Animal models are important research tools in psychiatry and should mimic some of the human conditions of interest. According to DSM-IV [1], major depression is characterised by either depressed mood or anhedonia, in combination with four additional symptoms related to weight changes, sleep disturbances, psychomotor agitation or retardation, fatigue, feelings of worthlessness or guilt, diminished cognitive functioning, or recurrent thoughts of death. The presence of some of these symptoms can be defined operationally (e.g., loss of appetite and weight, sleep disturbances, cognitive and psychomotor changes), and thus can be assessed in laboratory animals.

Stressful experiences have been reported to favour the development of depression in humans [e.g. 2,3]. Therefore, in order to provoke depressive-like behavioural changes, some animal models for this phenotype are generated by exposing them to stressful situations [4]–[8]. In rats, application of chronic mild stress (CMS) procedures resulted in a variety of behavioural, neurochemical, neuroendocrine and neuroimmune alterations resembling some of the dysfunctions observed in human depression [9]–[16]. Therefore, the CMS model, developed by Willner and colleagues [4], has attracted a lot of interest due to its potential of combining several validity criteria requested for an animal model of depression [16], [17]. In terms of symptoms evoked by CMS, the induction of anhedonia was the primary focus in this model [4]. Anhedonia, a core symptom of depression, was modelled by inducing a decrease in responsiveness to rewards reflected by a reduced consumption and/or preference of sweetened solutions. In a more recent review, Willner [17] summarises results of positive reproduction of CMS-induced anhedonia as well as ‘anomalous’ findings. In this context the attributes ‘anomalous’ or ‘paradox’ refer to findings that include CMS-induced anxiolysis and hyperlocomotion and apparently are contrary to ‘classic’ comorbidities of depression-related behaviour such as increased anxiety and reduced locomotor activity [17], [18]. Most studies were performed in rats but the few that used mice generally point towards the applicability of a non-standardised CMS procedure to induce anhedonic behaviour in mice as well. One reason for the adoption of this approach to mice was the introduction of genetic mouse models as tools in psychiatric disorder research. Using mice with specific genetic modifications in suspected vulnerability genes in combination with CMS as environmental factor will allow scrutinising the role of both, the candidate gene and stress in a genetically predisposed animal, as risk factors for depression.

Studies published on the effects of CMS on mouse behaviour agreed on the importance of the strain used and showed that some strains are responsive to the CMS procedure, a finding which strongly depends on the respective endpoint defined [19]–[24]. The co-occurrence of CMS-induced alterations in palatable liquid consumption and other behavioural and physiological parameters, suggested to reflect depressive-like behaviour, has rarely been studied in mice. Pothion and colleagues [21] investigated three different mouse strains in terms of sucrose consumption, body weight changes, coat state, spontaneous alternations in the Y-maze and spatial learning in the Morris water maze test. Only in one strain (CBA/H) a decrease in sucrose consumption was found along with changes in physiological or behavioural parameters. Therefore, a CMS-induced reduction of sucrose consumption was not predictive of the occurrence of any other parameter assessed in the study. Applying a different chronic stress procedure in BL/6N mice, comprising more severe stressors presented in a more sequential than unpredictable manner, Strekalova and colleagues [25] described an association of a stress-provoked decrease in sucrose preference and behavioural measures that were restricted to increased passivity in the forced swim test (FST) as well as decreased novel object exploration. An increase in anxiety-related behaviour and locomotor disturbances were found to be induced by the stress procedure independent of the induction of “anhedonic” behaviour [25]. In other studies using the CMS procedure, an increase in immobility in the FST [26]–[28], decreased grooming [23], altered performance in cognitive tasks [29] as well as changes in anxiety-like behaviour [20], [24] were observed. These behavioural measures were considered to reflect additional depression-related symptoms [17]. Unfortunately consumption of sweetened solutions was not assessed in all these studies.

A CMS model with a decrease in intake and preference of sweetened solutions as central readout presents specific advantages. Contrary to operant behaviour it can be implemented without cost-intensive apparatus, it is non-invasive (in contrast to e.g. intracranial self-stimulation), and the progressive evolution of a depression-related symptom as well as the time course of antidepressant-induced resolution of the symptom can be traced by repeated measurements. The latter is rather difficult for a variety of test paradigms used to assess, for example, anxiety-like behaviour. As stated by Anisman and Matheson [5], an appropriate model of depression requires that multiple behavioural tests be employed to approximate the range of symptoms that characterise depressive illness. Therefore, the aim of our studies was to further investigate the feasibility to establish a CMS model which includes the measurement of intake and preference of a sweetened liquid and addresses additional indicators of depressive-like behaviour. We used a stress-procedure which included most of the commonly used “mild” stressors [30] but was devoid of food or water deprivation. Measurements were performed 2–3 times per week with the aim to possibly gain information on a direct effect of the precedent stressor on “hedonic” behaviour. CMS effects on intake of a 0.2% saccharin solution and body weight gain were assessed in different mouse strains as the vulnerability for stress-induced changes is supposed to be genetically determined. In selected mouse strains, we investigated the influence of CMS on anxiety-related behaviour and on passive behaviour in the FST. The fluctuations in saccharin intake observed in the first experiments showed a tendency of association to the precedent stressor which according to our interpretation had some impact on nocturnal activity of the mice. Therefore, an independent experiment aimed at detecting the influence of overnight illumination as particular stressor on subsequent saccharin intake and activity in parallel.

