Pierre Vandergheynst

This paper introduces REGEN, a GNN framework for learning gene interaction networks from bulk transcriptomic data and predicting patient outcomes, showing improved performance across cancer types.

The paper introduces Riboclette, a conditional deep learning model that predicts ribosome footprints under amino acid deprivation and identifies key codons and motifs driving translation stalling.

The paper introduces a graph representation that combines static and dynamic protein data, improving performance in three tasks related to protein-ligand interactions.

This paper introduces a deep learning framework called Genesis to learn protein structural patterns and demonstrates its ability to design novel protein folds with high protease resistance.

This study introduces RiboGL, a model combining graph and recurrent neural networks to predict ribosome density from mRNA secondary structure, outperforming existing methods.

RosettaSurf is a computational design method that optimizes protein surfaces for functional sites, showing success in generating epitope mimics through surface-centric design.