Coupling Molecular Dynamics and Deep Learning to Mine Protein Conformational Space [data and software]

Matteo Degiacomi
This work features generative neural networks (autoencoders) trained on protein structures produced by molecular simulations. Autoencoders are used to obtain new, plausible conformations complementing and extending pre-existing ones, usable in a protein-protein docking scenario.
This data repository is not currently reporting usage information. For information on how your repository can submit usage information, please see our documentation.