# DeePTB

[DeePTB](https://github.com/deepmodeling/DeePTB) is an innovative Python package that uses deep learning to accelerate ab initio electronic structure simulations. It offers versatile, accurate, and efficient simulations for a wide range of materials and phenomena. Trained on small systems, DeePTB can predict electronic structures of large systems, handle structural perturbations, and integrate with molecular dynamics for finite temperature simulations, providing comprehensive insights into atomic and electronic behavior. See more details in [DeePTB-SK: Nat Commun 15, 6772 (2024)](https://www.nature.com/articles/s41467-024-51006-4) and [DeePTB-E3: arXiv:2407.06053](https://arxiv.org/pdf/2407.06053).

DeePTB trains the model based on the Structure, Eigenvalues, Hamiltonian, Density matrix, and Overlap matrix  from first-principles calcualtions. DeePTB team provides the interfaces [dftio](https://github.com/deepmodeling/dftio) with other first-principles softwares. [dftio](https://github.com/deepmodeling/dftio) fully supports the interfaces with ABACUS, and can transfer the Structure, Eigenvalues, Hamiltonian, Density matrix, and Overlap matrix from ABACUS into the format used in [DeePTB](https://github.com/deepmodeling/DeePTB).