Mitogenomes Reveal Two Major Influxes of Papuan Ancestry across Wallacea Following the Last Glacial Maximum and Austronesian Contact

Abstract

The tropical archipelago of Wallacea contains thousands of individual islands interspersed between mainland Asia and Near Oceania, and marks the location of a series of ancient oceanic voyages leading to the peopling of Sahul-i.e., the former continent that joined Australia and New Guinea at a time of lowered sea level-by 50,000 years ago. Despite the apparent deep antiquity of human presence in Wallacea, prior population history research in this region has been hampered by patchy archaeological and genetic records and is largely concentrated upon more recent history that follows the arrival of Austronesian seafarers ~3000-4000 years ago (3-4 ka). To shed light on the deeper history of Wallacea and its connections with New Guinea and Australia, we performed phylogeographic analyses on 656 whole mitogenomes from these three regions, including 186 new samples from eight Wallacean islands and three West Papuan populations. Our results point to a surprisingly dynamic population history in Wallacea, marked by two periods of extensive demographic change concentrated around the Last Glacial Maximum ~15 ka and post-Austronesian contact ~3 ka. These changes appear to have greatly diminished genetic signals informative about the original peopling of Sahul, and have important implications for our current understanding of the population history of the region.

Keywords: Sahul; human migrations; mitochondria; mtDNA; phylogeography.

Figure 1

Historical land coverage across study regions and sampling locations of new mitogenomes. Exposed land areas for the Sunda and Sahul continental shelves and the interceding Wallacean islands are shown for the current period (light grey) and inferred for lower sea stands occurring ~65 ka (−50 m; medium grey) and ~20 ka (−120 m; dark grey) before the current period [13]. The locations of major biogeographic boundaries separating Wallacea from the Sunda and Sahul shelves are shown as black (Wallace’s Line) and green dashed lines (Lydekker’s Line), respectively. Sampling locations (red dots) are indicated by their abbreviated population IDs (see Table S1, Supplementary Materials), with sample size indicated directly beneath.

Figure 2

BEAST consensus tree for 656 mitogenomes from Wallacea, New Guinea, and Australia. The tree is based on putative Australo-Papuan-affiliated haplogroups, split into the two main non-African macrohaplogroups M (A) and N (B). Samples from Wallacea (WLC) are coloured green, with those from Papua (PAP; i.e., New Guinea and Island Melanesia) and Australia (AUS) being coloured blue and red, respectively. All monophyletic clades are collapsed.

Figure 2

BEAST consensus tree for 656 mitogenomes from Wallacea, New Guinea, and Australia. The tree is based on putative Australo-Papuan-affiliated haplogroups, split into the two main non-African macrohaplogroups M (A) and N (B). Samples from Wallacea (WLC) are coloured green, with those from Papua (PAP; i.e., New Guinea and Island Melanesia) and Australia (AUS) being coloured blue and red, respectively. All monophyletic clades are collapsed.

Figure 3

Distribution of TMRCAs for all monophyletic clades. Distributions are shown for each of the 68 monophyletic clades with >50% support (support shown in text to the right of each distribution). Clades are organised by region—AUS = Australia; PAP = Papua (i.e., New Guinea and Island Melanesia); WLC = Wallacea—and are coloured according to the number of tips (samples) that they contain. Vertical lines of each distribution indicate median estimated TMRCA. Additional information for each clade is provided in Table S5 (Supplementary Materials) and indexed according to integer labels on the y-axis in the current plot.

Figure 4

Properties of aggregated TMRCAs across Wallacea, New Guinea, and Australia. Probability distributions (PDF; (A)) and cumulative distributions (CDF; (B)) for the TMRCAs aggregated across all monophyletic clades in each region (see key in (A)). TMRCAs for the 50th and 90th percentiles are indicated by the lower and upper dashed lines, respectively, in (B). TMRCAs were deeper on average for Australia, even after controlling for the number of tips (samples) in the clade (C). Linear and quadratic regression fits are shown as dashed and solid lines, respectively.

Figure 5

Estimated migration rates across Wallacea, New Guinea, and Australia. Distribution of the mean migration rates across each region across time for the four best-performing BayesTraits models. For each model, migration rates were estimated from 1000 SIMMAP stochastic mappings, with each migration event comprising a single simulated state transition occurring on a branch of the consensus BEAST tree. Transition rate matrices and ancestral node states were derived from BayesTraits (see Figure S4, Supplementary Materials, for other parameterisations). Migration rates are scaled to account for the expected number of migration events (see Section 2).