Gene regulation in primates evolves under tissue-specific selection pressures

Abstract

Regulatory changes have long been hypothesized to play an important role in primate evolution. To identify adaptive regulatory changes in humans, we performed a genome-wide survey for genes in which regulation has likely evolved under natural selection. To do so, we used a multi-species microarray to measure gene expression levels in livers, kidneys, and hearts from six humans, chimpanzees, and rhesus macaques. This comparative gene expression data allowed us to identify a large number of genes, as well as specific pathways, whose inter-species expression profiles are consistent with the action of stabilizing or directional selection on gene regulation. Among the latter set, we found an enrichment of genes involved in metabolic pathways, consistent with the hypothesis that shifts in diet underlie many regulatory adaptations in humans. In addition, we found evidence for tissue-specific selection pressures, as well as lower rates of protein evolution for genes in which regulation evolves under natural selection. These observations are consistent with the notion that adaptive circumscribed changes in gene regulation have fewer deleterious pleiotropic effects compared with changes at the protein sequence level.

Figure 1. Estimates of lineage-specific expression changes.

A. Increase (green bars) and decrease (red bars) of gene expression levels in the human (d_H, top) and chimpanzee (d_C, bottom) lineages are plotted. B. Box plots of the estimated expression changes (y-axis) along the human (red) and chimpanzee (purple) lineages in liver, kidney, and heart (x-axis).

Figure 2. Examples of expression patterns that are consistent with the action of natural selection.

Liver expression profiles from the three species are plotted for genes whose regulation has likely evolved under stabilizing (A) or directional (B) selection. In all panels, the mean (±s.e.m) log expression level (y-axis) of each species (x-axis) is plotted relative to the human value.

Figure 3. Comparison of data across tissues.

Venn diagrams showing the number of genes whose regulation likely evolved under stabilizing (A) and directional (B) selection in liver, kidney, and heart.

Figure 4. Directional selection on gene regulation in humans affects metabolic pathways.

The interaction network was generated using the Ingenuity Pathway Analysis (IPA) tool (version 6.0). All shaded nodes represent genes whose regulation evolves under directional selection. Transcription factors are shaded in orange. Specific metabolic functions that are associated with the individual genes are listed.

Figure 5. Tissue-specific selection on gene regulation.

Examples of expression patterns that are consistent with the action of directional selection on gene regulation in the human liver (A), kidney (B), or heart (C) and the action stabilizing selection on gene regulation in the other two tissues. In the top panels, we plot the normalized log-expression intensities of all the probes for these genes from all relevant hybridizations and in the bottom panel the estimated relative log expression levels (±s.e.m). On the x-axis, HL stands for expression results from human liver; HK - human kidney; HH - human heart; CL - chimpanzee liver; CK - chimpanzee kidney; CH - chimpanzee heart; RL - rhesus macaque liver; RK - rhesus macaque kidney; RH - rhesus macaque heart.

Figure 6. Protein evolution and selection on gene regulation.

Cumulative distributions of d_N/d_S values (x-axis) of (A) genes whose regulation evolved under stabilizing selection in the liver (red), directional selection in the liver (blue), or for which we do not have evidence for selection on gene regulation in the liver (green), and (B) genes whose regulation evolved under stabilizing selection in one (pink), two (red), or three (black) tissues. The smaller panels show the d_N/d_S medians in the three groups. The error bars are 95% confidence intervals calculated using bootstrapping (1000 repetitions).