Upper Palaeolithic Siberian genome reveals dual ancestry of Native Americans

Abstract

The origins of the First Americans remain contentious. Although Native Americans seem to be genetically most closely related to east Asians, there is no consensus with regard to which specific Old World populations they are closest to. Here we sequence the draft genome of an approximately 24,000-year-old individual (MA-1), from Mal'ta in south-central Siberia, to an average depth of 1×. To our knowledge this is the oldest anatomically modern human genome reported to date. The MA-1 mitochondrial genome belongs to haplogroup U, which has also been found at high frequency among Upper Palaeolithic and Mesolithic European hunter-gatherers, and the Y chromosome of MA-1 is basal to modern-day western Eurasians and near the root of most Native American lineages. Similarly, we find autosomal evidence that MA-1 is basal to modern-day western Eurasians and genetically closely related to modern-day Native Americans, with no close affinity to east Asians. This suggests that populations related to contemporary western Eurasians had a more north-easterly distribution 24,000 years ago than commonly thought. Furthermore, we estimate that 14 to 38% of Native American ancestry may originate through gene flow from this ancient population. This is likely to have occurred after the divergence of Native American ancestors from east Asian ancestors, but before the diversification of Native American populations in the New World. Gene flow from the MA-1 lineage into Native American ancestors could explain why several crania from the First Americans have been reported as bearing morphological characteristics that do not resemble those of east Asians. Sequencing of another south-central Siberian, Afontova Gora-2 dating to approximately 17,000 years ago, revealed similar autosomal genetic signatures as MA-1, suggesting that the region was continuously occupied by humans throughout the Last Glacial Maximum. Our findings reveal that western Eurasian genetic signatures in modern-day Native Americans derive not only from post-Columbian admixture, as commonly thought, but also from a mixed ancestry of the First Americans.

Figure 1

Sample locations and MA-1 genetic affinities. a, Geographical locations of Mal’ta and Afontova Gora-2 in south-central Siberia. For reference, Palaeolithic sites with individuals belonging to mtDNA haplogroup U are shown (red and black triangles): 1, Oberkassel; 2, Hohle Fels; 3, Dolni Vestonice; 4, Kostenki-14. A Palaeolithic site with an individual belonging to mtDNA haplogroup B is represented by the square: 5, Tianyuan Cave. Notable Palaeolithic sites with Venus figurines are marked by brown circles: 6, Laussel; 7, Lespugue; 8, Grimaldi; 9, Willendorf; 10, Gargarino. Other notable Palaeolithic sites are shown by grey circles: 11, Sungir; 12, Yana RHS. b, PCA (PC1 versus PC2) of MA-1 and worldwide human populations for which genomic tracts from recent European admixture in American and Siberian populations have been excluded. c, Heat map of the statistic f₃(Yoruba; MA-1, X) where X is one of 147 worldwide non-African populations (standard errors shown in Supplementary Fig. 21). The graded heat key represents the magnitude of the computed f₃ statistics.

Figure 2

Admixture graph for MA-1 and 16 complete genomes. An admixture graph with two migration edges (depicted by arrows) was fitted using TreeMix to relate MA-1 to 11 modern genomes from worldwide populations, 4 modern genomes produced in this study (Avar, Mari, Indian and Tajik), and the Denisova genome. Trees without migration, graphs with different number of migration edges, and residual matrices are shown in Supplementary Information, section 11. The drift parameter is proportional to 2N_e generations, where N_e is the effective population size. The migration weight represents the fraction of ancestry derived from the migration edge. The scale bar shows ten times the average standard error (s.e.) of the entries in the sample covariance matrix. Note that the length of the branch leading to MA-1 is affected by this ancient genome being represented by haploid genotypes.

Figure 3

Evidence of gene flow from a population related to MA-1 and western Eurasians into Native American ancestors. Allele frequency-based D-statistic tests of the forms. a, D (Yoruba, MA-1; Han, X), where X represents modern-day populations from North and South America. The D-statistic is significantly positive for all the tests, providing evidence for gene flow between Native American ancestors and the MA-1 population lineage; however, it is not informative with respect to the direction of gene flow. b, D (Yoruba, X; Han, Karitiana), where X represents non-African populations. Since all of the 17 tested western Eurasian populations are closer to Karitiana than to Han Chinese, the most parsimonious explanation is that Native Americans have western Eurasian-related ancestry. c, D (Sardinian, X; Papuan, Han), where X represents non-African populations. MA-1 is not significantly closer to Han Chinese than to Papuans, which is compatible with MA-1 having no Native American-related admixture in its ancestry. Thick and thin error bars correspond to 1 and 3 standard errors of the D-statistic, respectively.