Genome-wide association study of anthropometric traits in Korcula Island, Croatia

Abstract

Aim: To identify genetic variants underlying six anthropometric traits: body height, body weight, body mass index, brachial circumference, waist circumference, and hip circumference, using a genome-wide association study.

Methods: The study was carried out in the isolated population of the island of Korcula, Croatia, with 898 adult examinees who participated in the larger DNA-based genetic epidemiological study in 2007. Anthropometric measurements followed standard internationally accepted procedures. Examinees were genotyped using HumanHap 370CNV chip by Illumina, with a genome-wide scan containing 316730 single nucleotide polymorphisms (SNP).

Results: A total of 11 SNPs were associated with the investigated traits at the level of P<10(-5), with one SNP (rs7792939 in gene zinc finger protein 498, ZNF498) associated with body weight, hip circumference, and brachial circumference (P=3.59-5.73 x 10(-6)), and another one (rs157350 in gene delta-sarcoglycan, SGCD) with both brachial and hip circumference (P=3.70-6.08 x 10(-6). Variants in CRIM1, a gene regulating delivery of bone morphogenetic proteins to the cell surface, and ITGA1, involved in the regulation of mesenchymal stem cell proliferation and cartilage production, were also associated with brachial circumference (P=7.82 and 9.68 x 10(-6), respectively) and represent interesting functional candidates. Other associations involved those between genes SEZ6L2 and MAX and waist circumference, XTP6 and brachial circumference, and AMPA1/GRIA1 and height.

Conclusion: Although the study was underpowered for the reported associations to reach formal threshold of genome-wide significance under the assumption of independent multiple testing, the consistency of association between the 2 variants and a set of anthropometric traits makes CRIM1 and ITGA1 highly interesting for further replication and functional follow-up. Increased linkage disequilibrium between the used markers in an isolated population makes the formal significance threshold overly stringent, and changed allele frequencies in isolate population may contribute to identifying variants that would not be easily identified in large outbred populations.

Figure 1

Settlements on the island of Korčula, Croatia, included in the study

Figure 2

Genome-wide association study of height using Haploview software, showing peaks on chromosomes 1 and 5 reaching genome-wide significance level of P < 10⁻⁵.

Figure 3

Genome-wide association study of weight using Haploview software, showing peaks on chromosomes 7 and 14 reaching genome-wide significance level of P < 10⁻⁵.

Figure 4

Genome-wide association study of body mass index using Haploview software, showing a peak on chromosome 2 reaching genome-wide significance level of P < 10⁻⁵.

Figure 5

Genome-wide association study of brachial circumference using Haploview software, showing peaks on chromosomes 2, 5, 7, and 13 reaching genome-wide significance level of P < 10⁻⁵.

Figure 6

Genome-wide association study of hip circumference using Haploview software, showing peaks on chromosomes 5 and 7 reaching genome-wide significance level of P < 10⁻⁵.

Figure 7

Genome-wide association study of waist circumference using Haploview software, showing peaks on chromosomes 14 and 16 reaching genome-wide significance level of P < 10⁻⁵.