Chronic 17β-estradiol treatment improves negative valence, anhedonic profile, and social interactions in ovariectomized, middle-aged female rats

Abstract

Women experience depression at nearly 2-fold higher rates than men, with middle-age during the menopausal transition being particularly vulnerable. Preclinical studies commonly focus on young adult or aged subjects and/or rely upon a few behavioral tasks. Given the highly variable and heterogenous nature of depression, the current study implemented a behavioral battery to assess whether estradiol (E2, endogenously expressed in women and rats) would improve depressive measures using the Research Domain Criteria (RDoC) for negative valence, anhedonia, sociability, and anxiety in early middle-aged, ovariectomized (OVX) female rats. F344-cdf rats were OVX and injected daily with E2 (3 μg/ml, or oil). Behavioral testing began after 14 days of injections, which continued throughout the study. E2 improved the depressive profile when using a composite metric for negative valence (immobility on the forced swim task, FST), anhedonia (duration to initiate grooming following sucrose splash and latency to initiate grooming with sucrose), sociability (time interacting toward a novel conspecific), and novelty-induced anxiety (time spent investigating marbles). Interestingly, FST immobility significantly and positively correlated with sucrose preference to show they were opposingly related: higher immobility on FST corresponded to more sucrose ingested. Also, time spent in a chamber with a novel conspecific was less informative than time directed at the conspecific. Other tasks, such as the marble bury test showed some hoarding behavior. These nuances revealed difficulties in assessing behaviors within and across studies, but overall showed that E2 improved the depressive-like syndrome (DLS) in middle-aged females based upon the RDoC.

Keywords: Forced Swim Test (FST); anhedonia and sociability in middle-age depression; anxiety; estrogen; estrogen improves negative valence; sociability; sucrose preference.

Figure 1

Timeline of the experimental manipulations relative to the behavioral testing schedule. Female rats were ovariectomized (OVX) and then given 21 days to recover without experimental manipulations. Rats were randomly assigned to estradiol (E2, 3 μg/ml, s.c.) or sesame oil vehicle treatments (VEH, s.c.) and were 10–11 months of age at the start of the hormone treatment. Rats were tested in the behavioral tasks in the order listed. Days off from behavioral testing are denoted in black boxes with white lettering and indicate the number of days without behavioral testing. Due to unforeseen circumstances, the elevated plus maze (EPM) and ultrasonic vocalization (USV) data were unusable and denoted with gray boxes. SP, Sucrose Preference; SST, Sucrose Splash Test; MBT, Marble Bury Task; NSF, Novelty Suppressed Feeding; FST, Forced Swim Test.

Figure 2

Forced swim test (FST) as a metric for negative valence for acute threat. E2 treatment (A) reduced the time spent immobile, (B) increased the time spent climbing, and (C) increased the time spent swimming. ** p < 0.01, *** p < 0.001. VEH n = 15, E2 n = 16.

Figure 3

Sucrose preference (SP) timeline and sucrose splash test (SST) as a metric for positive valence for anhedonia. (A) Rats were exposed to a ten-day SP timeline that does not require drink or food deprivation. Rats were single housed and exposed to two drink bottles, 2% sucrose and drinking water for 3 days (denoted by white boxes) which was changed on the fourth day with 1% sucrose and drinking water for 7 days (denoted by gray hatched boxes). Testing was performed on the last 3 days of the 1% sucrose exposure. Bottle locations were counterbalanced, and locations swapped daily. (B) E2-treated rats drank significantly less 1% sucrose over the last 3 days of 1% SP testing compared to VEH-treated rats. (C) Total volume consumed during the last 3 days of 1% SP testing was similar between VEH and E2-treated rats. (D) After being splashed with 10% sucrose on the rats' backside, E2 treatment did not alter the latency to start grooming, nor (E) the total duration of grooming. *** p < 0.001. For SP, VEH n = 15, E2 n = 16. For the Splash Test, inadvertent disruptions reduced subject number to VEH n = 13, E2 n = 14.

