The population genetics of structural variation

Abstract

Population genetics is central to our understanding of human variation, and by linking medical and evolutionary themes, it enables us to understand the origins and impacts of our genomic differences. Despite current limitations in our knowledge of the locations, sizes and mutational origins of structural variants, our characterization of their population genetics is developing apace, bringing new insights into recent human adaptation, genome biology and disease. We summarize recent dramatic advances, describe the diverse mutational origins of chromosomal rearrangements and argue that their complexity necessitates a re-evaluation of existing population genetic methods.

Figure 1

Diploid copy numbers, corresponding CNV genotypes and the underlying quantitative data from an array CGH experiment. Top, biallelic CNV; bottom, multiallelic CNV (data from ref. 11). Note that there is not a 1:1 mapping of diploid copy numbers to CNV genotypes for the multiallelic CNV.

Figure 2

Cumulative number of RefSNP entries in dbSNP and cumulative number of variant loci in the Database of Genomic Variants, plotted as a function of time. Axes have been scaled differently to enhance visualization. RefSNP entries: left axis, blue (M = million). DGV entries: right axis, gray.

Figure 3

The maximal pairwise LD with a nearby SNP is lower around CNVs that are associated with segmental duplications than around CNVs in single-copy sequences.

Figure 4

Estimates of fine-scale recombination rate across the 8p23 inversion. Haplotypes from Supplementary Figure 2 were used to generate estimates of population genetic recombination rate using the method from ref. . Phylogenetic analysis of the SNP haplotypes uncovered two primary clades, and clade membership was used as a proxy for inversion status, with the minor allele assumed to be the inverted allele, arbitrarily. (a) Estimate of the population-scaled recombination rate (ρ = 4N_er) using 20 minor and 20 major (common) alleles. (b) Estimate of 4N_er using 40 haplotypes of the minor allele. (c) Estimate of 4N_er using 40 haplotypes of the major allele. As recombination is restricted in inversion heterozygotes, mutations that are private to either inversion background will be in extreme LD when considered at the population level, leading to low estimates of 4N_er in a. The analysis for a was run several times with different sets of minor and major haplotypes, and at most one ‘hotspot’ was detected visually.

Figure 5

Plots of population structure for 67 CNVs and 67 unlinked SNPs in 210 unrelated HapMap individuals, assuming three ancestral populations. The slightly improved clustering quality from SNP genotypes most likely relates to the lower frequency of missing genotypes in the SNP data.