Erinç Merdivan

DrugDiff generates novel small molecules with desired properties using a diffusion model guided by predictors.

The paper introduces MISATO, a dataset combining quantum mechanics properties and molecular dynamics simulations of protein-ligand complexes to support structure-based drug discovery.

TopEC improves enzyme function classification using 3D graph neural networks and a localized 3D descriptor, achieving high accuracy in EC class prediction.

The paper develops a mixed-effect random forest model to predict CRISPRi guide efficiency using data from depletion screens and gene-specific features, outperforming existing methods.