HOME > ElMD

ElMD

ElMD is a Python package that computes chemical similarity between material compositions (chemical formulas) using the Element Movers Distance, which adapts the Earth Mover’s Distance / Wasserstein distance to composition space by measuring the minimum “work” required to transform one element-fraction distribution into another.

Information
Case / Article
Learning Content
Review
Developer’s Voice

Information

Official site	https://github.com/lrcfmd/ElMD
Openness	★★★
License	GitHub badge/metadata: GPL-3.0 (as shown on the repository page) PyPI metadata: GNU LGPLv3 (as shown in the PyPI “License” field) Note: For practical use and redistribution, confirm the license by checking the LICENSE file included in the distribution/repository.
Core Developers	Leverhulme Research Centre for Functional Materials Design (LRCFMD), University of Liverpool
Availability	Python package (install via pip): `pip install ElMD` The official README notes that dependency conflicts may occur in some Python 3.8+ environments and suggests installing with `pip install ElMD --no-deps` as needed (then adding required dependencies such as `numpy`; optional acceleration via `numba`).
Related Papers	Cameron J. Hargreaves; Matthew S. Dyer; Michael W. Gaultois; Vitaliy A. Kurlin; Matthew J. Rosseinsky, “The Earth Mover’s Distance as a Metric for the Space of Inorganic Compositions,” Chemistry of Materials 2020, 32 (24), 10610–10620. DOI: https://doi.org/10.1021/acs.chemmater.0c03381 Sterling G. Baird; Tran Q. Diep; Taylor D. Sparks, “DiSCoVeR: a materials discovery screening tool for high performance, unique chemical compositions,” Digital Discovery 2022, 1, 226–240. DOI: https://doi.org/10.1039/D1DD00028D Q. Li; N. Fu; S. S. Omee; J. Hu, “MD-HIT: Machine learning for material property prediction with dataset redundancy control,” npj Computational Materials 10, 245 (2024). DOI: https://doi.org/10.1038/s41524-024-01426-z
Related Sites	ElM2D (high-performance implementation for building distance matrices/embeddings over many compositions): https://github.com/lrcfmd/ElM2D matminer integration discussion (community thread about ElMD/ElM2D): https://matsci.org/t/any-interest-in-incorporating-chemical-composition-distance-metric-elm2d-into-matminer/39052 DiSCoVeR (composition-based screening tool that uses ElMD): https://www.github.com/sparks-baird/mat_discover Awesome lists (brief listings that mention ElMD): https://github.com/marda-alliance/awesome_list https://github.com/tilde-lab/awesome-materials-informatics