Glucagon-like peptide-1 (GLP-1), released after meals and in association with gastric distension [1], is a potent anorexigenic peptide [2], [3], produced both in the periphery (pancreas, gut) and in discrete CNS sites. Within the brain, a major GLP-1 cell group arises from the nucleus tractus solitarius of the hindbrain [4] sending projections to many forebrain areas involved in feeding control [5], [6]. Therapeutic interest in the GLP-1 signaling system has focused largely on its incretin (insulin-releasing) properties, and has culminated in the discovery of a novel diabetes therapy, Exendin-4 (EX4), a long-acting GLP-1 analogue [7]. The observation that diabetic patients receiving EX4 therapy lose body weight [8] has intensified efforts to discover the neurobiological mechanisms/substrates downstream of GLP-1 signaling that mediate the weight loss effects of GLP-1. Recently, several studies have linked central GLP-1 receptor signaling to feeding control at the level of the mesolimbic reward system [9], [10], [11]. Given that common mesolimbic pathways confer reward from natural rewards (e.g. food) and drugs of abuse (e.g. alcohol)[12], we sought to determine whether the GLP-1 signaling system plays a role in alcohol intake and alcohol reward.

GLP-1 receptors are expressed in many brain areas relevant for reward-linked consummatory behaviors, including parts of the mesolimbic reward system such as the ventral tegmental area (VTA) [13]. Direct administration of EX4 into the VTA reduces food intake, food reward and food-motivated behavior [9]. Such a direct effect on the brain’s reward system might bring up the question of a potential role of GLP-1 to regulate rewarding consummatory behaviors that extend beyond feeding control, to those involved in reward more generally. A considerable body of evidence suggests a pivotal role for the VTA in the rewarding and reinforcing effects of alcohol [14]. Alcohol abuse is a widespread and debilitating disorder and there is therefore a great need for developing new, more effective pharmacotherapy. Hence the GLP-1 analogues already deemed clinically safe could be an attractive therapeutic option to reduce alcohol intake. However, the reduction of alcohol intake and the reduction of food intake do not always go hand in hand. Indeed, another clinically approved type 2 diabetes target, peroxisome proliferator-activated receptor-gamma, while effective at reducing alcohol intake surprisingly increases food intake [15]. In the case of GLP-1, however, there are indications that it might change food and alcohol intake in the same direction. Gastric bypass suppresses alcohol consumption in humans and this effect was potentially linked to elevated levels of GLP-1 [16].

In the present study, an over-arching hypothesis is that central GLP-1 signaling may provide a relevant therapeutic target, not only for disorders of feeding control, but also for substance use disorders such as alcohol use disorder. Specifically, we aim to show that enhanced GLP-1 signaling, by GLP-1 or EX4 administration, reduces alcohol intake in rats (in a free choice, limited access alcohol/water drinking paradigm) and reduces alcohol reward in mice (by suppressing the ability of alcohol to condition a place preference). Furthermore we identify the neuroanatomical substrate underlying the effect of the GLP-1R stimulation on alcohol consumption. Importantly, we also aim to uncover the contribution of the endogenous GLP-1 ligand to alcohol intake.

The present studies reveal an important role for GLP-1 in alcohol consumption and reward. Peripherally applied GLP-1 reduced consumption of a 20% ethanol solution and suppressed alcohol reward in the CPP test. EX4, a stable analogue of GLP-1 approved for clinical use in diabetic patients, was similarly able to reduce voluntary alcohol drinking. Furthermore our novel findings, that VTA stimulation of GLP-1Rs is sufficient to reduce alcohol drinking, point to this mesolimbic structure as the neuroanatomical substrate underlying the suppressive effect of GLP-1 on alcohol drinking. These results suggest that GLP-1R stimulation is sufficient to drive a reduction in ethanol-oriented behavior but do not attend to the issue of the involvement of endogenous GLP-1 in the regulation of alcohol drinking. However, a role for endogenously released GLP-1 in alcohol consumption is suggested by our results indicating that blockade of GLP-1Rs increases alcohol consumption.

