Jonathan Hess

The paper introduces an adversarial neural network to identify genetic resilience markers in Alzheimer's disease, finding five SNPs associated with resilience independent of polygenic risk scores.

This paper develops a framework using genomic context and genotype data in convolutional neural networks to predict type 2 diabetes risk, showing improved performance over polygenic risk scores.

The paper estimates genetic and environmental contributions to module eigengenes (MEs) derived from blood lymphocytes in older male twins, finding significant heritability in 56% of detected MEs.

This study identifies genetic resilience factors for Alzheimer's disease by constructing polygenic resilience scores that reduce genetic risk penetrance and correlate with polygenic risk scores in unaffected individuals.

The paper examines genetic correlations between neuropsychiatric disorders using structural MRI data from the ENIGMA consortium, finding significant overlaps in brain structure and genetic architecture.

BrainGENIE predicts brain-tissue gene expression from peripheral blood transcriptomes, outperforming existing methods in accuracy and biological relevance.

The paper investigates selective brain region vulnerability in ADHD by analyzing gene expression, cell abundance, and brain size changes using imaging and postmortem data.

This study identifies shared and sex-specific inflammatory pathways in PTSD through a meta-analysis of blood transcriptomes across different trauma types and biological sexes.