To identify the minimal BHT concentration which saturated PIN1-GFP internalization, we performed a dose-dependent response internalization assay. The lowest BHT concentration which was sufficient to induce PIN1-GFP internalization was 0.018 mM, while the PIN1-GFP internalization response was saturated at 0.18 mM BHT after 30 min (Figure 1). Because a BHT concentration of 0.18 mM was sufficient to saturate PIN internalization, the following experiments were carried out at 0.2 mM to minimize any secondary effects of BHT that might be induced at higher concentrations. The application of BHT alone (in the absence of BFA) had no effect on the distribution of PIN1 and PIN2 between the plasma membrane and endomembrane compartments (Figure 2) indicating that the enhanced accumulation of PINs in BFA compartments was not due to a direct inhibition of exocytosis by BHT. The application of BHT alone decreased the intensity of the signal in the plasma membrane for PIN1 but not for PIN2, indicating a differential regulation of cellular trafficking routes by BHT. The reduction in PIN1 signal intensity might reflect an increased rate of endocytosis and/or a reduced rate of exocytosis. The absence of a BHT effect on PIN internalization in the absence of BFA led us to next test whether the application of BHT alone was sufficient to modulate the root growth response.

The root growth response to BHT (Figure 3) correlated closely with the dose-dependent response of PIN1-GFP internalization to BHT, indicating that, despite the qualitative maintenance of PIN localization and distribution, BHT might nevertheless affect the function of auxin transporters.

In the BFA assay, BHT increased the rate of PIN internalization, whereas NAA inhibited it. Importantly, the application of different BFA concentrations was able to separate the processes which are involved in PIN internalization and PIN stability. For PIN2, a relatively low concentration of BFA (25 μM) preferentially inhibits recycling, whereas a high concentration (50 μM) also stops the targeting of vesicles to the vacuole for degradation (Kleine-Vehn et al., 2008). Thus, by understanding the effect on PIN internalization at low BFA concentrations we may accommodate the potential effects of BFA on the targeting of vesicles to the vacuole (Robert et al., 2010).

In agreement with experiments which used 50 μM BFA (Paponov et al., 2019b), the effect of BHT was stronger on PIN1 than it was on PIN2 internalization (Figure 4). However, at a low BFA concentration (25 μM), PIN2 was more sensitive to BHT, indicating that BHT could also be involved in PIN2 vacuolar targeting. The simultaneous application of BHT and NAA resulted in a level of PIN internalization more similar to that achieved after treatment with NAA alone than with BHT alone, suggesting that the BHT effects on PIN internalization are not due to an enhancement of PIN1 internalization but rather may be due to events occurring downstream of NAA. This observation is consistent with a hypothesis in which NAA inhibits PIN internalization, increasing the amount of PIN1 at the plasma membrane, and masking the downstream activity of BHT. The activity of BHT cannot be explained by changes which it induces in cellular redox status as the application of reduced glutathione did not lead to a similar effect on PIN1 and PIN2 internalization. Although PIN1 internalization was weakly increased, the opposite effect was observed for PIN2 (Figure 4). Taking into account that BHT acted downstream of NAA, we next investigated the effect of BHT on exocytosis.

By visualizing PINs after the washing out of BFA, we observed that the application of BHT stopped the release of PIN1 from BFA compartments to the plasma membrane, leading us to hypothesize that BHT inhibited exocytosis (Figure 5). However, BHT treatment did not inhibit the release of PIN2 from BFA compartments, suggesting that the observed BHT activity was specific to PIN1. It must be remembered here that BHT did not enhance the accumulation of PINs in the endosome compartments in the absence of BFA. BHT therefore does not appear to directly stop exocytosis. Instead, it is active in inhibiting exocytosis from the BFA compartments. We next tested whether the activity of BHT on PIN1 exocytosis was related to its being an antioxidant by comparing the effect of BHT on PIN exocytosis by applying either ROS (H₂O₂) or a ROS-induced stress (salt stress). One mM H₂O₂ inhibited the exocytosis of both PIN1 and PIN2 (Figure 5), indicating that the inhibition of PIN1 exocytosis by BHT might be due to its prooxidative rather than its oxidative properties. BHT did not, however, inhibit PIN2 exocytosis, therefore the activity of BHT cannot be explained solely by its antioxidant or prooxidant activity. Incubation with a reductant, DTT (Kovacik et al., 2009), did not affect exocytosis (Figure 6), further supporting the idea that the decrease in cellular ROS abundance is not sufficient to change PIN trafficking. Treatment with the natural flavonoids, quercetin and kaempferol, also did not affect the rate of PIN exocytosis (Figure 6), further supporting a unique type of inhibitory action of BHT on PIN1 exocytosis.

