Samuel Demharter

EpiRanha identifies epitope similarities using a structure- and residue-aware graph neural network, improving detection of cross-reactive epitopes and off-target interactions.

The paper disentangles protein-interaction and protein-quality effects in antibody-antigen binding using deep mutational scanning and evaluates models for their ability to predict these effects.

NAStructuralDB provides a processed dataset of antibody, Nanobody, and protein structures with molecular contact information and annotations to aid in predictive tasks.

The paper develops the ASD database to aggregate antibody-antigen interaction data from multiple sources, providing a standardized resource for computational model development.

The paper creates a dataset of antibody-antigen complexes with mutations and evaluates affinity prediction methods, finding that current models poorly predict binding effects compared to empirical methods.

This study shows that a single cocaine exposure causes long-lasting 3D genome structure changes in midbrain dopamine neurons, affecting gene regulation and synaptic plasticity.

This paper applies symbolic regression to clinical omics data to identify interpretable biomarker signatures that predict disease outcomes and reveal disease mechanisms.

The paper introduces Conos, a method for joint clustering of large single-cell RNA-seq datasets to identify recurrent cell subpopulations across multiple samples.