The current results, together with recent findings indicating an important role of GLP-1 agonists in food motivation/reward [9], amphetamine- [24], and cocaine- [25] induced behavior, highlight a potentially comprehensive role for GLP-1 in reward behavior control. The reason for this broad-spectrum effect of GLP-1 agonists might lie in the convergence of the neural substrate for all reward behaviors on the mesolimbic and/or nigrostriatal pathways. Notably the neuroanatomical distribution of the GLP-1R supports this hypothesis, as GLP-1R has been located in both key mesolimbic (VTA and NAc) and nigrostriatal structures in addition to its well-characterized hypothalamic distribution [13]. This resonates with the emerging concept that appetite-regulating peptides such as ghrelin, leptin, insulin, NPY and orexin, directly target the brain’s reward system where they serve to regulate “addictive” consummatory behaviors that extend beyond feeding control, to those involved in reward more generally [26], [27]. A key finding of this paper points to the mesolimbic VTA as an important neural substrate for the effects of GLP-1 on alcohol drinking.

The neurotransmitters downstream of GLP-1R activation leading to changes in reward behavior are not yet known. The VTA dopamine neurons provide a common mediator for drug and food reward behaviors and thus, are a likely downstream candidate. Notably preliminary data suggest that GLP-1R might be expressed on dopaminergic neurons in the VTA, making dopamine a possible downstream target [28]. That EX4 decreases amphetamine-induced hyperactivity and reward derived from cocaine, behaviors inherently linked to the mesolimbic dopamine, further strengthens the idea of a potential connection between the GLP-1 system and dopamine [24], [25]. Interestingly, it is not only the tegmental dopamine neurons that might receive input from the GLP-1. Emerging literature points to the substantia nigra dopamine neurons as another potential target for GLP-1. In fact this discovery has already been exploited in preclinical models of Parkinson’s disease and ongoing clinical trials [29], [30]. Notably GLP-1Rs in the VTA do not have to be directly present on the dopamine neurons to influence dopaminergic function. They could be located on GABAergic or glutamatergic neurons in the VTA thereby regulating dopamine transmission indirectly.

While our results clearly point to the VTA GLP-1R population as sufficient to alter alcohol intake, they do not eliminate the possibility that other brain GLP-1R-expressing populations might play a role in alcohol regulation in addition to those in the VTA when the agonist is applied systemically. In fact GLP-1Rs in the NAc [13] represent another interesting target with respect to reward behavior as their neuroanatomical location in the projection target of the VTA dopaminergic neurons might allow them to pre-synaptically regulate dopamine release or post-synaptically act on dopamine target neurons. Furthermore many of the hypothalamic (e.g. lateral hypothalamus) and brainstem (e.g. nucleus tractus solitarius) nuclei that densely express GLP-1Rs [13] are either directly or indirectly linked to the mesolimbic VTA allowing them to potentially influence the mesolimbic function.

Our results showing a role for GLP-1 in alcohol consumption are not the first to connect appetite-regulatory anorexigenic peptides to alcohol consumption. Previous studies indicate that, for example, melanocortins and cholecystokinin can also reduce alcohol intake e.g. [31], [32]. Notably both peptides have previously been shown to interact with GLP-1. Interestingly, as already mentioned, there is also precedence for approved anti-diabetic treatments (thiazolidinediones, pioglitazone and rosiglitazone) to reduce alcohol intake and reward [15]. Collectively, these data highlight the overlap and the neural crosstalk between pathways controlling food intake, blood glucose and alcohol drinking.

The potential link between GLP-1 and alcohol intake initially surfaced from the field of bariatric (weight loss) surgery. Surgical procedures such as Roux-en-Y gastric bypass have been reported to suppress consummatory behaviors, even for alcohol, effects potentially associated with reduced circulating levels of ghrelin and elevated levels of GLP-1 (compared to non-operated littermates) [16]. Interestingly, in this gastric bypass study while EX4 reduced alcohol intake in control rats, it was ineffective at reducing ethanol drinking in RYGB rats, i.e. rats that already have reduced alcohol consumption as a result of the surgery [16]. This finding is perhaps mirrored in our current results indicating that GLP-1 stimulation is most effective in those rats that consume the highest amount of alcohol and ineffective in their low drinking littermates. This selective potent effect in highest alcohol consumers might, of course, be of clinical advantage.

