Genome-wide association meta-analysis for early age-related macular degeneration highlights novel loci and insights for advanced disease

Abstract

Background: Advanced age-related macular degeneration (AMD) is a leading cause of blindness. While around half of the genetic contribution to advanced AMD has been uncovered, little is known about the genetic architecture of early AMD.

Methods: To identify genetic factors for early AMD, we conducted a genome-wide association study (GWAS) meta-analysis (14,034 cases, 91,214 controls, 11 sources of data including the International AMD Genomics Consortium, IAMDGC, and UK Biobank, UKBB). We ascertained early AMD via color fundus photographs by manual grading for 10 sources and via an automated machine learning approach for > 170,000 photographs from UKBB. We searched for early AMD loci via GWAS and via a candidate approach based on 14 previously suggested early AMD variants.

Results: Altogether, we identified 10 independent loci with statistical significance for early AMD: (i) 8 from our GWAS with genome-wide significance (P < 5 × 10^{- 8}), (ii) one previously suggested locus with experiment-wise significance (P < 0.05/14) in our non-overlapping data and with genome-wide significance when combining the reported and our non-overlapping data (together 17,539 cases, 105,395 controls), and (iii) one further previously suggested locus with experiment-wise significance in our non-overlapping data. Of these 10 identified loci, 8 were novel and 2 known for early AMD. Most of the 10 loci overlapped with known advanced AMD loci (near ARMS2/HTRA1, CFH, C2, C3, CETP, TNFRSF10A, VEGFA, APOE), except two that have not yet been identified with statistical significance for any AMD. Among the 17 genes within these two loci, in-silico functional annotation suggested CD46 and TYR as the most likely responsible genes. Presence or absence of an early AMD effect distinguished the known pathways of advanced AMD genetics (complement/lipid pathways versus extracellular matrix metabolism).

Conclusions: Our GWAS on early AMD identified novel loci, highlighted shared and distinct genetics between early and advanced AMD and provides insights into AMD etiology. Our data provide a resource comparable in size to the existing IAMDGC data on advanced AMD genetics enabling a joint view. The biological relevance of this joint view is underscored by the ability of early AMD effects to differentiate the major pathways for advanced AMD.

Keywords: Age-related macular degeneration (AMD); Automated phenotyping; CD46; Early AMD; Genome-wide association study (GWAS); International AMD genomics consortium (IAMDGC); Machine-learning; Meta-analysis; TYR; UK biobank (UKBB).

Fig. 1

Early AMD meta-analysis. Shown are the association results of the meta-analysis for early AMD: a by their position on the genome (Manhattan plot) with color indicating whether the locus was previously identified by Holliday et al. [12] (blue), novel for early AMD (red), or among the other advanced AMD loci identified by Fritsche et al. [9] (green); and b their distribution (QQ plot)

Fig. 2

Advanced vs early AMD effect sizes. Shown are advanced AMD effect sizes contrasted to early AMD effect sizes (effect sizes as log odds ratios) for the 34 known advanced AMD variants [9] (blue or green for P_early < 0.05 or P_early ≥ 0.05, respectively) and for the two novel (early) AMD variants (red, near CD46, TYR). Detailed results are shown in Table S16

Fig. 3

Etiological models and the respective expected association of a variant with early and advanced AMD