Evaluation of GWAS-identified genetic variants for age at menarche among Chinese women

Abstract

Study question: Do genetic polymorphisms which influence age at menarche in women of European ancestry also influence women of Chinese ancestry?

Summary answer: Many genetic variants influencing age at menarche in European populations appear to impact Chinese populations in a similar manner.

What is known and what this paper adds: Prior genome-wide association studies have uncovered 42 SNPs associated with age at menarche in European populations. This study is the first to demonstrate that many of the genetic determinants of age at menarche are shared between European and Chinese women.

Participants and setting: We evaluated 37 of 42 SNPs identified as associated with age at menarche from a recent, large meta-analysis, consisting primarily of women of European ancestry, in a population of 6929 Chinese women from Shanghai, China. We also constructed weighted genetic risk scores (GRSs) combining the number of effect variants for all 37 SNPs, or only the SNPs associated with age at menarche among our study population, to evaluate their joint influence on age at menarche.

Main results: For 32 of the 37 evaluated variants, the direction of the allele associations were the same between women of European ancestry and women of Chinese ancestry (P = 3.71 × 10(-6), binomial sign test); 9 of these were statistically significant. Subjects in the highest quintile of GRSs began menarche ∼5 months later than those in the lowest quintile. BIAS, LIMITATIONS AND GENERALIZABILITY TO OTHER POPULATIONS: Age at menarche was obtained by self-report, which can be subject to recall errors. The current analysis was restricted to loci which met or approached GWAS significance thresholds and did not evaluate loci which may act predominantly or exclusively in the Chinese population. The smaller sample size for our meta-analysis compared with meta-analyses conducted in European populations reduced the power to detect significant results.

Study funding/competing interests: This study was supported, in part, by grants from US National Institutes of Health (grants R01CA124558, R01CA090899, R01CA070867; R01CA064277 and R01CA092585 and UL1 RR024975), Ingram professorship funds and Allen Foundation funds. There are no competing interests to declare.

Figure 1

Association of genetic risk scores (GRS) with age at menarche. The mean difference in age at menarche (in weeks) between first quintile (reference) and the second to fifth quintiles of GRSall and GRSsel adjusted for birth year, education and disease status. GRSsel was calculated based on nine SNPs that were significantly associated with age at menarche in our population. GRSall was calculated based on all GWAS SNPs evaluated. The mean difference per menarche-age-increasing allele per SNPs included in each GRS is given along with 95% confidence intervals.