A method to address differential bias in genotyping in large-scale association studies

Abstract

In a previous paper we have shown that, when DNA samples for cases and controls are prepared in different laboratories prior to high-throughput genotyping, scoring inaccuracies can lead to differential misclassification and, consequently, to increased false-positive rates. Different DNA sourcing is often unavoidable in large-scale disease association studies of multiple case and control sets. Here, we describe methodological improvements to minimise such biases. These fall into two categories: improvements to the basic clustering methods for identifying genotypes from fluorescence intensities, and use of "fuzzy" calls in association tests in order to make appropriate allowance for call uncertainty. We find that the main improvement is a modification of the calling algorithm that links the clustering of cases and controls while allowing for different DNA sourcing. We also find that, in the presence of different DNA sourcing, biases associated with missing data can increase the false-positive rate. Therefore, we propose the use of "fuzzy" calls to deal with uncertain genotypes that would otherwise be labeled as missing.

Figure 1

Example of Biased Association Statistic Resulting from Missing Data in the MIP nsSNPs Dataset The top row shows the normalised fluorescent signal intensities for both alleles. The bottom row shows the contrasts (x-axis) plotted against the sum signal (y-axis). Clustering is based on the original Moorhead et al. [5] algorithm: blue and green crosses belong to both homozygous clouds, red to the heterozygous cloud and black indicates missing calls. The p-value for the association test is 0.036 using the original Moorhead et al. [5] algorithm and 0.55 using our modified procedure (which does not label any of the calls as missing).

Figure 2

Quantile–Quantile Plot Comparing the Observed Distribution of the Association Statistic (y-Axis) with the Predicted Distribution under the Null (x-Axis) The leftmost graph uses our set of calls for our best 7,446 nsSNPs and the rightmost graph relies on the original calls for the best 5,294 nsSNPs in 3,750 cases and 3,480 controls.

Figure 3

Distribution of p-Values for the Association Test between the 1958 BBC Samples and the UK Blood Donors (WTCCC Control Dataset) for Three Different Quality Thresholds