{"id":1,"date":"2025-04-09T08:36:42","date_gmt":"2025-04-09T08:36:42","guid":{"rendered":"http:\/\/localhost\/wordpress\/valancelabs\/?p=1"},"modified":"2025-05-13T16:06:51","modified_gmt":"2025-05-13T16:06:51","slug":"introducing-openqdc-the-open-source-hub-of-ml-ready-quantum-datasets","status":"publish","type":"post","link":"https:\/\/valancelabs.digitalhero.uk.com\/fr\/introducing-openqdc-the-open-source-hub-of-ml-ready-quantum-datasets\/","title":{"rendered":"Introducing OpenQDC – The Open-Source Hub of ML-Ready Quantum Datasets"},"content":{"rendered":"
\n
\n
\n

Introduction<\/h2>\n <\/div>\n
\n
\n

We curated and consolidated 40+ quantum mechanics (QM) datasets, covering 1.5 billion geometries across 70 atom species and 250+ QM methods, into a single, accessible hub called\u00a0OpenQDC<\/a>. It\u2019s open-source and the datasets are available for access through the\u00a0OpenQDC Python library<\/a>. Install it via pip (pip install OpenQDC) to start downloading and using various QM datasets in just a single line of code.\u2028\u2028<\/p>\n

Github page:\u00a0https:\/\/github.com\/valence-labs\/openQDC<\/a>\u2028\u2028<\/p>\n

Website:\u00a0https:\/\/www.openqdc.io\/<\/a><\/p> <\/div>\n <\/div>\n <\/div>\n<\/div>\n\n

\n
\"\"<\/figure>\n<\/div>\n\n\n
\n
\n
\n

Challenges with QM Datasets<\/span><\/h2>\n <\/div>\n
\n
\n

Developing robust MLIPs requires vast amounts of QM data. Unfortunately, there is a lack of standardized, plug-and-play datasets that can be used to train and test new ML algorithms, hindering the prototyping of new research in this field.\u2028\u2028<\/p>\n

Existing QM datasets span various methods and different chemical spaces. They\u2019re also scattered across several repositories (ex. QCArchive, ColabFit, NablaDFT, GEOM) with missing metadata (e.g. level of theory and units), adding an extra layer of complexity to working these datasets. This not only hampers the adoption and utility of the data, but also stifles opportunities for collaboration among physicists, chemists, ML experts, and experts in other fields, limiting the progress of ML research<\/p> <\/div>\n <\/div>\n <\/div>\n<\/div>\n\n\n

\n
\n
\n

Introducing OpenQDC<\/span><\/h2>\n
\n

With OpenQDC, we aim to unify and standardize existing, well-known datasets to advance the future of MLIP research. We collected publicly-available datasets and computed essential metadata that was missing but necessary for accurate data processing (e.g. energy, distance, force units, and isolated atom energies).<\/p> <\/div>\n <\/div>\n<\/div>\n\n\n