The data presented in this study were derived during the development of a CMS protocol focussed on consumption of sweet solutions as central readout measure for hedonic/motivational behaviour in mice. We used a stress-procedure which included most of the commonly used “mild” stressors [16], [17], [30] but was devoid of food or water deprivation. Five out of seven mouse strains investigated responded with a decrease in the consumption of the sweetened solution compared to the respective control group. As summarised by Willner [17], a variety of chronic stress protocols has been able to yield an anhedonic phenotype in rodents regardless of particular content or timetabling of microstressors in the respective CMS schedule. Strain-dependent effects of CMS on consumption of palatable solutions of mice have been reported earlier [20], [21], [24].

These general findings could be confirmed in our study for stressed BL/6J, D2Ola, D2JIco, FVB and BL/6N mice despite differences in the designs of the experiments. However, the effects of CMS appeared not to be enduring, since the saccharin intake of the respective control group decreased to the level of stressed animals after 4–6 weeks in the long-term CMS experiment. Trying to re-establish their working CMS protocol after moving to a new laboratory, Willner and colleagues reported similar problems of an initially obtained anhedonic CMS effect in rats that vanished after several weeks of stress application [16]. The discrepancy to previous studies was explained by a diurnal variation of CMS effects that were found to be more robust when the sucrose test was performed during the dark period [31]. In our study in mice, we followed the suggestion of measuring the intake behaviour during the first hours of the dark period, therefore we should have picked the most sensitive time period for measuring a CMS effect on saccharin intake. In a study of Pothion and colleagues [21] the difference between control and CMS groups of mice in a 24 hrs sucrose test was also only observed for the first 4 weeks after onset of stress. We observed strong fluctuations in the consummatory data in our experiments. These might be a consequence of (1) the short measurement interval and the consequential low intake during that time, (2) the assessment of consummatory behaviour more than once a week and (3) a possibly disturbing effect on the intake of control animals since CMS mice most of the time were kept and stressed in the same room [17].

One aim of the study was to identify potential differences on the impact of specific stressors contained in the CMS procedure on saccharin consumption and therefore, the protocol followed a fixed weekly schedule rather than being designed entirely in an unpredictable way. The preceding stressor with the largest effect on saccharin intake in the experiments was the wet cage. Our interpretation was that under this condition it was hard for the animals to rest. Indeed, keeping rats in a wet cage was used to establish an animal model of fatigue [34]. Thus, we followed the idea of a potential impact of mild disturbance of activity/sleep rhythm on saccharin consumption. Overnight illumination was applied as the sole stressor and measuring the subsequent saccharin intake was paralleled by recording homecage activity. As shown in Figure 6A, the volume of saccharin consumption during the first 2 hours at the beginning of the dark period of stressed animals dropped to a level similar to basal water consumption. In parallel, a reduction of activity was observed that was most prominent during the time when saccharin was presented. This suggests that the reduced saccharin intake was not only due to a shift of general consummatory behaviour but combined with a parallel shift and reduction in activity as observed during the same time interval. There was a moderate positive correlation of activity and intake during the time interval of saccharin presentation for LS as well as control animals. Therefore, the levels of activity and of saccharin intake are closely interwoven and the potential influence of a stressor preceding the saccharin measurement on activity changes should be considered.

In the rat version of the CMS model, changes in diurnal rhythms [35] and sleep architecture [36], [37] were reported. Further, D'Aquila et al. [31] showed the diurnal variation of CMS-induced anhedonic behaviour with its presence mainly during the active phase (dark period) of the animals. Papp and colleagues [38] concluded that the procedure causes a generalised disorganisation of internal rhythms which are postulated to play an important role in the pathophysiology of depression [39]. In mice, strain-dependent differences in locomotor activity rhythm and its changes due to daylight reversal [40], as well as a relation of sleep changes due to mild stressors - like environmental novelty - with trait anxiety [41] have been described.

