dscribe

What it is and what it does

DScribe is a materials-science-focused Python library that converts atomic structures into fixed-size numerical descriptors suitable for machine learning pipelines. It implements multiple descriptor types—including SOAP (Smooth Overlap of Atomic Positions), Coulomb matrix, ACSF (Atom-centered Symmetry Functions), and MBTR (Many-body Tensor Representation)—each capturing different aspects of atomic geometry and chemistry. The library wraps numpy, scipy, and scikit-learn for numerical computation and can parallelize descriptor creation across multiple processes via joblib.

Typical use involves loading or constructing atomic structures (via ASE), instantiating a descriptor class with domain-specific parameters, and calling create() to generate fixed-size feature vectors or sparse arrays. The package supports both spectrum calculation and derivative computation with respect to atomic positions, making it suitable for force-field fitting and sensitivity analysis. It targets materials scientists and machine-learning practitioners working on atomistic property prediction, structure similarity, and visualization tasks.

Use it for

• Generate SOAP descriptors for training machine-learning models to predict material properties from atomic structure.
• Compute Coulomb matrices for similarity-based clustering or retrieval of structurally related molecules and crystals.
• Calculate descriptor derivatives to fit interatomic potentials or analyze sensitivity of predictions to atomic positions.
• Parallelize descriptor creation across multiple CPU cores when processing large datasets of structures.
• Visualize and compare atomic structures in a fixed-dimensional descriptor space for exploratory analysis.

Worth the install?

AI-flagged interpretation of the facts on this page. Verify before relying on it.

Install

dscribe on PyPI

Before you install

Medium install friction due to compiled C/C++ components and multiple dependencies (numpy, scipy, ase, scikit-learn, joblib, sparse). Pre-built wheels available for Python 3.9–3.13 on macOS, Linux, and Windows. Last release was 321 days ago; maintenance status is aging.

Requires ASE (Atomic Simulation Environment) to construct or load atomic structures; compiled C/C++ extensions require a compatible build toolchain on source installs.

License in practice

Apache License 2.0 is permissive and allows commercial use, modification, and distribution with minimal restrictions. You must include a copy of the license and state significant changes.

Quickstart

pip install dscribe

from ase.build import molecule
from dscribe.descriptors import SOAP

water = molecule("H2O")
soap_desc = SOAP(species=["H", "O"], r_cut=5, n_max=8, l_max=6)
soap = soap_desc.create(water, centers=[0])

Package facts

Evidence: dscribe-2.1.2-cp310-cp310-macosx_10_9_x86_64.whl; dscribe-2.1.2-cp310-cp310-macosx_11_0_arm64.whl; dscribe-2.1.2-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl; dscribe-2.1.2-cp310-cp310-musllinux_1_2_x86_64.whl; dscribe-2.1.2-cp310-cp310-win32.whl; dscribe-2.1.2-cp310-cp310-win_amd64.whl; dscribe-2.1.2-cp311-cp311-macosx_10_9_x86_64.whl; dscribe-2.1.2-cp311-cp311-macosx_11_0_arm64.whl; dscribe-2.1.2-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl; dscribe-2.1.2-cp311-cp311-musllinux_1_2_x86_64.whl; dscribe-2.1.2-cp311-cp311-win32.whl; dscribe-2.1.2-cp311-cp311-win_amd64.whl; dscribe-2.1.2-cp312-cp312-macosx_10_13_x86_64.whl; dscribe-2.1.2-cp312-cp312-macosx_11_0_arm64.whl; dscribe-2.1.2-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl; dscribe-2.1.2-cp312-cp312-musllinux_1_2_x86_64.whl; dscribe-2.1.2-cp312-cp312-win32.whl; dscribe-2.1.2-cp312-cp312-win_amd64.whl; dscribe-2.1.2-cp313-cp313-macosx_10_13_x86_64.whl; dscribe-2.1.2-cp313-cp313-macosx_11_0_arm64.whl

Tags

More Scientific/Engineering packages

See also padelpy · mordredcommunity · aimsim-core · vesin · fairchem-core · matscipy · vesin-torch · mhfp · pyxtal · prolif