Leonhard Kohleick

The paper introduces an interpretable neural network architecture for genomic prediction, outperforming existing methods in disease risk prediction and capturing non-linear genetic interactions.

The paper uses genome-wide association testing on embeddings from a medical-history foundation model to identify genetic signals linked to biological pathways and drug targets.

This study integrates genetic variation with plasma protein measurements in South Asians to identify pQTLs and build a proteogenomic disease network for understudied populations.

The paper uses nanoparticle enriched mass spectrometry proteomics in British South Asians to identify novel variant-protein-disease mechanisms through integrative analysis of exome sequencing and proteomic data.