Related Experiment Video
Updated: Feb 6, 2026
Automated Protocols for Macromolecular Crystallization at the MRC Laboratory of Molecular Biology
Published on: January 24, 2018
Open Molecular Crystals 2025 (OMC25) dataset and models.
Vahe Gharakhanyan1, Luis Barroso-Luque2, Yi Yang3
1Fundamental AI Research, Meta, San Francisco, CA, US. vaheg@meta.com.
A new dataset of over 27 million molecular crystal structures, the Open Molecular Crystals 2025 (OMC25), has been released. This resource aims to accelerate the development of machine learning models for predicting crystal properties.
Area of Science:
- Materials Science
- Computational Chemistry
- Data Science
Background:
- Machine learning for molecular crystals is limited by a lack of labeled property data.
- Predicting crystal structure and properties requires extensive, high-quality datasets.
Purpose of the Study:
- Introduce the Open Molecular Crystals 2025 (OMC25) dataset.
- Facilitate the development of accurate machine learning models for molecular crystals.
Main Methods:
- Generated over 27 million molecular crystal structures.
- Relaxed ~230,000 structures using dispersion-inclusive DFT (PBE+D3).
- Included diverse chemical compounds and packing motifs.
Main Results:
- The OMC25 dataset contains diverse crystal structures and properties.
- Machine learning interatomic potentials were trained and evaluated on OMC25.
- Demonstrated the dataset's utility for advancing crystal structure prediction.
Conclusions:
- The OMC25 dataset addresses the scarcity of labeled data for molecular crystals.
- Public availability of OMC25 will accelerate ML model development.
- Facilitates research in materials science and computational chemistry.
More Related Videos
07:57Scaled Anatomical Model Creation of Biomedical Tomographic Imaging Data and Associated Labels for Subsequent Sub-surface Laser Engraving SSLE of Glass Crystals
Published on: April 25, 2017
06:19Author Spotlight: High-Throughput Screening to Obtain Crystal Hits for Protein Crystallography
Published on: March 10, 2023
Related Concept Videos
02:00Molecular Models
02:58Crystal Field Theory - Octahedral Complexes
To explain the observed behavior of transition metal complexes (such as colors), a model involving electrostatic interactions between the electrons from the ligands and the electrons in the unhybridized d orbitals of the central metal atom has been developed. This electrostatic model is crystal field theory (CFT). It helps to understand, interpret, and predict the colors, magnetic behavior, and some structures of coordination compounds of transition metals.
CFT focuses on...
02:42Ionic Crystal Structures
Most monatomic ions behave as charged spheres, and their attraction for ions of opposite charge is the same in every direction. Consequently, stable structures for ionic compounds result (1) when ions of one charge are surrounded by as many ions as possible of the opposite...
01:25Crystal Growth: Principles of Crystallization
Initiating crystallization involves manipulating the concentration of the solute and the temperature of the solution. Since crystal growth occurs when the ratio of concentration and solubility of the solute in the solvent...
02:46Crystal Field Theory - Tetrahedral and Square Planar Complexes
Crystal field theory (CFT) is applicable to molecules in geometries other than octahedral. In octahedral complexes, the lobes of the dx2−y2 and dz2 orbitals point directly at the ligands. For tetrahedral complexes, the d orbitals remain in place, but with only four ligands located between the axes. None of the orbitals points directly at the tetrahedral ligands. However, the dx2−y2 and dz2 orbitals (along the Cartesian axes) overlap with the ligands less than the dxy,...
03:51Molecular Orbital Theory II