12 new susceptibility loci for prostate cancer identified by genome-wide association study in Japanese population

Abstract

Genome-wide association studies (GWAS) have identified ~170 genetic loci associated with prostate cancer (PCa) risk, but most of them were identified in European populations. We here performed a GWAS and replication study using a large Japanese cohort (9,906 cases and 83,943 male controls) to identify novel susceptibility loci associated with PCa risk. We found 12 novel loci for PCa including rs1125927 (TMEM17, P = 3.95 × 10^-16), rs73862213 (GATA2, P = 5.87 × 10^-23), rs77911174 (ZMIZ1, P = 5.28 × 10^-20), and rs138708 (SUN2, P = 1.13 × 10^-15), seven of which had crucially low minor allele frequency in European population. Furthermore, we stratified the polygenic risk for Japanese PCa patients by using 82 SNPs, which were significantly associated with Japanese PCa risk in our study, and found that early onset cases and cases with family history of PCa were enriched in the genetically high-risk population. Our study provides important insight into genetic mechanisms of PCa and facilitates PCa risk stratification in Japanese population.

Fig. 1

Scheme for study design and screening results. First, we conducted discovery GWAS followed by imputation using 1000 Genomes Project Phase1 as a reference. Of the 2997 SNPs that were associated with PCa (P < 1 × 10⁻⁵), top 101 SNPs excluding those residing in previously reported loci were evaluated in the replication study using an independent cohort. A total of 12 SNPs were significantly associated with PCa (P < 5 × 10⁻⁸) after meta-analysis of discovery and replication cohorts

Fig. 2

Manhattan plot of GWAS. −log10 P value is plotted on the Y-axis. Each P value is calculated by a 1-degree-freedom Cochran-Armitage test

Fig. 3

Locus Explorer plots of novel five GWAS loci. a rs11125927 at chr.2. b rs73862213 at chr.3. c rs4554825 & rs77911174 at chr.10. d rs138708 at chr.22. The regional association plot (−log10(P) panel) depicts variant P-values relative to chromosomal position. Variants in linkage disequilibrium with the novel lead SNP(s) at r² ≥ 0.1 according to the 1000 Genomes JPT population are shaded in the Manhattan plot and linkage disequilibrium track (LD panel), with darker color denoting stronger correlation with the lead variant. Lower sections of the plot indicate the relative positions of genes and selected biological annotations. Annotations displayed are: histone modifications in ENCODE tier 1 cell lines (Histone track), the positions of variants that are eQTLs with prostate tumor expression in TCGA prostate adenocarcinoma samples (eQTL track), chromatin state categorizations in the PrEC cell-line by ChromHMM (ChromHMM track), the position of conserved element peaks (Conserved track) and the position of DNaseI hypersensitivity site peaks in ENCODE prostate cell lines (DNaseI track). Genes on the positive and negative strand are denoted by brown and turquoise color respectively (Gene track). The horizontal axis represents genomic coordinates in the hg19 reference genome

Fig. 4

The distribution of the polygenic risk score (PRS) for PCa in Japanese population. a The PRS distribution of the PCa cases (n = 4893) and the male control (n = 10,682) of GWAS. Density was estimated using the Gaussian kernel. The 5% higher and lower percentiles are shown as dotted lines. b The PRS distribution by the age at diagnosis of PCa in the GWAS cases (n = 4762). Density was estimated using the Gaussian kernel. Green, younger than 60 years (n = 129); blue, younger than 65 years (n = 781); gray, 65 years or older (n = 3852). c The PRS distribution by the presence of PCa family history in the GWAS cases (n = 4893). Density was estimated using the Gaussian kernel. Red, positive PCa family history (n = 272); blue, negative PCa family history (n = 4621). d The PRS distribution by the age at diagnosis of PCa in the JIKEI validation cohort (n = 2218). Density was estimated using the Gaussian kernel. Red, younger than 55 years (n = 94); green, younger than 60 years (n = 310); blue, younger than 65 years (n = 802); gray, 65 years or older (n = 802)