The development of accurate and efficient machine learning models for predicting the structure and properties of molecular crystals has been hindered by the scarcity of publicly available datasets of structures with property labels. To address this challenge, we introduce the Open Molecular Crystals 2025 (OMC25) dataset, a collection of over 27 million molecular crystal structures containing 12 elements and up to 300 atoms in the unit cell. The dataset was generated from dispersion-inclusive density functional theory (DFT) relaxation trajectories of over 230,000 randomly generated molecular crystal structures of around 50,000 organic molecules. OMC25 comprises diverse chemical compounds capable of forming different intermolecular interactions and a wide range of crystal packing motifs. We provide detailed information on the dataset's construction, composition, structure, and properties. To demonstrate the quality and use cases of OMC25, we further trained and evaluated state-of-the-art open-source machine learning interatomic potentials. By making this dataset publicly available, we aim to accelerate the development of more accurate and efficient machine learning models for molecular crystals.
@article{arxiv.2508.02651,
title = {Open Molecular Crystals 2025 (OMC25) Dataset and Models},
author = {Vahe Gharakhanyan and Luis Barroso-Luque and Yi Yang and Muhammed Shuaibi and Kyle Michel and Daniel S. Levine and Misko Dzamba and Xiang Fu and Meng Gao and Xingyu Liu and Haoran Ni and Keian Noori and Brandon M. Wood and Matt Uyttendaele and Arman Boromand and C. Lawrence Zitnick and Noa Marom and Zachary W. Ulissi and Anuroop Sriram},
journal= {arXiv preprint arXiv:2508.02651},
year = {2025}
}