Research notes on computational approaches to protein structure, folding, and dynamics.
Flow matching model that co-generates ligands and flexible protein pockets, addressing rigid-receptor limitations in …
A fast, diverse inverse folding method combining deep learning with Potts models to capture full sequence landscapes.
Foundational paper establishing the energy landscape theory, folding funnels, and the principle of minimal frustration.
A perspective paper defining the Grand Challenge of protein folding: distinguishing kinetic pathways from thermodynamic …