Figure 4

Assessment of E2 treatment on social interactions as a metric for social processes for disrupted affiliation. (A) The sociability test assessed whether the test rat spent time in the chamber with a novel conspecific female rat (R1) or an inanimate object (O). (B) The sociability index represented the time spent in the compartment with R1 compared to time in both side compartments and showed bimodal distributions that were statistically similar between VEH and E2. (C) VEH-treated rats spent more time in the chamber with R1 than with O, whereas E2-treated rats showed statistically similar times in both side chambers. (D) Quantifying the time that the test rat interacts with the box containing the R1 or the object showed that both E2 and VEH directed their attention more toward the R1 than the object in the first 5 min, which decreased in the second 5 min of assessment but still reached statistical significance. (E) The social novelty test assessed whether the test rat spent time in the chamber with R1 (familiar from the sociability trial) or a novel conspecific female rat (R2). (F) The social novelty index represented the time spent with R2 compared to time in both side compartments and showed bimodal distributions that were statistically similar between VEH and E2. (G) VEH-treated rats showed a tendency to spend more time in the chamber with R1 than with R2, but this did not reach statistical significance. E2-treated rats spent similar durations in both side chambers. (H) Quantifying the time that the test rat interacted with R1 and R2 showed no significant effect of E2 and VEH. C = center chamber, * p < 0.05, ** p < 0.01 *** p < 0.001, + p = 0.09 (with two-tailed, and <0.05 with one tailed paired t-test). VEH n = 15, E2 n = 16.

Figure 5

Marble bury task (MBT) and novelty suppressed feeding (NSF) as a metric for negative valence for potential threat. During the MB test, all five behaviors quantified failed to find significant effects of E2 on: (A) time spent investigating the marbles, (B) time spent grooming, (C) duration of immobility, (D) number of marbles buried by 2/3, and the number of marbles hoarded. For the NSF test, E2 had no effect on: (E) the time it took to approach food in the arena center and (F) amount of food consumed in the home cage. Notably, many rats never approached the food to create a ceiling effect. (G) A composite z-score for all the MBT behaviors (adjusted so that high z-scores indicated greater anxiety) marginally correlated with latency to approach food in the NSF (p = 0.054). (H) A negative correlation was significant when comparing the time spent investigating marbles on the MBT with time to approach food in the NSF (p = 0.019). Rats that showed high marble investigation tended to approach food quicker in the NSF. E2 and VEH treated rats were distributed throughout the correlation and did not fall within a particular region. White circles = VEH, Black triangles = E2. VEH n = 15, E2 n = 16.

Figure 6

Comparison of task assessments. (A) Comparing the negative valence-acute threat assessment of immobility on the FST with the positive valence assessment using 1% SP Index revealed a significantly positive correlation (p = 0.002): Rats showing the highest immobility on the FST consumed the most sucrose, which was in the opposite direction as expected. E2 treated rats tended to cluster in the lower left to reflect reduced immobility with higher anhedonia associated with a low SP Index. VEH n = 15, E2 n = 16. (B) Comparing the negative valence-acute threat assessment of immobility on the FST with the positive valence assessment using the time to initiate grooming after a sucrose splash on the backside showed a near significant correlation (p = 0.072): Rats showing the highest immobility on FST took the longest to initiate grooming on the SST, which was in the predicted direction. VEH n = 13, E2 n = 14 (due to loss of rats from splash test malfunction). (C) A composite DLS z-score was computed for the FST immobility, SST to start grooming, and the Sociability test for interacting with the novel rat in the first 5 min was computed and adjusted so that higher z-scores reflected DLS. A t-test was significant (** p < 0.01): E2-treated rats showed a significantly lower composite DLS z-score compared to VEH-treated rats to indicate that E2 lowered DLS. VEH n = 13, E2 n = 14. (D) A composite DLS z-score was computed for all metrics using immobility (FST), 1% SP Index (SP), duration to initiate grooming (SST), time interacting (1^st 5 min Sociability), and duration investigating (MB) and adjusted so that higher z-scores reflected DLS. A t-test was significant (* p < 0.01): E2-treated rats showed a significantly lower composite DLS z-score compared to VEH-treated rats to indicate that E2 lowered DLS. VEH, White Circles; E2, Black Triangles. SP, sucrose preference; SST, sucrose splash test; FST, forced swim test; MBT, Marble Bury Task.

Figure 7

Body weight changes during treatment. VEH and E2 groups had similar in body weights at the time of OVX and before treatments began to indicate no a-priori differences. After several weeks, E2 or VEH treatments began and during the weekly weight measures, rats treated with E2 (3 μg, s.c., daily) lost weight during the initial 2 weeks of E2 and then stabilized. VEH-treated rats showed a pattern of gaining weight during the same duration. VEH n = 15, E2 n = 16. Note, error bars are plotted for all points but in some cases, may be smaller than the symbol size. ***p < 0.001.