Lucien F. Krapp

This study identifies and characterizes nonlinear ion transport phenomena in β-barrel nanopores, linking lumen charge distribution to open-pore rectification and gating.

This paper introduces RISoTTo, a geometric deep learning method for RNA sequence design that incorporates molecular context, showing improved accuracy and binding affinity in in silico tests.

HandMol provides an immersive, collaborative molecular modeling tool using WebXR, AI, and HCI technologies, enabling natural interactions and real-time collaboration without specialized software.

This study uses a biological nanopore and deep learning to detect and distinguish single and multiple PTMs on -synuclein peptides at picomolar concentrations.

PeSTo predicts protein interacting interfaces using a parameter-free geometric transformer that acts on atom labels, outperforming existing methods and enabling analysis of dynamic structural data.