New loci associated with birth weight identify genetic links between intrauterine growth and adult height and metabolism

Abstract

Birth weight within the normal range is associated with a variety of adult-onset diseases, but the mechanisms behind these associations are poorly understood. Previous genome-wide association studies of birth weight identified a variant in the ADCY5 gene associated both with birth weight and type 2 diabetes and a second variant, near CCNL1, with no obvious link to adult traits. In an expanded genome-wide association meta-analysis and follow-up study of birth weight (of up to 69,308 individuals of European descent from 43 studies), we have now extended the number of loci associated at genome-wide significance to 7, accounting for a similar proportion of variance as maternal smoking. Five of the loci are known to be associated with other phenotypes: ADCY5 and CDKAL1 with type 2 diabetes, ADRB1 with adult blood pressure and HMGA2 and LCORL with adult height. Our findings highlight genetic links between fetal growth and postnatal growth and metabolism.

Figure 1

Regional plots of seven loci associated with birth weight at P<5×10⁻⁸. For each of the CCNL1 (a), ADCY5 (b), HMGA2 (c), CDKAL1 (d), 5q11.2 (e), LCORL (f), and ADRB1 (g) regions, SNPs are plotted with their meta-analysis P values (as –log10 values) as a function of genomic position (NCBI Build 36). In each panel, the European discovery stage SNP taken forward for follow-up is represented by a purple circle (with global [discovery + follow-up] meta-analysis P value), with its discovery P value denoted by a purple diamond. Estimated recombination rates (taken from HapMap) are plotted to reflect the local LD structure around the associated SNPs and their correlated proxies (according to a blue to red scale from r² = 0 to 1, based on pairwise r² values from HapMap CEU). Gene annotations were taken from the University of California Santa Cruz genome browser.

Figure 1

Regional plots of seven loci associated with birth weight at P<5×10⁻⁸. For each of the CCNL1 (a), ADCY5 (b), HMGA2 (c), CDKAL1 (d), 5q11.2 (e), LCORL (f), and ADRB1 (g) regions, SNPs are plotted with their meta-analysis P values (as –log10 values) as a function of genomic position (NCBI Build 36). In each panel, the European discovery stage SNP taken forward for follow-up is represented by a purple circle (with global [discovery + follow-up] meta-analysis P value), with its discovery P value denoted by a purple diamond. Estimated recombination rates (taken from HapMap) are plotted to reflect the local LD structure around the associated SNPs and their correlated proxies (according to a blue to red scale from r² = 0 to 1, based on pairwise r² values from HapMap CEU). Gene annotations were taken from the University of California Santa Cruz genome browser.

Figure 1

Regional plots of seven loci associated with birth weight at P<5×10⁻⁸. For each of the CCNL1 (a), ADCY5 (b), HMGA2 (c), CDKAL1 (d), 5q11.2 (e), LCORL (f), and ADRB1 (g) regions, SNPs are plotted with their meta-analysis P values (as –log10 values) as a function of genomic position (NCBI Build 36). In each panel, the European discovery stage SNP taken forward for follow-up is represented by a purple circle (with global [discovery + follow-up] meta-analysis P value), with its discovery P value denoted by a purple diamond. Estimated recombination rates (taken from HapMap) are plotted to reflect the local LD structure around the associated SNPs and their correlated proxies (according to a blue to red scale from r² = 0 to 1, based on pairwise r² values from HapMap CEU). Gene annotations were taken from the University of California Santa Cruz genome browser.

Figure 1

Regional plots of seven loci associated with birth weight at P<5×10⁻⁸. For each of the CCNL1 (a), ADCY5 (b), HMGA2 (c), CDKAL1 (d), 5q11.2 (e), LCORL (f), and ADRB1 (g) regions, SNPs are plotted with their meta-analysis P values (as –log10 values) as a function of genomic position (NCBI Build 36). In each panel, the European discovery stage SNP taken forward for follow-up is represented by a purple circle (with global [discovery + follow-up] meta-analysis P value), with its discovery P value denoted by a purple diamond. Estimated recombination rates (taken from HapMap) are plotted to reflect the local LD structure around the associated SNPs and their correlated proxies (according to a blue to red scale from r² = 0 to 1, based on pairwise r² values from HapMap CEU). Gene annotations were taken from the University of California Santa Cruz genome browser.

