Grey wolf genomic history reveals a dual ancestry of dogs

Abstract

The grey wolf (Canis lupus) was the first species to give rise to a domestic population, and they remained widespread throughout the last Ice Age when many other large mammal species went extinct. Little is known, however, about the history and possible extinction of past wolf populations or when and where the wolf progenitors of the present-day dog lineage (Canis familiaris) lived^1-8. Here we analysed 72 ancient wolf genomes spanning the last 100,000 years from Europe, Siberia and North America. We found that wolf populations were highly connected throughout the Late Pleistocene, with levels of differentiation an order of magnitude lower than they are today. This population connectivity allowed us to detect natural selection across the time series, including rapid fixation of mutations in the gene IFT88 40,000-30,000 years ago. We show that dogs are overall more closely related to ancient wolves from eastern Eurasia than to those from western Eurasia, suggesting a domestication process in the east. However, we also found that dogs in the Near East and Africa derive up to half of their ancestry from a distinct population related to modern southwest Eurasian wolves, reflecting either an independent domestication process or admixture from local wolves. None of the analysed ancient wolf genomes is a direct match for either of these dog ancestries, meaning that the exact progenitor populations remain to be located.

Fig. 1. Seventy-two ancient wolf genomes.

a, Sampling locations of ancient wolves and one ancient dhole analysed here, on a base map from Natural Earth (naturalearthdata.com). b, Ages and sequencing coverage of ancient wolves. c, PC1 from a PCA on outgroup f₃-statistics plotted against sample age. PCs were calculated from ancient wolves only, with present-day wolves and dogs projected onto the plot. d, Heterozygosity estimates from sampling of two reads at sites ascertained as heterozygous in a coyote. Bars denote 95% CIs from block jackknifing.

Fig. 2. One hundred thousand years of wolf population history.

a, Admixture graph fit by qpGraph to selected ancient wolves, with two outlier (|Z| > 3) f-statistics (worst = 3.16). b, Best-fitting qpAdm models for post-LGM and present-day wolves. An ancient dhole was used as the outgroup for Eurasian wolves to capture any unsampled divergent ancestry, while a coyote was used as the outgroup for North American wolves. Bars denote ±1 standard error estimated from a block jackknife. c, F_ST for pairs of sample groups with mean dates separated by ≤12,500 years. Bars denote ±1.96 standard errors d, MSMC2 results for pairs of male X chromosomes, with sample ages indicated by blue lines. A sharp upwards spike in the curve corresponds to population divergence, with estimated timings indicated by red lines. Example curves for two pairs of wolves (left and middle) and a summary of results for all pairs (right) are shown. kyr, thousand years.

Fig. 3. Natural selection in the ancient wolf time series.

a, –log₁₀(P values) (two sided, not adjusted for multiple comparisons) from linear regression for association between allele frequency and sample age. b, Quantile–quantile plot comparing the P values in a to those expected under a uniform distribution (top) and likewise for results from a simulated neutrally evolving population (effective population size (N_e) = 50,000) (bottom). c, Allele observations in ancient wolves and frequencies in present-day populations for lead variants from the three strongest peaks. Bars denote 95% binomial CIs. d, Local P values (from a) and TMRCA inferred using Relate on modern wolves and dogs for the region surrounding IFT88. The genome-wide histogram (quantiles in grey lines) shows that this locus has the most recent TMRCA in the genome.

Fig. 4. The ancestry of dogs.

a, PCA on post-LGM and present-day wolves (X), based on f₄-statistics only of the form f₄(X,A;B,C), where A, B and C are any of 21 wolves predating 28 ka. Dogs are projected, and coloured by f₄(AndeanFox,X;Zhokhov dog 9.5 ka,Tel Hreiz dog 7.2 ka). b, For dogs (X), f₄(AndeanFox,X;Zhokhov dog 9.5 ka,Tel Hreiz dog 7.2 ka) horizontally against f₄(AndeanFox,X;Belaya Gora wolf 18 ka,Hohle Fels wolf 13 ka) vertically (Pearson’s r = 0.86, P = 3 × 10^–23). Bars denote ±1 standard error estimated from a block jackknife. Silhouettes from phylopic.org. c, log₁₀(P values) for qpAdm models fit to dog targets, where a low P value means the model can be rejected. An ancient dhole was used to represent unsampled, divergent ancestry; models including this source have black outlines. Points are jittered horizontally to avoid overlap. d, qpAdm ancestry proportions for dogs, using the Zhokhov (9.5 ka) dog and a present-day Syrian wolf as proxies for eastern and western dog progenitor ancestry, respectively. Bars denote ±1 standard error estimated from a block jackknife. e, Map of early and relevant later dogs and their ancestry proportions as in d. Black crosses indicate the locations of wolves from 25–10 ka that can be rejected as dog progenitors. Base map from the mapdata R package. k, thousand years. f, Admixture graph model of major dog lineage relationships, fit by qpGraph with no outlier f-statistics. Edge lengths are in units of F_ST (×1,000).

