The making of the African mtDNA landscape

Abstract

Africa presents the most complex genetic picture of any continent, with a time depth for mitochondrial DNA (mtDNA) lineages >100,000 years. The most recent widespread demographic shift within the continent was most probably the Bantu dispersals, which archaeological and linguistic evidence suggest originated in West Africa 3,000-4,000 years ago, spreading both east and south. Here, we have carried out a thorough phylogeographic analysis of mtDNA variation in a total of 2,847 samples from throughout the continent, including 307 new sequences from southeast African Bantu speakers. The results suggest that the southeast Bantu speakers have a composite origin on the maternal line of descent, with approximately 44% of lineages deriving from West Africa, approximately 21% from either West or Central Africa, approximately 30% from East Africa, and approximately 5% from southern African Khoisan-speaking groups. The ages of the major founder types of both West and East African origin are consistent with the likely timing of Bantu dispersals, with those from the west somewhat predating those from the east. Despite this composite picture, the southeastern African Bantu groups are indistinguishable from each other with respect to their mtDNA, suggesting that they either had a common origin at the point of entry into southeastern Africa or have undergone very extensive gene flow since.

Figure 1

Map of Africa showing the samples used in the present work. The pie charts represent the haplogroup composition of the main African regions, combining some sub-clades for convenience, and excluding the contribution of haplogroups of non-African origin. Population codes are as defined in table 1.

Figure 2

mtDNA skeleton showing a schematic phylogeny of African haplogroups used in the present paper to classify HVS-I sequences. The skeleton includes HVS-I and some coding-region RFLPs (with an arrow pointing in the direction of site gain).

Figure 3

Plot showing the first two principal components of haplogroup frequency profiles for the African samples (population codes as in table 1).

Figure 4

Networks of (a) L1a and (b) L1b lineages. Circle sizes are proportional to the haplotype frequency in the sample.

Figure 5

Networks of (a) L1c, (b) L1d, and (c) L1e lineages

Figure 6

Network of L2a lineages

Figure 7

Networks of (a) L2b, (b) L2c, and (c) L2d lineages

Figure 8

Networks of (a) L3f, (b) L3g, and (c) L3b lineages

Figure 9

Networks of (a) L3d and (b) L3e lineages