Figure 1

Regional plots of seven loci associated with birth weight at P<5×10⁻⁸. For each of the CCNL1 (a), ADCY5 (b), HMGA2 (c), CDKAL1 (d), 5q11.2 (e), LCORL (f), and ADRB1 (g) regions, SNPs are plotted with their meta-analysis P values (as –log10 values) as a function of genomic position (NCBI Build 36). In each panel, the European discovery stage SNP taken forward for follow-up is represented by a purple circle (with global [discovery + follow-up] meta-analysis P value), with its discovery P value denoted by a purple diamond. Estimated recombination rates (taken from HapMap) are plotted to reflect the local LD structure around the associated SNPs and their correlated proxies (according to a blue to red scale from r² = 0 to 1, based on pairwise r² values from HapMap CEU). Gene annotations were taken from the University of California Santa Cruz genome browser.

Figure 1

Regional plots of seven loci associated with birth weight at P<5×10⁻⁸. For each of the CCNL1 (a), ADCY5 (b), HMGA2 (c), CDKAL1 (d), 5q11.2 (e), LCORL (f), and ADRB1 (g) regions, SNPs are plotted with their meta-analysis P values (as –log10 values) as a function of genomic position (NCBI Build 36). In each panel, the European discovery stage SNP taken forward for follow-up is represented by a purple circle (with global [discovery + follow-up] meta-analysis P value), with its discovery P value denoted by a purple diamond. Estimated recombination rates (taken from HapMap) are plotted to reflect the local LD structure around the associated SNPs and their correlated proxies (according to a blue to red scale from r² = 0 to 1, based on pairwise r² values from HapMap CEU). Gene annotations were taken from the University of California Santa Cruz genome browser.

Figure 1

Regional plots of seven loci associated with birth weight at P<5×10⁻⁸. For each of the CCNL1 (a), ADCY5 (b), HMGA2 (c), CDKAL1 (d), 5q11.2 (e), LCORL (f), and ADRB1 (g) regions, SNPs are plotted with their meta-analysis P values (as –log10 values) as a function of genomic position (NCBI Build 36). In each panel, the European discovery stage SNP taken forward for follow-up is represented by a purple circle (with global [discovery + follow-up] meta-analysis P value), with its discovery P value denoted by a purple diamond. Estimated recombination rates (taken from HapMap) are plotted to reflect the local LD structure around the associated SNPs and their correlated proxies (according to a blue to red scale from r² = 0 to 1, based on pairwise r² values from HapMap CEU). Gene annotations were taken from the University of California Santa Cruz genome browser.

Figure 2

Associations between birth weight and known type 2 diabetes (T2D; a and b), systolic blood pressure (SBP, c and d) or height (e and f) loci from the discovery meta-analysis of N=26,836 individuals. Plots a, c and e are quantile-quantile plots: the black triangles (associated with lower birth weight) and circles (associated with higher birth weight) represent observed P-values after removing the loci that achieved P < 5×10⁻⁸ in the overall meta-analysis, and the black line represents expected P-values under the null. The grey area defines the approximate 95% confidence interval around the expected line. Plots b, d and f show, respectively, the T2D, SBP or height effect size (left-hand y-axis), taken from published meta-analyses^,,,, against the birth weight effect size (x-axis), with a superimposed frequency histogram showing the number of SNPs in each category of birth weight effect size (right-hand y-axis). The odds ratios for type 2 diabetes are all obtained from the published DIAGRAM+ Consortium meta-analysis, the largest available reference sample of European descent, and while they do not necessarily reach genome-wide significance in that sample, all loci have shown associations with type 2 diabetes at P < 5×10⁻⁸ (see Online Methods for details of published studies). Effect sizes are aligned to the T2D risk allele or the SBP- or height-increasing allele. Colours indicate birth weight association P-values: P<5e-08 (red); P>=5e-08 and P<0.001 (orange); P>=0.001 and P<0.01 (yellow); P>0.01 (white). The triangles in plot f are SNPs known to be associated with age at menarche. There were more associations between height loci and higher birth weight than expected under the null, and a slight excess of associations between T2D or SBP loci and lower birth weight (binomial sign test P = 0.02, 0.09 and 3×10⁻¹⁰ for b, d and f, respectively).

