Genome-wide meta-analysis identifies five new susceptibility loci for pancreatic cancer

Abstract

In 2020, 146,063 deaths due to pancreatic cancer are estimated to occur in Europe and the United States combined. To identify common susceptibility alleles, we performed the largest pancreatic cancer GWAS to date, including 9040 patients and 12,496 controls of European ancestry from the Pancreatic Cancer Cohort Consortium (PanScan) and the Pancreatic Cancer Case-Control Consortium (PanC4). Here, we find significant evidence of a novel association at rs78417682 (7p12/TNS3, P = 4.35 × 10^-8). Replication of 10 promising signals in up to 2737 patients and 4752 controls from the PANcreatic Disease ReseArch (PANDoRA) consortium yields new genome-wide significant loci: rs13303010 at 1p36.33 (NOC2L, P = 8.36 × 10^-14), rs2941471 at 8q21.11 (HNF4G, P = 6.60 × 10^-10), rs4795218 at 17q12 (HNF1B, P = 1.32 × 10^-8), and rs1517037 at 18q21.32 (GRP, P = 3.28 × 10^-8). rs78417682 is not statistically significantly associated with pancreatic cancer in PANDoRA. Expression quantitative trait locus analysis in three independent pancreatic data sets provides molecular support of NOC2L as a pancreatic cancer susceptibility gene.

Fig. 1

Association results, recombination hotspots, and LD plots for new pancreatic cancer susceptibility regions. The top half of each panel shows the association results for the meta-analysis of PanScan I+II, PanScan III, and PanC4 (gray diamonds). The results for the replication of the marker SNP at each locus are shown for PANDoRA (light blue diamonds) and the combined meta-analysis results (red diamonds). Overlaid are likelihood ratio statistics estimating putative recombination hotspots across the region based on the inference using the CEU 1000 G Phase 3 data. Genomic coordinates are plotted on the x axis (Genome build hg19), P values for the association analysis are shown on the left y axis, and recombination hotspot likelihood ratio on the right y axis. The bottom half of each panel shows LD heat maps based on r² values from the 1000 G Phase 3 CEU population for all variants included in the analysis. Shown are results for chromosomes 1p36.33 (a), 8q21.11 (b), 17q12 (c), 18q21.32 (d), and 7p12 (e)

Fig. 2

Functional analysis of the 1p36.33 risk locus. a The set of most likely functional variants at 1p36.33 and their P value rank (1–10, in red) is shown as well as overlapping RefSeq genes on chr1: 885,555-904,522 (NCBI GRCh37/Hg19). ENCODE data for histone modification marks (H3K4me1, H3K4me3, H3K27Ac) are indicated by colored density plots. Open chromatin (DNase hypersensitivity regions, DNase clusters) and binding of transcription factors (TF ChIP) are indicated by horizontal bars. The numbers next to each bar indicate the number of cell lines with DNase clusters, or the number of different transcription factors bound across all tested cell lines. The panel is adapted from the UCSC Genome Browser. b Expression QTLs in histologically normal autopsy-derived pancreatic tissues (n = 149) from the GTEx consortium (GTEx), the Laboratory of Translational Genomics histologically normal adjacent-to-tumor pancreatic tissue set (LTG, n = 95), and the TCGA pancreatic cancer tissue set (TCGA/PAAD, n = 115). Normalized NOC2L expression is shown on the y axis and genotypes at the marker SNP at 1p36.33 on the x axis. Risk-increasing alleles are marked in red. Note that no samples in the LTG and TCGA/PAAD sets were of the minor homozygous risk genotype (GG). The box-and-whisker plots show the median (horizontal middle line within each box), interquartile range (top and bottom horizontal lines of each box), and 1.5 times the IQR (whiskers). c Analysis of the effects of 1p36.33 variants on transcription factor motifs for rs13303160 (r² = 0.93 with rs13303010 in 1000 G EUR). The risk allele (C) at this marker alters predicted DNA-binding motifs for SMARCC1 and AP-1 proteins