected macrophages (EV-THP-1 and EV-THP-1inf) were concentrated in a Speedvac. For LC-MS/MS, the filter-aided sample preparation (FASP) method was used, following the manufacturer's protocol (Expedeon, San Diego, CA). The samples were reduced by adding 10 mM DTT for 30 min at room temperature (RT) and centrifuging in a spin filter at 14,000× g for 15 min at rt. After washing twice with 8 M urea in 50 mM Tris-HCl buffer, samples were washed again 2× with the urea/Tris-HCl buffer and 3× with 50 mM ammonium bicarbonate. Then, samples were digested with trypsin (Sigma-Aldrich, St. Louis, MO) was performed, as described by Ribeiro et al. (2018). Peptides were eluted from the filter using 0.1% formic acid and subjected to high-resolution LC-MS/MS analysis in a QE Plus Orbitrap (Thermo Fisher Scientific) equipped with a Nanospray Flex Ion Source (Thermo Fisher Scientific). Using a Dionex UltiMate 3000 RSLCnano UHPLC system (Thermo Fisher Scientific), peptides were separated with a PicoFrit column (75-μm ID × OD 360 μm, 25-cm length, New Objective, Woburn, MA) packed in-house with reversed-phase Aqua C18 porous silica (5 μm, 125 Å, Phenomenex). The column was equilibrated before sample injection at a flow rate of 0.5 μL/min with 95% solvent A (100% H₂O, 0.1% formic acid) and 5% solvent B (90% acetonitrile, 0.1% formic acid). Samples were then injected onto the C18 column, and the same equilibration phase was run for 10 min. Elution of the peptides was performed using a linear gradient of solvent B up to 35% for 85 min, followed by a 5-min increase to 95%, where the plateau was maintained for 9 min. The column was then re-equilibrated with 5% solvent B for 10 min before injection of the next sample. An automated 2-h run was programmed into the Xcalibur software (Thermo Fisher Scientific), and each sample was analyzed in technical duplicates. Full scan spectra were collected from the 400–1,600 m/z range. Peptides were not excluded based on charge state, and 1 microscan for both full and MS/MS scans were acquired.

The spectra were searched using Proteome Discoverer (PD) 2.1.1.21 (Thermo Fisher Scientific) and filtered via Percolator with an estimated false-discovery rate (FDR) of 1 against sequences from T. cruzi, human, bovine, human keratin, and porcine trypsin. Parameters for the database search were as follows: 2 and 1 Da for peptide and fragment mass tolerance, respectively, cysteine carbamidomethylation and methionine oxidation as fixed and variable modifications, respectively. The dataset was further processed through Scaffold Q + 4.8.2 (Proteome Software, Portland, OR), merged, and the probability of their peptide assignments and protein identifications was assessed. Files were exported from Scaffold 4.8.2 for further analysis in Scaffold PerSPECtives (Proteome Software). Only peptides with ≥95% probability were accepted. The criteria for human protein identification included detection of at least two uniquely identified peptides and a probability score of ≥99%. The results were further filtered with the following peptide thresholds: Fisher's exact test (p-value) ≤0.001; fold change ≥50% and ≤50%. Gene ontology (GO) annotation was carried out using FunRich (version 3.1.3; http://www.funrich.org/) with the NCBI database (downloaded on 28 March 2019).

All statistical tests were performed using GraphPad Prism version 6 (GraphPad Software, CA, USA). The Mann-Whitney U-test was used to determine differences between two groups. Analysis of variance (ANOVA) followed by Tukey's post-test was carried out to compare multiple groups. The differences were considered significant when p was < 0.05.

Scanning electron microscopy (SEM) micrographs of THP-1-derived macrophages uninfected (EV-THP-1), infected (EV-THP-1 inf), or only treated with EVs from trypomastigotes (EV-TY) showed the presence of round-shaped vesicles with the expected size for exosomes (50–100 nm) and ectosomes (100–200 nm) on the surface of their plasma membrane (Figure 1). Compared to uninfected macrophages and those incubated with EV-TY, infected macrophages released a larger number of vesicles. EVs were isolated from the supernatants of THP-1 macrophages through a series of ultracentrifugation steps. The NTA showed a size distribution of 50–200 nm for all EVs (Supplementary Figure 1). The concentration of vesicles was also measured in the same experiment, revealing an increase in vesicle release by infected THP-1 macrophages (EV-THP-inf) (Figure 2A). In the immunoblotting analysis, the exosomal marker proteins CD63 and CD9 and the surface membrane protein MHC II were detected in EV-THP-1 and EV-THP-1 inf samples (Figure 2B). The presence of parasite surface proteins was only found in the EV-TY group (Figure 2B). The increase in EVs released from infected macrophages is related to presence of parasite from 24 to 72 h. (Figure 3A). However, the EVs release did not appear to increase when the number of parasites augment in infected cells (Figure 3B). After that, cells start to lyse and new trypomastigotes are released in the extracellular milieu.

