Genome-wide analysis of cold adaptation in indigenous Siberian populations

Abstract

Following the dispersal out of Africa, where hominins evolved in warm environments for millions of years, our species has colonised different climate zones of the world, including high latitudes and cold environments. The extent to which human habitation in (sub-)Arctic regions has been enabled by cultural buffering, short-term acclimatization and genetic adaptations is not clearly understood. Present day indigenous populations of Siberia show a number of phenotypic features, such as increased basal metabolic rate, low serum lipid levels and increased blood pressure that have been attributed to adaptation to the extreme cold climate. In this study we introduce a dataset of 200 individuals from ten indigenous Siberian populations that were genotyped for 730,525 SNPs across the genome to identify genes and non-coding regions that have undergone unusually rapid allele frequency and long-range haplotype homozygosity change in the recent past. At least three distinct population clusters could be identified among the Siberians, each of which showed a number of unique signals of selection. A region on chromosome 11 (chr11:66-69 Mb) contained the largest amount of clustering of significant signals and also the strongest signals in all the different selection tests performed. We present a list of candidate cold adaption genes that showed significant signals of positive selection with our strongest signals associated with genes involved in energy regulation and metabolism (CPT1A, LRP5, THADA) and vascular smooth muscle contraction (PRKG1). By employing a new method that paints phased chromosome chunks by their ancestry we distinguish local Siberian-specific long-range haplotype signals from those introduced by admixture.

Figure 1. Population structure analyses in Siberian populations.

(A) Averaged sampling locations of the Siberian populations genotyped in this study. (B) Principal component analysis of Siberian populations and reference populations from West Asia (European) and Southeast Asia (Vietnamese). Each dot in the plot represents an individual. The PC axes were rotated 180 degrees anti-clockwise to emphasize the similarity to the geographic map of Eurasia. (C) ADMIXTURE analysis at K = 4. (D) Coancestry heatmap for the Siberian individuals and reference populations (Europe, Vietnamese) output by ChromoPainter/fineSTRUCTURE. The heatmap shows the number of shared genetic chunks between the individuals. The raw data is shown on the bottom left and the aggregated data is shown on the upper right of the heatmap. Adjacent to the heatmap is also the ADMIXTURE plot of the respective individuals. To the left is the maximum a posteriori (MAP) tree generated by fineSTRUCTURE which shows the groupings of the different populations. The following abbreviations are used in the Figure: ALT, Altai-Kizhi; BUR, Buryats; CEU, European; CHB, Han Chinese; CHK, Chukchi; E/SE Asia, East/Southeast Asia; ESK, Eskimo; EVN, Evens; EVK, Evenks; KRK, Koryaks; SHR, Shors; TEL, Teleuts; VTN, Vietnamese; X1, Northeastern Siberian admixed individuals; X2, Southern and Central Siberian admixed individuals; YKT, Yakuts. Reference populations are labelled in italics. Outliers removed in downstream analysis are blacked out in the tree.

Figure 2. Zooming on the region on chromosome 11 that showed the strongest signals in the Northeastern Siberian populations.

The |iHS|, XP-EHH and PBS scores that showed strong signals (amongst top 10 ranking windows) in the Northeastern Siberian populations are shown in the upper panels for the different Siberian populations. The pink highlights mark the windows present in the top 10 ranking windows in the Northeastern Siberian populations. The rankings are marked on the respective windows in the respective test panels. Protein-coding genes present in the 4 Mb region are shown under the test plots with the genes present in our predefined cold adaptation list marked in bold font (CPT1A and LRP5). The position on the chromosome is given in Mb. The paintings of the phased chromosomes for the region in the Northeastern and Central Siberian individuals are shown underneath the Position legend. The aggregated ancestral probabilities from ChromoPainter for the Northeastern Siberian individuals are displayed below the paintings. The dotted red line shows the threshold for the upper 5% tail (0.75) and the black dotted line shows the mean of the genome-wide probabilities distribution of the Northeastern Siberian ancestor (red).

Figure 3. Genome-wide distribution of significant selection windows.

The distribution of the significant windows of the three different selection tests results (A) XP-EHH, (B) iHS and (C) PBS for the Northeastern Siberian populations. The x-axis show the count of significant windows (Tables S4–S6 in File S2) per 3 Mb region and the y-axis show the amount of 3 Mb regions that had the respective count displayed on the x-axis. In all the different selection tests, the region on chromosome 11:66–69 Mb is the region with the most significant selection windows (highlighted in red).