Figure 2

Associations between birth weight and known type 2 diabetes (T2D; a and b), systolic blood pressure (SBP, c and d) or height (e and f) loci from the discovery meta-analysis of N=26,836 individuals. Plots a, c and e are quantile-quantile plots: the black triangles (associated with lower birth weight) and circles (associated with higher birth weight) represent observed P-values after removing the loci that achieved P < 5×10⁻⁸ in the overall meta-analysis, and the black line represents expected P-values under the null. The grey area defines the approximate 95% confidence interval around the expected line. Plots b, d and f show, respectively, the T2D, SBP or height effect size (left-hand y-axis), taken from published meta-analyses^,,,, against the birth weight effect size (x-axis), with a superimposed frequency histogram showing the number of SNPs in each category of birth weight effect size (right-hand y-axis). The odds ratios for type 2 diabetes are all obtained from the published DIAGRAM+ Consortium meta-analysis, the largest available reference sample of European descent, and while they do not necessarily reach genome-wide significance in that sample, all loci have shown associations with type 2 diabetes at P < 5×10⁻⁸ (see Online Methods for details of published studies). Effect sizes are aligned to the T2D risk allele or the SBP- or height-increasing allele. Colours indicate birth weight association P-values: P<5e-08 (red); P>=5e-08 and P<0.001 (orange); P>=0.001 and P<0.01 (yellow); P>0.01 (white). The triangles in plot f are SNPs known to be associated with age at menarche. There were more associations between height loci and higher birth weight than expected under the null, and a slight excess of associations between T2D or SBP loci and lower birth weight (binomial sign test P = 0.02, 0.09 and 3×10⁻¹⁰ for b, d and f, respectively).

Figure 2

Associations between birth weight and known type 2 diabetes (T2D; a and b), systolic blood pressure (SBP, c and d) or height (e and f) loci from the discovery meta-analysis of N=26,836 individuals. Plots a, c and e are quantile-quantile plots: the black triangles (associated with lower birth weight) and circles (associated with higher birth weight) represent observed P-values after removing the loci that achieved P < 5×10⁻⁸ in the overall meta-analysis, and the black line represents expected P-values under the null. The grey area defines the approximate 95% confidence interval around the expected line. Plots b, d and f show, respectively, the T2D, SBP or height effect size (left-hand y-axis), taken from published meta-analyses^,,,, against the birth weight effect size (x-axis), with a superimposed frequency histogram showing the number of SNPs in each category of birth weight effect size (right-hand y-axis). The odds ratios for type 2 diabetes are all obtained from the published DIAGRAM+ Consortium meta-analysis, the largest available reference sample of European descent, and while they do not necessarily reach genome-wide significance in that sample, all loci have shown associations with type 2 diabetes at P < 5×10⁻⁸ (see Online Methods for details of published studies). Effect sizes are aligned to the T2D risk allele or the SBP- or height-increasing allele. Colours indicate birth weight association P-values: P<5e-08 (red); P>=5e-08 and P<0.001 (orange); P>=0.001 and P<0.01 (yellow); P>0.01 (white). The triangles in plot f are SNPs known to be associated with age at menarche. There were more associations between height loci and higher birth weight than expected under the null, and a slight excess of associations between T2D or SBP loci and lower birth weight (binomial sign test P = 0.02, 0.09 and 3×10⁻¹⁰ for b, d and f, respectively).