Alcohol, in addition to its direct reinforcing effect, can also provide a source of fluid and calories. For that reason a potential action of GLP-1 to generally reduce caloric intake rather than specifically reduce alcohol intake should be considered. In our rat studies, however, the collective data clearly point to a role of GLP-1 in ethanol consumption that is dissociable from its effects on fluid and caloric consumption. Water and food intake, in contrast to alcohol intake, were not altered by any of the GLP-1 treatments (IP or VTA) at any time point tested making an overall effect on satiety an unlikely explanation for the alcohol intake suppressive effects of GLP-1. Furthermore, alcohol represented only a small portion of calories consumed: at the 1 h measurement point calories consumed from alcohol were 7 to 14 and 40 to 50 kcal/kg per rat for alcohol and chow respectively. Note also the lack of effect of the GLP-1R antagonist, EX9, on food or water intake when a clear effect on alcohol consumption was present. This dissociation of effect was also noted for the lower dose of EX4 applied peripherally, though the higher dose and also intra-VTA EX4 reduced water intake. This may seem an unexpected divergence of effects between EX4 and GLP-1. However, even though both clearly target the same receptor, there are significant differences in potency and stability between them. There is emerging evidence that while EX4 is highly specific to the GLP-1R, the molecular and behavioral consequences of its receptor activation might be slightly different to those determined for GLP-1 [33], [34]. These differential effects of the two GLP-1R ligands might have contributed to the divergence of effect on alcohol vs. water intake observed here. Collectively, our data point to the possibility of reducing alcohol intake via GLP-1R stimulation without producing a simultaneous reduction in food and water intake. Moreover, GLP-1 reduced the ability of alcohol to condition a place preference in mice, an effect that reflects the reward of prior alcohol exposure. Note that no calories in any form (food or alcohol) are available during this test.

Interestingly, current results might also suggest higher sensitivity of alcohol intake behavior compared to water/food intake behavior to EX4, as a higher dose is needed to affect the latter. The overall lack of effect of GLP-1 or EX4 on food intake might be surprising; the doses used were low, however, and were previously shown to be ineffective in changing food intake in high-fat fed rats [19]. Indeed, it is possible that several weeks of alcohol drinking may have contributed to a reduced efficacy of GLP-1R agonists on food intake, since as mentioned above alcohol can provide an additional source of calories. Whether chronic alcohol intake, or the additional calories ingested by chronic alcohol intake, induces a reduced sensitivity to the anorexic effects of GLP-1R stimulation similarly to what has been noted in rats after a period of high-fat consumption [19] is an intriguing idea that may warrant further investigation.

An alternative explanation for the suppressive effects of GLP-1 on alcohol intake could involve induction of nausea or aversion, effects that have previously been linked to GLP-1 analogues [35], [36]. This seems unlikely as multiple publications indicate that while the activation of GLP-1Rs in the hindbrain and amygdala might result in nausea, this effect does not extend to the mesolimbic GLP-1R population [9], [10], [11]. Additionally, the peripheral doses of EX4 used here were not sufficiently high to produce taste or place aversion [24], [37].

Collectively our findings reveal that GLP-1 and its mesolimbic receptors can modulate alcohol intake and alcohol reward. Current results also implicate for the first time the endogenous GLP-1 in regulation of alcohol intake. These preclinical studies point to the possibility that GLP-1 analogues could be considered for the treatment of alcohol use disorder. Considering that GLP-1 analogues are not only already approved for clinical use, but may also offer additional benefits in the form of neuroprotection [30], [38], [39], they are certainly an attractive therapeutic target warranting further evaluation for their potential use in the treatment of alcohol use disorders.