Six new loci associated with body mass index highlight a neuronal influence on body weight regulation

Abstract

Common variants at only two loci, FTO and MC4R, have been reproducibly associated with body mass index (BMI) in humans. To identify additional loci, we conducted meta-analysis of 15 genome-wide association studies for BMI (n > 32,000) and followed up top signals in 14 additional cohorts (n > 59,000). We strongly confirm FTO and MC4R and identify six additional loci (P < 5 x 10(-8)): TMEM18, KCTD15, GNPDA2, SH2B1, MTCH2 and NEGR1 (where a 45-kb deletion polymorphism is a candidate causal variant). Several of the likely causal genes are highly expressed or known to act in the central nervous system (CNS), emphasizing, as in rare monogenic forms of obesity, the role of the CNS in predisposition to obesity.

Figure 1

Genome-wide association results for GIANT (stage 1). (a) Manhattan plot showing the significance of association of all SNPs in the stage 1 GIANT meta-analysis with BMI. SNPs are plotted on the x axis according to their position on each chromosome; association with BMI is indicated on the y axis (as −log₁₀ P value). SNPs previously reported to show association with BMI are shown in blue, signals examined but not confirmed in stage 2 samples are shown in red and the six new regions described here are highlighted in green. (b) Quantile-quantile plot of SNPs after stage 1 GIANT meta-analysis (black) and after removal of any SNPs within 500 kb of FTO- or MC4R-associated SNPs (blue). (c) Quantile-quantile plot of SNPs in the stage 1 GIANT meta-analysis for association with BMI (black) and after removal any SNPs surrounding FTO, MC4R and the six new loci reported here (green).

Figure 2

Regional association plots showing signals in stage 1 samples for replicating loci around TMEM18, GNPDA2, SH2B1, MTCH2, KCTD15 and NEGR1. (a–f) SNPs are plotted by position on chromosome against association with BMI (−log₁₀ P value). The figures highlight the most significant SNP after stage 1 meta-analysis (in purple) and the SNP selected for follow-up (diamond) in stage 2 analyses, labeled with its combined P value (stage 1 + stage 2). In most cases, the SNP followed up is the most significant SNP in the region (therefore, a purple diamond). Otherwise, the LD between the followed-up SNP and the most significant SNP in the region is indicated by the color of the diamond. Estimated recombination rates (from HapMap) are plotted in cyan to reflect the local LD structure. The SNPs surrounding the most significant SNP (purple diamond) are color-coded to reflect their LD with this SNP as in the inset (taken from pairwise r² values from the HapMap CEU database). Genes and the position of exons, as well as the direction of transcription, are noted below the plots (data from UCSC genome browser) with a gray area marking the extent of the region that includes any SNP with r² ≥ 0.3 relative to the most significant SNP (purple diamond). Hashmarks represent SNP positions on each genotyping array used by any individual study and also show SNP positions after imputation. In e, rs11084753 was selected as the reference SNP for the KCTD15 region and shows essentially identical results to rs415237. The two SNPs are virtually superimposed on the association plot.

Figure 3

Combined impact of risk alleles on average BMI in the population-based EPIC-Norfolk cohort. All eight confirmed SNPs were successfully genotyped in the EPIC-Norfolk cohort (14,409 individuals with complete genotype data). For each individual, the number of risk alleles (0,1,2) per SNP was weighted for their relative effect sizes estimated from the stage 2 cohort data only. Subsequently, the weighted risk alleles were summed for each individual, and the overall individual sum was rounded to the nearest integer to represent the individual's risk allele score. Along the x axis, individuals in each risk allele category are shown (grouped ≤3 and ≥13 at the extremes), and the mean BMI (± s.e.m.) is plotted (y axis on right), with the line representing the regression of the mean BMI values across the risk allele scores. The histogram (y axis on left) represents the number of individuals for each risk-score category.

Figure 4

Contribution of copy number polymorphism to BMI. (a) Quantile-quantile plot of the −log₁₀ P values for SNPs (n = 261) that tag copy number polymorphisms (r² > 0.8) in the stage 1 genome-wide meta-analysis data. The data generally conform to the uniform distribution expected under the null hypothesis of no association, with the exception of a strong association to the CNP-tagging SNP rs2815752 (near NEGR1). (b) Copy number variation in the NEGR1 association region near rs2815752. Heat map representation of the hybridization intensity of copy number probes (SNP 6.0 array) across the NEGR1 association region in 90 HapMap CEU samples. Darker shades of red indicate reduced hybridization intensity. The data indicate two regions of copy number variation (pale green and pink rectangles in lower panel) upstream of NEGR1. (c) Structural haplotypes and BMI association signal in the NEGR1 region. Two deletion polymorphisms (a 10-kb and a 45-kb deletion affecting nonoverlapping sequences upstream of NEGR1) segregate on distinct haplotypes. Both deletions remove conserved elements upstream of NEGR1 (top panel). In the bottom panel, the color of each SNP indicates the structural haplotype with which it is in strongest LD; the size of each circle indicates the strength of this LD. The 45-kb deletion is immediately flanked and perfectly tagged (r² = 1.0) by the two most strongly BMI-associated SNPs; these SNPs are separated by 47.3 kb on the reference genome sequence but by only 1.7 kb on the BMI-associated deletion haplotype (red). These SNPs flank but are not contained within the copy number variable region.