Figure 2

Associations between birth weight and known type 2 diabetes (T2D; a and b), systolic blood pressure (SBP, c and d) or height (e and f) loci from the discovery meta-analysis of N=26,836 individuals. Plots a, c and e are quantile-quantile plots: the black triangles (associated with lower birth weight) and circles (associated with higher birth weight) represent observed P-values after removing the loci that achieved P < 5×10⁻⁸ in the overall meta-analysis, and the black line represents expected P-values under the null. The grey area defines the approximate 95% confidence interval around the expected line. Plots b, d and f show, respectively, the T2D, SBP or height effect size (left-hand y-axis), taken from published meta-analyses^,,,, against the birth weight effect size (x-axis), with a superimposed frequency histogram showing the number of SNPs in each category of birth weight effect size (right-hand y-axis). The odds ratios for type 2 diabetes are all obtained from the published DIAGRAM+ Consortium meta-analysis, the largest available reference sample of European descent, and while they do not necessarily reach genome-wide significance in that sample, all loci have shown associations with type 2 diabetes at P < 5×10⁻⁸ (see Online Methods for details of published studies). Effect sizes are aligned to the T2D risk allele or the SBP- or height-increasing allele. Colours indicate birth weight association P-values: P<5e-08 (red); P>=5e-08 and P<0.001 (orange); P>=0.001 and P<0.01 (yellow); P>0.01 (white). The triangles in plot f are SNPs known to be associated with age at menarche. There were more associations between height loci and higher birth weight than expected under the null, and a slight excess of associations between T2D or SBP loci and lower birth weight (binomial sign test P = 0.02, 0.09 and 3×10⁻¹⁰ for b, d and f, respectively).

Figure 2

Associations between birth weight and known type 2 diabetes (T2D; a and b), systolic blood pressure (SBP, c and d) or height (e and f) loci from the discovery meta-analysis of N=26,836 individuals. Plots a, c and e are quantile-quantile plots: the black triangles (associated with lower birth weight) and circles (associated with higher birth weight) represent observed P-values after removing the loci that achieved P < 5×10⁻⁸ in the overall meta-analysis, and the black line represents expected P-values under the null. The grey area defines the approximate 95% confidence interval around the expected line. Plots b, d and f show, respectively, the T2D, SBP or height effect size (left-hand y-axis), taken from published meta-analyses^,,,, against the birth weight effect size (x-axis), with a superimposed frequency histogram showing the number of SNPs in each category of birth weight effect size (right-hand y-axis). The odds ratios for type 2 diabetes are all obtained from the published DIAGRAM+ Consortium meta-analysis, the largest available reference sample of European descent, and while they do not necessarily reach genome-wide significance in that sample, all loci have shown associations with type 2 diabetes at P < 5×10⁻⁸ (see Online Methods for details of published studies). Effect sizes are aligned to the T2D risk allele or the SBP- or height-increasing allele. Colours indicate birth weight association P-values: P<5e-08 (red); P>=5e-08 and P<0.001 (orange); P>=0.001 and P<0.01 (yellow); P>0.01 (white). The triangles in plot f are SNPs known to be associated with age at menarche. There were more associations between height loci and higher birth weight than expected under the null, and a slight excess of associations between T2D or SBP loci and lower birth weight (binomial sign test P = 0.02, 0.09 and 3×10⁻¹⁰ for b, d and f, respectively).

Figure 2

Associations between birth weight and known type 2 diabetes (T2D; a and b), systolic blood pressure (SBP, c and d) or height (e and f) loci from the discovery meta-analysis of N=26,836 individuals. Plots a, c and e are quantile-quantile plots: the black triangles (associated with lower birth weight) and circles (associated with higher birth weight) represent observed P-values after removing the loci that achieved P < 5×10⁻⁸ in the overall meta-analysis, and the black line represents expected P-values under the null. The grey area defines the approximate 95% confidence interval around the expected line. Plots b, d and f show, respectively, the T2D, SBP or height effect size (left-hand y-axis), taken from published meta-analyses^,,,, against the birth weight effect size (x-axis), with a superimposed frequency histogram showing the number of SNPs in each category of birth weight effect size (right-hand y-axis). The odds ratios for type 2 diabetes are all obtained from the published DIAGRAM+ Consortium meta-analysis, the largest available reference sample of European descent, and while they do not necessarily reach genome-wide significance in that sample, all loci have shown associations with type 2 diabetes at P < 5×10⁻⁸ (see Online Methods for details of published studies). Effect sizes are aligned to the T2D risk allele or the SBP- or height-increasing allele. Colours indicate birth weight association P-values: P<5e-08 (red); P>=5e-08 and P<0.001 (orange); P>=0.001 and P<0.01 (yellow); P>0.01 (white). The triangles in plot f are SNPs known to be associated with age at menarche. There were more associations between height loci and higher birth weight than expected under the null, and a slight excess of associations between T2D or SBP loci and lower birth weight (binomial sign test P = 0.02, 0.09 and 3×10⁻¹⁰ for b, d and f, respectively).