Iris Heid, Gonçalo Abecasis, Sudha Iyengar and colleagues report the results of a large genome-wide association meta-analysis of macular degeneration based on over 43,000 subjects. They identify 16 new risk loci, including some very rare coding variants. Advanced age-related macular degeneration (AMD) is the leading cause of blindness in the elderly, with limited therapeutic options. Here we report on a study of >12 million variants, including 163,714 directly genotyped, mostly rare, protein-altering variants. Analyzing 16,144 patients and 17,832 controls, we identify 52 independently associated common and rare variants (P < 5 × 10−8) distributed across 34 loci. Although wet and dry AMD subtypes exhibit predominantly shared genetics, we identify the first genetic association signal specific to wet AMD, near MMP9 (difference P value = 4.1 × 10−10). Very rare coding variants (frequency <0.1%) in CFH, CFI and TIMP3 suggest causal roles for these genes, as does a splice variant in SLC16A8. Our results support the hypothesis that rare coding variants can pinpoint causal genes within known genetic loci and illustrate that applying the approach systematically to detect new loci requires extremely large sample sizes.

Age-related macular degeneration (AMD) is a multifactorial disease and a prevalent cause of visual impairment in developed countries. Risk factors include environmental components and genetic determinants. The complement factor H (CFH) has been the first major susceptibility gene for AMD identified within 1q32. Here, we focused on a second region of interest in 10q26 where a recent meta-analysis revealed strongest evidence for linkage to AMD at a genome-wide significance level. Within an interval of 22 Mb, we have analyzed 93 single nucleotide polymorphisms for allelic association with AMD in two independent case–control cohorts of German origin (AMD _combinedn =1166; controls _combinedn =945). Significant association was found across a 60 kb region of high linkage disequilibrium harboring two genes PLEKHA1 and hypothetical LOC387715 . The strongest association ( P =10 ⁻³⁴ ) centered over a frequent coding polymorphism, Ala69Ser, at LOC387715 , strongly implicating this gene in the pathogenesis of AMD. Besides abundant expression in placenta, we demonstrate weak expression of LOC387715 in the human retina. At present, however, there is no functional information on this gene, which appears to have evolved recently within the primate lineage. The joint contribution of the common risk allele at LOC387715 , Ala69Ser, and at CFH , Tyr402His, was assessed in our case–control population, which suggests an additive model indicating an independent contribution of the two gene loci to disease risk. Our data show a disease odds ratio of 57.6 (95% CI: 37.2, 89.0) conferred by homozygosity for risk alleles at both CFH and LOC387715 when compared with the baseline non-risk genotype.

Age-related macular degeneration (AMD) is a common threat to vision. While classification of disease stages is critical to understanding disease risk and progression, several systems based on color fundus photographs are known. Most of these require in-depth and time-consuming analysis of fundus images. Herein, we present an automated computer-based classification algorithm. Algorithm development for AMD classification based on a large collection of color fundus images. Validation is performed on a cross-sectional, population-based study. We included 120 656 manually graded color fundus images from 3654 Age-Related Eye Disease Study (AREDS) participants. AREDS participants were >55 years of age, and non-AMD sight-threatening diseases were excluded at recruitment. In addition, performance of our algorithm was evaluated in 5555 fundus images from the population-based Kooperative Gesundheitsforschung in der Region Augsburg (KORA; Cooperative Health Research in the Region of Augsburg) study. We defined 13 classes (9 AREDS steps, 3 late AMD stages, and 1 for ungradable images) and trained several convolution deep learning architectures. An ensemble of network architectures improved prediction accuracy. An independent dataset was used to evaluate the performance of our algorithm in a population-based study. κ Statistics and accuracy to evaluate the concordance between predicted and expert human grader classification. A network ensemble of 6 different neural net architectures predicted the 13 classes in the AREDS test set with a quadratic weighted κ of 92% (95% confidence interval, 89%-92%) and an overall accuracy of 63.3%. In the independent KORA dataset, images wrongly classified as AMD were mainly the result of a macular reflex observed in young individuals. By restricting the KORA analysis to individuals >55 years of age and prior exclusion of other retinopathies, the weighted and unweighted κ increased to 50% and 63%, respectively. Importantly, the algorithm detected 84.2% of all fundus images with definite signs of early or late AMD. Overall, 94.3% of healthy fundus images were classified correctly. Our deep learning algoritm revealed a weighted κ outperforming human graders in the AREDS study and is suitable to classify AMD fundus images in other datasets using individuals >55 years of age.