The term zoopharmacognosy is derived from Greek words zoo (animal), pharma (drug), and gnosy (knowing), denoting an evolutionary phenomenon comprised of mostly ingestive behaviors aimed at preventing or reducing the harmful effects of pathogens and toxins. Particularly, when sick, certain wild animals will ingest herbs, soil, dirt, or insects that have medicinal properties [1]. Great apes often consume plants with non-nutritional values that have beneficial effects on gut acidity [2], [3], or combat intestinal parasitic infection [4]–[6]. Similarly, domestic horses, dogs, cats, and cows infected with a pathogen may ingest herbs containing nutrients and chemicals with anti-parasitic properties [7]. More interestingly, cattle and some birds eat clay-rich termite mound soil, which deactivates ingested pathogens or fruit toxins [8], [9]. Although the underlying psychological and physiological mechanisms of such learned self-medicating behaviour are unclear, its adaptive value is proposed to be widespread [10], encompassing laboratory animals.

The MRL/MpJ-Fas^lpr/2J (MRL/lpr) murine substrain spontaneously develops systemic autoimmune disease with clinical and serological manifestations reminiscent of human systemic lupus erythematosus, SLE [11]. Due to a lpr mutation on chromosome 19 and dysfunctional Fas receptor in negative selection of autoreactive T cells [12], [13], MRL/lpr mice develop florid disease by 3 months, with few surviving beyond 6 months of age [14]. Age-matched congenic MRL/MpJ +/+ (MRL +/+) controls develop a mild form of the disease and have a life span of up to two years [15]. Three studies by Grota and colleagues suggested that MRL/lpr mice adopt a learning pattern similar to wild animals to restore homeostasis within the immune system. Initial evidence came from a conditioning study, which utilized repeated pairings of access to a palatable stimulus (undiluted chocolate milk) with injections of a noxious, immunosuppressive drug cyclophosphamide (CY) after 23-hr fluid deprivation. Compared to MRL +/+ controls which manifest a mild form of disease, severely sick MRL/lpr mice did not show strong taste aversion learning when exposed to the 1-hr “chocolate milk vs. tap water” preference test [16]. This “learning deficit” was not observed prior to the development of systemic disease, or when non-immunosuppressive unconditioned stimuli were used, suggesting MRL/lpr mice rather associated chocolate milk with relief of autoimmune symptoms following pairings with CY. In an extension of their work, the same group demonstrated that fluid-deprived MRL/lpr mice “voluntarily” consumed more CY dissolved in chocolate milk than age-matched congenic MRL +/+ controls [17]. Consistent with the results from the conditioning study, consumption of CY solution differed between the two MRL substrains only when severe autoimmune symptoms in MRL/lpr mice emerged. Considering that dilutions of chocolate milk and fluid deprivation did not have a significant effect on CY consumption, it was proposed that autoimmune mice learned to consume more CY in an effort to correct their immune system dysregulation [18].

Although some classical conditioning studies have shown that rats can develop a preference for flavoured solutions associated with recovery from illness [19], [20], several lines of reasoning preclude the aforementioned inference on the perception of therapeutic effect and induction of “self-medication” in the studies above. Namely, impaired taste avoidance in conditioned autoimmune MRL/lpr mice [16] could be confounded by deficits that have been subsequently reported in this substrain including altered gustatory input [21], increased perseverance [22], and/or altered emotional reactivity and motivation [23]. As in the original taste aversion experiments, the study documenting “voluntary” consumption of CY-laced chocolate milk included 23-hr fluid deprivation [17], which introduces confounding effects of physiological and psychological stress induced by prolonged thirst. Moreover, repeated weekly bleedings from the retro-orbital sinus and anesthesia could also affect recovery and ingestive behaviour in the two groups. In the third study, where mice were fluid non-deprived, mean volume of CY-laced chocolate milk consumed on weekdays was merely ∼1 ml higher in a large cohort of diseased MRL/lpr mice (N = 86) when compared to age-matched controls, N = 78 [18]. Although intake was compared between two substrains and genders, no comparisons were made between mice exposed to CY and vehicle only, or shown as a preference over plain water intake, which was available during weekends only. In summary, such an invasive, single-choice, cross-sectional approach precludes a clear answer on whether increased CY consumption in diseased mice is due to differences in thirst levels, responsiveness to a palatable solution/protein content, or indeed – to an altered immune status. If the therapeutic effect of CY is perceived and an adaptive behavioural strategy is learned, one may expect increased preference for a therapeutic drug as the autoimmune disease progresses. Using a continuous choice paradigm and ad lib access to tap water, we presently examine this possibility by longitudinally assessing the preference for CY-laced sucrose solution in non-deprived, age-matched MRL/lpr and MRL +/+ mice. A more appropriate design may employ aqueous CY solution, thus eliminating the caloric and incentive properties of sucrose. However, due to its unpalatable, “metallic” taste and negligible intake of CY dissolved in water [18], we mixed CY with 16% sucrose solution to avoid protein content, increase palatability and thus achieve the therapeutic dose range of CY (∼70–100 mg/b.w.). Functional effects of voluntary CY and sucrose intake were assessed using a battery of behavioural tests and immunopathological measures.

In general, MRL/lpr males were lighter than controls throughout the study (Substrain: F_1,51 = 25.461, p<.001), but prolonged exposure to CY further reduced their body weight at an older age (Substrain×Treatment×Age: F_11,561 = 4.245, p<.001; Figure 1).

