Social status alters immune regulation and response to infection in macaques

Abstract

Social status is one of the strongest predictors of human disease risk and mortality, and it also influences Darwinian fitness in social mammals more generally. To understand the biological basis of these effects, we combined genomics with a social status manipulation in female rhesus macaques to investigate how status alters immune function. We demonstrate causal but largely plastic social status effects on immune cell proportions, cell type-specific gene expression levels, and the gene expression response to immune challenge. Further, we identify specific transcription factor signaling pathways that explain these differences, including low-status-associated polarization of the Toll-like receptor 4 signaling pathway toward a proinflammatory response. Our findings provide insight into the direct biological effects of social inequality on immune function, thus improving our understanding of social gradients in health.

Fig. 1. Experimental paradigm

(A) Timeline for group formation in phase one (green: January 2013 to March 2014) and phase two (blue: March 2014 to March 2015), with timelines for behavioral data collection and sample collection shown below.The schematic below the timeline illustrates how groups were formed in phase one, rearranged at the study midpoint, and allowed to organize into new hierarchies during phase two. (B) Example of group formation: Each line represents a different female, introduced sequentially into a new social group. All females entered the group with the same Elo rating but rapidly established a stable hierarchy that persisted until the end of phase one. (C) Order of introduction into a newly formed social group predicted dominance rank (Elo rating) in phase one (green: Pearson's r = −0.57, P = 4.1 × 10⁻⁵) and phase two (blue: r = −0.68, P = 3.3 × 10⁻⁷). (D) Dominance rank predicted rates of received harassment in phase one (green: r = −0.64, P = 2.0 × 10⁻⁶) and phase two (blue: r = −0.90, P = 1.8 × 10⁻¹⁷). (E) Rates of grooming interactions in phase one (green: r = 0.53, P = 2.1 × 10⁻⁴) and phase two (blue: r = 0.75, P = 4.0 × 10⁻⁹). In (C) to (E), lines show the best-fit slope and intercept from a linear model. Rates of harassment and grooming in (D) and (E) are mean-centered to 0 for each social group.

Fig. 2. Cell type–specific effects of dominance rank on gene expression

(A) PCA separates the five FACS-purified immune cell types we investigated (sampled from 45 distinct females in two phases of the study; see table S3). The number of rank-responsive genes in each cell type is shown in parentheses (FDR < 10%; black line shows permutation-based null expectations). (B) Rank effects on gene expression in phase one are positively correlated with rank effects on gene expression in phase two, indicating plasticity in these effects (see also fig. S5). (C) Meta-analysis across cell types identifies NK-specific effects as the most common pattern, followed by effects that are shared across NK and helper Tcells. (D) Mediation analysis for received harassment (top) and grooming rates (bottom) for helper Tcells (left) and NK cells (right). Genes are ordered by the effect size of rank on gene expression levels (dark gray crossmarks; gaps in effect sizes occur because only rank-responsive genes are shown), and “lollipops” connect the effect of dominance rank without including the mediator to the effect of dominance rank when the mediator is taken into account. Colored lines show significant mediating effects, based on 1000 bootstrap iterations. (E) Proportion of rank-responsive genes with significant mediation effects for received harassment (orange), grooming (green), or both (beige).

Fig. 3. Social status influences the immune response to LPS stimulation

(A) PCA decomposition of the control (LPS−) and LPS–stimulated (LPS+) gene expression data. PC1 separates samples by condition; PC2 separates by rank. (B) Across all LPS-responsive genes, the effect of LPS stimulation is larger in low-ranking females than in high-ranking females (data for lowest- versus highest-ranking females are shown). abs(LPS effect): absolute value of the LPS effect on gene expression levels. (C) The four categories of genes affected by LPS in a rank-dependent manner. (D) Selected GO term enrichment for category I and II genes (see table S7 for the complete set). (E) Open chromatin regions near category I genes are enriched for predicted NF-κB binding sites, whereas open chromatin regions near category II genes are enriched for interferon regulatory factor binding sites. Error bars denote the 95% confidence interval of the odds ratio (OR); asterisks indicate statistical significance at P < 0.0001.

Fig. 4. Dominance rank polarizes TLR4 responses to LPS stimulation

(A) Key players in the MyD88-dependent and TRIF-dependent response to LPS-induced TLR4 signaling. Rank-responsive genes in these pathways are shown in blue (category I genes) and purple (category II genes). (B) Rank-responsive genes that are up-regulated upon stimulation via the MyD88 pathway (“MyD88-induced”) are almost universally (89.3%) more highly expressed in low-status females in the LPS+ condition, whereas TRIF-induced, rank-responsive genes are split (Mann-Whitney test for the difference between MyD88-induced and TRIF-induced genes: P = 8.31 × 10⁻⁷). (C) MyD88-induced genes are overrepresented among category I genes [FET log₂(OR) = 1.95, P = 1.6 × 10⁻¹⁵] but significantly underrepresented in category II [log₂(OR) = −2.14, P = 4.1 × 10⁻⁴]. TRIF-induced genes are significantly overrepresented in category II [log₂(OR) = 0.89, P = 0.04]. (D) Median gene expression levels across all MyD88- and TRIF-induced genes for each female, by female dominance rank.