Applying deep learning in population genomics is challenging because of computational issues and lack of interpretable models. Here, we propose GenNet, a novel open-source deep learning framework for predicting phenotypes from genetic variants. In this framework, interpretable and memory-efficient neural network architectures are constructed by embedding biologically knowledge from public databases, resulting in neural networks that contain only biologically plausible connections. We applied the framework to seventeen phenotypes and found well-replicated genes such as HERC2 and OCA2 for hair and eye color, and novel genes such as ZNF773 and PCNT for schizophrenia. Additionally, the framework identified ubiquitin mediated proteolysis, endocrine system and viral infectious diseases as most predictive biological pathways for schizophrenia. GenNet is a freely available, end-to-end deep learning framework that allows researchers to develop and use interpretable neural networks to obtain novel insights into the genetic architecture of complex traits and diseases.

Increasing evidence shows that thinner retinal nerve fiber layer (RNFL) and ganglion cell layer (GCL), assessed on optical coherence tomography (OCT), are reflecting global brain atrophy. Yet, little is known on the relation of these layers with specific brain regions. Using voxel-based analysis, we aimed to unravel specific brain regions associated with these retinal layers. We included 2,235 persons (mean age: 67.3 years, 55% women) from the Rotterdam Study (2007–2012) who had gradable retinal OCT images and brain magnetic resonance imaging (MRI) scans, including diffusion tensor (DT) imaging. Thicknesses of peripapillary RNFL and perimacular GCL were measured using an automated segmentation algorithm. Voxel-based morphometry protocols were applied to process DT-MRI data. We investigated the association between retinal layer thickness with voxel-wise gray matter density and white matter microstructure by performing linear regression models. We found that thinner RNFL and GCL were associated with lower gray matter density in the visual cortex, and with lower fractional anisotropy and higher mean diffusivity in white matter tracts that are part of the optic radiation. Furthermore, thinner GCL was associated with lower gray matter density of the thalamus. Thinner RNFL and GCL are associated with gray and white matter changes in the visual pathway suggesting that retinal thinning on OCT may be specifically associated with changes in the visual pathway rather than with changes in the global brain. These findings may serve as a basis for understanding visual symptoms in elderly patients, patients with Alzheimer's disease, or patients with posterior cortical atrophy.

We investigated the association of specific retinal sublayer thicknesses on optical coherence tomography (OCT) with brain magnetic resonance imaging (MRI) markers. We included 2124 persons (mean age 67.0 years; 56% women) from the Rotterdam Study who had gradable retinal OCT images and brain MRI scans. Thickness of retinal nerve fiber layer (RNFL), ganglion cell layer (GCL), and inner plexiform layer were measured on OCT images. Volumetric, microstructural, and focal markers of brain tissue were assessed on MRI. We found that thinner RNFL, GCL, and inner plexiform layer were associated with smaller gray-matter and white-matter volume. Furthermore, we found that thinner RNFL and GCL were associated with worse white-matter microstructure. No association was found between retinal sublayer thickness and white-matter lesion volumes, cerebral microbleeds, or lacunar infarcts. Markers of retinal neurodegeneration are associated with markers of cerebral atrophy, suggesting that retinal OCT may provide information on neurodegeneration in the brain.

Objective: To investigate whether retinal microvascular damage is related to normal-appearing white matter microstructure on diffusion tensor MRI. Methods: We included 2,436 participants (age ≥45 years) from the population-based Rotterdam Study (2005-2009) who had gradable retinal images and brain MRI scans. Retinal arteriolar and venular calibers were measured semiautomatically on fundus photographs. White matter microstructure was assessed using diffusion tensor MRI. We used linear regression models to investigate the associations of retinal vascular calibers with markers of normal-appearing white matter microstructure, adjusting for age, sex, the fellow vascular caliber, and additionally for structural MRI markers and cardiovascular risk factors. Results: Narrower arterioles and wider venules were associated with poor white matter microstructure: adjusted difference in fractional anisotropy per SD decrease in arteriolar caliber -0.061 (95% confidence interval -0.106 to -0.016), increase in venular caliber -0.054 (-0.096 to -0.011), adjusted difference in mean diffusivity per SD decrease in arteriolar caliber 0.048 (0.007-0.088), and increase in venular caliber 0.047 (0.008-0.085). The associations for venules were more prominent in women. Conclusions: Retinal vascular calibers are related to normal-appearing white matter microstructure. This suggests that microvascular damage in the white matter is more widespread than visually detectable as white matter lesions.