Ascertainment biases in SNP chips affect measures of population divergence

Abstract

Chip-based high-throughput genotyping has facilitated genome-wide studies of genetic diversity. Many studies have utilized these large data sets to make inferences about the demographic history of human populations using measures of genetic differentiation such as F(ST) or principal component analyses. However, the single nucleotide polymorphism (SNP) chip data suffer from ascertainment biases caused by the SNP discovery process in which a small number of individuals from selected populations are used as discovery panels. In this study, we investigate the effect of the ascertainment bias on inferences regarding genetic differentiation among populations in one of the common genome-wide genotyping platforms. We generate SNP genotyping data for individuals that previously have been subject to partial genome-wide Sanger sequencing and compare inferences based on genotyping data to inferences based on direct sequencing. In addition, we also analyze publicly available genome-wide data. We demonstrate that the ascertainment biases will distort measures of human diversity and possibly change conclusions drawn from these measures in some times unexpected ways. We also show that details of the genotyping calling algorithms can have a surprisingly large effect on population genetic inferences. We not only present a correction of the spectrum for the widely used Affymetrix SNP chips but also show that such corrections are difficult to generalize among studies.

FIG 1.

Folded frequency spectrum for 19 African Americans for synonymous sequencing data and for SNP chip data. Only SNPs without missing data are included.

FIG 2.

Folded frequency spectrum for 20 European Americans for synonymous sequencing data and for SNP chip data. Only SNPs without missing data are included.

FIG 3.

The 2D Celera frequency spectra (density) for 20 European Americans and 19 African Americans for the SNP chip data (left) and the synonymous SNPs from the resequencing data (right).

FIG 4.

The effect of ascertainment bias on the frequency spectrum. The frequency spectrum is projected down to ten individuals for all populations for the NIEHS data. We simulated ascertainment in each of the five populations with an ascertainment sample of ten individuals.

FIG 5.

Folded frequency spectrum for 45 unrelated Japanese HapMap individuals. The individuals were genotyped using approximately 500,000 SNPs on the Affymetrix SNP 500k chip set. The frequency spectrum is shown for SNPs binned based on their maximum BRLMM confidence score.

FIG 6.

Pairwise F_ST between European Americans and Africans for different ascertainment schemes. Standard error bars were estimated using 1,000 bootstrap samples. For the black bars, the SNPs are sampled independently and for the gray bars, the SNPs are sampled genewise from the 251 genes. The ascertainment was performed in African Americans and a varying number of individuals were used for the ascertainment. N_Asc is the number of ascertained SNPs. The F_ST estimate using all SNPs (no ascertainment bias) is labeled “None.”

FIG 7.

Mean pairwise F_ST components between pairs of populations using the NIEHS data. The ascertainment was performed in African Americans and a different number of individuals were used for the ascertainment. Each SNP gives an estimate for the total variance and the between population variance. The plot shows the normalized mean variances. We normalized by dividing by the mean total variance and mean between population variance, respectively, for all the SNPs in the sample (regardless of ascertainment).

FIG 8.

Mean pairwise distances within and between Africans and European Americans based on the two first principal components. Standard errors are estimated using bootstrap. The light colors are standard errors based on a gene-wise bootstrap and the dark colors are the standard bootstrap where the SNPs are sampled independently. Ascertainment, using an increasing number of individuals, was simulated using the Asian, the Hispanic, and the African-American population, respectively, from the NIEHS resequencing data. There are 5,948 SNPs without missing data in any population.

FIG 9.

PCA plot for the first two principal components for four populations from the NIEHS data. The left plot has no ascertainment bias. In the right plot, ascertainment was performed using all the 24 individuals from the Asian populations. All SNPs that were polymorphic in the four populations were used. Out of the 8,231 SNPs, 2,751 were ascertained in the left plot. We resampled 2,751 random SNPs without replacement from the 8,231 SNPs and performed PCA on them. None of the 1,000 resamples gave a higher distance between the European Americans than the distance between the African Americans and the Africans.

FIG 10.

We fitted the frequency spectrum of the Celera European Americans for the synonymous SNPs using a mixture of exponentials. The spectra for the observed and the fitted data are folded.

FIG 11.

The Celera European Americans synonymous frequency spectra for the resequencing data, the SNP chip data, and the corrected frequency spectrum. The correction assumed that two ascertainment panels were used and the SNPs were ascertained if both alleles were observed at least twice.