The main finding of the present study is that BHT stops PIN1 exocytosis from BFA compartments without affecting PIN2 exocytosis. This regulation is ROS-independent. We cannot exclude the possibility that BHT also enhanced endocytosis, because a reduction in the signal of PIN1 on the plasma membrane and an increased PIN1 internalization during pre-incubation by BHT might occur due to a combination of inhibition of exocytosis and stimulation of endocytosis. Previous experiments with cycloheximide (CHX) showed that PIN1 was internalized in to BFA compartments and, upon withdrawal of BFA, PIN reappeared at the plasma membrane in a manner which was independent of protein synthesis (Geldner et al., 2001). Because the effect of BHT on PIN1 synthesis is unknown, we cannot exclude the possibility that a BHT-induced increase in PIN1 internalization was due to increased de novo PIN1 biosynthesis. However, the fact that the PIN1 signal in the cell did not increase after BHT treatment (Figure 2), and that the PIN1 level was reduced on the plasma membrane, suggests that the main mechanism of BHT action is related to inhibition of exocytosis. Taken together, the evidence presented here indicates that BHT might directly affect PIN1 trafficking by interacting with as yet unidentified targets, rather than acting through the regulation of ROS abundance.

BHT is one of the most widely used antioxidants in the food industry and has been extensively investigated in animal systems and in terms of human health (Nieva-Echevarria et al., 2015); however, plant responses to BHT have received less attention. Nevertheless, several interesting and unusual activities of BHT have been discovered in plants, such as an induction of shoot branching (Grochowska and Buta, 1985). At the cellular level, BHT induces large structural changes in the Golgi apparatus and the endoplasmic reticulum (Bakeeva et al., 2001), suggesting that BHT not only blocks exocytosis of PIN1 but also interferes with other cell functions.

We suggest three alternative hypotheses to explain the modulation of PIN trafficking by BHT observed in our investigation. The first hypothesis is that BHT acts as an antioxidant and indirectly regulates PIN trafficking by ROS scavenging. The second hypothesis is that BHT acts as a prooxidant to produce ROS that then affect PIN trafficking. The third hypothesis is that BHT acts directly on some as yet unidentified molecular targets to modulate PIN trafficking.

If our first hypothesis—that BHT acts as a ROS scavenger in modulating PIN trafficking—were correct, we would expect that BHT effects counteract ROS effects. However, BHT and ROS both inhibited PIN1 exocytosis; they also had unrelated actions with respect to PIN2 trafficking (Figure 5), BHT did not change PIN2 exocytosis, whereas H₂O₂ inhibited exocytosis (Zwiewka et al., 2015).

A different pattern of activity for PIN1 and PIN2 trafficking was also indicated by our experiment with the reduced form of glutathione (GSH) (Figure 4) and the reducing agent DTT (Figure 6), both of which are known to reduce ROS concentration in plants (Kovacik et al., 2009; Yin et al., 2017). These results indicated that the specific effect of BHT on PIN trafficking cannot be explained exclusively by the modulation of ROS concentration. Interestingly, GSH and BHT showed different activity patterns, differentially modulating PIN1 and PIN2 internalization. GSH enhanced PIN1 internalization, possibly by stimulation of PIN1 endocytosis and/or inhibition of exocytosis. This GSH activity cannot be explained by the antioxidant properties of GSH because ROS showed the same activity on PIN1 internalization. However, GSH acted as an antioxidant, decreasing PIN2 internalization in a reverse response to that induced by ROS (Zwiewka et al., 2015; Figure 5). The antioxidant effects of GSH on PIN2 internalization but not on PIN1 internalization might be related to the localization of PIN2 in the outermost layers of the roots (epidermis and cortex), as these layers are more sensitive to external stimuli and exogenous GSH application. This difference in GSH responses further supports the importance of redox status in the regulation of polar auxin transport. However, the transcriptional regulation of PIN expression seems to be the main mechanism regulating PIN activity under oxidative conditions in Arabidopsis roots (Koprivova et al., 2010; Yu et al., 2013).

The second hypothesis—that BHT acts as a pro-oxidant that affects PIN trafficking—is supported by the observation that BHT and H₂O₂ act in a similar manner on PIN1 exocytosis (Figure 5). Pro-oxidant activity is possible for BHT since some antioxidants do behave as pro-oxidants under certain circumstances (Valko et al., 2004). Indeed, BHT can interact with oxygen in aqueous media (aerobic conditions) to generate O₂^*– (superoxide) (Smirnova et al., 2002), whereas inside the seedlings, BHT acts as a ROS scavenger (Smirnova et al., 2002).

