Thomas Hamelryck

BIFROST generates high-quality protein structure fragments using a Deep Markov Model, faster and with less input than current methods.

GISA identifies rare protein conformations by computing Gauss integrals as topological-geometric descriptors, revealing new entangled structures and potential errors in protein models.

This paper introduces THESEUS-PP, a probabilistic programming approach for protein structure superposition that uses Bayesian models to account for correlated atom positions and heteroscedasticity.