Chronic immunosuppressive treatment prevented splenomegaly in MRL/lpr mice (Substrain×Treatment: F_1,52 = 11.350, p<.001, Figure 6A). Normalized spleen mass was accompanied by significantly lower serum anti-dsDNA (Substrain×Treatment: F_1,55 = 20.933, p<.001, Figure 6B), anti-cardiolipin (Treatment: F_1,52 = 29.001, p<.001, Figure 6C), and anti-PR3 autoantibody levels in this group (K₃ = 37.141, p<.001, U = 8.0, P<0.001 Figure 6D). In summary, unrestricted exposure to sweetened CY solution abolished severe signs of systemic autoimmunity. However, it did not prevent well-documented low brain weight in the MRL/lpr substrain (data not shown) [30], [31].

The current study tested the hypothesis that zoopharmacognosy is operational in laboratory mice affected by a progressive, chronic disease. The overall premise was that when autoimmune/inflammatory disease manifests, MRL/lpr mice will increase preference for an immunosuppressive drug because of learned therapeutic consequences. Compared to studies which involved classical conditioning and fluid-deprivation [17], [18], we used a rather “ethological approach” by providing ad lib access to water and immunosuppressive CY solution. Such a design enabled experimental animals to freely choose between the solutions, akin to the unrestricted access to diverse fluids and foods in natural habitats available to wild mice. However, our results do not support self-medication in laboratory mice, because none of the three expectations were met. Firstly, MRL/lpr mice did not increase their consumption of CY-laced sucrose solution alongside disease progression. Secondly, they failed to display higher preference for CY-laced sucrose solution in comparison to diseased Veh lpr and asymptomatic CY +/+ controls. Lastly, the dose of CY ingested (a measure independent of the preference) was lower in diseased MRL/lpr mice than in CY +/+ group. Therefore, the notion that autoimmune mice consume solutions that have been paired or laced with CY in an “effort to correct their immune system dysregulation” [18] could not be confirmed with the present set of results. As such, this study is in line with a contrarian view on “dietary wisdom” in omnivores that was largely “attributed both to overreliance on theory and to lack of critical attention to data” [32].

If a therapeutic effect of an immunosuppressant can be perceived and learned indeed, one may expect that diseased MRL/lpr mice would drink CY dissolved in water. However, this was not observed by Grota and colleagues, prompting the authors to dilute CY in chocolate milk to improve its palatability [18]. In the current study, we counteracted the taste of CY with 16% sucrose solution and observed comparable CY consumption in the first week of exposure (Figure 3). This confirmed that taste sensitivity to CY was comparable in 11 week-old MRL/lpr mice and age-matched MRL +/+ controls. Subsequent decrease in intake/preference of the CY lpr group however, does not seem to reflect nutritional or learning deficit. This conclusion is based on evidence that diseased MRL/lpr mice show preference for carbohydrate-rich food [e.g., Veh lpr group performance, Figure 4; [33]] and do not display generalized learning deficit [16], [34]. Therefore, one may assume that reduced preference for CY-laced sucrose mixture and impaired performance in the brief sucrose preference test in both drug-treated groups are attributable to the repelling and cytotoxic properties of CY. Moreover, it is documented that even acute exposure to CY reduces the number of taste buds and impairs responsiveness to sucrose in mice [35], [36]. In the MRL/lpr strain however, severe systemic disease per se may further lead to reduced gustatory nerve responses [21] and depressive-like behaviour [23], [24], which may jointly aggravate their response to sucrose in the present study.

The current findings are also in line with the study testing the notion of “dietary wisdom” in diabetic rodents [37]. Specifically, laboratory rats affected by a diabetes-like disease failed to develop a strong preference for high fat diets, proposed to have beneficial post-ingestional properties. In the MRL strain, one may hypothesize that altered genetic make-up after repeated inbreeding impaired the adaptive survival mechanisms operational in wild animals. In support of this hypothesis, inbreeding has been shown to have significant detrimental effects on the survivorship of mice reintroduced into a natural habitat [38], offspring survival and reproductive success [39]. Indeed, the effects of laboratory inbreeding can be exemplified by the gradual decline in the autoimmune phenotype (http://jaxmice.jax.org/strain/006825.html) and severity of behavioral deficits in the MRL/ lpr substrain [40], [41].

Although zoopharmacognosy could not be shown in the present study, two other important concepts emerged from the data collected. The first is the causal link between autoimmunity and aberrant behaviour. CY proved to be a potent immunosuppressant that abolished systemic immunopathology, as shown by reduced spleen weight and autoantibody levels in MRL/lpr mice. These findings are consistent with previous observations that brief, 1-hr access to CY-laced chocolate milk over 3–4 weeks results in significant reductions in lymphadenopathy and serum anti-ssDNA antibody levels [17], [18], as well as with generalized immunosuppression after repeated 100 mg/kg/week intraperitoneal CY injections [42]. Along the same line, ad lib access to the immunosuppressive solution abolished several behavioural deficits, as shown previously for anxiety-like and motivated behaviours following CY treatment [24], [42]. Conversely, the lack of effectiveness in preventing excessive floating in the forced swim test and brain atrophy suggest a role for non-immunological factors, such as genetic lesions and/or neuroendocrine changes [43].

The second concept that emerged relates to the non-invasive administration route of a noxious drug in experimental mice. Indeed, the present results suggest that lacing it with a palatable ingredient can produce a therapeutic dose comparable to the injection route. As shown in Figure 3, the weekly dose voluntarily ingested was relatively constant in each substrain and can likely be adjusted by increasing the number of exposure days and/or concentration of sucrose or the drug itself. By avoiding repeated exposure to handling, oral gavage, and injections, such an approach can minimize the confounding effects of stress and reduce variance, thus increasing consistency and precision across behavioural and physiological studies.