Extended Data Fig. 1. f-statistics informing on wolf population history.

Bars denote ±1.96 standard errors for f₃-statistics, and ±3 standard errors for f₄-statistics, estimated from a block jackknife. a) Outgroup f₃-statistics quantifying shared genetic drift with a present-day wolf (Fig. S3). b) f₄-statistics contrasting affinities to a pre-LGM and a post-LGM Siberian wolf (Fig. S4). c) f₄-statistics contrasting affinities to a Siberian and a European pre-LGM wolf (Fig. S6). d) f₄-statistics quantifying whether a ~60 ky old Siberian wolf is closer to a contemporaneous European wolf or other individuals (Fig. S7). e) f₄-statistics quantifying whether a coyote is closer to a ~100ky old Siberian wolf or later individuals.

Extended Data Fig. 2. Placing dogs into wolf diversity in a ‘pre-LGM f₄ PCA’.

PCA on wolves that lived after 25 ka (including present-day), based on profiles of f₄-statistics only of the form f₄(X,A;B,C), where A, B, and C are wolves that lived prior to 28 kya. Dogs are projected. Dogs are coloured according to the f₄-statistic f₄(AndeanFox,X;Zhokhov dog 9.5ka,Tel Hreiz dog 7.2ka), with negative values going towards blue and positive values towards red. A few wolves (in colour) and dogs (in black) of particular interests are indicated with text labels. a) PC1 vs PC2 with the full set of wolves. b) PC3 vs PC4 with the full set of wolves. c) PC1 vs PC2 with western Chinese and North American outlier wolves removed. d) PC3 vs PC4 with western Chinese and North American outlier wolves removed.

Extended Data Fig. 3. Affinities of dogs to ancient wolves.

a) f₄-statistics of the form f₄(AndeanFox,X;wolf A,wolf B), quantifying for all individuals X whether they share more drift with wolf A or wolf B. The ages of A and B are indicated with dashed lines, with positive values indicating affinity to the upper individual and negative values indicating affinity to the lower individual. Bars denote ±3 standard errors estimated from a block jackknife.

Extended Data Fig. 4. A schematic model of how deep population structure could explain why dogs require ancestry from an outgroup population in qpAdm analyses.

Under this model, there is deep population structure between different wolf populations, including the wolf population that becomes the progenitor of dogs. High rates of gene flow over time largely homogenises the ancestry of all populations, but it does not completely erase the deep structure. If the true dog progenitor population is not sampled, a single-source qpAdm model involving one of the sampled wolf populations will not fit dog ancestry, because dogs do not share all of the genetic drift that has occurred in the history of the sampled population. But if an outgroup population is included as a source in qpAdm, this can account for the ‘missing’ deep ancestry in dogs, and therefore result in a model that fits dog ancestry.

Extended Data Fig. 5. Projecting dogs onto present-day wolf population structure.

Principal components analyses performed only on modern wolves, with modern dogs projected.

Extended Data Fig. 6. "Ocean plot" searching for the best available wolf match for the ancestry of eastern dogs.

With the Siberian Zhokhov dog (9.5k BP) as the target, each candidate wolf X was added in turn into the rotating qpAdm analysis. When X is not part of the sources, it is placed in the reference list. Models placed within the gray space labelled “Failed” have p-values fall below the lower limit of the plot.

Extended Data Fig. 7. "Ocean plot" searching for the best available wolf match for the west Eurasian wolf-related ancestry in western dogs.

With the African Basenji dog as a target, all available post-LGM and present-day wolf genomes X are tested as sources combined with the 9.5k-year old Siberian Zhokhov dog, which is assumed to represent a baseline for the Eastern-related dog progenitor ancestry. When X is not part of the sources, it is placed in the reference list. If a target has a model with p > 0.01, models with a larger number of sources are not plotted. Only four individuals achieve good fits in the two-source model (Zhokhov + X): WolfSyria, Wolf07Israel, Wolf20Iran and Wolf19India. For other individuals, including ancient and present-day European wolves, the two-source model can be rejected, and a three-source model with an unsampled ancestry component (Zhokhov + X + unsampled) is needed to fit the data.