The genetic architecture of adaptations to high altitude in Ethiopia

Abstract

Although hypoxia is a major stress on physiological processes, several human populations have survived for millennia at high altitudes, suggesting that they have adapted to hypoxic conditions. This hypothesis was recently corroborated by studies of Tibetan highlanders, which showed that polymorphisms in candidate genes show signatures of natural selection as well as well-replicated association signals for variation in hemoglobin levels. We extended genomic analysis to two Ethiopian ethnic groups: Amhara and Oromo. For each ethnic group, we sampled low and high altitude residents, thus allowing genetic and phenotypic comparisons across altitudes and across ethnic groups. Genome-wide SNP genotype data were collected in these samples by using Illumina arrays. We find that variants associated with hemoglobin variation among Tibetans or other variants at the same loci do not influence the trait in Ethiopians. However, in the Amhara, SNP rs10803083 is associated with hemoglobin levels at genome-wide levels of significance. No significant genotype association was observed for oxygen saturation levels in either ethnic group. Approaches based on allele frequency divergence did not detect outliers in candidate hypoxia genes, but the most differentiated variants between high- and lowlanders have a clear role in pathogen defense. Interestingly, a significant excess of allele frequency divergence was consistently detected for genes involved in cell cycle control and DNA damage and repair, thus pointing to new pathways for high altitude adaptations. Finally, a comparison of CpG methylation levels between high- and lowlanders found several significant signals at individual genes in the Oromo.

Figure 1. Hemoglobin and oxygen saturation measurements.

Box plots describe variation in the Amhara 05 (dark grey boxes), Amhara 95 (grey boxes) and Oromo (white boxes) for Hb concentration (g/dL) among males (A) and females (B) and for O₂ sat also among males (E) and females (F). Box plots show the median (horizontal line), interquartile range (box), and range (whiskers), except the extreme values represented by circles. Statistically significant differences after multiple test correction between groups (unpaired two-sided two-sample t-test) are bolded in C, D, G, and H.

Figure 2. Hemoglobin association test within Amhara.

The QQplot represents the excess of strong association with Hb among Amhara individuals (A). The observed −log10 p-value distribution is ranked from smallest to largest and plotted (y-axis) against the expected −log10 p-value (y-axis) in black. The grey area indicates the 95% confidence interval (see methods). Genome-wide (GW) significance level (after multiple test correction) is indicated by the dashed line. The Manhattan plot (B) shows the GW significance achieved by a set of high-LD SNPs in chromosome 1. The box plots describe the correlation between hemoglobin levels and the 3 genotypes of the top and GW significant SNP (rs10803083) among high (C) and low altitude (D) Amhara.

Figure 3. Power plots.

The effect of β and MAF on the power of association tests based on the Ethiopian sample size (corrected for the number of SNPs tested within 10 kb from gene) is illustrated for EPAS1 (A, 72 SNPs)), EGLN1 (B, 38 SNPs) and any gene within the Response to Hypoxia gene ontology category (C, 1309 SNPs).