Singapore Genome Variation Project: a haplotype map of three Southeast Asian populations

Abstract

The Singapore Genome Variation Project (SGVP) provides a publicly available resource of 1.6 million single nucleotide polymorphisms (SNPs) genotyped in 268 individuals from the Chinese, Malay, and Indian population groups in Southeast Asia. This online database catalogs information and summaries on genotype and phased haplotype data, including allele frequencies, assessment of linkage disequilibrium (LD), and recombination rates in a format similar to the International HapMap Project. Here, we introduce this resource and describe the analysis of human genomic variation upon agglomerating data from the HapMap and the Human Genome Diversity Project, providing useful insights into the population structure of the three major population groups in Asia. In addition, this resource also surveyed across the genome for variation in regional patterns of LD between the HapMap and SGVP populations, and for signatures of positive natural selection using two well-established metrics: iHS and XP-EHH. The raw and processed genetic data, together with all population genetic summaries, are publicly available for download and browsing through a web browser modeled with the Generic Genome Browser.

Figure 1.

Principal component analysis plots of genetic diversity across HapMap, HGDP, and SGVP populations. Each figure represents the genetic diversity seen across the populations considered, with each sample mapped onto a spectrum of genetic variation represented by two axes of variations corresponding to two eigenvectors of the PCA. (A) Individuals from each population in the HapMap and SGVP are represented by a unique color, while samples from HGDP are broadly grouped by geography in which a unique color is assigned to each geographical location. (B) Comparison between CHS and samples from Far East Asia found in the HapMap and HGDP. (C) A plot of the third and fourth axes of variation for the seven populations from HapMap and SGVP. (D) A plot of the first two axes of variation when the PCA is run on only the three Far East Asian populations comprising the Singapore Chinese, HapMap Han Chinese in Beijing, China, and Japanese in Tokyo, Japan. (E) A plot of the first two principal components in a separate analysis within the three SGVP populations. (F) A plot of the second and third principal components within the SGVP populations. The same color scheme has been used in C–F; the legend for the color assignment can be found in C.

Figure 2.

Allele frequency comparison between pairs of populations. The axes in each figure represent the allele frequencies for each of the two represented populations. For each SNP, we define the minor allele after agglomerating the genotype data from all three SGVP populations and subsequently calculate the frequency of this allele in each population. Twenty allele frequency bins each spanning 0.05 units are constructed for each population, and we tabulate the number of SNPs found in each bin. The intensity of the contour represents the number of SNPs that displayed the corresponding allele frequencies in the two populations, from a low number of SNPs (purple) to a higher number of SNPs (red). The figure panels compare the allelic spectrum among CHS-MAS (A), CHS-INS (B), MAS-INS (C), and CHS-CHB (D).

Figure 3.

Decay of LD with distance. Decay of LD as measured by the r² statistic with increasing distance up to 250 kb for each of the HapMap and SGVP populations, where 90 chromosomes were chosen from each population to perform the LD calculation. Only SNPs with minor allele frequencies ≥5% in each population were considered in this analysis.

Figure 4.

LD variation and population-specific recombination rates at CDKAL1. The extent of LD variation between pairs of SGVP and HapMap populations at the CDKAL1 gene, with separate LD heatmaps and recombination rates estimated from genotype data at each population. Population-specific recombination rates are shown except for CHB and JPT, where the same HapMap estimated recombination rates for JPT+CHB are used.