DeepH-dock seamlessly integrates deep learning with first-principles calculations. It serves as a modular and extensible bridge, functioning both as the dedicated interface for the DeepH-pack suite and as a standalone tool for coupling deep learning models with computational materials science workflows.
DeepH-pack is a general-purpose neural network package for deep-learning electronic structure calculations. As the latest evolution of the DeepH framework, it integrates all prior methodologies into a unified, cohesive toolkit. This enhanced version has been fully rebuilt using JAX, delivering greater computational efficiency and expanded functionality.
