Genetic origins of social networks in rhesus macaques

Abstract

Sociality is believed to have evolved as a strategy for animals to cope with their environments. Yet the genetic basis of sociality remains unclear. Here we provide evidence that social network tendencies are heritable in a gregarious primate. The tendency for rhesus macaques, Macaca mulatta, to be tied affiliatively to others via connections mediated by their social partners - analogous to friends of friends in people - demonstrated additive genetic variance. Affiliative tendencies were predicted by genetic variation at two loci involved in serotonergic signalling, although this result did not withstand correction for multiple tests. Aggressive tendencies were also heritable and were related to reproductive output, a fitness proxy. Our findings suggest that, like humans, the skills and temperaments that shape the formation of multi-agent relationships have a genetic basis in nonhuman primates, and, as such, begin to fill the gaps in our understanding of the genetic basis of sociality.

Figure 1. Social networks of adult rhesus macaques.

Networks represent grooming (a, b), aggression (c, d), and spatial proximity (e, f) interactions observed in 2010 (a, c, e), and 2011 (b, d, f). Nodes represent individual animals (n = 87 in 2010, n = 98 in 2011). Females are squares, males circles. Node colour represents dominance rank, increasing from low (pale colours), to mid (medium colours), to high rank (dark colours). Lines represent the presence of an interaction between a pair of individuals with line thickness increasing with the frequency of interaction.

Figure 2. Predictive plots for the relationship between sociality and relative reproductive output.

Plots control for sex and rank. (a) Proximity eigenvector - the tendency of an individual to spend time in proximity with individuals who themselves spend time in proximity to others - increased significantly along with reproductive output. (b) The relationship between aggression outstrength and reproductive output was statistically significant and consistent with disruptive selection. Individuals with the greatest reproductive output directed both the lowest and highest amounts of aggression to others. Relationships for males (blue, n = 29) and females (pink, n = 58) shown in inset graphs. Plots generated in MLwiN.

Figure 3. Association between grooming and serotonergic gene profiles.

Individuals were grouped according to presence of minor (less frequent) alleles, S for 5-HTTLPR, L for TPH2. We found no significant association between grooming eigenvector (GE) and the 5-HTTLPR (a, b) or TPH2 (c, d) polymorphisms as main effects in either year of study (2010: a,c; 2011: b,d). (bar graphs = mean ± SE). The interaction between these variables was a significant predictor of GE in quantitative genetic analyses (P = 0.037). Based on this interaction (e), individuals had major alleles at both loci (n₂₀₁₀ = 27; n₂₀₁₁ = 29), the major allele at one loci and minor allele at the other (n₂₀₁₀ = 18 and 22; n₂₀₁₁ = 23 and 19), or minor alleles at both loci (n₂₀₁₀ = 18; n₂₀₁₁ = 23). Individuals with minor alleles at both loci had significantly lower GE scores than individuals with at least one major allele in both 2010 (f) and 2011 (i). GE for individuals with at least one major allele did not differ significantly and these data were collapsed (g, j) (see also Supplementary Fig. S3 for sample sizes and mean GE using raw data for all possible gene profiles). Two-tailed t-tests of collapsed data were statistically significant (2010: t = 2.63, P = 0.011; 2011: t = 4.18, P = 0.00007). Sociograms of the grooming networks in 2010 (h) and 2011(k). Squares are females, circles males. Lines represent the presence of a grooming interaction between dyads with line thickness increasing with frequency of interaction. Individuals with the highest GE are represented by largest node sizes and central graph positions. Based on their serotonergic gene profiles, rhesus macaques with minor alleles at both loci (red nodes) had the lowest GE. These individuals have small node sizes and are toward the graph's periphery, sometimes with no grooming partners (nodes in bottom left). Two females homozygous XL for 5-HTTLPR (white nodes) were excluded from analyses. **P ≤ 0.01, * P ≤ 0.05.