Large-scale association analysis identifies new lung cancer susceptibility loci and heterogeneity in genetic susceptibility across histological subtypes

Abstract

Although several lung cancer susceptibility loci have been identified, much of the heritability for lung cancer remains unexplained. Here 14,803 cases and 12,262 controls of European descent were genotyped on the OncoArray and combined with existing data for an aggregated genome-wide association study (GWAS) analysis of lung cancer in 29,266 cases and 56,450 controls. We identified 18 susceptibility loci achieving genome-wide significance, including 10 new loci. The new loci highlight the striking heterogeneity in genetic susceptibility across the histological subtypes of lung cancer, with four loci associated with lung cancer overall and six loci associated with lung adenocarcinoma. Gene expression quantitative trait locus (eQTL) analysis in 1,425 normal lung tissue samples highlights RNASET2, SECISBP2L and NRG1 as candidate genes. Other loci include genes such as a cholinergic nicotinic receptor, CHRNA2, and the telomere-related genes OFBC1 and RTEL1. Further exploration of the target genes will continue to provide new insights into the etiology of lung cancer.

Figure 1. Manhattan plots of lung cancer risk overall and by histological subtypes

(a) lung cancer risk overall, 29,266 cases and 56,450 controls (b) adenocarcinoma, 11,273 cases and 55,483 controls (c) squamous cell carcinoma 7,426 cases and 55,627 controls. Each locus is annotated by their cytoband locations. The X‐axis represents chromosomal locations and the Y‐axis represents −log10(P‐value). Black denotes the previously known loci and Red denotes the new loci identified in this analysis

Figure 2. Scatter plots comparing variants across the 6q27, 15q21.1, 8p12 and 11q23.3 susceptibility loci and (Y-axis) their associated with lung cancer (or lung adenocarcinoma, as relevant) and (X-axis) the lung cis–eQTL (GTEx)

Each variant (dot) is colored relative the degree of linkage disequilibrium (r²) with sentinel lung cancer variant (marked) at that locus. Indented table, association between sentinel variant and lung cancer (or histological subtype) as well as the eQTL evidence in lung epithelium for the microarray (Laval, UBC, Groningen) and RNAseq (NCI and GTEx) cohorts. At 6q27, 15q21.1 and 8p12, the variants associated with lung cancer also tend to be those that that are lung cis-eQTL’s for RNASET2, SECISBP2L and NRG1, respectively. At 11q23.3, while the sentinel variant (rs1056562) is a lung cis-eQTL for AMICA1, additional variants are AMICA1 lung cis-eQTL’s, but not associated with lung adenocarcinoma and vice versa suggesting an alternate candidate gene may be responsible for this association or a pleiotropic effect at this locus.

Figure 3. eQTL and smoking behavior analysis of the 8p21 lung cancer susceptibility locus. Upper panel

Scatter plots of variants across the 8p21 locus and their associated with lung cancer (Y-axis) and CHRNA2 eQTL (X-axis) in lung epithelial tissues (panel a) and CHRNA2 eQTL in brain cerebellum tissues (panel b). Panel C. eQTL association between rs11780471 across tissues from different parts of the brain from GTEx and Braineac consortia noting CHRNA2 cis- eQTL effect appears restricted to the brain cerebellum. Panel D. Association between rs11780471 and smoking phenotypes, noting evidence for association between smoking status (ever vs never) and age of initiation, with lung cancer risk allele carriers (G) more likely to be ever smokers and take up smoking earlier. Fagerström Test for Nicotine Dependence (FTND) index, error bars indicate the 95% confidence intervals.