Sebastian Raschka

The paper develops a machine learning classifier, hotspotter, to predict protein:protein interaction hot spots using features like accessible surface area and evolutionary conservation.

The paper uses machine learning to identify flexibility signatures in GPCRs that distinguish active from inactive states based on ligand-induced structural changes.

The paper identifies a strong trend in protein-ligand interactions where proteins prefer to donate hydrogen bonds and ligands accept them, leading to the development of tools to predict and design ligand complexes.

The paper introduces Screenlamp, a toolkit for hypothesis-driven ligand screening, and demonstrates its use in discovering GPCR inhibitors for invasive species control.