Multi-trait genome-wide association study identifies new loci associated with optic disc parameters

Abstract

A new avenue of mining published genome-wide association studies includes the joint analysis of related traits. The power of this approach depends on the genetic correlation of traits, which reflects the number of pleiotropic loci, i.e. genetic loci influencing multiple traits. Here, we applied new meta-analyses of optic nerve head (ONH) related traits implicated in primary open-angle glaucoma (POAG); intraocular pressure and central corneal thickness using Haplotype reference consortium imputations. We performed a multi-trait analysis of ONH parameters cup area, disc area and vertical cup-disc ratio. We uncover new variants; rs11158547 in PPP1R36-PLEKHG3 and rs1028727 near SERPINE3 at genome-wide significance that replicate in independent Asian cohorts imputed to 1000 Genomes. At this point, validation of these variants in POAG cohorts is hampered by the high degree of heterogeneity. Our results show that multi-trait analysis is a valid approach to identify novel pleiotropic variants for ONH.

Keywords: Genome-wide association studies; Optic nerve diseases.

Fig. 1

Manhattan plot of single trait analysis for cup area (a), disc area (b), and vertical cup–disc ratio (c). Manhattan plot for multi-trait analysis of the optic nerve head (ONH) SHom (d) and SHet (e).

Fig. 2

Phenotype (a) and genetic (b) correlations between cup area, disc area, vertical cup–disc ratio, intraocular pressure, and central corneal thickness. a Partial pearson correlation coefficient s between cup area (CA), disc area (DA), vertical cup–disc ratio (VCDR), intraocular pressure (IOP), and central corneal thickness (CCT) adjusted for age and sex in the Rotterdam study I. b Genetic correlation coefficient (Rg) for CA, DA, VCDR, IOP, and CCT calculated by LD score regression; *p < 0.05, **p < 0.0001.

Fig. 3

Regional, chromatin state, and eQTL plot for rs11158547 (PPP1R36-PLEKHG3). Panel a shows the regional assocaiations plots with −log10 p value depicted on the y-axis, genes mapped by either position, eQTL or chromatin interaction are depicted in red on the x-axis; panel b shows 15 core chromatin states of varaints plotted in panel a for 13 brain tissues from Roadmap epidenomes described on the y-axis. E054 ganglion eminence derived primary cultured neurospheres, E053 cortex-derived primary cultured neurospheres, E071 brain hippocampus middle, E074 brain substantia nigra, E068 brain anterior caudate, E069 brain cingulate gyrus, E072 brain inferior temporal lobe, E067 brain angular gyrus, E073 brain dorsolateral prefrontal cortex, E070 brain germinal matrix, E082 fetal brain female, E081 fetal brain male, E125 NH-A astrocytes primary cells. Panel c depicts varaints that overlap eQTLs from selected eQTL databases described in the legend of panel (c).

Fig. 4

Regional, chromatin state and eQTL plot for rs1028727 (SERPINE3). Panel a shows the regional assocaiations plots with −log10 p value depicted on the y-axis, genes mapped by either position, eQTL or chromatin interaction are depicted in red on the x-axis; panel b shows 15 core chromatin states of varaints plotted in panel a for 13 brain tissues from Roadmap epidenomes described on the y-axis. E054 ganglion eminence derived primary cultured neurospheres, E053 cortex-derived primary cultured neurospheres, E071 brain hippocampus middle, E074 brain substantia nigra, E068 brain anterior caudate, E069 brain cingulate gyrus, E072 brain inferior temporal lobe, E067 brain angular gyrus, E073 brain dorsolateral prefrontal cortex, E070 brain germinal matrix, E082 fetal brain female, E081 fetal brain male, E125 NH-A astrocytes primary cells. Panel c depicts varaints that overlap eQTLs from selected eQTL databases described in the legend of panel (c).