Structural diversity and African origin of the 17q21.31 inversion polymorphism

Abstract

The 17q21.31 inversion polymorphism exists either as direct (H1) or inverted (H2) haplotypes with differential predispositions to disease and selection. We investigated its genetic diversity in 2,700 individuals, with an emphasis on African populations. We characterize eight structural haplotypes due to complex rearrangements that vary in size from 1.08-1.49 Mb and provide evidence for a 30-kb H1-H2 double recombination event. We show that recurrent partial duplications of the KANSL1 gene have occurred on both the H1 and H2 haplotypes and have risen to high frequency in European populations. We identify a likely ancestral H2 haplotype (H2') lacking these duplications that is enriched among African hunter-gatherer groups yet essentially absent from West African populations. Whereas H1 and H2 segmental duplications arose independently and before human migration out of Africa, they have reached high frequencies recently among Europeans, either because of extraordinary genetic drift or selective sweeps.

Figure 1. Duplication architecture of 17q21.31

(a) Frequency of haplotypes (H2D, H1D) carrying duplications (CNP155 and CNP205) and those not carrying duplications (ND) are shown for three major continental groups (Africans, Asians, and Europeans) based on analysis of 620 individuals. (b) Read-depth-based copy number estimates of the 17q21.31 region from 46 representative European genomes show different patterns of duplications for the KANSL1 and NSF regions. Colors indicate the absolute copy number genome-wide for each given segment . The heatmap is aligned to the H1 haplotype structure at the bottom (reference genome) where colored boxes indicate segmental duplications as described in Zody et al. , and the black line represents single-copy regions. The heatmap distinguishes genotypes for a 205 kbp copy-number polymorphism (CNP205) associated with H2D, a 155 kbp polymorphism (CNP155) associated with H1D, and copy-number variation of a 210 kbp segment of NSF, which ranges from 2–8 copies (CNP210). Note that CNP205 and CNP155 have a diploid copy number of two in the reference genome assembly (shown at the bottom) and CNP210 has instead a diploid copy number of four. (c) Population stratification of duplicated alleles. CNP155 and CNP205 show increased allele frequency (23.1% and 19.6%, respectively) among Europeans; CNP210 shows a significant increase in copy number among Asians, compared to Europeans and Africans.

Figure 2. Alternative structural haplotypes of 17q21.31

(a) FISH cohybridization experiments using probes mapping to CNP155/CNP205 (WIBR2-2342H02 in green), NSF CNP210 duplication (WIBR2-1321L07 in red), and at the single-copy region (WIBR2-3237D21 in blue) are shown. (b) Shown are eight distinct structural haplotypes (five H1 and three H2) ranging in size from 1.08 to 1.49 Mbp. Colored boxes indicate segmental duplications as determined by complete sequencing of large-insert BAC clones by Zody et al. . Hashed boxes correspond to regions present in single copy in that specific haplotype but duplicated in others. The locations of three core duplicons mapping in close proximity to the inversion breakpoints are shown. These represent some of the most abundant and rapidly evolving duplicated sequences in the human genome . The duplication content for each haplotype is indicated in parentheses. Four main haplotypes are defined based on KANSL1 copy number and on the length of the duplication (Boettger et al. nomenclature in parentheses): H1′ (direct haplotype) and H2′ (inverted haplotype) with one copy each of KANSL1, H1D (H1.β2.γ1) with a long duplication of the gene, and H2D (H2.α2.γ2) with a short duplication. H1′ configurations with one copy of NSF are defined as H1.1 (H1.β1.γ1), with two copies as H1.2 (H1.β1.γ2), and with three copies as H1.3 (H1.β1.γ3). H1D configurations with three copies of the long duplication are defined as H1D.3 (H1.β3.γ1). Similarly, H2′ configurations with one copy of NSF are defined as H2.1 and with two copies as H2.2 (H2.α1.γ2).

Figure 3. Haplotype frequency of 17q21.31 inversion in Africa

Frequency of direct (H1), inverted (H2′), and inverted with duplication (H2D) haplotypes in 818 individuals (1636 chromosomes) from 23 African populations. The H2′ haplotype is absent from virtually all Western African individuals except for the Pygmy populations (Bakola, Biaka, and Mbuti). The H2′ haplotype frequency is highest in the Beja from Sudan likely due to admixture from neighboring Middle Eastern countries. The inversion is also at appreciable frequencies in the other hunter-gatherer populations (San, Hadza, Sandawe, Boni, and Sengwer).

Figure 4. Phylogenetic relationship between H1 and H2 haplotypes

(a) Alignment of 43 SNPs from a 136 kbp LD block within the inversion region (chr17:41466118-41602794, NCBI build36) from HapMap individuals (total N = 728 individuals; 1456 chromosomes) were used to build a maximum likelihood tree with 1000 bootstrap replicates (all branches with 100% bootstrap support). (b) An unrooted neighbor-joining tree was constructed using MEGA4 complete deletion option based on 204,447 aligned base pairs from unique sequence within the inversion. The number of mutations for each branch is indicated above the branch. African individuals are highlighted in red and Europeans are highlighted in blue.

Figure 5. Historical exchange between H1 and H2 haplotypes

(a) Divergence plotted in 5 kbp sliding windows. A 30 kbp region (chr17:41213364-41248960, middle red bar) of reduced divergence over the 5′ end of CRHR1 is revealed. The spike in divergence at 41.35 Mbp corresponds to a simple TATA repeat tract. Median-joining haplotype networks based on the HapMap collection for (b) the region proximal to the 5′ end of CRHR1 (chr17:41011056-41091056, far left red bar), (c) the region of reduced divergence, and (d) the region distal to the region of reduced divergence (chr17:41410073-41425073, far right red bar). The proportion of H1′ (blue), H1D (orange), H2′ (red), and H2D (green) haplotypes are shown. The haplotypes form distinct clades proximal and distal to the CRHR1 region while over the region of reduced divergence the haplotypes are mixed creating a large haplogroup where H1 chromosomes have sequence similar to the H2 chromosomes. Red tick marks represent the number of mutations separating each haplogroup.

Figure 6. Evolutionary history of 17q21.31 haplotypes

We propose a model where the H2′ haplotype represents the ancestral configuration of the 17q21.31 region in humans. Approximately 2.3 mya, the inversion toggled back to the direct orientation and spread to South Africa prior to the emergence of modern humans. The H2D duplication arose in Africa 1.3 mya, and the H1D duplication independently arose much more recently, approximately 250,000 years ago. The H1′ haplotype spread throughout Western Africa, and all haplotypes spread to the Middle East and Europe as part of the out-of-Africa migration.