DScribe is a software package for machine learning that provides popular feature transformations ("descriptors") for atomistic materials simulations. DScribe accelerates the application of machine learning for atomistic property prediction by providing user-friendly, off-the-shelf descriptor implementations. The package currently contains implementations for Coulomb matrix, Ewald sum matrix, sine matrix, Many-body Tensor Representation (MBTR), Atom-centered Symmetry Function (ACSF) and Smooth Overlap of Atomic Positions (SOAP). Usage of the package is illustrated for two different applications: formation energy prediction for solids and ionic charge prediction for atoms in organic molecules. The package is freely available under the open-source Apache License 2.0.
@article{arxiv.1904.08875,
title = {DScribe: Library of Descriptors for Machine Learning in Materials Science},
author = {Lauri Himanen and Marc O. J. Jäger and Eiaki V. Morooka and Filippo Federici Canova and Yashasvi S. Ranawat and David Z. Gao and Patrick Rinke and Adam S. Foster},
journal= {arXiv preprint arXiv:1904.08875},
year = {2023}
}