Based on the potential for the production of ROS in an aqueous medium at the root surface and the fact that ROS inhibit exocytosis (Zwiewka et al., 2015 and as shown in Figure 5), this hypothesis predicts that BHT would inhibit the exocytosis of PIN2, which is expressed in the epidermis, but not of PIN1, which is expressed in the endodermis and central cylinder. However, the observed BHT response was opposite to this expectation: BHT inhibited PIN1 exocytosis and had no effect on PIN2 exocytosis (Figure 5). Thus, the different patterns of exocytosis of PIN1 and PIN2 in response to BHT and H₂O₂ do not support the idea that the activity of BHT on PIN trafficking is not related to its potential prooxidant activity.

Interestingly, hydrogen peroxide inhibits exocytosis but also stimulates endocytosis, as observed by its effects in the absence of BFA (Zwiewka et al., 2015). By contrast, BHT did not enhance endocytosis, as the application of BHT alone did not affect PIN internalization (Figure 2). This difference between H₂O₂ and BHT activities provide further support for the conclusion that the mode of BHT action cannot be explained by its pro-oxidant activity.

The inhibitory effect of BHT on PIN1 exocytosis resembles that of the auxin transport inhibitors NPA and TIBA. Early studies on the PIN trafficking machinery showed that TIBA and NPA blocked the transfer of PIN1 from the BFA compartments to the membrane that occurred during cell washing after BFA treatment (Geldner et al., 2001). However, the pattern of BHT activity on PIN trafficking differs from the activity of the transport inhibitors, because TIBA and NPA inhibit both exocytosis and endocytosis (Geldner et al., 2001). By contrast, pre-treatment with BHT stimulated PIN internalization, indicating that BHT did not inhibit endocytosis (Paponov et al., 2019b; Figures 1, 4).

The activity of auxin transport inhibitors on auxin transport activity has been attributed to their binding to the multi-drug resistant ABCB type transporters, a plasma membrane aminopeptidase, and other proteins (including PINs themselves) (Teale and Palme, 2018). The sensitivity to NPA is lower for PIN trafficking than that for polar auxin transport, indicating that inhibition of auxin transport is not due to blocking of PIN trafficking (Petrasek et al., 2003). By contrast, the dose responses of PIN internalization and root growth to BHT treatment (Figure 3) showed similar sensitivities, indicating that the inhibition of root growth by BHT might be due to the blocking of PIN trafficking. The identified differences in activities between NPA/TIBA and BHT indicate that the mechanism of action of BHT is likely to differ from that of auxin transport inhibitors.

In contrast to BHT, flavonoids did inhibit PIN1 exocytosis (Figure 6), indicating that the mechanism of BHT action is also different from that of these naturally occurring antioxidants. The inability of flavonoids to inhibit PIN1 exocytosis agrees with previously published data for wild-type plants (Peer et al., 2004). This action of flavonoids differs from that of auxin transport inhibitors, although flavonoids and NPA share binding sites on NPA-interacting proteins (Jacobs and Rubery, 1988). Interestingly, although flavonoids do not inhibit PIN1 exocytosis in wild-type Arabidopsis, flavonoids inhibit PIN1 exocytosis in the flavonoid-deficient mutant, tt4 (Peer et al., 2004). In contrast to PIN1 trafficking, PIN2 trafficking was not affect by flavonoids in the tt4 mutant (Peer et al., 2004), further supporting different mechanisms for the regulation of PIN1 and PIN2.

The application of BHT alone did not induce PIN internalization, supporting the existence of different targets of BHT and BFA actions. Inhibition of PIN exocytosis in BFA wash-out experiments indicates BHT interference with cell recovery after the removal of BFA from cells.

Endosidin2 has also shown an ability to inhibit the recovery of PIN trafficking from the BFA compartment to the plasma membrane (Zhang et al., 2016). However, this drug inhibits PIN2 recovery from the BFA compartment, and endosidin2 application also reduced PIN2 abundance on the membrane. Our finding that BHT did not affect PIN2 recovery from BFA compartments and did not reduce the abundance of PIN2 on the membrane indicates that endosidin2 activity differs from that of BHT.

Based on our BFA assay, we identify BHT as a chemical which is able to inhibit PIN1 exocytosis. This activity suggests that BHT might be a promising pharmacological tool for the investigation of PIN trafficking regulation under different genetic and environmental conditions and can be potentially used as a tool to study membrane trafficking in other organisms.