Evaluating the performance of Affymetrix SNP Array 6.0 platform with 400 Japanese individuals

Abstract

Background: With improvements in genotyping technologies, genome-wide association studies with hundreds of thousands of SNPs allow the identification of candidate genetic loci for multifactorial diseases in different populations. However, genotyping errors caused by genotyping platforms or genotype calling algorithms may lead to inflation of false associations between markers and phenotypes. In addition, the number of SNPs available for genome-wide association studies in the Japanese population has been investigated using only 45 samples in the HapMap project, which could lead to an inaccurate estimation of the number of SNPs with low minor allele frequencies. We genotyped 400 Japanese samples in order to estimate the number of SNPs available for genome-wide association studies in the Japanese population and to examine the performance of the current SNP Array 6.0 platform and the genotype calling algorithm "Birdseed".

Results: About 20% of the 909,622 SNP markers on the array were revealed to be monomorphic in the Japanese population. Consequently, 661,599 SNPs were available for genome-wide association studies in the Japanese population, after excluding the poorly behaving SNPs. The Birdseed algorithm accurately determined the genotype calls of each sample with a high overall call rate of over 99.5% and a high concordance rate of over 99.8% using more than 48 samples after removing low-quality samples by adjusting QC criteria.

Conclusion: Our results confirmed that the SNP Array 6.0 platform reached the level reported by the manufacturer, and thus genome-wide association studies using the SNP Array 6.0 platform have considerable potential to identify candidate susceptibility or resistance genetic factors for multifactorial diseases in the Japanese population, as well as in other populations.

Figure 1

Genotyping results of the 1^st set of 200 samples using the SNP Array 6.0 platform. Colours are based on every 48 samples analyzed simultaneously as a batch. a. Concentration of purified PCR products for each sample. b. QC call rate for each sample. c. Overall call rate for each sample, as determined by the Birdseed algorithm using total 198 samples that passed the default 86% QC criteria. d. Overall call rate for each sample, as determined by the Birdseed algorithm using samples in the same batch.

Figure 2

Genotyping results of 2^nd set of 200 samples using the SNP Array 6.0 platform. a. Concentration of purified PCR products for each sample. b. QC call rate for each sample. c. Overall call rate for each sample, as determined by the Birdseed algorithm using a total of 191 samples that passed the default 86% QC criteria. d. Overall call rate for each sample, as determined by the Birdseed algorithm using samples in the same batch.

Figure 3

Assay criteria for experimental errors occurring on running batches. The CV of purified PCR product concentration is determined for each running batch. Overall call rate for each sample was determined by the Birdseed algorithm using samples in the same batch.

Figure 4

Agarose gel electrophoresis pattern showing genomic DNA from batch #1 of the 2^nd set (lanes 1–8) and batch #2 of the 2^nd set (lanes 9–16). Fifty nanograms of genomic DNA for each of the sample was electrophoresed on 1.0% agarose gels. M1 and M2 indicate lambda DNA digested with Hind III and 100-bp DNA ladder marker, respectively.

Figure 5

Genotype calling accuracy with Birdseed algorithm. a-d. Genotype calls determined using 198 samples with over 86% QC criteria were used as a reference. The average overall call rate for the 4 sets of the 12 samples were determined with 7 different sample sizes; 12 samples, 24 samples, 36 samples, 48 samples, 72 samples, 96 samples and 198 samples. The average concordance rates for the 4 sets of 12 samples were determined by comparison with the reference genotype calls. A negative correlation with a P value of 0.0053 and a positive correlation with a P value of 0.0115 were shown for overall call rate and concordance rate by fitting the power-law distribution to the data with least-squares approximation.

Figure 6

Removal of low-quality samples by adjusting QC criteria. Overall call rate for each sample was determined using total samples that passed the QC criteria. a. Overall call rate and QC call rate for each sample plotted with QC criteria > 86% and > 95%. b. Overall call rate (OCR) determined with 86% QC criteria compared with that determined with 95% QC criteria. c. Overall call rate (OCR) determined with 86% QC criteria compared with that determined using 184 samples.