Diversity of lactase persistence in African milk drinkers

Abstract

The genetic trait of lactase persistence is attributable to allelic variants in an enhancer region upstream of the lactase gene, LCT. To date, five different functional alleles, -13910*T, -13907*G, -13915*G, -14009*G and -14010*C, have been identified. The co-occurrence of several of these alleles in Ethiopian lactose digesters leads to a pattern of sequence diversity characteristic of a 'soft selective sweep'. Here we hypothesise that throughout Africa, where multiple functional alleles co-exist, the enhancer diversity will be greater in groups who are traditional milk drinkers than in non-milk drinkers, as the result of this sort of parallel selection. Samples from 23 distinct groups from 10 different countries were examined. Each group was classified 'Yes 'or 'No' for milk-drinking, and ethnicity, language spoken and geographic location were recorded. Predicted lactase persistence frequency and enhancer diversity were, as hypothesised, higher in the milk drinkers than the non-milk-drinkers, but this was almost entirely accounted for by the Afro-Asiatic language speaking peoples of east Africa. The other groups, including the 'Nilo-Saharan language speaking' milk-drinkers, show lower frequencies of LP and lower diversity, and there was a north-east to south-west decline in overall diversity. Amongst the Afro-Asiatic (Cushitic) language speaking Oromo, however, the geographic cline was not evident and the southern pastoralist Borana showed much higher LP frequency and enhancer diversity than the other groups. Together these results reflect the effects of parallel selection, the stochastic processes of the occurrence and spread of the mutations, and time depth of milk drinking tradition.

Fig. 1

Scatter plots of lactase persistence (LP) and nucleotide diversity (Pi) in groups who traditionally milk animals and drink milk, or do not. a Inferred LP frequency in the milk drinking and non-milk drinking African groups. b Pi for the 3 regions sequenced. LP frequency calculated from the combined allele frequency using all 5 known functional alleles and assuming dominance, 2pq + q ², where q = combined allele frequency for all 5 functional alleles and p corresponds to the combined allele frequency for all alleles without a functional variant. Milk drinkers filled triangles; non-milk drinkers open triangles. Horizontal bars show medians. Difference in LP frequency and difference in Enhancer Pi in milk drinkers and non-milk drinkers are both statistically significant (LP frequency: p = 0.0056; Enhancer Pi: p = 0.00288, Mann Whitney Rank test)

Fig. 2

Genetic and linguistic differentiation of the groups under study. a PCO plot of pairwise Fsts showing the first two principal components, PCO1 (64.8 %) on the X axis and PCO2 (32.55 %) on the Y axis b Plot of nucleotide diversity, Pi (Y axis), versus LP frequency calculated from the combined data of all 5 functional alleles (X axis) r ² = 0.86 p ≪ 0.001. Fsts calculated using the three sequenced regions combined, but similar results were obtained for the separated regions. Triangles Afro-asiatic language speakers; circles Niger Congo languages; squares Nilo-Saharan and diamond Khoisan. Filled symbols are milk-drinking populations while open symbols are not. Supplementary Figure 2 shows correlations of the data subdivided by language group and milk drinking status

Fig. 3

Interpolated smoothed contour maps of LCT enhancer diversity. a Pi × 10² and b inferred lactase persistence frequency in Africa. Dots indicate data points. Lactase persistence frequency calculated from the sum of the five functional alleles (−13907*G, −13910*T, −13915*G, −14009*G and −14010*C), and assuming dominance

Fig. 4

Scatter plot showing correlation of nucleotide diversity (Pi) (Y axis) and inferred LP frequency (X axis) in different Oromo groups. This strong correlation r ² 0.98 p ≪ 0.001 is attributable to co-selection of 5 different LP alleles. 4 newly collected, geographically distinct groups are shown as triangles, (see Supplementary Table 3 for data) in comparison with the Oromo collection shown in Table 1, (‘Oromo table 1’), and also the Oromo group previously published (Jones et al. 2013) (‘Various’), both of which are shown as squares. The data point marked as a darker triangle is that obtained from the pastoralist Borana from the south