Genetic Predisposition to Multiple Myeloma at 5q15 Is Mediated by an ELL2 Enhancer Polymorphism

Abstract

Multiple myeloma (MM) is a malignancy of plasma cells. Genome-wide association studies have shown that variation at 5q15 influences MM risk. Here, we have sought to decipher the causal variant at 5q15 and the mechanism by which it influences tumorigenesis. We show that rs6877329 G > C resides in a predicted enhancer element that physically interacts with the transcription start site of ELL2. The rs6877329-C risk allele is associated with reduced enhancer activity and lowered ELL2 expression. Since ELL2 is critical to the B cell differentiation process, reduced ELL2 expression is consistent with inherited genetic variation contributing to arrest of plasma cell development, facilitating MM clonal expansion. These data provide evidence for a biological mechanism underlying a hereditary risk of MM at 5q15.

Keywords: cancer genetics; genome-wide association studies; multiple myeloma; single nucleotide polymorphisms.

Graphical abstract

Figure 1

Regional Plots of Association Results of the 5q15 Locus (A and B) The region of association maps to a ∼40 kb haplotype block within ELL2. Genotyped (triangles) and imputed (dots) SNPs are shown based on their chromosomal position (NCBI build 37 human genome) on the x axis and −log₁₀ p value on the y axis from (A) GWAS meta-analysis in UK MRC MyIX and MyXI trials and German GMMG trials (3,790 case subjects and 7,304 control subjects), and (B) HRDMM (red) and non-HRDMM (blue) case-control meta-analysis in the UK and German populations (1,363 HRDMM case subjects, 1,339 non-HRDMM case subjects, and 7,304 control subjects). Color intensity of each SNP reflects the extent of LD with the lead SNP, rs11372862 (white r² = 0 to dark red/blue r² = 1). Recombination rates, estimated using HapMap samples of European ancestry, are shown by a light blue line. The relative positions of ELL2 and C5orf27 mapping to 5q15 are shown. rs1423269 and rs11372862 are annotated in black dotted lines. (C) Summary data-based Mendelian randomization analysis at 5q15. Upper panel - brown dots represent p values for SNPs from the HRDMM case-control meta-analysis (1,363 cases and 7,304 controls), diamonds represent p values for probes from the SMR test; lower panel - crosses represent eQTL p values of SNPs from MM plasma cells from 183 MRC MyIX trial patients (GEO: GSE21349) and 658 Heidelberg GMMG patients (EMBL-EBI: E-MTAB-2299), with genes passing the SMR (i.e., P_SMR < 0.00833) and HEIDI (i.e. P_HEIDI > 0.05) tests highlighted in red. Probeset ID refers to Affymetrix U133 2.0 Plus Array custom chip definition file (CDF v.17) mapping to Entrez genes.

Figure 2

Epigenetic Landscape at the 5q15 Locus HRDMM (red) and non-HRDMM (blue) case-control meta-analysis as shown in Figure 1B. ChIP-seq from GM12878 (pink peaks), JJN3, KMS11, and L363 (black peaks) are shown, annotated with the ChIP’d histone modification marks H3K4Me1, H3K4Me3, and H3K27Ac. DNaseI HS and ChromHMM data for GM12878 were assessed from ENCODE. A ∼8kb active enhancer (chr5:95,259,093-95,267,656) within ELL2 is shaded, predicted by ChromHMM, DNaseI HS, as well as H3K4Me1, H3K4Me3, and H3K27Ac peaks. rs3777185, rs6877329, rs3777184, rs889302, rs2015159, and rs4563648 are localized within the enhancer with r² ≥ 0.8 with rs11372862 (Table S3). Asterisk (^∗) marks the enhancer region interacting with the ELL2 promoter in both GM12878 and KMS11 (chr5:95,260,175-95,264,576) encompassing rs6877329 and rs3777184. The positions of rs1423269, rs6877329, and rs3777184 are marked with black dotted lines.

Figure 3

rs6877329 Is Associated with Reduced Enhancer Activity and Differential Nuclear Protein Binding (A) rs6877329-C risk allele shows decreased expression over the protective G-allele. Allele-specific constructs containing a putative regulatory sequence flanking rs6877329 and rs3777184 were cloned into the pGL3 luc+ SV40-promoter vector and transfected into KMS11. The ratio of luminescence from the experimental pGL3-constructs to the Renilla internal control, pRL-SV40, was normalized to the empty pGL3 luc+ SV40-promoter vector. Data shown are mean ± SEM from three independent experiments performed in triplicate. Differences in gene expression were assessed by the two-tailed t test. (B) Electrophoretic mobility shift assay in GM11992 showing differential nuclear protein binding to alleles of rs6877329. Increased protein binding observed for the non-risk G-allele. Asterisk (^∗) indicates specific protein shift band.

Figure 4

Gene Expression Correlations with ELL2 in Multiple Myeloma Expression correlation between ELL2 and BiP, and ATF6, ELL1, and POU2AF1 was examined in 259 UK MM patients (GEO: GSE21349) and 246 German (GER) MM patients (EMBL-EBI: E-MTAB-372). Lines show linear regression fits. Expression correlation was assessed by Pearson’s product-moment correlation test. p values were combined from independent datasets using Fisher’s Method.