Benjamin Wild

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.

NetworkVI integrates multi-omics data using a biologically informed variational autoencoder, enabling interpretable cell phenotyping and discovery of lineage-specific immune states.

The paper tracks honeybee colony activity over time and shows that mechanical interactions transfer circadian information, leading to synchronized collective behavior.