Next, we evaluated the importance of the interaction of EVs from T. cruzi trypomastigotes with TLRs for the interaction and internalization of the parasite. The CHO reporter cell line contained an inducible NF-κB-dependent promoter driving the surface expression of CD25 (Campos et al., 2001). CHO cells were incubated with different concentrations of (EV-TY) and with EV-THP-1inf or EV-THP-1. The expression of CD25, which indicates activation of NF-κB, was measured by flow cytometry. These EVs did not increase the induction of CD25 expression by CHO/CD14 or CHO/CD14/TLR4 cells (Figure 4). Previous studies using wild-type, TLR2- or TLR4-knockout murine macrophages from C57BL/6 mice (WT, TLR2^−/−, or TLR4^−/− C57BL/6) showed that TLR2 but not in TLR4 was required for production of nitric oxide (NO) or TNF-α following stimulation with EV-TY and activate MAPKs (ERK 1/2, p38 and JNK) (Nogueira et al., 2015). The data presented in Figure 4 confirmed these previous results showing that the expression of CD25 through the activation of NF-κB was induced in CHO/CD14/TLR2, but not CHO/CD14/TLR4, exposed to EV-TY. Importantly, EV-THP-1 and EV-THP-1inf were also found to quantitatively promote the expression of CD25 in CHO/CD14/TLR2 cells, but not TLR4 (Figure 4), indicating that both EVs derived from T. cruzi (EV-TY) and macrophages interact with TLR2, but not TLR4, activating NF-κB. This result also suggested that induction by macrophage EVs was not due to the presence of parasite molecules, as when we used the same number of particles of non-infected macrophages, the induction was similar. The presence of tGPI-mucins and glycoinositolphospholipids (GIPLs) in the EV-TY was likely responsible for the induction of potent inflammatory responses in macrophages (Almeida et al., 2000; Trocoli Torrecilhas et al., 2009).

The participation of TLR2 in the host-cell infection by T. cruzi was then investigated. To test this hypothesis, infection experiments were performed in CHO/CD14 cells, transfected or not with TLR2 or TLR4. Upon prior exposure to culture supernatants of trypomastigotes or EVs, cells transfected with TLR2, but not TLR4- or non-transfected cells were increase the susceptibility of target cells to T. cruzi infection. A remarkable (up to 6–7-fold) increase in percentage of infected cells was observed in TLR2-transfected CHO/CD14 cells exposed either to total shedding or EV-TY (Figure 5).

TLRs are involved in the recognition of T. cruzi following the activation of host cells to produce TNF-α, IL-12, and NO (Campos et al., 2004; Koga et al., 2006). Macrophages showed differences in TLR gene expression upon stimulation with EVs and T. cruzi infection. We analyzed the gene expression of TLR2, TLR4 by RT-qPCR in macrophages untreated and treated with EV-TY, EV-THP-1control, and EV-THP-1 inf. The gene expression analysis in macrophages treated with EV-THP-1inf and EV-TY revealed alterations in TLR2 and TLR4 (Figure 6).

TLR2 expression is essential for proinflammatory cytokine production (Campos and Gazzinelli, 2004). RT-qPCR analysis was performed to assess the changes in gene expression of cytokines and transcription factors. Macrophages, therefore, were incubated with EVs (EV-THP-1 control, EV-THP-1 inf and EV-TY) and also infected with T. cruzi. Evaluation of the cytokine gene expression profile revealed an increase in IL-1β levels after 6 h in both T. cruzi-infected cells and in those exposed to EV-THP-1inf (Figure 6). There was also an increase in the transcript levels of IL-1β after 1 h of T. cruzi infection. After 24 h of T. cruzi infection or stimulation with EV-THP-1 inf, no change in IL-1β transcript levels was observed, whereas a marked reduction was seen in cells that were treated with EV-TY or EV-THP-1. After 1 and 6 h of T. cruzi infection, the cells showed elevated transcript levels of IL-6. The same result was observed after 1 and 6 h of treatment with EV-TY or EV-THP-1 inf. However, 24 h after the other treatments, there was a reduction in IL-6 gene expression, except for T. cruzi infection. In the TNF-α gene expression analysis, elevation of the transcript level was observed after 1 and 6 h of treatment with EV-THP-1inf and after 6 h of treatment with EV-THP-1. Only T. cruzi infection induced the gene expression of TNF-α at 24 h.

Signal transduction through cytokine receptor-binding occurs via the JAK/STAT pathway signaling. We observed the gene expression of STAT1 and STAT3 in the macrophages stimulated with the different EVs. STAT1 and STAT3 gene expression increased only in response to T. cruzi infection (Figure 7). Stimulation with the different EVs reduced the gene expression of STAT3 at 1 and 6 h (Figure 7).

We performed mass spectrometry-based proteomic analysis (LC-MS/MS) to determine the content of the EVs purified from uninfected (EV-THP-1) and infected macrophages (EV-THP-1 inf). A total of 123 proteins were found in THP-1-EVs and 89 were found in EV-THP-1 inf, from a total of 154 proteins in both samples (Figure 8A). Using FunRich (version 3.1.3), we compared the list of identified proteins to previously published EV data in the Exocarta database (www.exocarta.org) and found that the majority of the proteins had been previously observed to be present in EVs from different sources (Figure 8B). T. cruzi-infected host-cell derived EVs carry proteins from the parasite, as previously described (Ramirez et al., 2017). We also looked for T. cruzi proteins in EV-THP-1 inf. We found 6 proteins (i.e., HSP60, tryparedoxin peroxidase, trans-sialidase Group II, flagellar calcium-binding protein, surface protein TolT and paraflagellar rod protein 2) (Supplementary Table 1). We also compared the levels of abundance of the 58 common proteins by calculating their fold change. The abundance of 20 proteins increased and 38 decreased after infection with T. cruzi (Supplementary Table 2). Most of the proteins found in EV-THP-1 and EV-THP-1 inf are involved in binding, immunological and metabolic processes based on GO term annotations (Figure 8C). Moreover, the majority of the proteins in EV-THP-1 and EV-THP-1 inf were localized in exosomes (Figure 8D). Noteworthy, there was a higher percentage of proteins with catalytic activity in EV-THP-1 inf, particularly enzymes such as trans-sialidase (Figure 8E). It is possible that some of these proteins from T. cruzi were not directly associated with the EVs obtained from infected macrophages and were released in the culture supernatant of the infected cells concomitantly with EV-THP-1 inf production. Furthermore, although unlike, the presence of remaining proteins from the parasites used to infected cells cannot be fully excluded.

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.