LeMaterial: an open source initiative to accelerate materials discovery and research

Today, we are thrilled to announce the launch of LeMaterial, an open-source collaborative project led by Entalpic and Hugging Face. LeMaterial aims to simplify and accelerate materials research, making it easier to train ML models, identify novel materials and explore chemical spaces. ⚛️🤗

As a first step, we are releasing a dataset called LeMat-Bulk, which unifies, cleans and standardizes the most prominent material datasets, including Materials Project, Alexandria and OQMD — giving rise to a single harmonized data format with 6.7M entries and 7 materials properties.

LeMaterial is standing on the shoulders of giants and we are building upon incredible projects which have been instrumental in the development of this initiative: Optimade, Materials Project, Alexandria and OQMD, and more to come. Please credit them accordingly when using LeMaterial.

Why LeMaterial?

The world of materials science, at the intersection of quantum chemistry and machine learning, is brimming with opportunity — from brighter LEDs, to electro-chemical batteries, more efficient photovoltaic cells and recyclable plastics, the applications are endless. By leveraging machine learning (ML) on large, structured datasets, researchers can perform high-throughput screening and testing of new materials at unprecedented scales, significantly accelerating the discovery cycle of novel compounds with desired properties. In this paradigm, data becomes the essential fuel powering ML models that can guide experiments, reduce costs, and unlock breakthroughs faster than ever before.

This field is fueled by very complete datasets such as Materials Project, Alexandria and OQMD, all open-source and under a CC-BY-4.0 license. However, those datasets vary in format, parameters, and scope, presenting the following challenges:

Materials Project and LeMat-BulkUnique treemap

Achieving a clean, unified and standardized dataset

View the complete Datacard