Taken together, in addition to strain-dependent intake of sweetened liquids [21], [42], [43] and stress effects on the reward system [42], [44], the sensitivity to changes in activity/sleep due to the CMS procedure contributes to the final decrease in consumption behaviour. This could be of specific relevance for those studies that apply mild stressors and determine intake or preference of sweetened solutions following different stressors [21]. A consequence could be a higher variation in the anhedonic profile as observed in our study.

Besides the measurement of saccharin intake our second focus was to address additional indicators of anxiety- and depressive-like behaviour. Therefore, animals of three strains of mice were additionally characterised regarding CMS effects on anxiety-related behaviour. Furthermore, the animals were investigated in the FST, a test often used to evaluate antidepressant-like properties of substances [45]. First, BL/6J and D2Ola mice were tested in above mentioned paradigms after CMS experience of more than 10 weeks. Second, a different batch of BL/6J mice was investigated after 2 weeks of CMS experience when the decrease in saccharin intake became apparent. Third, experiments with CMS-experienced BL/6N mice also addressed the influence of illumination during behavioural testing [18]. Testing BL/6J and D2Ola mice after long-term CMS experience revealed that BL/6J mice remained unaffected by CMS, whereas D2Ola mice of the CMS group showed a decrease in anxiety-related behaviour. In the second group of BL/6J mice, after 2 weeks of CMS, again no difference in anxiety-like behaviour was seen compared to the control group. The anxiolytic-like effect of CMS in D2Ola mice is commonly appraised ‘anomalous’, yet has also been found in other chronic stress paradigms involving rats, other mouse strains and different anxiety tests [23], [46]–[52]. Generally, these findings are interpreted as either being due to blunted emotionality [52] or caused by methodological differences [48] of CMS procedures that yield a ‘classic’ anxiogenic stress response. Nevertheless, the resilience of BL/6J mice against disturbing CMS effects on anxiety-related behaviour as shown by Mineur et al. [24] could be confirmed in our study.

According to Strekalova et al. [18] bright and even moderate illumination conditions (>5 lx) can confound anxiety- and depression-related behavioural readout in chronically stressed BL/6N mice in common test paradigms by eliciting hyperlocomotion. Furthermore, chronic stress in general is supposed to exert stimulating effects on locomotor activity [53] that might mask other stress effects in anxiety- as well as in depression-related test paradigms [18]. For this reason, in our study involving BL/6N mice, illumination levels of the test apparatus were attenuated and testing was performed at the beginning of the dark phase. Under these conditions, no CMS-induced changes were observed in the DaLi. In the mHb test a CMS-induced hyperlocomotion and increased vertical exploration was paralleled by an increased time spent on the board, thus fitting into the picture drawn by Strekalova et al [18]. Since hyperlocomotion still appeared under red light conditions in the open field test in BL/6N mice (data not shown), our CMS protocol seems to exert additional effects on reactivity to a test situation that lie beyond an increased sensitivity to even moderate illumination conditions. Possibly in line with this concept are the results of all conducted FSTs in our study where no significant CMS-induced change in immobility was observed. According to the outlined concept, an increased immobility might have been concealed by CMS-induced hyperarousal, rather independent of test time and illumination.

Taken together, our findings on anxiety- and depression-related behaviour point towards a higher reactivity to a novel situation in response to CMS. This might imply the need to put the ‘anomalous’ behavioural profile in response to our CMS protocol in perspective - although this conclusion is highly speculative in respect to our limited data. Taking into account the above described inefficiency of CMS to alter anxiety-related behaviour in BL/6J mice, the presented data suggest that the occurrence of anhedonic behaviour and changes in behaviour assessed in tests for anxiety- or depression-related behaviour were uncoupled from each other.

Strain effects of CMS are further diversified by different responses of body weight gain. Whereas BL/6J and D2Ola mice showed a reduced body weight gain due to CMS, BL/6N remained entirely uninfluenced by CMS in this parameter. Apparently stressor intensity was high enough to yield an attenuation of body weight gain in D2Ola and BL/6J mice, while BL/6N mice seem to require stronger stressor application to show the same effect [18], [25]. Particularly in the face of contradictory findings reported in other CMS studies [20], [21] we consider the observed changes in body weight gain as a verification of CMS effectiveness in general rather than associating them with the phenomenology of major depression.

On the basis of the results obtained so far, our next steps in the direction of a CMS model in mice will include some modifications of the CMS procedure and the experimental design. Assessment of consummatory behaviour will be accompanied by detailed determination of homecage activity during the saccharin tests, and finally, the effects of antidepressant treatment on the diverse behavioural endpoints included in the present study will decide upon the applicability of our CMS model in general and additionally might reveal a possible relation of ‘anomalous’ behavioural changes to symptoms observed in human depression.