Reunion behavior after social separation is associated with enhanced HPA recovery in young marmoset monkeys

Abstract

The relationships that offspring develop with caregivers can exert a powerful influence on behavior and physiology, including the hypothalamic-pituitary-adrenal (HPA) axis. In many mammalian species, offspring-caregiver relationships are largely limited to interactions with mother. Marmoset monkeys receive care in early life from multiple classes of caregivers in addition to the mother, including fathers and siblings. We evaluated whether affiliative social interactions with family members in marmosets were associated with differences in cortisol reactivity to a short-term social separation stressor, and whether these variations in affiliative interactions upon reunion predicted how well marmosets subsequently regulated HPA axis function after cessation of the stressor. Marmosets were separated from the family for 8h at three developmental time points (6-, 12-, and 18-months of age), and interactions of the separated marmoset with the family group were recorded during reunion. Urinary cortisol was measured prior to social separation, every 2h during the separation, and on the morning after separation. Heightened cortisol reactivity during social separation did not predict affiliative social behavior upon reunion but higher rates of grooming and play behavior predicted enhanced HPA regulation. Marmosets with higher rates of grooming and play with family members upon reunion had post-stress cortisol levels closer to preseparation baseline than marmosets with lower rates of affiliative reunion behavior. Combined with previous research showing the early programming effects of social interactions with caregivers, as well as the buffering effect of a close social partner during stress, the current study highlights the high degree of behavioral and HPA adaptability to social stressors across development in marmoset monkeys.

Keywords: Family; Hypothalamic-pituitary-adrenal; Primate; Regulation; Social behavior.

Figure 1

Mean (±SEM) frequencies of grooming and play during undisturbed home cage observations (gray) and post-separation reunion observations (black). Grooming initiation (a) and play bouts initiated and received (b,d) were significantly higher during home cage observations than following reunion, while received grooming from family members (c) was significantly higher following reunion than during home cage observations. Asterisks indicate differences at specific ages in the case of significant age × social condition interaction effects.

Figure 2

Mean (±SEM) frequencies of social behavior collapsed across ages. Solid lines represent model predictions at CORT reactivity values at the 25^th and 75^th percentiles. For illustrative purposes, data were split at the median for CORT reactivity. n.s. indicates that the regression coefficient in the MLM for CORT reactivity was not significant.

Figure 3

Mean (±SEM) cortisol regulation collapsed across ages. Solid lines represent model predictions at 0 and 1 grooming bouts. For illustrative purposes, data were split by individuals who initiated no grooming bouts with family members upon reunion, and individuals who initiated at least one grooming bout with a family member upon reunion. Asterisks indicate a significant regression coefficient in the MLM. n.s. indicates regression coefficient in the MLM was not significant.

Figure 4

Raw mean (±SEM) cortisol regulation collapsed across ages. Solid lines represent model predictions at 0 and 1 bouts of play. For illustrative purposes, data were split by individuals who received no play from family members upon reunion, and individuals who received at least one play bout from a family member upon reunion. . Small family = 2 caregivers, Large family = 3+ caregivers. Asterisks indicate a significant regression coefficient in the MLM. n.s. indicates regression coefficient in the MLM was not significant.