Features of evolution and expansion of modern humans, inferred from genomewide microsatellite markers

Abstract

We study data on variation in 52 worldwide populations at 377 autosomal short tandem repeat loci, to infer a demographic history of human populations. Variation at di-, tri-, and tetranucleotide repeat loci is distributed differently, although each class of markers exhibits a decrease of within-population genetic variation in the following order: sub-Saharan Africa, Eurasia, East Asia, Oceania, and America. There is a similar decrease in the frequency of private alleles. With multidimensional scaling, populations belonging to the same major geographic region cluster together, and some regions permit a finer resolution of populations. When a stepwise mutation model is used, a population tree based on TD estimates of divergence time suggests that the branches leading to the present sub-Saharan African populations of hunter-gatherers were the first to diverge from a common ancestral population (approximately 71-142 thousand years ago). The branches corresponding to sub-Saharan African farming populations and those that left Africa diverge next, with subsequent splits of branches for Eurasia, Oceania, East Asia, and America. African hunter-gatherer populations and populations of Oceania and America exhibit no statistically significant signature of growth. The features of population subdivision and growth are discussed in the context of the ancient expansion of modern humans.

Figure  1

Among-locus distribution of the total number of alleles observed in 1,056 individuals at di-, tri-, and tetranucleotide STRs.

Figure  2

Among-locus distribution of the within-population variance in the repeat scores at di-, tri-, and tetranucleotide STRs. For each STR, the values of the within-population variance were averaged over all 52 populations.

Figure  3

Distribution and clusters of 52 populations from the first two PCs in the multidimensional-scaling plot of F_ST values at 377 STRs. Most populations are indicated with numbers (see the “Material and Methods” section). The X- and Y-axes represent PC1 and PC2, respectively. ⧫ = Mozabite; ◊ = three Middle East samples; □ = Basque, Sardinian, and Orcadian samples; ○ = five other samples from Europe; ▵ = East Asian Altaic-speaking populations; ▴ = two Han populations; * = Kalash; ● = remaining samples.

Figure  4

Multidimensional scaling on the F_ST values at 377 STRs. A, Separation of sub-Saharan African and American populations in a plot of PC4 versus PC1. B, Separation of Oceania in a plot of PC5 versus PC2 (samples from Africa and America are suppressed).

Figure  5

Population tree based on T_D estimates of divergence time. A. Divergence among major groups. The time estimates are based on 374 STRs (three outlying STRs with tetranucleotide repeats were omitted). Arrows indicate the time (lower bounds, in ky) between adjacent nodes, assuming a generation length of 25 years. B, Schemes of divergence within the major groups, based on the 374 STRs. Time estimates within each continental group were omitted, because they may be biased owing to possible differential gene flows from other groups.

Figure  6

Reduced population tree, showing four separation events (see table 3)